From 601231e0bf0004d13aefbb715679d43a4281a41b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ezequiel=20Leonardo=20Casta=C3=B1o?= <14986783+ELC@users.noreply.github.com> Date: Wed, 18 Jun 2025 23:40:34 -0300 Subject: [PATCH] Scraped pydata-berlin-2022 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes #xxx Event config: ~~~yaml repo_dir: W:\Repositories\pyvideo-data # Copy the event template here and adapt to the event parameters # Only repo_dir: and events: are loaded # ============================================================================= events: # - title: PyData Virginia 2025 # dir: pydata-virginia-2025 # youtube_list: # - https://www.youtube.com/playlist?list=PLGVZCDnMOq0qLS7Mk-jI9jhb4t5UY6yDW # related_urls: # - label: Conference Website # url: https://pydata.org/virginia2025 # language: eng # dates: # begin: 2025-04-18 # end: 2025-04-19 # default: 2025-04-18 # minimal_download: false # issue: xxx # overwrite: # # all: true # takes precedence over add_new_files and existing_files_fields # add_new_files: true # existing_files_fields: # - duration # - thumbnail_url # - videos # - description # - language # - recorded # - related_urls # - speakers # - tags # - title # tags: # - title: PyData Global 2024 # dir: pydata-global-2024 # youtube_list: # - https://www.youtube.com/playlist?list=PLGVZCDnMOq0otKlHvES9iBFtVQ71yZhed # related_urls: # - label: Conference Website # url: https://pydata.org/global2024 # language: eng # dates: # begin: 2024-12-03 # end: 2024-12-05 # default: 2024-12-03 # minimal_download: false # issue: xxx # overwrite: # # all: true # takes precedence over add_new_files and existing_files_fields # add_new_files: true # existing_files_fields: # - duration # - thumbnail_url # - videos # - description # - language # - recorded # - related_urls # - speakers # - tags # - title # tags: - title: PyData New York City 2024 dir: pydata-new-york-city-2024 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0ohEIZ-_wM2W_xqSVjyA3dC related_urls: - label: Conference Website url: https://pydata.org/nyc2024 language: eng dates: begin: 2024-11-06 end: 2024-11-08 default: 2024-11-06 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Tel Aviv 2024 dir: pydata-tel-avid-2024 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0pRsGPxDvLZfuufNgqREc0a related_urls: - label: Conference Website url: https://pydata.org/telaviv2024/ language: eng dates: begin: 2024-11-04 end: 2024-11-04 default: 2024-11-04 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Paris 2024 dir: pydata-paris-2024 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0pKya8gksd00ennKuyoH7v7 related_urls: - label: Conference Website url: https://pydata.org/paris2024 language: eng dates: begin: 2024-09-25 end: 2024-09-26 default: 2024-09-25 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Amsterdam 2024 dir: pydata-amsterdam-2024 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0reU2lzNZCn9obkyRVaSnpF related_urls: - label: Conference Website url: https://web.archive.org/web/20240822042916/https://amsterdam.pydata.org/ language: eng dates: begin: 2024-09-18 end: 2024-09-20 default: 2024-09-18 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Vermont 2024 dir: pydata-vermont-2024 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0pME_xSRdmoYFzhlsHJYM8I related_urls: - label: Conference Website url: https://pydata.org/vermont2024/ language: eng dates: begin: 2024-07-29 end: 2024-07-30 default: 2024-07-29 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Eindhoven 2024 dir: pydata-eindhoven-2024 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0q7a2aoNP1au_1egfZEjGL6 related_urls: - label: Conference Website url: https://pydata.org/eindhoven2024/ language: eng dates: begin: 2024-07-11 end: 2024-07-11 default: 2024-07-11 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData London 2024 dir: pydata-london-2024 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0rrhYTNedKKuJ9716fEaAdK related_urls: - label: Conference Website url: https://pydata.org/london2024/ language: eng dates: begin: 2024-06-14 end: 2024-06-16 default: 2024-06-14 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Berlin 2024 dir: pydata-berlin-2024 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0r2tGyr-hjbnCrjXRkCMvwB related_urls: - label: Conference Website url: https://2024.pycon.de/ language: eng dates: begin: 2024-06-14 end: 2024-06-16 default: 2024-06-14 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Global 2023 dir: pydata-global-2023 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0poULd1C4oUdPbPkTe4poJx related_urls: - label: Conference Website url: https://pydata.org/global2023/ language: eng dates: begin: 2023-12-06 end: 2023-12-08 default: 2023-12-06 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Eindhoven 2023 dir: pydata-eindhoven-2023 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0qkbJjIfppGO44yhDV2i4gR related_urls: - label: Conference Website url: https://web.archive.org/web/20240930133013/http://pydata.org/eindhoven2023 language: eng dates: begin: 2023-11-30 end: 2023-11-30 default: 2023-11-30 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData New York City 2023 dir: pydata-new-york-city-2023 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0o79mT1hHyqtFDSNzXXSYQM related_urls: - label: Conference Website url: https://pydata.org/nyc2023/ language: eng dates: begin: 2023-11-01 end: 2023-11-03 default: 2023-11-01 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Amsterdam 2023 dir: pydata-amsterdam-2023 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0pADyz2VboxPFIdrsozlENg related_urls: - label: Conference Website url: https://amsterdam2023.pydata.org/cfp/schedule/ language: eng dates: begin: 2023-09-14 end: 2023-09-16 default: 2023-09-14 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Seattle 2023 dir: pydata-seattle-2023 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0q81_-rt5jzJ--ZEgcNArKb related_urls: - label: Conference Website url: https://pydata.org/seattle2023/ language: eng dates: begin: 2023-04-26 end: 2023-04-28 default: 2023-04-26 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Berlin 2023 dir: pydata-berlin-2023 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0peDguAzds7kVmBr8avp46K related_urls: - label: Conference Website url: https://2023.pycon.de/ language: eng dates: begin: 2023-04-17 end: 2023-04-19 default: 2023-04-17 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Yerevan 2023 dir: pydata-yerevan-2023 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0pJKftCB2BtalTDE-2xS20g language: eng dates: begin: 2023-10-23 end: 2024-11-07 default: 2023-10-23 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Trójmiasto 2023 dir: pydata-trojmiasto-2023 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0qS0mI7s9tpXnS-XV5l_Ibs related_urls: - label: Conference Website url: https://www.meetup.com/pl-PL/pydata-trojmiasto/ language: eng dates: begin: 2023-10-24 end: 2023-10-24 default: 2023-10-24 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Tel Avid 2022 dir: pydata-tel-avid-2022 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0p6o_fjjdNPqy1rps49z2S0 related_urls: - label: Conference Website url: https://pydata.org/telaviv2022/ language: eng dates: begin: 2022-12-13 end: 2022-12-13 default: 2022-12-13 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Eindhoven 2022 dir: pydata-eindhoven-2022 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0pI60MsrFpHcII1qWm7drmZ related_urls: - label: Conference Website url: https://pydata.org/eindhoven2022/ language: eng dates: begin: 2022-12-02 end: 2022-12-02 default: 2022-12-02 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Global 2022 dir: pydata-global-2022 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0qgYUt0yn7F80wmzCnj2dEq related_urls: - label: Conference Website url: https://pydata.org/global2022/ language: eng dates: begin: 2022-12-01 end: 2022-12-03 default: 2022-12-01 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData New York City 2022 dir: pydata-new-york-city-2022 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0opPc5-dp6ZDCFvOqDBlUuv related_urls: - label: Conference Website url: https://pydata.org/nyc2022/ language: eng dates: begin: 2022-11-09 end: 2022-11-11 default: 2022-11-09 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Yerevan 2022 dir: pydata-yerevan-2022 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0qWwVVDmdOw6oxAlqqH8Ca- related_urls: - label: Conference Website url: https://pydata.org/yerevan2022/ language: eng dates: begin: 2022-08-12 end: 2022-08-13 default: 2022-08-12 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData London 2022 dir: pydata-london-2022 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0qT0MXnci7VBSF-U-0WaQ-w related_urls: - label: Conference Website url: https://pydata.org/london2022/ language: eng dates: begin: 2022-06-17 end: 2022-06-19 default: 2022-06-17 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Berlin 2022 dir: pydata-berlin-2022 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0p0Fal8_YKg6fPXnf3iPtwD related_urls: - label: Conference Website url: https://2022.pycon.de/ language: eng dates: begin: 2022-04-11 end: 2022-04-13 default: 2022-04-11 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Global 2021 dir: pydata-global-2021 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0rHb3JXG6puQnUAclFFZMlh related_urls: - label: Conference Website url: https://pydata.org/global2021/ language: eng dates: begin: 2021-10-28 end: 2021-10-30 default: 2021-10-28 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Eindhoven 2021 dir: pydata-eindhoven-2021 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0rBKcoKoaWJiMrDGdNr2_S0 related_urls: - label: Conference Website url: https://pydata.org/eindhoven2021/ language: eng dates: begin: 2021-11-12 end: 2021-11-12 default: 2021-11-12 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Global 2020 dir: pydata-global-2020 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0r0eC9BnITmYJ786p9Y1Q8D related_urls: - label: Conference Website url: https://pydataglobal.github.io/ language: eng dates: begin: 2020-11-11 end: 2020-11-15 default: 2020-11-11 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Eindhoven 2020 dir: pydata-eindhoven-2020 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0qpKjuGgNOgtOxIuATvnqEr related_urls: - label: Conference Website url: https://pydata.org/eindhoven2020/schedule/ language: eng dates: begin: 2020-10-07 end: 2020-10-09 default: 2020-10-07 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Amsterdam 2020 dir: pydata-amsterdam-2020 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0oX4ymLgldSvpfiZj-S8-fH related_urls: - label: Conference Website url: https://datasciencedistrict.nl/pydata-festival-amsterda/ language: eng dates: begin: 2020-06-15 end: 2020-06-20 default: 2020-06-15 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData South Africa 2018 dir: pydata-south-africa-2018 youtube_list: - https://www.youtube.com/watch?v=Lvw3Lp3KrTM&list=PLGjWYNrNnSuc78h5x23A5mLAzWlCl9LGf related_urls: - label: Conference Website url: https://2018.za.pycon.org/ language: eng dates: begin: 2018-10-11 end: 2018-10-12 default: 2018-10-11 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: - title: PyData Hamburg 2021 dir: pydata-hamburg-2021 youtube_list: - https://www.youtube.com/playlist?list=PLGVZCDnMOq0qbRG8gBRkosFfhWrObasQF related_urls: - label: Conference Website url: https://www.meetup.com/pydata-hamburg/ language: eng dates: begin: 2020-11-03 end: 2021-03-03 default: 2021-03-03 minimal_download: false issue: xxx overwrite: # all: true # takes precedence over add_new_files and existing_files_fields add_new_files: true existing_files_fields: - duration - thumbnail_url - videos - description - language - recorded - related_urls - speakers - tags - title tags: # ISO_639-3 language codes https://en.wikipedia.org/wiki/ISO_639-3 # languages = { # 'ita': 'Italian', # 'zho': 'Chinese', # 'por': 'Portuguese', # 'ukr': 'Ukrainian', # 'deu': 'German', # 'eng': 'English', # 'rus': 'Russian', # 'fra': 'French', # 'spa': 'Spanish', # 'eus': 'Basque', # 'cat': 'Catalan', # 'glg': 'Galician', # 'kor': 'Korean', # 'lit': 'Lithuanian', # 'jpn': 'Japanese', # 'ces': 'Czech', # 'pol': 'Polish', # 'heb': 'Hebrew', # 'tha': 'Thai', # } ~~~ Scraped with [pyvideo_scrape](https://github.com/pyvideo/pyvideo_scrape) --- pydata-berlin-2022/category.json | 3 + ...-network-inference-time-with-openvino.json | 48 +++++++++++++++ ...ty-best-practices-in-machine-learning.json | 48 +++++++++++++++ ...n-python-with-tensorflow-and-spektral.json | 48 +++++++++++++++ ...books-for-data-science-by-the-jetbrai.json | 48 +++++++++++++++ ...w-about-ai-adoption-in-the-enterprise.json | 48 +++++++++++++++ ...ata-scientist-s-guide-to-code-reviews.json | 48 +++++++++++++++ ...g-for-fraud-detection-on-marketplaces.json | 48 +++++++++++++++ ...-python-coders-with-dvc-and-streamlit.json | 56 +++++++++++++++++ ...adability-on-the-web-for-the-visually.json | 48 +++++++++++++++ ...cksand-while-engineering-a-computer-v.json | 48 +++++++++++++++ ...niel-ringler-sankey-plots-with-python.json | 48 +++++++++++++++ ...shboard-will-help-to-put-your-machine.json | 48 +++++++++++++++ .../dario-cannone-unclear-code-hurts.json | 48 +++++++++++++++ .../david-making-mlops-uncool-again.json | 60 +++++++++++++++++++ ...itioning-from-science-to-data-science.json | 48 +++++++++++++++ ...orduz-introduction-to-uplift-modeling.json | 48 +++++++++++++++ ...adi-do-we-really-need-data-scientists.json | 48 +++++++++++++++ ...loading-for-large-scale-deep-learning.json | 48 +++++++++++++++ ...ata-drift-in-machine-learning-systems.json | 48 +++++++++++++++ ...-pitfalls-when-transforming-the-targe.json | 48 +++++++++++++++ ...vanced-forecasting-probabilistic-glob.json | 48 +++++++++++++++ ...ein-to-create-real-ish-synthetic-data.json | 48 +++++++++++++++ .../gonul-ayci-you-shall-not-share.json | 48 +++++++++++++++ ...ducing-the-dask-active-memory-manager.json | 48 +++++++++++++++ ...-scikit-learn-machine-learning-models.json | 48 +++++++++++++++ ...riting-your-r-analysis-code-in-python.json | 48 +++++++++++++++ ...r-than-yours-what-does-that-even-mean.json | 48 +++++++++++++++ ...project-lessons-learned-in-production.json | 48 +++++++++++++++ ...ing-applications-fast-and-simple-with.json | 48 +++++++++++++++ ...rce-package-for-document-intelligence.json | 48 +++++++++++++++ ...-datapoint-selection-for-billion-poin.json | 48 +++++++++++++++ ...upyterlite-jupyter-webassembly-python.json | 48 +++++++++++++++ ...p-your-data-analysis-on-a-single-core.json | 55 +++++++++++++++++ ...o-slack-bot-based-workflow-automation.json | 48 +++++++++++++++ ...s-and-views-updating-pandas-internals.json | 48 +++++++++++++++ ...-fundamentals-of-relational-databases.json | 48 +++++++++++++++ ...lle-dado-emily-gorcenski-career-panel.json | 48 +++++++++++++++ ...age-classifier-knows-whats-in-a-photo.json | 48 +++++++++++++++ ...xai-meets-natural-language-processing.json | 48 +++++++++++++++ ...re-than-30-machine-learning-use-cases.json | 48 +++++++++++++++ ...-data-labelling-with-weak-supervision.json | 48 +++++++++++++++ ...hristen-creating-3d-maps-using-python.json | 52 ++++++++++++++++ ...-hayward-serious-time-for-time-series.json | 48 +++++++++++++++ ...erience-diversity-and-culture-in-open.json | 48 +++++++++++++++ ...-personal-data-projects-to-re-own-the.json | 48 +++++++++++++++ ...nteractive-plots-and-apps-with-hvplot.json | 52 ++++++++++++++++ ...hine-learning-and-science-with-python.json | 48 +++++++++++++++ ...kit-learn-open-source-journey-keynote.json | 52 ++++++++++++++++ ...lgrim-data-science-at-scale-with-dask.json | 48 +++++++++++++++ ...ing-algorithms-predict-reader-prefere.json | 48 +++++++++++++++ ...tering-identifying-product-clusters-f.json | 48 +++++++++++++++ ...cret-sauce-of-data-science-management.json | 48 +++++++++++++++ .../sonam-biases-in-language-models.json | 48 +++++++++++++++ ...ity-how-ai-is-widening-social-divides.json | 48 +++++++++++++++ ...f-n-dimensional-arrays-and-dataframes.json | 48 +++++++++++++++ ...-tensorflow-pytorch-and-deepstack-how.json | 48 +++++++++++++++ ...in-python-compliant-with-scikit-learn.json | 48 +++++++++++++++ ...-data-unit-tests-and-why-we-need-them.json | 48 +++++++++++++++ ...