Merge pull request #2 from christianversloot/add-testing-action

Add automated testing to repository

Author: christianversloot

.github/workflows/python-package.yml

@@ -0,0 +1,36 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Python package
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.6', '3.7', '3.8', '3.9']
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+  "python.formatting.provider": "black"
+}

assets/basic_template.py

@@ -9,28 +9,29 @@
 
 '''
 
-from tensorflow.keras.utils import get_file
 import numpy as np
 
+
 def load_data(path='<Dataset_slug>.npz', size='small'):
-  """Loads the <Dataset name>
-  # Arguments
-      path: path where to cache the dataset locally
-          (relative to ~/.keras/datasets).
-      size: small or large, indicating dummy dataset size to return.
-  # Returns
-      Tuple of Numpy arrays: `(input_train, target_train), (input_test, target_test)`.
-  """
+    """Loads the <Dataset name>
+    # Arguments
+        path: path where to cache the dataset locally
+            (relative to ~/.keras/datasets).
+        size: small or large, indicating dummy dataset size to return.
+    # Returns
+        Tuple of Numpy arrays: `(input_train, target_train),
+                                  (input_test, target_test)`.
+    """
 
     if size == 'small':
-      input_train = np.array([1, 2])
-      target_train = np.array([0, 1])
-      input_test = np.array([2, 3])
-      target_test = np.array([1, 0])
+        input_train = np.array([1, 2])
+        target_train = np.array([0, 1])
+        input_test = np.array([2, 3])
+        target_test = np.array([1, 0])
     else:
-      input_train = np.array([1, 2, 84, 9, 1, 48, 2])
-      target_train = np.array([0, 1, 0, 0, 0, 1, 1])
-      input_test = np.array([2, 3, 32, 84, 99, 1, 2])
-      target_test = np.array([1, 0, 0, 0, 1, 0, 1])
-  
-    return (input_train, target_train), (input_test, target_test)
+        input_train = np.array([1, 2, 84, 9, 1, 48, 2])
+        target_train = np.array([0, 1, 0, 0, 0, 1, 1])
+        input_test = np.array([2, 3, 32, 84, 99, 1, 2])
+        target_test = np.array([1, 0, 0, 0, 1, 0, 1])
+
+    return (input_train, target_train), (input_test, target_test)

extra_keras_datasets/__init__.py

@@ -6,4 +6,6 @@
 from . import kmnist
 from . import svhn
 from . import stl10
-from . import iris
+from . import iris
+
+__all__ = ['emnist', 'kmnist', 'svhn', 'stl10', 'iris']

extra_keras_datasets/emnist.py

@@ -1,55 +1,68 @@
-'''
+"""
   Import the EMNIST dataset
   Source: https://www.nist.gov/itl/products-and-services/emnist-dataset
-  Description: The EMNIST dataset is a set of handwritten character digits derived from the NIST Special Database 19  and converted to a 28x28 pixel image format and dataset structure that directly matches the MNIST dataset
+  Description: The EMNIST dataset is a set of handwritten character
+  digits derived from the NIST Special Database 19  and converted to
+  a 28x28 pixel image format and dataset structure that directly
+  matches the MNIST dataset
 
