Merge pull request #27 from dimitrismistriotis/update-library-to-1dot…

…3dot1

Update library to 1dot3dot1

CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## Version 1.3.1
+
+* scikit-learn to 1.3.1
+* pandas to 2.1.1
+* numpy to 1.26.0
+* scipy to 1.11.3
+
 ## Version 1.3.0
 
 * scikit-learn to 1.3.0

profanity_check/data/train_model.py

@@ -1,6 +1,7 @@
 """Train Model from data"""
 import hashlib
 import subprocess
+import sys
 from pathlib import Path
 
 import pandas as pd
@@ -18,8 +19,8 @@ def sha256sum(filename) -> str:
 
     Helper method from StackOverflow: https://stackoverflow.com/a/44873382
     """
-    with open(filename, "rb", buffering=0) as f:
-        return hashlib.file_digest(f, "sha512").hexdigest()
+    with open(filename, "rb", buffering=0) as file_to_check:
+        return hashlib.file_digest(file_to_check, "sha512").hexdigest()
 
 
 if __name__ == "__main__":
@@ -30,19 +31,33 @@ def sha256sum(filename) -> str:
     data_file = Path(__file__).parent / DATA_FILE_NAME
     if not data_file.exists():
         print(f"Could not find {DATA_FILE_NAME}, will try to extract.")
-        subprocess.run(["./decompress_data"])
+        #
+        # Note: check=False as per pylint's recommendation, in detail
+        # > The ``check`` keyword is set to False by default. It means the process
+        # > launched by ``subprocess.run`` can exit with a non-zero exit code and
+        # > fail silently. It's better to set it explicitly to make clear what the
+        # > error-handling behavior is.
+        #
+        # A check raising an exception should be added at some point
+        #
+        decompression = subprocess.run(["./decompress_data"], check=False)
 
-        hash_sha512 = sha256sum(data_file)
+        # Check if decompression without errors
+        if decompression.returncode != 0:
+            print("Error in decompressing the data.")
+            sys.exit(1)
+
+        hash_sha256 = sha256sum(data_file)
         hash_file = Path(__file__).parent / HASH_OF_DATA_FILE
         stored_hash = hash_file.read_text().strip().split(" ")[0]
         print(stored_hash)
 
         print()
-        print(f"SHA512 hash of {DATA_FILE_NAME}: {hash_sha512}")
+        print(f"SHA256 hash of {DATA_FILE_NAME}: {hash_sha256}")
         print(f"Stored hash to check against: {stored_hash}")
         print()
 
-        assert hash_sha512 == stored_hash, (
+        assert hash_sha256 == stored_hash, (
             f"Hash of {DATA_FILE_NAME} does not match stored hash. "
             "Please download the data again."
         )

requirements.txt

@@ -1,6 +1,8 @@
-joblib==1.3.1
-numpy==1.24.4
+joblib==1.3.2
+numpy==1.24.4; python_version <= '3.8'
+numpy==1.26.0; python_version >= '3.9'
 # Used for the training script:
-pandas==2.0.3
-scikit-learn==1.3.0
-scipy==1.11.1; python_version >= '3.10'
+pandas==2.0.3; python_version < '3.8'
+pandas==2.1.1; python_version >= '3.9'
+scikit-learn==1.3.1
+scipy==1.11.3; python_version >= '3.10'

setup.py

@@ -6,7 +6,7 @@
 
 setuptools.setup(
     name="alt-profanity-check",
-    version="1.3.0",
+    version="1.3.1",
     author="Victor Zhou (original author), Menelaos Kotoglou, Dimitrios Mistriotis",
     author_email="dimitrios@mistriotis.com",
     description=(
@@ -17,7 +17,7 @@
     long_description_content_type="text/markdown",
     url="https://github.com/dimitrismistriotis/alt-profanity-check",
     packages=setuptools.find_packages(),
-    install_requires=["scikit-learn==1.3.0", "joblib>=1.3.1"],
+    install_requires=["scikit-learn==1.3.1", "joblib>=1.3.1"],
     python_requires=">=3.8",
     package_data={"profanity_check": ["data/model.joblib", "data/vectorizer.joblib"]},
     classifiers=[