-how-to-trust-your-deep-learning-code.json | 48 +++++++++++++++ ...and-anomaly-detection-for-wind-energy.json | 48 +++++++++++++++ ...bak-introduction-to-mlops-with-mlflow.json | 48 +++++++++++++++ ...t-map-data-with-python-and-postgresql.json | 48 +++++++++++++++ ...lexible-imaging-with-the-core-imaging.json | 52 ++++++++++++++++ ...chine-learning-on-data-you-cannot-see.json | 48 +++++++++++++++ ...-forge-supporting-the-growth-of-the-v.json | 48 +++++++++++++++ ...-learning-testing-ecosystem-of-python.json | 48 +++++++++++++++ 67 files changed, 3214 insertions(+) create mode 100644 pydata-berlin-2022/category.json create mode 100644 pydata-berlin-2022/videos/adrian-boguszewski-optimize-your-network-inference-time-with-openvino.json create mode 100644 pydata-berlin-2022/videos/alejandro-saucedo-secure-ml-automated-security-best-practices-in-machine-learning.json create mode 100644 pydata-berlin-2022/videos/aleksander-molak-practical-graph-neural-networks-in-python-with-tensorflow-and-spektral.json create mode 100644 pydata-berlin-2022/videos/alena-guzharina-overcoming-5-hurdles-to-using-jupyter-notebooks-for-data-science-by-the-jetbrai.json create mode 100644 pydata-berlin-2022/videos/alexander-cs-hendorf-5-things-you-want-to-know-about-ai-adoption-in-the-enterprise.json create mode 100644 pydata-berlin-2022/videos/alexandra-worner-a-data-scientist-s-guide-to-code-reviews.json create mode 100644 pydata-berlin-2022/videos/andreu-mora-unsupervised-shallow-learning-for-fraud-detection-on-marketplaces.json create mode 100644 pydata-berlin-2022/videos/antoine-toubhans-flexible-ml-experiment-tracking-system-for-python-coders-with-dvc-and-streamlit.json create mode 100644 pydata-berlin-2022/videos/asya-frumkin-can-you-read-this-or-how-i-improved-text-readability-on-the-web-for-the-visually.json create mode 100644 pydata-berlin-2022/videos/bettina-heinlein-challenge-accepted-how-to-escape-the-quicksand-while-engineering-a-computer-v.json create mode 100644 pydata-berlin-2022/videos/daniel-ringler-sankey-plots-with-python.json create mode 100644 pydata-berlin-2022/videos/daniel-willemsen-welmoet-verbaan-how-a-simple-streamlit-dashboard-will-help-to-put-your-machine.json create mode 100644 pydata-berlin-2022/videos/dario-cannone-unclear-code-hurts.json create mode 100644 pydata-berlin-2022/videos/david-making-mlops-uncool-again.json create mode 100644 pydata-berlin-2022/videos/dr-hannah-bohle-come-as-you-are-transitioning-from-science-to-data-science.json create mode 100644 pydata-berlin-2022/videos/dr-juan-orduz-introduction-to-uplift-modeling.json create mode 100644 pydata-berlin-2022/videos/dr-setareh-sadjadi-do-we-really-need-data-scientists.json create mode 100644 pydata-berlin-2022/videos/dr-thomas-wollmann-squirrel-efficient-data-loading-for-large-scale-deep-learning.json create mode 100644 pydata-berlin-2022/videos/emeli-dral-detecting-drift-how-to-evaluate-and-explore-data-drift-in-machine-learning-systems.json create mode 100644 pydata-berlin-2022/videos/florian-wilhelm-honey-i-shrunk-the-target-variable-common-pitfalls-when-transforming-the-targe.json create mode 100644 pydata-berlin-2022/videos/franz-kiraly-sktime-python-toolbox-for-time-series-advanced-forecasting-probabilistic-glob.json create mode 100644 pydata-berlin-2022/videos/gatha-do-i-need-to-be-dr-frankenstein-to-create-real-ish-synthetic-data.json create mode 100644 pydata-berlin-2022/videos/gonul-ayci-you-shall-not-share.json create mode 100644 pydata-berlin-2022/videos/guido-imperiale-introducing-the-dask-active-memory-manager.json create mode 100644 pydata-berlin-2022/videos/guillaume-lemaitre-inpsect-and-try-to-interpret-your-scikit-learn-machine-learning-models.json create mode 100644 pydata-berlin-2022/videos/helena-schmidt-rewriting-your-r-analysis-code-in-python.json create mode 100644 pydata-berlin-2022/videos/illia-babounikau-my-forecast-is-better-than-yours-what-does-that-even-mean.json create mode 100644 pydata-berlin-2022/videos/jacopo-farina-using-a-database-in-a-data-science-project-lessons-learned-in-production.json create mode 100644 pydata-berlin-2022/videos/jan-benedikt-jagusch-christian-bourjau-making-machine-learning-applications-fast-and-simple-with.json create mode 100644 pydata-berlin-2022/videos/janis-meyer-deepdoctection-an-open-source-package-for-document-intelligence.json create mode 100644 pydata-berlin-2022/videos/jean-luc-stevens-seeing-the-needle-and-the-haystack-single-datapoint-selection-for-billion-poin.json create mode 100644 pydata-berlin-2022/videos/jeremy-tuloup-jupyterlite-jupyter-webassembly-python.json create mode 100644 pydata-berlin-2022/videos/jonathan-striebel-5-steps-to-speed-up-your-data-analysis-on-a-single-core.json create mode 100644 pydata-berlin-2022/videos/jordi-smit-slack-bots-101-an-introduction-into-slack-bot-based-workflow-automation.json create mode 100644 pydata-berlin-2022/videos/joris-van-den-bossche-on-blocks-copies-and-views-updating-pandas-internals.json create mode 100644 pydata-berlin-2022/videos/katharina-rasch-fundamentals-of-relational-databases.json create mode 100644 pydata-berlin-2022/videos/katharine-jarmul-matteo-guzzo-sieer-angar-marielle-dado-emily-gorcenski-career-panel.json create mode 100644 pydata-berlin-2022/videos/kilian-kluge-grokking-lime-how-can-we-explain-why-an-image-classifier-knows-whats-in-a-photo.json create mode 100644 pydata-berlin-2022/videos/larissa-haas-xai-meets-natural-language-processing.json create mode 100644 pydata-berlin-2022/videos/lina-weichbrodt-what-i-learned-from-monitoring-more-than-30-machine-learning-use-cases.json create mode 100644 pydata-berlin-2022/videos/maria-mestre-efficient-data-labelling-with-weak-supervision.json create mode 100644 pydata-berlin-2022/videos/martin-christen-creating-3d-maps-using-python.json create mode 100644 pydata-berlin-2022/videos/marysia-winkels-james-hayward-serious-time-for-time-series.json create mode 100644 pydata-berlin-2022/videos/melissa-weber-mendonca-beyond-the-basics-contributor-experience-diversity-and-culture-in-open.json create mode 100644 pydata-berlin-2022/videos/paula-gonzalez-avalos-your-data-your-insights-creating-personal-data-projects-to-re-own-the.json create mode 100644 pydata-berlin-2022/videos/philipp-rudiger-maxime-liquet-easily-build-interactive-plots-and-apps-with-hvplot.json create mode 100644 pydata-berlin-2022/videos/prabhant-singh-reproducible-machine-learning-and-science-with-python.json create mode 100644 pydata-berlin-2022/videos/reshama-shaikh-5-years-10-sprints-a-scikit-learn-open-source-journey-keynote.json create mode 100644 pydata-berlin-2022/videos/richard-pelgrim-data-science-at-scale-with-dask.json create mode 100644 pydata-berlin-2022/videos/sebastian-cattes-performing-content-can-nlp-and-deep-learning-algorithms-predict-reader-prefere.json create mode 100644 pydata-berlin-2022/videos/sebastian-wanner-christopher-lennan-transformer-based-clustering-identifying-product-clusters-f.json create mode 100644 pydata-berlin-2022/videos/shir-meir-lador-the-secret-sauce-of-data-science-management.json create mode 100644 pydata-berlin-2022/videos/sonam-biases-in-language-models.json create mode 100644 pydata-berlin-2022/videos/stefanie-stoppel-the-myth-of-neutrality-how-ai-is-widening-social-divides.json create mode 100644 pydata-berlin-2022/videos/stephannie-jimenez-gacha-data-apis-standardization-of-n-dimensional-arrays-and-dataframes.json create mode 100644 pydata-berlin-2022/videos/steven-kolawole-building-a-sign-to-speech-prototype-with-tensorflow-pytorch-and-deepstack-how.json create mode 100644 pydata-berlin-2022/videos/sylvain-marie-python-m5p-m5-prime-regression-trees-in-python-compliant-with-scikit-learn.json create mode 100644 pydata-berlin-2022/videos/theodore-meynard-what-are-data-unit-tests-and-why-we-need-them.json create mode 100644 pydata-berlin-2022/videos/tilman-krokotsch-how-to-trust-your-deep-learning-code.json create mode 100644 pydata-berlin-2022/videos/tobias-hoinka-predictive-maintenance-and-anomaly-detection-for-wind-energy.json create mode 100644 pydata-berlin-2022/videos/tobias-sterbak-introduction-to-mlops-with-mlflow.json create mode 100644 pydata-berlin-2022/videos/travis-hathaway-processing-open-street-map-data-with-python-and-postgresql.json create mode 100644 pydata-berlin-2022/videos/vaggelis-papoutsellis-dr-jakob-sauer-jorgensen-easy-and-flexible-imaging-with-the-core-imaging.json create mode 100644 pydata-berlin-2022/videos/valerio-maggio-ppml-machine-learning-on-data-you-cannot-see.json create mode 100644 pydata-berlin-2022/videos/wolf-vollprecht-jannis-leidel-jaime-rodriguez-guerra-conda-forge-supporting-the-growth-of-the-v.json create mode 100644 pydata-berlin-2022/videos/yunus-emrah-bulut-machine-learning-testing-ecosystem-of-python.json diff --git a/pydata-berlin-2022/category.json b/pydata-berlin-2022/category.json new file mode 100644 index 000000000..4281e5380 --- /dev/null +++ b/pydata-berlin-2022/category.json @@ -0,0 +1,3 @@ +{ + "title": "PyData Berlin 2022" +} diff --git a/pydata-berlin-2022/videos/adrian-boguszewski-optimize-your-network-inference-time-with-openvino.json b/pydata-berlin-2022/videos/adrian-boguszewski-optimize-your-network-inference-time-with-openvino.json new file mode 100644 index 000000000..e95fa4989 --- /dev/null +++ b/pydata-berlin-2022/videos/adrian-boguszewski-optimize-your-network-inference-time-with-openvino.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Adrian Boguszewski\n\nTrack: PyData: Deep Learning\nDuring the talk, I'll present the OpenVINO\u2122 Toolkit. You'll learn how to automatically convert the model using Model Optimizer and how to run the inference with OpenVINO Runtime to infer your model with low latency on the CPU and iGPU you already have. The magic with only a few lines of code.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/PKERX8\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1359, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/PKERX8", + "url": "https://2022.pycon.de/program/PKERX8" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/z2kjm3xbhbA/maxresdefault.webp", + "title": "Adrian Boguszewski: Optimize your network inference time with OpenVINO", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=z2kjm3xbhbA" + } + ] +} diff --git a/pydata-berlin-2022/videos/alejandro-saucedo-secure-ml-automated-security-best-practices-in-machine-learning.json b/pydata-berlin-2022/videos/alejandro-saucedo-secure-ml-automated-security-best-practices-in-machine-learning.json new file mode 100644 index 000000000..857bace17 --- /dev/null +++ b/pydata-berlin-2022/videos/alejandro-saucedo-secure-ml-automated-security-best-practices-in-machine-learning.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Alejandro Saucedo\n\nTrack: PyData: Machine Learning & Stats\nAs data science capabilities scale, the core concept of security becomes growingly critical. In this talk we will introduce the security challenges and solutions for data science practitioners relevant to each of the phases of the machine learning lifecycle, and we will provide a practical set of best practices and frameworks that can be adopted to ensure a relevant level of security is present in the multiple stages of the machine learning lifecycle.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/APTWQS\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1494, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://2022.pycon.de/program/APTWQS", + "url": "https://2022.pycon.de/program/APTWQS" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/82uiA5evtyU/maxresdefault.webp", + "title": "Alejandro Saucedo: Secure ML: Automated Security Best Practices in Machine Learning", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=82uiA5evtyU" + } + ] +} diff --git a/pydata-berlin-2022/videos/aleksander-molak-practical-graph-neural-networks-in-python-with-tensorflow-and-spektral.json b/pydata-berlin-2022/videos/aleksander-molak-practical-graph-neural-networks-in-python-with-tensorflow-and-spektral.json new file mode 100644 index 000000000..6adeb3bea --- /dev/null +++ b/pydata-berlin-2022/videos/aleksander-molak-practical-graph-neural-networks-in-python-with-tensorflow-and-spektral.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Aleksander Molak\n\nTrack: PyData: Deep Learning\nGraph neural networks (GNNs) have become one of the hottest research topics in recent years. Their popularity is reinforced by hugely successful industry applications in social networks, biology, chemistry, neuroscience and many other areas. One of the main challenges faced by data scientists and researchers who want to apply graph networks in their work is that they require different data structures and a slightly different training approach than traditional deep learning models. During the workshop we\u2019ll demonstrate how to implement graph neural networks, how to prepare your data and \u2013 finally \u2013 how to train a GNN model for node-level and graph-level tasks using Spektral and TensorFlow.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/ZMFZUB\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 5428, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/ZMFZUB", + "url": "https://2022.pycon.de/program/ZMFZUB" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/hCY0_6etLjk/maxresdefault.webp", + "title": "Aleksander Molak: Practical graph neural networks in Python with TensorFlow and Spektral", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=hCY0_6etLjk" + } + ] +} diff --git a/pydata-berlin-2022/videos/alena-guzharina-overcoming-5-hurdles-to-using-jupyter-notebooks-for-data-science-by-the-jetbrai.json b/pydata-berlin-2022/videos/alena-guzharina-overcoming-5-hurdles-to-using-jupyter-notebooks-for-data-science-by-the-jetbrai.json new file mode 100644 index 000000000..b98d510fe --- /dev/null +++ b/pydata-berlin-2022/videos/alena-guzharina-overcoming-5-hurdles-to-using-jupyter-notebooks-for-data-science-by-the-jetbrai.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Alena Guzharina\n\nTrack: PyData: Jupyter\nJupyter notebooks have pretty much become the standard for data science and data analysis teams. However, there\u2019s still a number of pain points when it comes to working with them. \r\n\r\nToday we\u2019ll discuss setting up environments, getting data from data providers, writing code without IDE support, and sharing results, as well as collaboration and reproducibility. We\u2019ll also explain how our team tackles these problems in Datalore.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/9D9X8L\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1499, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/9D9X8L", + "url": "https://2022.pycon.de/program/9D9X8L" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/I_1y4pQ5ZQw/maxresdefault.webp", + "title": "Alena Guzharina: Overcoming 5 Hurdles to Using Jupyter Notebooks for Data Science, by the JetBrai...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=I_1y4pQ5ZQw" + } + ] +} diff --git a/pydata-berlin-2022/videos/alexander-cs-hendorf-5-things-you-want-to-know-about-ai-adoption-in-the-enterprise.json b/pydata-berlin-2022/videos/alexander-cs-hendorf-5-things-you-want-to-know-about-ai-adoption-in-the-enterprise.json new file mode 100644 index 000000000..23d4c0420 --- /dev/null +++ b/pydata-berlin-2022/videos/alexander-cs-hendorf-5-things-you-want-to-know-about-ai-adoption-in-the-enterprise.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Alexander CS Hendorf\n\nTrack: General: Production\nAll one needs is strategy, skill and resources to make digitalization and AI happen. So why is everything taking so long? Shouldn\u2019t you all be finished yesterday already? Or: how do we start? A practitioner's talk for everyone involved making AI happen in enterprises with use cases.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/EMNPJW\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1711, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/EMNPJW", + "url": "https://2022.pycon.de/program/EMNPJW" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/0UG_JLUWJOQ/maxresdefault.webp", + "title": "Alexander CS Hendorf: 5 Things You Want to Know About AI Adoption in the Enterprise", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=0UG_JLUWJOQ" + } + ] +} diff --git a/pydata-berlin-2022/videos/alexandra-worner-a-data-scientist-s-guide-to-code-reviews.json b/pydata-berlin-2022/videos/alexandra-worner-a-data-scientist-s-guide-to-code-reviews.json new file mode 100644 index 000000000..72744f53d --- /dev/null +++ b/pydata-berlin-2022/videos/alexandra-worner-a-data-scientist-s-guide-to-code-reviews.