   ~~~ Important note ~~~
   Please cite the following paper when using or referencing the dataset:
-  Cohen, G., Afshar, S., Tapson, J., & van Schaik, A. (2017). EMNIST: an extension of MNIST to handwritten letters. Retrieved from http://arxiv.org/abs/1702.05373
+  Cohen, G., Afshar, S., Tapson, J., & van Schaik, A. (2017). EMNIST:
+  an extension of MNIST to handwritten letters.
+  Retrieved from http://arxiv.org/abs/1702.05373
 
-'''
+"""
 
 from tensorflow.keras.utils import get_file
-import numpy as np
 from zipfile import ZipFile
 from scipy import io as sio
 import os
 
-def load_data(path='emnist_matlab.npz', type='balanced'):
-  """Loads the EMNIST dataset.
-  # Arguments
-      path: path where to cache the dataset locally
-          (relative to ~/.keras/datasets).
-      type: any of balanced, byclass, bymerge, digits, letters, mnist (defaults to balanced)
-  # Returns
-      Tuple of Numpy arrays: `(input_train, target_train), (input_test, target_test)`.
-  """
-  path = get_file(path,
-                    origin='http://www.itl.nist.gov/iaui/vip/cs_links/EMNIST/matlab.zip')
-  with ZipFile(path, 'r') as opened_zip:
-
-    # Read file and temporarily store it
-    file_name = f'./{type}.mat'
-    f = open(file_name, 'wb')
-    f.write(opened_zip.read(f'matlab/emnist-{type}.mat'))
-    f.close()
-
-    # Load data from Matlab file.
-    # Source: https://stackoverflow.com/a/53547262
-    mat = sio.loadmat(file_name)
-    data = mat['dataset']
-    input_train = data['train'][0,0]['images'][0,0]
-    target_train = data['train'][0,0]['labels'][0,0].flatten()
-    input_test = data['test'][0,0]['images'][0,0]
-    target_test = data['test'][0,0]['labels'][0,0].flatten()
-
-    # Remove data when loaded
-    os.remove(file_name)
-
-    # Reshape input data
-    # Source: https://stackoverflow.com/a/53547262
-    input_train = input_train.reshape((input_train.shape[0], 28, 28), order='F')
-    input_test = input_test.reshape((input_test.shape[0], 28, 28), order='F')
-
-    # Return data
-    return (input_train, target_train), (input_test, target_test)
+
+def load_data(path="emnist_matlab.npz", type="balanced"):
+    """Loads the EMNIST dataset.
+    # Arguments
+        path: path where to cache the dataset locally
+            (relative to ~/.keras/datasets).
+        type: any of balanced, byclass, bymerge, digits, letters,
+                mnist (defaults to balanced)
+    # Returns
+        Tuple of Numpy arrays: `(input_train, target_train),
+                                  (input_test, target_test)`.
+    """
+    path = get_file(
+        path, origin=("http://www.itl.nist.gov/iaui/vip/cs_links/EMNIST/"
+                      "matlab.zip")
+    )
+    with ZipFile(path, "r") as opened_zip:
+
+        # Read file and temporarily store it
+        file_name = f"./{type}.mat"
+        f = open(file_name, "wb")
+        f.write(opened_zip.read(f"matlab/emnist-{type}.mat"))
+        f.close()
+
+        # Load data from Matlab file.
+        # Source: https://stackoverflow.com/a/53547262
+        mat = sio.loadmat(file_name)
+        data = mat["dataset"]
+        input_train = data["train"][0, 0]["images"][0, 0]
+        target_train = data["train"][0, 0]["labels"][0, 0].flatten()
+        input_test = data["test"][0, 0]["images"][0, 0]
+        target_test = data["test"][0, 0]["labels"][0, 0].flatten()
+
+        # Remove data when loaded
+        os.remove(file_name)
+
+        # Reshape input data
+        # Source: https://stackoverflow.com/a/53547262
+        input_train = input_train.reshape(
+          (input_train.shape[0], 28, 28), order="F"
+        )
+        input_test = input_test.reshape(
+          (input_test.shape[0], 28, 28), order="F"
+        )
+
+        # Return data
+        return (input_train, target_train), (input_test, target_test)

extra_keras_datasets/iris.py

@@ -1,82 +1,94 @@
-'''
+"""
   Import the Iris dataset
   Source: http://archive.ics.uci.edu/ml/datasets/Iris
-  Description: The data set contains 3 classes of 50 instances each, where each class refers to a type of iris plant.
+  Description: The data set contains 3 classes of 50 instances each, where
+  each class refers to a type of iris plant.
 
   ~~~ Important note ~~~
   Please cite the following paper when using or referencing the dataset:
-  Fisher,R.A. "The use of multiple measurements in taxonomic problems" Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to Mathematical Statistics" (John Wiley, NY, 1950).
-'''
+  Fisher,R.A. "The use of multiple measurements in taxonomic problems"
+  Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions
+  to Mathematical Statistics" (John Wiley, NY, 1950).
+"""
 
 from tensorflow.keras.utils import get_file
 import numpy as np
 import math
 
-def load_data(path='iris.npz', test_split=0.2):
-  '''Loads the Iris dataset.
-  # Arguments
-      path: path where to cache the dataset locally
-          (relative to ~/.keras/datasets).
-      test_split: percentage of data to use for testing (by default 20%)
-  # Returns
-      Tuple of Numpy arrays: `(input_train, target_train), (input_test, target_test)`.
-      Input structure: (sepal length, sepal width, petal length, petal width)
-      Target structure: 0 = iris setosa; 1 = iris versicolor; 2 = iris virginica.
-  '''
-  path = get_file(path,
-                    origin='http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data')
 
