Migrate to Python 3.9+ and modernize dependencies

README.md

@@ -36,7 +36,7 @@ HateSonar allows you to detect hate speech and offensive language in text, witho
 ## Feature Support
 * Hate speech and offensive language detection
 
-HateSonar officially supports Python 2.7 & 3.4–3.6
+HateSonar officially supports Python 3.9+
 
 ## Installation
 To install HateSonar, simply use `pip`:

hatesonar/api.py

@@ -2,17 +2,13 @@
 Model API.
 """
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
 import os
 
 import joblib
 import numpy as np
 
 
-class Sonar(object):
+class Sonar:
 
     def __init__(self):
         BASE_DIR = os.path.join(os.path.dirname(__file__), './data')
@@ -49,7 +45,7 @@ def get_class_idx():
                     return i
 
         class_idx = get_class_idx()
-        features = self.preprocessor.get_feature_names()
+        features = self.preprocessor.get_feature_names_out()
         weights = self.estimator.coef_[class_idx]
         word2weight = {f: w for f, w in zip(features, weights)}
         tokenize = self.preprocessor.build_analyzer()

hatesonar/crawler/blog.py

@@ -4,7 +4,7 @@
 import requests
 
 
-class BlogCrawler(object):
+class BlogCrawler:
 
     def __init__(self):
         pass

hatesonar/crawler/twitter.py

@@ -20,7 +20,7 @@ def load_keys():
     return consumer_key, consumer_secret, access_token, access_token_secret
 
 
-class TwitterAPI(object):
+class TwitterAPI:
 
     def __init__(self, consumer_key, consumer_secret, access_token, access_token_secret):
         auth = tweepy.OAuthHandler(consumer_key, consumer_secret)

hatesonar/trainer/task.py

@@ -2,15 +2,11 @@
 Baseline model.
 """
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
 import argparse
 import os
 
+import joblib
 import pandas as pd
-from sklearn.externals import joblib
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import classification_report
@@ -28,7 +24,7 @@ def main(args):
     x_train = vectorizer.fit_transform(x_train)
 
     print('Fitting...')
-    clf = LogisticRegression(penalty='l1')
+    clf = LogisticRegression(penalty='l1', solver='saga', max_iter=1000)
     clf.fit(x_train, y_train)
 
     print('Saving...')
@@ -48,8 +44,8 @@ def main(args):
     SAVE_DIR = os.path.join(os.path.dirname(__file__), '../data')
     parser = argparse.ArgumentParser(description='Training a classifier')
     parser.add_argument('--dataset', default=os.path.join(DATA_DIR, 'labeled_data.csv'), help='dataset')
-    parser.add_argument('--model_file', default=os.path.join(SAVE_DIR, 'model.pkl'), help='model file')
-    parser.add_argument('--preprocessor', default=os.path.join(SAVE_DIR, 'preprocess.pkl'), help='preprocessor')
+    parser.add_argument('--model_file', default=os.path.join(SAVE_DIR, 'model.joblib'), help='model file')
+    parser.add_argument('--preprocessor', default=os.path.join(SAVE_DIR, 'preprocess.joblib'), help='preprocessor')
     parser.add_argument('--test_size', type=float, default=0.3, help='test data size')
     args = parser.parse_args()
     main(args)

requirements.txt

@@ -1,16 +1,16 @@
-click==7.1.2
-Flask==1.1.2
-gunicorn==20.1.0
-itsdangerous==1.1.0
-Jinja2==3.0.3
-joblib==1.0.1
-MarkupSafe==1.1.1
-numpy==1.22.2
-pandas==1.2.4
-python-dateutil==2.8.1
-pytz==2021.1
-scikit-learn==0.24.2
-scipy==1.8.0
-six==1.16.0
-threadpoolctl==2.1.0
-Werkzeug==2.0.3
+click>=8.0.0
+Flask>=2.0.0
+gunicorn>=20.1.0
+itsdangerous>=2.0.0
+Jinja2>=3.0.0
+joblib>=1.0.0
+MarkupSafe>=2.0.0
+numpy>=1.19.0
+pandas>=1.1.0
+python-dateutil>=2.8.0
+pytz>=2021.1
+scikit-learn>=0.24.0
+scipy>=1.5.0
+six>=1.15.0
+threadpoolctl>=2.1.0
+Werkzeug>=2.0.0

setup.py

@@ -25,12 +25,12 @@
     sys.exit()
 