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Alexandra W\u00f6rner\n\nTrack: General: Python & PyData Friends\nA crucial aspect of software engineering teams' working agreements are code reviews. By applying the four-eyes principle on code, teams can reduce the number of bugs and errors, uncover misunderstandings early and ensure a certain level of quality across their common code base. \r\nIn essence, the relevance of code reviews does not change for data teams, including data scientists. However, due to the often experimental nature of data science tasks, standard code reviews do not always work well and therefore need some tweaks. \r\n\r\nThis talk will give a data scientist's view on code reviews, focussing on which aspects data scientists can pull from the general process and what needs to be adjusted in order to have effective and satisfying code reviews. Building on that, you will get recommendations for the following questions:\r\n* When and what should I review?\r\n* What feedback should I give?\r\n* What tools support me in executing this task?\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/YT7WM7\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1807, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/YT7WM7", + "url": "https://2022.pycon.de/program/YT7WM7" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/h8oI24i9dPk/maxresdefault.webp", + "title": "Alexandra W\u00f6rner: A data scientist's guide to code reviews", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=h8oI24i9dPk" + } + ] +} diff --git a/pydata-berlin-2022/videos/andreu-mora-unsupervised-shallow-learning-for-fraud-detection-on-marketplaces.json b/pydata-berlin-2022/videos/andreu-mora-unsupervised-shallow-learning-for-fraud-detection-on-marketplaces.json new file mode 100644 index 000000000..51ad3b798 --- /dev/null +++ b/pydata-berlin-2022/videos/andreu-mora-unsupervised-shallow-learning-for-fraud-detection-on-marketplaces.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Andreu Mora\n\nTrack: PyData: Machine Learning & Stats\nCombating fraud, scams and wrongdoings in large marketplaces and platforms that connect millions of individuals as sellers and shoppers poses a very exciting and also difficult problem. Adyen leverages massive transaction information to solve this problem for platforms such as eBay or GoFundMe. In this talk we'll cover how we defined the problem, iterated on it and leveraged open source data tooling over python (airflow, spark, tensorflow, keras) and shallow unsupervised learning to solve it.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/GCVHBH\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1488, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/GCVHBH", + "url": "https://2022.pycon.de/program/GCVHBH" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/Ce_IPb7htGY/maxresdefault.webp", + "title": "Andreu Mora: Unsupervised shallow learning for fraud detection on marketplaces", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=Ce_IPb7htGY" + } + ] +} diff --git a/pydata-berlin-2022/videos/antoine-toubhans-flexible-ml-experiment-tracking-system-for-python-coders-with-dvc-and-streamlit.json b/pydata-berlin-2022/videos/antoine-toubhans-flexible-ml-experiment-tracking-system-for-python-coders-with-dvc-and-streamlit.json new file mode 100644 index 000000000..b2cf944e1 --- /dev/null +++ b/pydata-berlin-2022/videos/antoine-toubhans-flexible-ml-experiment-tracking-system-for-python-coders-with-dvc-and-streamlit.json @@ -0,0 +1,56 @@ +{ + "description": "Speaker:: Antoine Toubhans\n\nTrack: PyData: PyData & Scientific Libraries Stack\nThere are tons of tools to do data science. Too often, data scientists end up using a monolithic AI platform that \u201cdoes everything by clicking on a UI\u201d. In this talk, I will walk you through a pythonic and flexible ML experiment tracking system based on 1) GIT \ud83d\ude42 2) [DVC](https://dvc.org/) (Data Version Control) to track the data 3) [Streamlit](https://streamlit.io/) to build a data exploration app. I will quickly introduce the tools separately and then focus on how they can be combined together to build a tailor-made experiment tracking system.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/WADNGC\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2738, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/WADNGC", + "url": "https://2022.pycon.de/program/WADNGC" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://dvc.org/", + "url": "https://dvc.org/" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://streamlit.io/", + "url": "https://streamlit.io/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/YOSVMMwTlHM/maxresdefault.webp", + "title": "Antoine Toubhans: Flexible ML Experiment Tracking System for Python Coders with DVC and Streamlit", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=YOSVMMwTlHM" + } + ] +} diff --git a/pydata-berlin-2022/videos/asya-frumkin-can-you-read-this-or-how-i-improved-text-readability-on-the-web-for-the-visually.json b/pydata-berlin-2022/videos/asya-frumkin-can-you-read-this-or-how-i-improved-text-readability-on-the-web-for-the-visually.json new file mode 100644 index 000000000..f57588631 --- /dev/null +++ b/pydata-berlin-2022/videos/asya-frumkin-can-you-read-this-or-how-i-improved-text-readability-on-the-web-for-the-visually.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Asya Frumkin\n\nTrack: PyData: Computer Vision\nI will explain my approach of detecting texts on top of an image background that are unreadable to people with visual impairment. I will explain the challenges I. encountered when using different OCR architectures for this task and talk about the solution I came up with.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/MCLBLZ\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1743, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/MCLBLZ", + "url": "https://2022.pycon.de/program/MCLBLZ" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/dIDWJ3uTl8I/maxresdefault.webp", + "title": "Asya Frumkin: Can you Read This? (Or: how I Improved Text Readability on the Web for the Visually...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=dIDWJ3uTl8I" + } + ] +} diff --git a/pydata-berlin-2022/videos/bettina-heinlein-challenge-accepted-how-to-escape-the-quicksand-while-engineering-a-computer-v.json b/pydata-berlin-2022/videos/bettina-heinlein-challenge-accepted-how-to-escape-the-quicksand-while-engineering-a-computer-v.json new file mode 100644 index 000000000..a8ca86d5d --- /dev/null +++ b/pydata-berlin-2022/videos/bettina-heinlein-challenge-accepted-how-to-escape-the-quicksand-while-engineering-a-computer-v.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Bettina Heinlein\n\nTrack: PyData: Computer Vision\nHave you ever been in a situation where you do not know the next step? This talk presents the challenges encountered while building a Computer Vision application, and how problem-solving strategies were utilized. While the discussed strategies are applicable to Computer Vision, they can also be applied to Software Engineering and beyond.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/BHZG8Z\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1539, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/BHZG8Z", + "url": "https://2022.pycon.de/program/BHZG8Z" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/hq-Adl0uTzs/maxresdefault.webp", + "title": "Bettina Heinlein: Challenge Accepted - How to Escape the Quicksand While Engineering a Computer V...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=hq-Adl0uTzs" + } + ] +} diff --git a/pydata-berlin-2022/videos/daniel-ringler-sankey-plots-with-python.json b/pydata-berlin-2022/videos/daniel-ringler-sankey-plots-with-python.json new file mode 100644 index 000000000..528b46f3a --- /dev/null +++ b/pydata-berlin-2022/videos/daniel-ringler-sankey-plots-with-python.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Daniel Ringler\n\nTrack: PyData: Visualization\nThis talk provides an introduction to Sankey plots with a focus on creating them with various Python libraries. We will talk about the pros and cons of the libraries, give practical advice on how and when to use them, and what you should regard when creating Sankey plots yourself.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/7SFQNW\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1581, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/7SFQNW", + "url": "https://2022.pycon.de/program/7SFQNW" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/rgwr3wDQ3uQ/maxresdefault.webp", + "title": "Daniel Ringler: Sankey Plots with Python", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=rgwr3wDQ3uQ" + } + ] +} diff --git a/pydata-berlin-2022/videos/daniel-willemsen-welmoet-verbaan-how-a-simple-streamlit-dashboard-will-help-to-put-your-machine.json b/pydata-berlin-2022/videos/daniel-willemsen-welmoet-verbaan-how-a-simple-streamlit-dashboard-will-help-to-put-your-machine.json new file mode 100644 index 000000000..5e43c367f --- /dev/null +++ b/pydata-berlin-2022/videos/daniel-willemsen-welmoet-verbaan-how-a-simple-streamlit-dashboard-will-help-to-put-your-machine.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Dani\u00ebl Willemsen Welmoet Verbaan\n\nTrack: PyData: Visualization\nHave you struggled getting your valuable machine learning model into the hands of users? No matter how good your ML model is; a lack of monitoring and insights can prevent users from using your product. For this reason, you should build a monitoring dashboard that serves two functions: a. Monitoring of performance metrics and b. Delivering insights to improve understanding of the model & it\u2019s predictions. In this talk, we explain how these two functions combined contribute towards the primary goal of getting a valuable model into the hands of users & show how easy it is to create such a dashboard through streamlit.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/METVVV\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1811, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/METVVV", + "url": "https://2022.pycon.de/program/METVVV" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/2AYLBuwtfJo/maxresdefault.webp", + "title": "Dani\u00ebl Willemsen Welmoet Verbaan: How a simple streamlit dashboard will help to put your machine...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=2AYLBuwtfJo" + } + ] +} diff --git a/pydata-berlin-2022/videos/dario-cannone-unclear-code-hurts.json b/pydata-berlin-2022/videos/dario-cannone-unclear-code-hurts.json new file mode 100644 index 000000000..182f3531b --- /dev/null +++ b/pydata-berlin-2022/videos/dario-cannone-unclear-code-hurts.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Dario Cannone\n\nTrack: General: Python & PyData Friends\nCode may work or not, but it will always tell a story. Computers will not complain about how you write it (except correct syntax), but human readers will. This talk is about writing clear code and caring for the human beings that will read it. Yourself included.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/GSG7KQ\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1834, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/GSG7KQ", + "url": "https://2022.pycon.de/program/GSG7KQ" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi/CkeuNL8LAC0/maxresdefault.jpg", + "title": "Dario Cannone: Unclear Code Hurts", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=CkeuNL8LAC0" + } + ] +} diff --git a/pydata-berlin-2022/videos/david-making-mlops-uncool-again.json b/pydata-berlin-2022/videos/david-making-mlops-uncool-again.json new file mode 100644 index 000000000..206f5a74f --- /dev/null +++ b/pydata-berlin-2022/videos/david-making-mlops-uncool-again.json @@ -0,0 +1,60 @@ +{ + "description": "Speaker:: David\n\nTrack: PyData: Machine Learning & Stats\nMachine learning operations (MLOps) have gained attention among practitioners aiming to automate the development of Machine Learning models, attempting to mimic the impact of DevOps in software. \r\n\r\nHowever, MLOps platforms are usually built isolated from the software development process, arguing that the well-proven tools used for DevOps can't be applied to Machine Learning projects.\r\n\r\nIn this workshop, we will use [HuggingFace](https://huggingface.co/) to train a model that predicts labels for GitHub issues. \r\n\r\nBy extending the power of Git and Github with [DVC](https://dvc.org/) and [CML](https://cml.dev/), our workflow will be able to handle the entire lifecycle of a Machine Learning model using the same tools and platforms that have been proven to work for software development.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/3PVNYH\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 4631, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/3PVNYH", + "url": "https://2022.pycon.de/program/3PVNYH" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://dvc.org/", + "url": "https://dvc.org/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://cml.dev/", + "url": "https://cml.dev/" + }, + { + "label": "https://huggingface.co/", + "url": "https://huggingface.co/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/_kN3sDC3XKY/maxresdefault.webp", + "title": "David: Making MLOps uncool again", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=_kN3sDC3XKY" + } + ] +} diff --git a/pydata-berlin-2022/videos/dr-hannah-bohle-come-as-you-are-transitioning-from-science-to-data-science.json b/pydata-berlin-2022/videos/dr-hannah-bohle-come-as-you-are-transitioning-from-science-to-data-science.json new file mode 100644 index 000000000..1b59aa81f --- /dev/null +++ b/pydata-berlin-2022/videos/dr-hannah-bohle-come-as-you-are-transitioning-from-science-to-data-science.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Dr. Hannah Bohle\n\nTrack: General: Community, Diversity, Carreer, Life and everything else\nI would like to give a little insight into my journey from academia to industry. \r\n\r\nI started working as a data scientist after more than a decade in quantitative science and leaving my post-doc position in neuroscience. Now I am often asked by scientists how I made the transition. In my talk, I want to encourage newcomers, show them what they might already bring to the table, help them avoid pitfalls, and explain what I think might be helpful in finding a first job as a data scientist. I'll also touch on the tech stack needed and what role Python plays in that. Come as you are!\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/3L8NHL\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1706, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/3L8NHL", + "url": "https://2022.pycon.de/program/3L8NHL" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/rUyPurQEszc/maxresdefault.webp", + "title": "Dr. Hannah Bohle: Come as you are: Transitioning from Science to Data Science", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=rUyPurQEszc" + } + ] +} diff --git a/pydata-berlin-2022/videos/dr-juan-orduz-introduction-to-uplift-modeling.json b/pydata-berlin-2022/videos/dr-juan-orduz-introduction-to-uplift-modeling.json new file mode 100644 index 000000000..fd8522bdb --- /dev/null +++ b/pydata-berlin-2022/videos/dr-juan-orduz-introduction-to-uplift-modeling.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Dr. Juan Orduz\n\nTrack: PyData: Machine Learning & Stats\nIn this talk we introduce uplift modelling, a method to estimate causal effects of a treatment, e.g. a marketing campaign, to effectively target customers that are most likely to respond to it. We describe the most common methods to estimate such effects by working a concrete example.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/QY7P98\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2645, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/QY7P98", + "url": "https://2022.pycon.de/program/QY7P98" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/VWjsi-5yc3w/maxresdefault.webp", + "title": "Dr. Juan Orduz: Introduction to Uplift Modeling", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=VWjsi-5yc3w" + } + ] +} diff --git a/pydata-berlin-2022/videos/dr-setareh-sadjadi-do-we-really-need-data-scientists.json b/pydata-berlin-2022/videos/dr-setareh-sadjadi-do-we-really-need-data-scientists.json new file mode 100644 index 000000000..82fdce04b --- /dev/null +++ b/pydata-berlin-2022/videos/dr-setareh-sadjadi-do-we-really-need-data-scientists.