-  # Read data from file
-  f = open(path, 'r')
-  lines = f.readlines()
-  
-  # Process each line into input/target structure
-  samples = []
-  for line in lines:
-    sample = line_to_list(line)
-    if sample is not None:
-      samples.append(sample)
-  f.close()
+def load_data(path="iris.npz", test_split=0.2):
+    """Loads the Iris dataset.
+    # Arguments
+        path: path where to cache the dataset locally
+            (relative to ~/.keras/datasets).
+        test_split: percentage of data to use for testing (by default 20%)
+    # Returns
+        Tuple of Numpy arrays: `(input_train, target_train),
+                                  (input_test, target_test)`.
+        Input structure: (sepal length, sepal width, petal length,
+                            petal width)
+        Target structure: 0 = iris setosa; 1 = iris versicolor;
+                            2 = iris virginica.
+    """
+    path = get_file(
+        path,
+        origin=("http://archive.ics.uci.edu/ml/machine-learning-databases/"
+                "iris/iris.data")
+    )
 
-  # Randomly shuffle the data
-  np.random.shuffle(samples)
+    # Read data from file
+    f = open(path, "r")
+    lines = f.readlines()
 
-  # Compute test_split in length
-  num_test_samples = math.floor(len(samples) * test_split)
+    # Process each line into input/target structure
+    samples = []
+    for line in lines:
+        sample = line_to_list(line)
+        if sample is not None:
+            samples.append(sample)
+    f.close()
 
-  # Split data
-  training_data = samples[num_test_samples:]
-  testing_data = samples[:num_test_samples]
+    # Randomly shuffle the data
+    np.random.shuffle(samples)
+
+    # Compute test_split in length
+    num_test_samples = math.floor(len(samples) * test_split)
+
+    # Split data
+    training_data = samples[num_test_samples:]
+    testing_data = samples[:num_test_samples]
+
+    # Split into inputs and targets
+    input_train = [i[0:4] for i in training_data]
+    input_test = [i[0:4] for i in testing_data]
+    target_train = [i[4] for i in training_data]
+    target_test = [i[4] for i in testing_data]
+
+    # Return data
+    return (input_train, target_train), (input_test, target_test)
 
-  # Split into inputs and targets
-  input_train = [i[0:4] for i in training_data]
-  input_test = [i[0:4] for i in testing_data]
-  target_train = [i[4] for i in training_data]
-  target_test = [i[4] for i in testing_data]
 
-  # Return data
-  return (input_train, target_train), (input_test, target_test)
-  
 def line_to_list(line):
-  '''
+    """
     Convert a String-based line into a list with input and target data.
-  '''
-  elements = line.split(',')
-  if len(elements) > 1:
-    target = target_string_to_int(elements[4])
-    full_sample = [float(i) for i in elements[0:4]]
-    full_sample.append(target)
-    return tuple(full_sample)
-  else:
-    return None
+    """
+    elements = line.split(",")
+    if len(elements) > 1:
+        target = target_string_to_int(elements[4])
+        full_sample = [float(i) for i in elements[0:4]]
+        full_sample.append(target)
+        return tuple(full_sample)
+    else:
+        return None
+
 
 def target_string_to_int(target_value):
-  '''
+    """
     Convert a String-based into an Integer-based target value.
-  '''
-  if target_value == 'Iris-setosa\n':
-    return 0
-  elif target_value == 'Iris-versicolor\n':
-    return 1
-  else:
-    return 2
+    """
+    if target_value == "Iris-setosa\n":
+        return 0
+    elif target_value == "Iris-versicolor\n":
+        return 1
+    else:
+        return 2