Updated valx to version 0.2.4.

Author: Infinitode

.gitignore

@@ -2,4 +2,5 @@ __pycache__
 *.pyc
 dist/
 build/
-venv/
+env/
+.venv/

README.md

@@ -11,6 +11,12 @@ An open-source Python library for data cleaning tasks. It includes functions for
 > Please downgrade to `numpy` version `1.26.4`. Our ValX **DecisionTreeClassifier** AI model, relies on lower versions of `numpy`, because it was trained on these versions.
 > For more information see: https://techoverflow.net/2024/07/23/how-to-fix-numpy-dtype-size-changed-may-indicate-binary-incompatibility-expected-96-from-c-header-got-88-from-pyobject/
 
+## Changes in 0.2.4
+
+Fixed a major incompatibility issue with `scikit-learn` due to version changes in `scikit-learn v1.3.0` which causes compatibility issues with versions later than `1.2.2`. ValX can now be used with `scikit-learn` versions earlier and later than `1.3.0`!
+
+We've also removed `scikit-learn==1.2.2` as a dependency, as most versions of `scikit-learn` will now work.
+
 ## Changes in 0.2.3
 
 We have introduced a new optional `info_type` parameter into our `detect_sensitive_information`, and `remove_sensitive_information` functions, to allow you to have fine-grained control over what sensitive information you want to detect or remove.

setup.py

@@ -15,10 +15,10 @@
     packages=find_packages(),
     package_data={'valx': ['models/*']},
     install_requires=[
-        'scikit-learn==1.2.2'  # for the AI to function properly
+        'scikit-learn'
     ],
     classifiers=[
-        'Development Status :: 3 - Alpha',
+        'Development Status :: 5 - Production/Stable',
         'Intended Audience :: Developers',
         'License :: OSI Approved :: MIT License',
         'Programming Language :: Python :: 3.6',

test.py

@@ -14,7 +14,7 @@ def main():
     # Print out all detected words
     print([d['Word'] for d in detected_profanity])
 
-    removed = remove_profanity(sample_text, "text_cleaned.txt", language="All")
+    remove_profanity(sample_text, "text_cleaned.txt", language="All")
 
     # New version
     print(detect_hate_speech("You're so stupid."))

test_new.py

@@ -3,6 +3,7 @@
 
 # New version, that includes AI detection
 import pickle
+from sklearn import __version__ as sklearnversion
 from sklearn.tree import DecisionTreeClassifier  # Import the DecisionTreeClassifier class
 from sklearn.feature_extraction.text import CountVectorizer  # Import the CountVectorizer class
 
@@ -2902,8 +2903,18 @@ def remove_sensitive_information(text_data, output_file=None, info_type=["email"
 
 # New version
 MODEL_DIR = os.path.join(os.path.dirname(__file__), 'models')
-DECISION_TREE_MODEL_PATH = os.path.join(MODEL_DIR, 'decision_tree_model.sav')
 COUNT_VECTORIZER_PATH = os.path.join(MODEL_DIR, 'count_vectorizer.sav')
+DEFAULT_MODEL_FILENAME = "decision_tree_model.sav"
+UPGRADED_MODEL_FILENAME = "classifier_upgraded.pkl"
+
+# Check scikit-learn version
+SKLEARN_VERSION = tuple(map(int, sklearnversion.split(".")))
+
+# Set the model path based on the version
+if SKLEARN_VERSION >= (1, 3, 0):
+    DECISION_TREE_MODEL_PATH = os.path.join(MODEL_DIR, UPGRADED_MODEL_FILENAME)
+else:
+    DECISION_TREE_MODEL_PATH = os.path.join(MODEL_DIR, DEFAULT_MODEL_FILENAME)
 
 # Load the saved models
 model = pickle.load(open(DECISION_TREE_MODEL_PATH, 'rb'))