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Dr. Setareh Sadjadi\n\nTrack: General: Community, Diversity, Carreer, Life and everything else\nThe term Data Science has emerged in the late 70s in a wider spectrum of research and industry and since then we observed an increasing trend for it, especially from late 90s. Data Science job became very hot between 2010-2018 and many companies started hiring data scientists worldwide and many people have been changing their career to data science, from academia or IT industry. However, we have been hearing about \u201cdeath of data science\u201d here and there in the past 2 years as AI/ML field has been growing and many automated ML tools emerging.\r\nLooking at Google Trends for \u201cData Science\u201d shows a slow decreasing pattern since mid 2020 as well. That means people have started to google less for \u201cData Science\u201d. And the job descriptions have become more in the direction of Machine Learning Engineering for so many companies. The job definition of data science has always been vague, and any company has been adopting it to their own needs, but it might be now the time to properly define this job. In this talk I would like to talk about what the job of a data science is and if data science is really going to die and why there is a gap between data science job descriptions and the real skills of the workforce looking for the jobs.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/BKSMFA\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1579, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/BKSMFA", + "url": "https://2022.pycon.de/program/BKSMFA" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/PxCVbpDYaCM/maxresdefault.webp", + "title": "Dr. Setareh Sadjadi: Do we really need Data Scientists?", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=PxCVbpDYaCM" + } + ] +} diff --git a/pydata-berlin-2022/videos/dr-thomas-wollmann-squirrel-efficient-data-loading-for-large-scale-deep-learning.json b/pydata-berlin-2022/videos/dr-thomas-wollmann-squirrel-efficient-data-loading-for-large-scale-deep-learning.json new file mode 100644 index 000000000..3c466bbe2 --- /dev/null +++ b/pydata-berlin-2022/videos/dr-thomas-wollmann-squirrel-efficient-data-loading-for-large-scale-deep-learning.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Dr. Thomas Wollmann\n\nTrack: PyData: Data Handling\nData stall in deep learning training refers to the case where combined throughput of data loading and transformation is less than the consumption rate of the model, leading to idling of expensive GPU resources and prolonged training. \r\n\r\nData loading in deep learning pipelines have a very specific set of constraints, performance requirements, and cost structure. While Object Store is a low-cost storage solution, repeated retrieval can be expensive and slow, which can lead to data stall. SSD is an expensive storage solution with fast retrieval, which is not as scalable as Object Store. Run-time transformation is a common subsequent step, which is highly variable across model configurations, and highly dependent on the data loading step. Any configuration of data loading which is optimal in one scenario is almost certainly sub-optimal in another. Therefore, an ideal data pipeline should be elastic and adaptable.\r\n\r\nWe present solutions to these challenges. Our approach uses chain-able components to express the deep learning data pipeline with pluggable executors to decouple IO-bound and CPU-bound operations, and to scale out to clusters of machines. We discuss the importance of sharding and caching for cost reduction, and the unification of storage and loading based on open standard file formats. We hope that our efforts make large-scale model training accessible to a wider community of researchers and practitioners, and enable sustainable deep learning pipelines.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/CHTY3U\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2438, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/CHTY3U", + "url": "https://2022.pycon.de/program/CHTY3U" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/pZPbi4EmqEo/maxresdefault.webp", + "title": "Dr. Thomas Wollmann: Squirrel - Efficient Data Loading for Large-Scale Deep Learning", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=pZPbi4EmqEo" + } + ] +} diff --git a/pydata-berlin-2022/videos/emeli-dral-detecting-drift-how-to-evaluate-and-explore-data-drift-in-machine-learning-systems.json b/pydata-berlin-2022/videos/emeli-dral-detecting-drift-how-to-evaluate-and-explore-data-drift-in-machine-learning-systems.json new file mode 100644 index 000000000..8082750bc --- /dev/null +++ b/pydata-berlin-2022/videos/emeli-dral-detecting-drift-how-to-evaluate-and-explore-data-drift-in-machine-learning-systems.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Emeli Dral\n\nTrack: PyData: Machine Learning & Stats\nWhen your ML model is in production, you might observe input data and prediction drift. In absence of ground truth, drift can serve as a proxy for the model performance. But how exactly to evaluate it? In this talk, I will give an overview of the possible approaches, and how to implement and visualize the results.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/ASW8CJ\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1770, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://2022.pycon.de/program/ASW8CJ", + "url": "https://2022.pycon.de/program/ASW8CJ" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/0wdCMvU1vCQ/maxresdefault.webp", + "title": "Emeli Dral: Detecting drift: how to evaluate and explore data drift in machine learning systems", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=0wdCMvU1vCQ" + } + ] +} diff --git a/pydata-berlin-2022/videos/florian-wilhelm-honey-i-shrunk-the-target-variable-common-pitfalls-when-transforming-the-targe.json b/pydata-berlin-2022/videos/florian-wilhelm-honey-i-shrunk-the-target-variable-common-pitfalls-when-transforming-the-targe.json new file mode 100644 index 000000000..a6d7ee0d1 --- /dev/null +++ b/pydata-berlin-2022/videos/florian-wilhelm-honey-i-shrunk-the-target-variable-common-pitfalls-when-transforming-the-targe.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Florian Wilhelm\n\nTrack: PyData: Machine Learning & Stats\nFeature engineering takes up a huge part in the work-life of a data scientist. Sometimes this doesn't stop at features but also the target variable itself is transformed leading to all kinds of unexpected consequences. In this talk, you will learn about common pitfalls, how a transformation can affect the error measure, the math behind it and even how all this can be used to your advantage.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/7YDWYL\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1944, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/7YDWYL", + "url": "https://2022.pycon.de/program/7YDWYL" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/fdKy_FFzZF4/maxresdefault.webp", + "title": "Florian Wilhelm: Honey, I shrunk the target variable! Common pitfalls when transforming the targe...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=fdKy_FFzZF4" + } + ] +} diff --git a/pydata-berlin-2022/videos/franz-kiraly-sktime-python-toolbox-for-time-series-advanced-forecasting-probabilistic-glob.json b/pydata-berlin-2022/videos/franz-kiraly-sktime-python-toolbox-for-time-series-advanced-forecasting-probabilistic-glob.json new file mode 100644 index 000000000..5db388a23 --- /dev/null +++ b/pydata-berlin-2022/videos/franz-kiraly-sktime-python-toolbox-for-time-series-advanced-forecasting-probabilistic-glob.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Franz Kiraly\n\nTrack: PyData: PyData & Scientific Libraries Stack\nsktime is a widely used scikit-learn compatible library for learning with time series.\r\n\r\nThe forecasting module of sktime provides a unified, sklearn-compatible, and composable interface to the pydata/numfocus ecosystem and beyond.\r\n\r\nThis tutorial covers advanced topics in forecasting using sktime: probabilistic forecasting, and forecasting with panel data, including global forecasting and hierarchical forecasting.\r\n\r\nA continuation of the sktime introductory tutorial at pydata [link]\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/GCYTM3\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 5257, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/GCYTM3", + "url": "https://2022.pycon.de/program/GCYTM3" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/4Rf9euAhjNc/maxresdefault.webp", + "title": "Franz Kiraly: sktime - python toolbox for time series: advanced forecasting - probabilistic, glob...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=4Rf9euAhjNc" + } + ] +} diff --git a/pydata-berlin-2022/videos/gatha-do-i-need-to-be-dr-frankenstein-to-create-real-ish-synthetic-data.json b/pydata-berlin-2022/videos/gatha-do-i-need-to-be-dr-frankenstein-to-create-real-ish-synthetic-data.json new file mode 100644 index 000000000..ef1a4463e --- /dev/null +++ b/pydata-berlin-2022/videos/gatha-do-i-need-to-be-dr-frankenstein-to-create-real-ish-synthetic-data.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Gatha\n\nTrack: General: Ethics\nSynthetic datasets have caught the fancy of researchers, statisticians, and analysts. Also called fake or proxy data, not only does it address the privacy needs of the data subjects but also offers a workaround in case of unprecedented situations. Take the example of clinical data requirements during the SARS-Cov-2 pandemic. This talk introduces the concept of synthetic data to the audience who is curious about the hype surrounding it and see themselves using it in future. Apart from the appreciation of synthetic datasets and their different types, we would also see how the realness of such Frankenstein datasets is gauged. I would also discuss the options that are available for their generation, and how you do not need to be a mad scientist to make realistic synthetic datasets.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/3VAZ7R\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1765, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/3VAZ7R", + "url": "https://2022.pycon.de/program/3VAZ7R" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/vqRxxuDu4kE/maxresdefault.webp", + "title": "Gatha: Do I need to be Dr. Frankenstein to create real-ish synthetic data?", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=vqRxxuDu4kE" + } + ] +} diff --git a/pydata-berlin-2022/videos/gonul-ayci-you-shall-not-share.json b/pydata-berlin-2022/videos/gonul-ayci-you-shall-not-share.json new file mode 100644 index 000000000..b447a3695 --- /dev/null +++ b/pydata-berlin-2022/videos/gonul-ayci-you-shall-not-share.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: G\u00f6n\u00fcl Ayc\u0131\n\nTrack: PyData: Machine Learning & Stats\nOnline social network users frequently share personal information online. While each post is targeted to a certain audience, it is not always easy to judge what the privacy implications of shared content will be. To ensure that privacy is preserved, each user has to think through these implications before sharing content, which is difficult at best. Recent work advocates the use of intelligent systems that can help people preserve their privacy by helping users decide whether a content is private or not so that the user can take an action accordingly; e.g., only share with family as opposed to publicly. \r\n\r\nIn this talk, I propose an agent that helps its user to determine the privacy of content she is willing to share. The agent uses only the content that the user has shared before, without discriminating between the content modality (e.g., image, text, and so on). Each content in the system is only represented with tags. The tags can be automatically created using a tool such as Clarifai, where 20 tags would automatically be assigned to an image. Alternatively, the user might herself choose to tag the content. This enables our approach to make use of content from different online social networks as long as tags are associated with the content. The agent learns the privacy label of a content using random forests, a well-known machine learning technique. The features are extracted using the Term Frequency\u2013Relevance Frequency (TF-RF) method.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/KG3LKN\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1572, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/KG3LKN", + "url": "https://2022.pycon.de/program/KG3LKN" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/v2ZucdZj3bY/maxresdefault.webp", + "title": "G\u00f6n\u00fcl Ayc\u0131: You shall not share!", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=v2ZucdZj3bY" + } + ] +} diff --git a/pydata-berlin-2022/videos/guido-imperiale-introducing-the-dask-active-memory-manager.json b/pydata-berlin-2022/videos/guido-imperiale-introducing-the-dask-active-memory-manager.json new file mode 100644 index 000000000..3a3c84f00 --- /dev/null +++ b/pydata-berlin-2022/videos/guido-imperiale-introducing-the-dask-active-memory-manager.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Guido Imperiale\n\nTrack: PyData: PyData & Scientific Libraries Stack\nThe Active Memory Manager is a new experimental feature of Dask which aims to reduce the memory footprint of the cluster, prevent hard to debug out-of-memory issues, and make worker retirement more robust.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/MZUDYP\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1769, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/MZUDYP", + "url": "https://2022.pycon.de/program/MZUDYP" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/pYtjhhVLqFQ/maxresdefault.webp", + "title": "Guido Imperiale: Introducing the Dask Active Memory Manager", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=pYtjhhVLqFQ" + } + ] +} diff --git a/pydata-berlin-2022/videos/guillaume-lemaitre-inpsect-and-try-to-interpret-your-scikit-learn-machine-learning-models.json b/pydata-berlin-2022/videos/guillaume-lemaitre-inpsect-and-try-to-interpret-your-scikit-learn-machine-learning-models.json new file mode 100644 index 000000000..7b481acb3 --- /dev/null +++ b/pydata-berlin-2022/videos/guillaume-lemaitre-inpsect-and-try-to-interpret-your-scikit-learn-machine-learning-models.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Guillaume Lemaitre\n\nTrack: PyData: Machine Learning & Stats\nThis tutorial presents the different inspection techniques currently available to inspect a machine-learning model developed with scikit-learn. In addition, we compare all these methods and pinpoint their limitations.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/9LZTRR\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 5039, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/9LZTRR", + "url": "https://2022.pycon.de/program/9LZTRR" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/V03NkNGEF3w/maxresdefault.webp", + "title": "Guillaume Lemaitre: Inpsect and try to interpret your scikit-learn machine-learning models", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=V03NkNGEF3w" + } + ] +} diff --git a/pydata-berlin-2022/videos/helena-schmidt-rewriting-your-r-analysis-code-in-python.json b/pydata-berlin-2022/videos/helena-schmidt-rewriting-your-r-analysis-code-in-python.json new file mode 100644 index 000000000..21e03f656 --- /dev/null +++ b/pydata-berlin-2022/videos/helena-schmidt-rewriting-your-r-analysis-code-in-python.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Helena Schmidt\n\nTrack: General: Python & PyData Friends\nR and Python are two of the most powerful tools for any kind of\r\ndata analysis. But both programming languages have their strengths and\r\nweaknesses. This means it can be necessary to switch from one to the\r\nother.\r\nWhen is it a good idea to rewrite your R code in Python?\r\nAnd what are good tools to do that successfully?