 required = [
-    'numpy>=1.14.0', 'pandas>=0.22.0', 'scikit-learn>=0.19.1', 'scipy>=1.0.0', 'joblib>=0.16.0'
+    'numpy>=1.19.0', 'pandas>=1.1.0', 'scikit-learn>=0.24.0', 'scipy>=1.5.0', 'joblib>=1.0.0'
 ]
 
 setup(
     name=NAME,
-    version='0.0.7',
+    version='0.0.8',
     description=DESCRIPTION,
     long_description=long_description,
     long_description_content_type='text/markdown',
@@ -41,14 +41,16 @@
     install_requires=required,
     include_package_data=True,
     license=LICENSE,
+    python_requires='>=3.9',
     classifiers=[
         'License :: OSI Approved :: MIT License',
         'Programming Language :: Python',
-        'Programming Language :: Python :: 2.7',
-        'Programming Language :: Python :: 3.4',
-        'Programming Language :: Python :: 3.5',
-        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.9',
+        'Programming Language :: Python :: 3.10',
+        'Programming Language :: Python :: 3.11',
+        'Programming Language :: Python :: 3.12',
+        'Programming Language :: Python :: 3.13',
         'Programming Language :: Python :: Implementation :: CPython',
-        'Programming Language :: Python :: Implementation :: PyPy'
     ],
 )

tox.ini

@@ -1,5 +1,5 @@
 [tox]
-envlist = py27,py36
+envlist = py39,py310,py311,py312
 
 [testenv]
 deps=pytest

verify_migration.py

@@ -0,0 +1,117 @@
+#!/usr/bin/env python
+"""
+Verification script for Python 3.9+ migration.
+Run this after installing dependencies to verify the migration was successful.
+"""
+
+import sys
+
+def check_python_version():
+    """Check if Python version is 3.9 or higher."""
+    print(f"Python version: {sys.version}")
+    if sys.version_info < (3, 9):
+        print("❌ ERROR: Python 3.9+ is required!")
+        return False
+    print("✅ Python version OK")
+    return True
+
+def check_imports():
+    """Check if all required imports work."""
+    try:
+        import joblib
+        print(f"✅ joblib {joblib.__version__}")
+    except ImportError as e:
+        print(f"❌ Failed to import joblib: {e}")
+        return False
+
+    try:
+        import numpy
+        print(f"✅ numpy {numpy.__version__}")
+    except ImportError as e:
+        print(f"❌ Failed to import numpy: {e}")
+        return False
+
+    try:
+        import pandas
+        print(f"✅ pandas {pandas.__version__}")
+    except ImportError as e:
+        print(f"❌ Failed to import pandas: {e}")
+        return False
+
+    try:
+        import sklearn
+        print(f"✅ scikit-learn {sklearn.__version__}")
+    except ImportError as e:
+        print(f"❌ Failed to import sklearn: {e}")
+        return False
+
+    try:
+        import scipy
+        print(f"✅ scipy {scipy.__version__}")
+    except ImportError as e:
+        print(f"❌ Failed to import scipy: {e}")
+        return False
+
+    return True
+
+def check_hatesonar():
+    """Check if hatesonar can be imported and works."""
+    try:
+        from hatesonar import Sonar
+        print("✅ HateSonar imported successfully")
+
+        # Try to create an instance
+        sonar = Sonar()
+        print("✅ Sonar instance created successfully")
+
+        # Try a simple prediction
+        result = sonar.ping(text="This is a test")
+        print("✅ Sonar.ping() works correctly")
+        print(f"   Result keys: {result.keys()}")
+
+        return True
+    except Exception as e:
+        print(f"❌ Failed to test HateSonar: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def main():
+    """Run all verification checks."""
+    print("=" * 60)
+    print("HateSonar Python 3.9+ Migration Verification")
+    print("=" * 60)
+    print()
+
+    print("Step 1: Checking Python version...")
+    version_ok = check_python_version()
+    print()
+
+    if not version_ok:
+        print("Please install Python 3.9 or higher and try again.")
+        sys.exit(1)
+
+    print("Step 2: Checking dependencies...")
+    imports_ok = check_imports()
+    print()
+
+    if not imports_ok:
+        print("Please install dependencies: pip install -e .")
+        sys.exit(1)
+
+    print("Step 3: Testing HateSonar...")
+    hatesonar_ok = check_hatesonar()
+    print()
+
+    if hatesonar_ok:
+        print("=" * 60)
+        print("✅ All checks passed! Migration successful!")
+        print("=" * 60)
+    else:
+        print("=" * 60)
+        print("❌ Some checks failed. Please review the errors above.")
+        print("=" * 60)
+        sys.exit(1)
+
+if __name__ == "__main__":
+    main()