\r\nWhat pitfalls are there?\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/ZEA9NJ\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2220, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/ZEA9NJ", + "url": "https://2022.pycon.de/program/ZEA9NJ" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/Es8HGYVweU0/maxresdefault.webp", + "title": "Helena Schmidt: Rewriting your R analysis code in Python", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=Es8HGYVweU0" + } + ] +} diff --git a/pydata-berlin-2022/videos/illia-babounikau-my-forecast-is-better-than-yours-what-does-that-even-mean.json b/pydata-berlin-2022/videos/illia-babounikau-my-forecast-is-better-than-yours-what-does-that-even-mean.json new file mode 100644 index 000000000..57ea49e6f --- /dev/null +++ b/pydata-berlin-2022/videos/illia-babounikau-my-forecast-is-better-than-yours-what-does-that-even-mean.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Illia Babounikau\n\nTrack: PyData: Machine Learning & Stats\nForecasting is one of the most popular applications of Machine Learning. In the last decades, it went from large numbers, few factors, and simple algorithms to small numbers, many factors, and complex ML models. Moreover, some modern forecasting models can predict not only naive point estimators of the target variable but their probability distributions. As an example, BlueYonder delivers demand forecasts in the form of demand probability distribution on a very granular level (e.g. for each product, store, and day).\r\nHowever, established forecast evaluation procedures and criteria (e.g. directly using metrics like RMAE, RMSE, MAPE, etc., and comparing these metrics between various data categories) often turn out to be inappropriate and biased. Therefore, it is important to understand the limitations of the traditionally used metrics and approaches. BlueYonder has implemented forecast evaluation techniques to address these limitations. \r\nIn this talk, I will present the most important issues in forecast evaluation and their possible resolutions based on the real use cases of demand forecasting developed within BlueYonder.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/WHHMWQ\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1769, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/WHHMWQ", + "url": "https://2022.pycon.de/program/WHHMWQ" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/ldzRfYeI6TA/maxresdefault.webp", + "title": "Illia Babounikau: My forecast is better than yours! What does that even mean?", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=ldzRfYeI6TA" + } + ] +} diff --git a/pydata-berlin-2022/videos/jacopo-farina-using-a-database-in-a-data-science-project-lessons-learned-in-production.json b/pydata-berlin-2022/videos/jacopo-farina-using-a-database-in-a-data-science-project-lessons-learned-in-production.json new file mode 100644 index 000000000..f520be349 --- /dev/null +++ b/pydata-berlin-2022/videos/jacopo-farina-using-a-database-in-a-data-science-project-lessons-learned-in-production.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Jacopo Farina\n\nTrack: PyData: Data Handling\nStoring and processing data in a relational database for a machine learning project presents unique challenges. Processing large volumes can take long, source data has to be continuously ingested and kept up to date, the schema needs to change over time while the application is running daily. The amount of available tools and options can be confusing. In this talk, we'll present the solutions and tricks we developed in four years operating a machine learning project in production.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/VUHBWP\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1689, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/VUHBWP", + "url": "https://2022.pycon.de/program/VUHBWP" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/x0R5_GvKTvc/maxresdefault.webp", + "title": "Jacopo Farina: Using a database in a data science project - Lessons learned in production", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=x0R5_GvKTvc" + } + ] +} diff --git a/pydata-berlin-2022/videos/jan-benedikt-jagusch-christian-bourjau-making-machine-learning-applications-fast-and-simple-with.json b/pydata-berlin-2022/videos/jan-benedikt-jagusch-christian-bourjau-making-machine-learning-applications-fast-and-simple-with.json new file mode 100644 index 000000000..76787a979 --- /dev/null +++ b/pydata-berlin-2022/videos/jan-benedikt-jagusch-christian-bourjau-making-machine-learning-applications-fast-and-simple-with.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Jan-Benedikt Jagusch Christian Bourjau\n\nTrack: General: Production\nTaking trained machine learning models from inside a Jupyter notebook and deploying them into a production microservice is painful for two reasons:\r\n\r\n- Models are not fully self-contained and need to be packaged together with their environment\r\n- Models are optimized for batch processing but slow down for single-row predictions, which could lead to timeouts in a fast-paced online microservice.\r\n\r\nIn this talk, you will learn how to use the Open Neural Network Exchange (ONNX) framework to compile models into fully-self contained computational graphs, which can reduce single-row inference time by up to 99%, while also drastically simplifying model management.\r\n\r\nYou will be introduced to the ONNX ecosystem, such as the `sklearn-onnx` and `onnxmltools` libraries for converting models into ONNX graphs, and will learn how to write converters for custom estimators and transformers.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/BLVRVL\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2700, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/BLVRVL", + "url": "https://2022.pycon.de/program/BLVRVL" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/fucKKi2zMw4/maxresdefault.webp", + "title": "Jan-Benedikt Jagusch Christian Bourjau: Making Machine Learning Applications Fast and Simple with...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=fucKKi2zMw4" + } + ] +} diff --git a/pydata-berlin-2022/videos/janis-meyer-deepdoctection-an-open-source-package-for-document-intelligence.json b/pydata-berlin-2022/videos/janis-meyer-deepdoctection-an-open-source-package-for-document-intelligence.json new file mode 100644 index 000000000..2e4571661 --- /dev/null +++ b/pydata-berlin-2022/videos/janis-meyer-deepdoctection-an-open-source-package-for-document-intelligence.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Janis Meyer\n\nTrack: PyData: Natural Language Processing\nExtracting information from business documents is difficult. They often have a complex visual structure and the information they contain is not tagged. Let me introduce deepdoctection: A tool box that is intended to facilitate entry into this topic.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/HP9KVN\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1749, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/HP9KVN", + "url": "https://2022.pycon.de/program/HP9KVN" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/EXmJjpEQxrM/maxresdefault.webp", + "title": "Janis Meyer: deepdoctection - An open source package for document intelligence", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=EXmJjpEQxrM" + } + ] +} diff --git a/pydata-berlin-2022/videos/jean-luc-stevens-seeing-the-needle-and-the-haystack-single-datapoint-selection-for-billion-poin.json b/pydata-berlin-2022/videos/jean-luc-stevens-seeing-the-needle-and-the-haystack-single-datapoint-selection-for-billion-poin.json new file mode 100644 index 000000000..214096a3d --- /dev/null +++ b/pydata-berlin-2022/videos/jean-luc-stevens-seeing-the-needle-and-the-haystack-single-datapoint-selection-for-billion-poin.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Jean-Luc Stevens\n\nTrack: PyData: Visualization\nPython tools like Bokeh and Dash let you build custom Web-based interactive visualization apps and dashboards. While these solutions work well to visualize megabyte-sized datasets, web technologies (including WebGL) stuggle to render gigabyte or larger datasets efficiently, because they transfer all the data into the client browser. Pre-rendering the data on the server using a tool like Datashader can visualize such large datasets efficiently, but the resulting static renderings make exploring individual datapoints difficult.\r\n\r\nThis talk introduces an easy-to-use hvPlot API that leverages HoloViews, Datashader, Bokeh, and Panel to build dashboards that do server-side rendering of billions of data points without losing the ability to interactively inspect individual samples in the browser.\r\n\r\nThese tools let you dump in your data and immediately see both the overall structure and explore the individual data items without having to program with events, callbacks, or other advanced mechanisms, and with very little programming required at all.\r\n\r\nSee hvPlot.holoviz.org, holoviews.org, and panel.org for more details and how to get started!\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/9LDACE\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1771, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/9LDACE", + "url": "https://2022.pycon.de/program/9LDACE" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/Nyf0oYWUN18/maxresdefault.webp", + "title": "Jean-Luc Stevens: Seeing the needle AND the haystack: single-datapoint selection for billion-poin...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=Nyf0oYWUN18" + } + ] +} diff --git a/pydata-berlin-2022/videos/jeremy-tuloup-jupyterlite-jupyter-webassembly-python.json b/pydata-berlin-2022/videos/jeremy-tuloup-jupyterlite-jupyter-webassembly-python.json new file mode 100644 index 000000000..906d4e7d2 --- /dev/null +++ b/pydata-berlin-2022/videos/jeremy-tuloup-jupyterlite-jupyter-webassembly-python.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Jeremy Tuloup\n\nTrack: PyData: Jupyter\nJupyterLite is a JupyterLab distribution that runs entirely in the web browser, backed by in-browser language kernels such as the WebAssembly powered Pyodide kernel.\r\n\r\nJupyterLite enables data science and interactive computing with the PyData scientific stack, directly in the browser, without installing anything or running a server.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/LSVVWT\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2096, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/LSVVWT", + "url": "https://2022.pycon.de/program/LSVVWT" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/4rDRs_W9ICM/maxresdefault.webp", + "title": "Jeremy Tuloup: JupyterLite: Jupyter \u2764\ufe0f WebAssembly \u2764\ufe0f Python", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=4rDRs_W9ICM" + } + ] +} diff --git a/pydata-berlin-2022/videos/jonathan-striebel-5-steps-to-speed-up-your-data-analysis-on-a-single-core.json b/pydata-berlin-2022/videos/jonathan-striebel-5-steps-to-speed-up-your-data-analysis-on-a-single-core.json new file mode 100644 index 000000000..e75d1c940 --- /dev/null +++ b/pydata-berlin-2022/videos/jonathan-striebel-5-steps-to-speed-up-your-data-analysis-on-a-single-core.json @@ -0,0 +1,55 @@ +{ + "description": "Speaker:: Jonathan Striebel\n\nTrack: PyData: PyData & Scientific Libraries Stack\nYour data analysis pipeline works. \nCould it be faster? Probably.\nDo you need to parallelize? Not yet.\n\nWe'll go through optimization steps that boost the performance of your data analysis pipeline on a single core, reducing time & costs.\nThis walkthrough shows tools and strategies to identify and mitigate bottlenecks,\nand demonstrate them in an example. The 5 steps cover profiling, memory optimizations, and various speedups such as jit-ing with numba.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/VYS8XY\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1774, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/VYS8XY", + "url": "https://2022.pycon.de/program/VYS8XY" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "Education", + "Julia", + "NumFOCUS", + "Opensource", + "PyData", + "Python", + "Tutorial", + "coding", + "how to program", + "learn", + "learn to code", + "python 3", + "scientific programming", + "software" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/7Tka8UureD0/maxresdefault.webp", + "title": "Jonathan Striebel: 5 Steps to Speed Up Your Data-Analysis on a Single Core", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=7Tka8UureD0" + } + ] +} diff --git a/pydata-berlin-2022/videos/jordi-smit-slack-bots-101-an-introduction-into-slack-bot-based-workflow-automation.json b/pydata-berlin-2022/videos/jordi-smit-slack-bots-101-an-introduction-into-slack-bot-based-workflow-automation.json new file mode 100644 index 000000000..92d2eedc2 --- /dev/null +++ b/pydata-berlin-2022/videos/jordi-smit-slack-bots-101-an-introduction-into-slack-bot-based-workflow-automation.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Jordi Smit\n\nTrack: General: Python & PyData Friends\nMost developers work with Slack every day, yet very few of them know about the awesome things you can do when you build your own slack bot.\r\nFor example, recently, we built a slack bot that automates our hiring assessment sending process. During this talk, we will discuss the lessons we learned during the creation of this slack bot, and we will teach you to build and deploy your first bot.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/SFDVVA\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1370, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/SFDVVA", + "url": "https://2022.pycon.de/program/SFDVVA" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/jB5LGEjFVvU/maxresdefault.webp", + "title": "Jordi Smit: Slack bots 101: An introduction into slack bot-based workflow automation", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=jB5LGEjFVvU" + } + ] +} diff --git a/pydata-berlin-2022/videos/joris-van-den-bossche-on-blocks-copies-and-views-updating-pandas-internals.json b/pydata-berlin-2022/videos/joris-van-den-bossche-on-blocks-copies-and-views-updating-pandas-internals.json new file mode 100644 index 000000000..99ca2d260 --- /dev/null +++ b/pydata-berlin-2022/videos/joris-van-den-bossche-on-blocks-copies-and-views-updating-pandas-internals.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Joris Van den Bossche\n\nTrack: PyData: PyData & Scientific Libraries Stack\na.k.a. \u201cGetting rid of the SettingWithCopyWarning\u201d\r\n\r\nPandas\u2019 current behavior on whether indexing returns a view or copy is confusing, even for experienced users. But it doesn\u2019t have to be this way. We can make this aspect of pandas easier to grasp by simplifying the copy/view rules, and at the same time make pandas more memory-efficient. And get rid of the SettingWithCopyWarning.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/XJMXFK\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1818, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/XJMXFK", + "url": "https://2022.pycon.de/program/XJMXFK" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/aBeEN2klZQE/maxresdefault.webp", + "title": "Joris Van den Bossche: On Blocks, Copies and Views: updating pandas' internals", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=aBeEN2klZQE" + } + ] +} diff --git a/pydata-berlin-2022/videos/katharina-rasch-fundamentals-of-relational-databases.json b/pydata-berlin-2022/videos/katharina-rasch-fundamentals-of-relational-databases.json new file mode 100644 index 000000000..7d1a3b3a7 --- /dev/null +++ b/pydata-berlin-2022/videos/katharina-rasch-fundamentals-of-relational-databases.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Katharina Rasch\n\nTrack: PyData: Data Handling\nAre you somewhat comfortable with using SQL to access data, but are curious to know what happens behind the scenes when you send off your query? Then this is the talk for you!\r\n\r\nRelational database systems have been around since the 1970s and they are stacked full of cool ideas and concepts for making data handling fast and secure. And we are still using them, nearly unchanged, 50 years later! Reason enough, I think, to learn a bit more about how they work and the fundamentals of their design.\r\n\r\nAudience level: If you have played around with SQL / written some smaller queries, you\u2019ll be just fine.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/KMFPAN\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2386, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/KMFPAN", + "url": "https://2022.pycon.de/program/KMFPAN" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/QQUpQ1tpF_o/maxresdefault.webp", + "title": "Katharina Rasch: Fundamentals of relational databases", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=QQUpQ1tpF_o" + } + ] +} diff --git a/pydata-berlin-2022/videos/katharine-jarmul-matteo-guzzo-sieer-angar-marielle-dado-emily-gorcenski-career-panel.json b/pydata-berlin-2022/videos/katharine-jarmul-matteo-guzzo-sieer-angar-marielle-dado-emily-gorcenski-career-panel.json new file mode 100644 index 000000000..f1f7438ca --- /dev/null +++ b/pydata-berlin-2022/videos/katharine-jarmul-matteo-guzzo-sieer-angar-marielle-dado-emily-gorcenski-career-panel.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Katharine Jarmul Matteo Guzzo Sieer Angar Marielle Dado Emily Gorcenski\n\nTrack: General: Community, Diversity, Carreer, Life and everything else\nWorking in the 21st century is very different from the past. Especially the digital space offers many opportunities to work in the office and remotely. In your hometown or somewhere else on the globe. Some companies even work completely remotely. Or, as a freelancer, you can be your own boss. Or running a company, where you are in charge of all the decisions. This panel invites folks with diverse careers to ponder the differences in these choices and give advice to you (and their former selves!) on choices along the way.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/SDQEB8\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 3644, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/SDQEB8", + "url": "https://2022.pycon.de/program/SDQEB8" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/ae1IOcdonNE/maxresdefault.webp", + "title": "Katharine Jarmul Matteo Guzzo Sieer Angar Marielle Dado Emily Gorcenski: Career Panel", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=ae1IOcdonNE" + } + ] +} diff --git a/pydata-berlin-2022/videos/kilian-kluge-grokking-lime-how-can-we-explain-why-an-image-classifier-knows-whats-in-a-photo.json b/pydata-berlin-2022/videos/kilian-kluge-grokking-lime-how-can-we-explain-why-an-image-classifier-knows-whats-in-a-photo.json new file mode 100644 index 000000000..f5d916f0e --- /dev/null +++ b/pydata-berlin-2022/videos/kilian-kluge-grokking-lime-how-can-we-explain-why-an-image-classifier-knows-whats-in-a-photo.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Kilian Kluge\n\nTrack: PyData: Computer Vision\nMany machine learning models are too complex for humans to comprehend. Algorithms like LIME can explain model outputs, even without looking at a model\u2019s internal structure. This talk provides attendees with a deep understanding of this approach.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/ZJUWZJ\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1840, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/ZJUWZJ", + "url": "https://2022.pycon.de/program/ZJUWZJ" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/xijusY83dT4/maxresdefault.webp", + "title": "Kilian Kluge: Grokking LIME: How can we explain why an image classifier \"knows\" what\u2019s in a photo...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=xijusY83dT4" + } + ] +} diff --git a/pydata-berlin-2022/videos/larissa-haas-xai-meets-natural-language-processing.json b/pydata-berlin-2022/videos/larissa-haas-xai-meets-natural-language-processing.json new file mode 100644 index 000000000..452d05afd --- /dev/null +++ b/pydata-berlin-2022/videos/larissa-haas-xai-meets-natural-language-processing.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Larissa Haas\n\nTrack: PyData: Natural Language Processing\nThe idea of Explainable AI (XAI) gets more and more attention, as customers and users want to understand AI models and the reason behind predictions. But it is difficult to apply \"traditional\" XAI approaches out of the box to Natural Language Processing/Understanding models. For human viewers, sentences lose their meaning when turned into numbers and vectors, words become irrelevant when they appear midst of 1000 others. In this talk, I will show you different solution options and approaches, alternatives, and lessons learned based on a real-world NLP use case.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/F3SZL3\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1951, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/F3SZL3", + "url": "https://2022.pycon.de/program/F3SZL3" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/66A5D6NU17U/maxresdefault.webp", + "title": "Larissa Haas: XAI meets Natural Language Processing", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=66A5D6NU17U" + } + ] +} diff --git a/pydata-berlin-2022/videos/lina-weichbrodt-what-i-learned-from-monitoring-more-than-30-machine-learning-use-cases.json b/pydata-berlin-2022/videos/lina-weichbrodt-what-i-learned-from-monitoring-more-than-30-machine-learning-use-cases.json new file mode 100644 index 000000000..e17ad6944 --- /dev/null +++ b/pydata-berlin-2022/videos/lina-weichbrodt-what-i-learned-from-monitoring-more-than-30-machine-learning-use-cases.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Lina Weichbrodt\n\nTrack: General: Production\nThis talk summarizes the most important insights I gained from running more than 30 machine learning use cases in production. We will take a loan prediction model as an example use case and cover questions like:\r\n\r\n- What is the difference between metrics for model training and metrics for model monitoring?\r\n- Which metrics are generally useful to be monitored? \r\n- Which metrics should you prioritize?\r\n- How can monitoring be set up using a traditional software monitoring stack (tools like Grafana and Prometheus)?\r\n\r\nThis talk will be useful for you if you:\r\n- are a hands-on engineer or data scientist\r\n- want to use your team's or company's existing monitoring and dashboarding infrastructure to monitor machine learning stacks \r\n- are a beginner or intermediate in MLOPs\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/SEXPKA\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2200, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/SEXPKA", + "url": "https://2022.pycon.de/program/SEXPKA" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/wWxqnZb-LSk/maxresdefault.webp", + "title": "Lina Weichbrodt: What I learned from monitoring more than 30 Machine Learning Use Cases", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=wWxqnZb-LSk" + } + ] +} diff --git a/pydata-berlin-2022/videos/maria-mestre-efficient-data-labelling-with-weak-supervision.json b/pydata-berlin-2022/videos/maria-mestre-efficient-data-labelling-with-weak-supervision.json new file mode 100644 index 000000000..2344fcb03 --- /dev/null +++ b/pydata-berlin-2022/videos/maria-mestre-efficient-data-labelling-with-weak-supervision.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Maria Mestre\n\nTrack: PyData: Natural Language Processing\nData labelling is often considered a separate task that takes place before the real \"machine learning work\" happens, similar to waterfall software engineering practices. However this is typically a wrong approach that leads to failure of the whole project. In this talk, we will show how to use weak supervision techniques to not only label large amounts of data significantly faster than with other techniques, but to also protect your ML project from issues in the annotation step which can cause catastrophic errors further downstream.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/LAUL7F\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1794, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://2022.pycon.de/program/LAUL7F", + "url": "https://2022.pycon.de/program/LAUL7F" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/5NvSn4rel04/maxresdefault.webp", + "title": "Maria Mestre: Efficient data labelling with weak supervision", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=5NvSn4rel04" + } + ] +} diff --git a/pydata-berlin-2022/videos/martin-christen-creating-3d-maps-using-python.json b/pydata-berlin-2022/videos/martin-christen-creating-3d-maps-using-python.json new file mode 100644 index 000000000..b18db73df --- /dev/null +++ b/pydata-berlin-2022/videos/martin-christen-creating-3d-maps-using-python.json @@ -0,0 +1,52 @@ +{ + "description": "Speaker:: Martin Christen\n\nTrack: PyData: PyData & Scientific Libraries Stack\nIn this talk it is shown how to create 3D Maps using Open Data and Python. There are many open data sources available now for direct download, for example on AWS ( https://aws.amazon.com/opendata ). This talks shows how to download and process the data to create textured 3D models.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/V3CCHQ\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1807, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/V3CCHQ", + "url": "https://2022.pycon.de/program/V3CCHQ" + }, + { + "label": "https://aws.amazon.com/opendata", + "url": "https://aws.amazon.com/opendata" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/ie-WzjxWJ94/maxresdefault.webp", + "title": "Martin Christen: Creating 3D Maps using Python", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=ie-WzjxWJ94" + } + ] +} diff --git a/pydata-berlin-2022/videos/marysia-winkels-james-hayward-serious-time-for-time-series.json b/pydata-berlin-2022/videos/marysia-winkels-james-hayward-serious-time-for-time-series.json new file mode 100644 index 000000000..1778095fc --- /dev/null +++ b/pydata-berlin-2022/videos/marysia-winkels-james-hayward-serious-time-for-time-series.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Marysia Winkels James Hayward\n\nTrack: PyData: PyData & Scientific Libraries Stack\nFrom inventory to website visitors, resource planning to financial data, time-series data is all around us. Knowing what comes next is key to success in this dynamically changing world. And for that we need reliable forecasting models. While complex & deep models may be good at forecasting, they typically give us little insight about the underlying patterns in our data. Such insights however may be a key to not only forecasting the future but shaping it.\r\n\r\nIn this tutorial, we'll cover relatively simple approaches for time series analysis and seasonality modelling with Pandas.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/DTTQ9D\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 4689, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/DTTQ9D", + "url": "https://2022.pycon.de/program/DTTQ9D" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/2b725bplNt8/maxresdefault.webp", + "title": "Marysia Winkels James Hayward: (Serious) Time for Time Series", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=2b725bplNt8" + } + ] +} diff --git a/pydata-berlin-2022/videos/melissa-weber-mendonca-beyond-the-basics-contributor-experience-diversity-and-culture-in-open.json b/pydata-berlin-2022/videos/melissa-weber-mendonca-beyond-the-basics-contributor-experience-diversity-and-culture-in-open.json new file mode 100644 index 000000000..bdc3a99f7 --- /dev/null +++ b/pydata-berlin-2022/videos/melissa-weber-mendonca-beyond-the-basics-contributor-experience-diversity-and-culture-in-open.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Melissa Weber Mendon\u00e7a\nBeyond the basics: Contributor experience, diversity and culture in Open Source Projects. (Keynote)\n\nTrack: Plenary\nHow can we go beyond the basics when engaging new contributors and improving an open-source project's culture around inclusiveness, accessibility, and different axes of diversity? In this talk, we'll explore a few actions and assumptions about these topics and how they are related to volunteer work and the efforts of maintainers and contributors.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/NVBLKH\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 3030, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/NVBLKH", + "url": "https://2022.pycon.de/program/NVBLKH" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/lQWDRg99B6w/maxresdefault.webp", + "title": "Melissa Weber Mendon\u00e7a: Beyond the basics: Contributor experience, diversity and culture in open...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=lQWDRg99B6w" + } + ] +} diff --git a/pydata-berlin-2022/videos/paula-gonzalez-avalos-your-data-your-insights-creating-personal-data-projects-to-re-own-the.json b/pydata-berlin-2022/videos/paula-gonzalez-avalos-your-data-your-insights-creating-personal-data-projects-to-re-own-the.json new file mode 100644 index 000000000..e7fc5b094 --- /dev/null +++ b/pydata-berlin-2022/videos/paula-gonzalez-avalos-your-data-your-insights-creating-personal-data-projects-to-re-own-the.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Paula Gonzalez Avalos\n\nTrack: PyData: Visualization\nWe are all constantly collecting and sharing personal data in exchange for services. And although often this data is available to us as users as well, it's not common that we take back control of it and use it despite having the skills to do so. In this talk, I will show three examples to illustrate how we can apply common data science libraries together with data shared via mobile apps or collected manually to build little data visualization projects that provide unique, contextual and intmiate insights. Projects like this help expand the application scope of Data Scientists and they are also a good introduction to working with data for all other `python` coders.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/UMN7FB\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1667, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/UMN7FB", + "url": "https://2022.pycon.de/program/UMN7FB" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/_XvD83yhe3E/maxresdefault.webp", + "title": "Paula Gonzalez Avalos: Your data, your insights: creating personal data projects to (re-)own the...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=_XvD83yhe3E" + } + ] +} diff --git a/pydata-berlin-2022/videos/philipp-rudiger-maxime-liquet-easily-build-interactive-plots-and-apps-with-hvplot.json b/pydata-berlin-2022/videos/philipp-rudiger-maxime-liquet-easily-build-interactive-plots-and-apps-with-hvplot.json new file mode 100644 index 000000000..72333616f --- /dev/null +++ b/pydata-berlin-2022/videos/philipp-rudiger-maxime-liquet-easily-build-interactive-plots-and-apps-with-hvplot.json @@ -0,0 +1,52 @@ +{ + "description": "Speaker:: Philipp Rudiger Maxime Liquet\n\nTrack: PyData: Visualization\nDo you use the `.plot()` API of pandas or xarray? Do you ever wish it was easier for you or your collaborators to try out different combinations of the parameters in your data-processing pipeline? This tutorial will introduce you to [hvPlot](https://hvplot.holoviz.org/), a library that:\r\n* supercharges the `.plot` API with extra capabilities like interactive plots, rendering of very large datasets, and simple composition and linking of plots, and\r\n* makes it really easy to build interactive web applications, whether to make data exploration easier for yourself or for sharing your results with others, by simply replacing arguments in your method calls with widgets.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/38HQZ3\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 5177, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/38HQZ3", + "url": "https://2022.pycon.de/program/38HQZ3" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://hvplot.holoviz.org/", + "url": "https://hvplot.holoviz.org/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/xlFMLQKZi3I/maxresdefault.webp", + "title": "Philipp Rudiger Maxime Liquet: Easily build interactive plots and apps with hvPlot", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=xlFMLQKZi3I" + } + ] +} diff --git a/pydata-berlin-2022/videos/prabhant-singh-reproducible-machine-learning-and-science-with-python.json b/pydata-berlin-2022/videos/prabhant-singh-reproducible-machine-learning-and-science-with-python.json new file mode 100644 index 000000000..54def53b1 --- /dev/null +++ b/pydata-berlin-2022/videos/prabhant-singh-reproducible-machine-learning-and-science-with-python.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Prabhant Singh\n\nTrack: PyData: PyData & Scientific Libraries Stack\nWith machine learning being used in all domains of science, reproducibility and openness is major concern for these experiments and workflows, This tutorial will discuss various experiment tracking tools and focus on OpenML for dataset, model, run, and benchmark reproducibility(via openml-python).\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/87BFX7\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 4541, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/87BFX7", + "url": "https://2022.pycon.de/program/87BFX7" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/0ShpadTHsro/maxresdefault.webp", + "title": "Prabhant Singh: Reproducible machine learning and science with python", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=0ShpadTHsro" + } + ] +} diff --git a/pydata-berlin-2022/videos/reshama-shaikh-5-years-10-sprints-a-scikit-learn-open-source-journey-keynote.json b/pydata-berlin-2022/videos/reshama-shaikh-5-years-10-sprints-a-scikit-learn-open-source-journey-keynote.json new file mode 100644 index 000000000..6c4352ef1 --- /dev/null +++ b/pydata-berlin-2022/videos/reshama-shaikh-5-years-10-sprints-a-scikit-learn-open-source-journey-keynote.json @@ -0,0 +1,52 @@ +{ + "description": "Speaker:: Reshama Shaikh\n\nTrack: Plenary\nWe all use open source tools in various capacities, yet knowing how to contribute to open source is not as well known or accessible. The limited knowledge and education surrounding contributing to open source could be one explanation of the low participation rates by underrepresented persons in open source. Open source sprints are hands-on \u201cworkshops\u201d or \u201chackathons\u201d where contributors collaborate to resolve coding and documentation issues posted on a GitHub repository. \r\n\r\nI will share how I organized my first open source sprint in 2017, which was in-person and held in New York City. Over the next 5 years, I organized in-person sprints from San Francisco, USA to Nairobi, Kenya, as well as pivoting to online sprints due to the global pandemic. In this keynote, I will share highlights, challenges and lessons learned. (https://www.dataumbrella.org/sprints).\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/CLGY3M\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2310, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://www.dataumbrella.org/sprints", + "url": "https://www.dataumbrella.org/sprints" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/CLGY3M", + "url": "https://2022.pycon.de/program/CLGY3M" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/ZUqJaCWPvmk/maxresdefault.webp", + "title": "Reshama Shaikh: 5 Years, 10 Sprints, A scikit-learn Open Source Journey (Keynote)", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=ZUqJaCWPvmk" + } + ] +} diff --git a/pydata-berlin-2022/videos/richard-pelgrim-data-science-at-scale-with-dask.json b/pydata-berlin-2022/videos/richard-pelgrim-data-science-at-scale-with-dask.json new file mode 100644 index 000000000..a54427c3c --- /dev/null +++ b/pydata-berlin-2022/videos/richard-pelgrim-data-science-at-scale-with-dask.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Richard Pelgrim\n\nTrack: PyData: PyData & Scientific Libraries Stack\nA Pythonic introduction to methods for scaling your data science and machine learning work to larger datasets and larger models with Dask, all while staying within the comfort of the tools and APIs you know and love from the PyData stack (such as numpy, pandas, and scikit-learn). \r\n\r\nWe'll discuss:\r\n- How to reason about when you need to scale your data and machine learning work and when not to;\r\n- How to leverage distribute computation on your local workstation (such as your laptop) to analyze larger datasets and build larger, more complex models;\r\n- How to harness the power of clusters to support larger-than-memory computation, all from the comfort of your own laptop.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/RTPEWV\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 4997, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/RTPEWV", + "url": "https://2022.pycon.de/program/RTPEWV" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/xi6Ki23K24g/maxresdefault.webp", + "title": "Richard Pelgrim: Data Science at Scale with Dask", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=xi6Ki23K24g" + } + ] +} diff --git a/pydata-berlin-2022/videos/sebastian-cattes-performing-content-can-nlp-and-deep-learning-algorithms-predict-reader-prefere.json b/pydata-berlin-2022/videos/sebastian-cattes-performing-content-can-nlp-and-deep-learning-algorithms-predict-reader-prefere.json new file mode 100644 index 000000000..7c1d08bbf --- /dev/null +++ b/pydata-berlin-2022/videos/sebastian-cattes-performing-content-can-nlp-and-deep-learning-algorithms-predict-reader-prefere.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Sebastian Cattes\n\nTrack: PyData: Natural Language Processing\nCan we predict a reader's engagement time before publishing an article?\r\n\r\nThis talk presents a use case performed together with a regional German newspaper that analyses to what extent user engagement can be understood and predicted based on an article's texts and metadata.\r\n\r\nA combination of advanced statistical and NLP deep learning models (BERT) was trained on a corpus of articles to model online reading behavior.\r\n\r\nThe talk focuses on the applied methods and shows Explainable AI techniques to get a microscopic understanding of driving mechanisms of user engagement.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/XQMVKN\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1805, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/XQMVKN", + "url": "https://2022.pycon.de/program/XQMVKN" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/A9ngf-CUSq4/maxresdefault.webp", + "title": "Sebastian Cattes: Performing Content: Can NLP and Deep Learning algorithms predict reader prefere...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=A9ngf-CUSq4" + } + ] +} diff --git a/pydata-berlin-2022/videos/sebastian-wanner-christopher-lennan-transformer-based-clustering-identifying-product-clusters-f.json b/pydata-berlin-2022/videos/sebastian-wanner-christopher-lennan-transformer-based-clustering-identifying-product-clusters-f.json new file mode 100644 index 000000000..af308fe19 --- /dev/null +++ b/pydata-berlin-2022/videos/sebastian-wanner-christopher-lennan-transformer-based-clustering-identifying-product-clusters-f.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Sebastian Wanner Christopher Lennan\n\nTrack: PyData: Natural Language Processing\nIn this talk we will be presenting a case-study of how we used two open source libraries, Sentence-Transformers and Facebook Faiss, to successfully cluster offers at idealo.de based on text data. \r\n\r\nClustering text data is a well studied problem and we want to show how a state of the art approach succeeded in a business setting and how relatively easy it is to realise such a project with current open source tools. \r\n\r\nWe will present our Transformer based clustering approach in detail and compare its performance across different optimisation strategies (additive angular margin, contrastive, and triplet loss), as well as against other approaches, e.g. probabilistic record linkage.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/URDTCT\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2684, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/URDTCT", + "url": "https://2022.pycon.de/program/URDTCT" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/6y9tfCK8W30/maxresdefault.webp", + "title": "Sebastian Wanner Christopher Lennan: Transformer based clustering: Identifying product clusters f...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=6y9tfCK8W30" + } + ] +} diff --git a/pydata-berlin-2022/videos/shir-meir-lador-the-secret-sauce-of-data-science-management.json b/pydata-berlin-2022/videos/shir-meir-lador-the-secret-sauce-of-data-science-management.json new file mode 100644 index 000000000..fb630063b --- /dev/null +++ b/pydata-berlin-2022/videos/shir-meir-lador-the-secret-sauce-of-data-science-management.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Shir Meir Lador\n\nTrack: PyData: Machine Learning & Stats\nThe question - \u201chow to become a successful data scientist?\u201d is often discussed in conferences like these. Today I would like to address a second level question. How to make the success scale? How to build a DS team in which the whole is greater than the sum of its parts?\r\nThe question - \u201chow to become a successful data scientist?\u201d is often discussed in conferences like these. Today I would like to address a second level question. How to make the success scale? How to build a DS team in which the whole is greater than the sum of its parts?\r\nIn this talk, I will share lessons learned during my 4 years as data science team & group leader on how to build a DS team that prospers while addressing the unique challenges of leading such a team.\r\nWe will discuss how to create the setting for a DS to grow and research while driving winning results for the organization. I will share our AI playbook that enables us to select the right projects to maximize our value and to collaborate with our partners most effectively to bring them to production. In addition we will discuss the importance of communication with upper management and how to do it right.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/LWUWAU\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 3232, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/LWUWAU", + "url": "https://2022.pycon.de/program/LWUWAU" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/tbBfVHIh-38/maxresdefault.webp", + "title": "Shir Meir Lador: The secret sauce of data science management", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=tbBfVHIh-38" + } + ] +} diff --git a/pydata-berlin-2022/videos/sonam-biases-in-language-models.json b/pydata-berlin-2022/videos/sonam-biases-in-language-models.json new file mode 100644 index 000000000..8bbdbffab --- /dev/null +++ b/pydata-berlin-2022/videos/sonam-biases-in-language-models.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: sonam\n\nTrack: General: Ethics\nThe talk is an attempt to measure biases in most popular language models and we propose a solution to reduce the bias, and promote social inclusion and diversity based on gender. We have covered both methods on contextual and non contextual word em- bedding debiasing techniques. We have also tried to compare the biases in different models, like Flair, Bert and glove. The dataset used is Winograd-schema style sentences with entities corresponding to people referred by their occupation (e.g. the nurse, the doctor, the carpenter).\r\nThe use of AI in sensitive areas including for hiring, criminal justice and health- care makes it more important to look under the hood for bias and fairness. AI being shaped by flawed and societal biases.\r\nUnderlying data rather than the algorithm itself are most often the main source of the issue. and how can we use finetuning and projection methods to overcome those biases in models\r\nThere have been several cases where google translator or any other language models have given racial or gender biased results. \r\nWhen a gender neutral language like finnish is translated to English it gives male biased results.\r\nDue to word embeddings trained on news articles may exhibit the gender stereotypes found in society.\r\nWe have finetuned model and have tried debiasing non contextual embeddings.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/HXCMKR\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1782, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/HXCMKR", + "url": "https://2022.pycon.de/program/HXCMKR" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/SdjmhbFNR_Q/maxresdefault.webp", + "title": "sonam: Biases in Language Models", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=SdjmhbFNR_Q" + } + ] +} diff --git a/pydata-berlin-2022/videos/stefanie-stoppel-the-myth-of-neutrality-how-ai-is-widening-social-divides.json b/pydata-berlin-2022/videos/stefanie-stoppel-the-myth-of-neutrality-how-ai-is-widening-social-divides.json new file mode 100644 index 000000000..def099389 --- /dev/null +++ b/pydata-berlin-2022/videos/stefanie-stoppel-the-myth-of-neutrality-how-ai-is-widening-social-divides.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Stefanie Stoppel\n\nTrack: General: Ethics\nMany people expect artificial intelligence to be neutral - or at least more objective than we humans are. But is it really? In recent years, researchers and activists have shown that it is in fact not, and that our biases end up becoming part of AI systems. My talk will shed light on how algorithms become discriminatory, how difficult it is to build \"fair and responsible\" AI, and what we should do to prevent the systems we build from cementing existing injustices.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/ML7XNX\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2695, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://2022.pycon.de/program/ML7XNX", + "url": "https://2022.pycon.de/program/ML7XNX" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/Q5P4elINDws/maxresdefault.webp", + "title": "Stefanie Stoppel: The Myth of Neutrality: How AI is widening social divides", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=Q5P4elINDws" + } + ] +} diff --git a/pydata-berlin-2022/videos/stephannie-jimenez-gacha-data-apis-standardization-of-n-dimensional-arrays-and-dataframes.json b/pydata-berlin-2022/videos/stephannie-jimenez-gacha-data-apis-standardization-of-n-dimensional-arrays-and-dataframes.json new file mode 100644 index 000000000..d2a7abbe4 --- /dev/null +++ b/pydata-berlin-2022/videos/stephannie-jimenez-gacha-data-apis-standardization-of-n-dimensional-arrays-and-dataframes.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Stephannie Jimenez Gacha\n\nTrack: PyData: PyData & Scientific Libraries Stack\nWe would like to introduce the consortium of Data APIs, where we will be presenting our motivation, objectives and progress of the standardization process after one year of activity. We will dive into a small history lesson of the current state of the Python data and scientific ecosystem and understand the current fragmentation of the APIs. Then, we will start discussing the efforts of standardization for N-dimensional arrays and dataframes. Finally. we will talk about the roadmap for the next year.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/BMFVFG\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1592, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/BMFVFG", + "url": "https://2022.pycon.de/program/BMFVFG" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/__EkpdeVGY4/maxresdefault.webp", + "title": "Stephannie Jimenez Gacha: Data Apis: Standardization of N-dimensional arrays and dataframes", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=__EkpdeVGY4" + } + ] +} diff --git a/pydata-berlin-2022/videos/steven-kolawole-building-a-sign-to-speech-prototype-with-tensorflow-pytorch-and-deepstack-how.json b/pydata-berlin-2022/videos/steven-kolawole-building-a-sign-to-speech-prototype-with-tensorflow-pytorch-and-deepstack-how.json new file mode 100644 index 000000000..6857dd036 --- /dev/null +++ b/pydata-berlin-2022/videos/steven-kolawole-building-a-sign-to-speech-prototype-with-tensorflow-pytorch-and-deepstack-how.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Steven Kolawole\n\nTrack: PyData: Computer Vision\nBuilding an E2E working prototype that detects sign language meanings in images/videos and generates equivalent, realistic voice of words communicated by the sign language, in real-time, won't be completed in a day's work. Here I'd explain how it happened and what I learned in the process.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/WWPUGX\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1567, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/WWPUGX", + "url": "https://2022.pycon.de/program/WWPUGX" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/X9JwoWccpYI/maxresdefault.webp", + "title": "Steven Kolawole: Building a Sign-to-Speech prototype with TensorFlow, Pytorch and DeepStack: How...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=X9JwoWccpYI" + } + ] +} diff --git a/pydata-berlin-2022/videos/sylvain-marie-python-m5p-m5-prime-regression-trees-in-python-compliant-with-scikit-learn.json b/pydata-berlin-2022/videos/sylvain-marie-python-m5p-m5-prime-regression-trees-in-python-compliant-with-scikit-learn.json new file mode 100644 index 000000000..4cc5839b0 --- /dev/null +++ b/pydata-berlin-2022/videos/sylvain-marie-python-m5p-m5-prime-regression-trees-in-python-compliant-with-scikit-learn.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Sylvain Mari\u00e9\n\nTrack: PyData: Machine Learning & Stats\nRegression trees are powerful Machine Learning models capable of both flexibility in modeling as well as interpretability when the tree is not too deep. The M5 algorithm, introduced by Quinlan in 1992 to provide more compact and smooth models for regression, was improved by Wang & Witten in 1997, under the name M5 Prime (acronym M5' or M5P). The algorithm gained popularity in particular a dozen years later with the Weka Machine Learning toolbox, providing a java-based implementation.\r\n\r\n`python-m5p` is an implementation of the M5P algorithm compliant with scikit-learn.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/8KXYBD\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1058, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/8KXYBD", + "url": "https://2022.pycon.de/program/8KXYBD" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/KkEVD3JncdI/maxresdefault.webp", + "title": "Sylvain Mari\u00e9: `python-m5p` - M5 Prime regression trees in python, compliant with scikit-learn", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=KkEVD3JncdI" + } + ] +} diff --git a/pydata-berlin-2022/videos/theodore-meynard-what-are-data-unit-tests-and-why-we-need-them.json b/pydata-berlin-2022/videos/theodore-meynard-what-are-data-unit-tests-and-why-we-need-them.json new file mode 100644 index 000000000..9c5b181ad --- /dev/null +++ b/pydata-berlin-2022/videos/theodore-meynard-what-are-data-unit-tests-and-why-we-need-them.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Theodore Meynard\n\nTrack: PyData: Data Handling\nI will introduce the concept of data unit tests and why they are important in the workflow of data scientists when building data products. In this talk, you will learn a new tool you can use to ensure the quality of the products you build.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/MPWLWP\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2050, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://2022.pycon.de/program/MPWLWP", + "url": "https://2022.pycon.de/program/MPWLWP" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/Kshch2G8AB4/maxresdefault.webp", + "title": "Theodore Meynard: What are data unit tests and why we need them", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=Kshch2G8AB4" + } + ] +} diff --git a/pydata-berlin-2022/videos/tilman-krokotsch-how-to-trust-your-deep-learning-code.json b/pydata-berlin-2022/videos/tilman-krokotsch-how-to-trust-your-deep-learning-code.json new file mode 100644 index 000000000..30e4df51d --- /dev/null +++ b/pydata-berlin-2022/videos/tilman-krokotsch-how-to-trust-your-deep-learning-code.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Tilman Krokotsch\n\nTrack: PyData: Deep Learning\nErrors in Deep Learning are hard to catch as training often fails silently s. Unit testing can catch those errors early and lets you make changes to your code base with confidence. Learn about the unique challenges of testing Deep Learning systems and how to trust your code again with hands-on examples explained on a realistic Deep Learning repository.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/YQK7UU\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1777, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/YQK7UU", + "url": "https://2022.pycon.de/program/YQK7UU" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/ICKATFuYQTE/maxresdefault.webp", + "title": "Tilman Krokotsch: How to Trust Your Deep Learning Code", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=ICKATFuYQTE" + } + ] +} diff --git a/pydata-berlin-2022/videos/tobias-hoinka-predictive-maintenance-and-anomaly-detection-for-wind-energy.json b/pydata-berlin-2022/videos/tobias-hoinka-predictive-maintenance-and-anomaly-detection-for-wind-energy.json new file mode 100644 index 000000000..7ab1bd9d5 --- /dev/null +++ b/pydata-berlin-2022/videos/tobias-hoinka-predictive-maintenance-and-anomaly-detection-for-wind-energy.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Tobias Hoinka\n\nTrack: PyData: Machine Learning & Stats\nThis talk will describe predictive modeling applications in wind turbine maintenance, the challenges of anomaly detection and ways to move to more automatic diagnoses by modeling past documented defects.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/3EZH9P\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 1817, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/3EZH9P", + "url": "https://2022.pycon.de/program/3EZH9P" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/qCmnb_6ThpM/maxresdefault.webp", + "title": "Tobias Hoinka: Predictive Maintenance and Anomaly Detection for Wind Energy", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=qCmnb_6ThpM" + } + ] +} diff --git a/pydata-berlin-2022/videos/tobias-sterbak-introduction-to-mlops-with-mlflow.json b/pydata-berlin-2022/videos/tobias-sterbak-introduction-to-mlops-with-mlflow.json new file mode 100644 index 000000000..808039b1b --- /dev/null +++ b/pydata-berlin-2022/videos/tobias-sterbak-introduction-to-mlops-with-mlflow.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Tobias Sterbak\n\nTrack: General: Production\nMachine learning requires experimenting with different datasets, data preparation steps, and algorithms to build a model that maximizes some target metric. Once you have built a model, you also need to deploy it to a production system, monitor its performance, and continuously retrain it on new data and compare with alternative models. A possible solution to managing parts of this complexity is offered by **MLFlow**.\r\n\r\nIn this tutorial, you will learn how to use MLflow to:\r\n\r\n- _Set up_ a tracking server and a model repository.\r\n- _Keep track_ of machine learning training and experiment results (parameters, metrics and artifacts) with **MLflow Tracking**.\r\n- _Package_ the training code in a reusable and reproducible format with **MLFlow Projects**.\r\n- _Deploy_ the model into a HTTP server with **MLFlow Models** and keep track of it's state.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/DV8PJT\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 5100, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de/program/DV8PJT", + "url": "https://2022.pycon.de/program/DV8PJT" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/IUF4s9SXnd4/maxresdefault.webp", + "title": "Tobias Sterbak: Introduction to MLOps with MLflow", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=IUF4s9SXnd4" + } + ] +} diff --git a/pydata-berlin-2022/videos/travis-hathaway-processing-open-street-map-data-with-python-and-postgresql.json b/pydata-berlin-2022/videos/travis-hathaway-processing-open-street-map-data-with-python-and-postgresql.json new file mode 100644 index 000000000..8def9e3be --- /dev/null +++ b/pydata-berlin-2022/videos/travis-hathaway-processing-open-street-map-data-with-python-and-postgresql.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Travis Hathaway\n\nTrack: PyData: Data Handling\nThe Open Street Map (OSM) project is a global, open-source database with over 50GB of data, and this number grows everyday with every user submission. With such a big data set out there, also comes a huge potential for analysis and use in scientific studies. \r\n\r\nIn this talk, you will learn how to get started with your own analysis using PostgreSQL as the data store and Python as the data processing language. To help you see exactly how this works, I first introduce the OSM data types, explain how to import this data into PostgreSQL and then cover how you can organise a Python project for data analysis.\r\n\r\nI end the talk by going over an example project, and there will also be plenty of links and resources for those wishing to learn even more.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/AKCLEP\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2236, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/AKCLEP", + "url": "https://2022.pycon.de/program/AKCLEP" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/z9_prnssu0w/maxresdefault.webp", + "title": "Travis Hathaway: Processing Open Street Map Data with Python and PostgreSQL", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=z9_prnssu0w" + } + ] +} diff --git a/pydata-berlin-2022/videos/vaggelis-papoutsellis-dr-jakob-sauer-jorgensen-easy-and-flexible-imaging-with-the-core-imaging.json b/pydata-berlin-2022/videos/vaggelis-papoutsellis-dr-jakob-sauer-jorgensen-easy-and-flexible-imaging-with-the-core-imaging.json new file mode 100644 index 000000000..ff0610c48 --- /dev/null +++ b/pydata-berlin-2022/videos/vaggelis-papoutsellis-dr-jakob-sauer-jorgensen-easy-and-flexible-imaging-with-the-core-imaging.json @@ -0,0 +1,52 @@ +{ + "description": "Speaker:: Vaggelis Papoutsellis Dr. Jakob Sauer J\u00f8rgensen\n\nTrack: PyData: PyData & Scientific Libraries Stack\nIn this talk, we present the [Core Imaging Library (CIL)](https://github.com/TomographicImaging/CIL), an open-source, object-oriented Python library for solving large scale imaging inverse problems. We give a brief introduction on inverse problems with motivating examples in different imaging applications such as denoising, deblurring and inpainting. Then, we present the optimisation framework of CIL, that is used to formalise and solve these problems with a wide range of CIL operators, functions and algorithms. Finally, we will demonstrate how to use CIL to reconstruct a real and challenging tomographic dataset with conventional analytic methods and iterative reconstruction algorithms\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/GSLJUY\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2751, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://github.com/TomographicImaging/CIL", + "url": "https://github.com/TomographicImaging/CIL" + }, + { + "label": "https://2022.pycon.de/program/GSLJUY", + "url": "https://2022.pycon.de/program/GSLJUY" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/Xd4erPj0uEs/maxresdefault.webp", + "title": "Vaggelis Papoutsellis Dr. Jakob Sauer J\u00f8rgensen: Easy and flexible imaging with the Core Imaging...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=Xd4erPj0uEs" + } + ] +} diff --git a/pydata-berlin-2022/videos/valerio-maggio-ppml-machine-learning-on-data-you-cannot-see.json b/pydata-berlin-2022/videos/valerio-maggio-ppml-machine-learning-on-data-you-cannot-see.json new file mode 100644 index 000000000..c5d59bb46 --- /dev/null +++ b/pydata-berlin-2022/videos/valerio-maggio-ppml-machine-learning-on-data-you-cannot-see.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Valerio Maggio\n\nTrack: PyData: Data Handling\nWhat if I tell you that you can run a complete ML pipeline on private data, without any anonymisation, nor even accessing the data in the first place? \ud83e\uddd0 And what If I also tell you that you can do that with no disruption to your existing pipeline, nor affecting the overall model performance? \ud83d\ude31 Well, that wouldn't be entirely true \ud83d\ude07 but in this workshop we'll explore the great potential **privacy-preserving machine learning** methods have to run _machine learning experiments on data you cannot see_. In the first part, we will first explore examples of exploits and vulnerabilities of Deep Learning models trained on anonymised data, whilst in the second part we will go much deeper into PPML methods, training DL on encrypted data, and more. You'll just have to be familiar with PyTorch, and DL basics to attend this workshop!\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/QHJ7SX\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 5308, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/QHJ7SX", + "url": "https://2022.pycon.de/program/QHJ7SX" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/gYKxQ6T8aH4/maxresdefault.webp", + "title": "Valerio Maggio: PPML: Machine Learning on Data you cannot see", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=gYKxQ6T8aH4" + } + ] +} diff --git a/pydata-berlin-2022/videos/wolf-vollprecht-jannis-leidel-jaime-rodriguez-guerra-conda-forge-supporting-the-growth-of-the-v.json b/pydata-berlin-2022/videos/wolf-vollprecht-jannis-leidel-jaime-rodriguez-guerra-conda-forge-supporting-the-growth-of-the-v.json new file mode 100644 index 000000000..eee70eb23 --- /dev/null +++ b/pydata-berlin-2022/videos/wolf-vollprecht-jannis-leidel-jaime-rodriguez-guerra-conda-forge-supporting-the-growth-of-the-v.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Wolf Vollprecht Jannis Leidel Jaime Rodr\u00edguez-Guerra\n\nTrack: General: Python & PyData Friends\nThe conda-forge project is one of the fastest growing Open Source communities out there \u2013 and most data scientists have probably heard of it. In this talk we explain the inner workings of conda-forge, its relationship to conda and PyPI, and we will explain how everyone can package software with conda-forge.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/TPZHC7\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2612, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de/program/TPZHC7", + "url": "https://2022.pycon.de/program/TPZHC7" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/nTNoCM5alyE/maxresdefault.webp", + "title": "Wolf Vollprecht Jannis Leidel Jaime Rodr\u00edguez-Guerra: conda-forge: supporting the growth of the v...", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=nTNoCM5alyE" + } + ] +} diff --git a/pydata-berlin-2022/videos/yunus-emrah-bulut-machine-learning-testing-ecosystem-of-python.json b/pydata-berlin-2022/videos/yunus-emrah-bulut-machine-learning-testing-ecosystem-of-python.json new file mode 100644 index 000000000..701cd796e --- /dev/null +++ b/pydata-berlin-2022/videos/yunus-emrah-bulut-machine-learning-testing-ecosystem-of-python.json @@ -0,0 +1,48 @@ +{ + "description": "Speaker:: Yunus Emrah Bulut\n\nTrack: PyData: Machine Learning & Stats\nIn this talk, I'll present the growing ecosystem of machine learning testing tools in Python. Machine learning validation and testing is an emerging concern in the MLOps domain and will become more so in the near future as several states (including European Commission) will put regulations on AI in place. I'll talk about several types of machine learning vulnerabilities and the available toolkits in Python that help machine learning practitioners test their models.\n\n\nRecorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.\nhttps://2022.pycon.de\nMore details at the conference page: https://2022.pycon.de/program/9UB3Z3\nTwitter: https://twitter.com/pydataberlin\nTwitter: https://twitter.com/pyconde", + "duration": 2563, + "language": "eng", + "recorded": "2022-04-11", + "related_urls": [ + { + "label": "Conference Website", + "url": "https://2022.pycon.de/" + }, + { + "label": "https://2022.pycon.de", + "url": "https://2022.pycon.de" + }, + { + "label": "https://twitter.com/pyconde", + "url": "https://twitter.com/pyconde" + }, + { + "label": "https://twitter.com/pydataberlin", + "url": "https://twitter.com/pydataberlin" + }, + { + "label": "https://2022.pycon.de/program/9UB3Z3", + "url": "https://2022.pycon.de/program/9UB3Z3" + } + ], + "speakers": [ + "TODO" + ], + "tags": [ + "artificial intelligence", + "data", + "data engineering", + "deep learning", + "ethics", + "machine learning", + "python" + ], + "thumbnail_url": "https://i.ytimg.com/vi_webp/lffKmis16ic/maxresdefault.webp", + "title": "Yunus Emrah Bulut: Machine Learning Testing Ecosystem of Python", + "videos": [ + { + "type": "youtube", + "url": "https://www.youtube.com/watch?v=lffKmis16ic" + } + ] +}