toxic-comment-classifier 0.1.0__tar.gz

toxic_comment_classifier-0.1.0/PKG-INFO

@@ -0,0 +1,27 @@
+Metadata-Version: 2.4
+Name: toxic_comment_classifier
+Version: 0.1.0
+Summary: A Python library for classifying toxic comments using deep learning.
+Author-email: Md Irfan Ali <irfanali29@hotmail.com>
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: numpy
+Requires-Dist: tensorflow
+Requires-Dist: pandas
+Requires-Dist: scikit-learn
+
+# toxic_comment_classifier
+
+# Toxic Comment Classifier
+
+A Python library for classifying toxic comments using deep learning.
+
+## Installation
+
+```bash
+pip install toxic_comment_classifier
+```

toxic_comment_classifier-0.1.0/README.md

@@ -0,0 +1,11 @@
+# toxic_comment_classifier
+
+# Toxic Comment Classifier
+
+A Python library for classifying toxic comments using deep learning.
+
+## Installation
+
+```bash
+pip install toxic_comment_classifier
+```

toxic_comment_classifier-0.1.0/pyproject.toml

@@ -0,0 +1,28 @@
+[project]
+name = "toxic_comment_classifier"
+version = "0.1.0"
+description = "A Python library for classifying toxic comments using deep learning."
+authors = [
+    { name = "Md Irfan Ali", email = "irfanali29@hotmail.com" }
+]
+license = { text = "MIT" }  # ← Use table again to avoid license-expression injection
+readme = "README.md"
+requires-python = ">=3.6"
+dependencies = [
+    "numpy",
+    "tensorflow",
+    "pandas",
+    "scikit-learn"
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent"
+]
+
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+license-files = []  # ← Prevent LICENSE.txt from being injected

toxic_comment_classifier-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

toxic_comment_classifier-0.1.0/toxic_classifier/__init__.py

@@ -0,0 +1 @@
+from .model import ToxicCommentClassifier

toxic_comment_classifier-0.1.0/toxic_classifier/model.py

@@ -0,0 +1,45 @@
+import os
+import pickle
+import numpy as np
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import load_model
+
+# === Constants ===
+MAXLEN = 100
+LIST_CLASSES = ["toxic", "severe_toxic", "obscene", "threat", "insult", "identity_hate"]
+
+
+# === Model Class ===
+class ToxicCommentClassifier:
+    def __init__(self):
+        """
+        Initializes the classifier by loading the model and tokenizer.
+        The model files are stored inside the 'models/' directory.
+        """
+        base_path = os.path.dirname(os.path.abspath(__file__))  # Get package directory
+        model_path = os.path.join(base_path, "models", "model.h5")
+        tokenizer_path = os.path.join(base_path, "models", "tokenizer.pickle")
+
+        # Load Tokenizer
+        with open(tokenizer_path, "rb") as handle:
+            self.tokenizer = pickle.load(handle)
+
+        # Load Model
+        self.model = load_model(model_path)
+
+    def classify(self, text: str) -> dict:
+        """
+        Classifies a given text and returns toxicity scores.
+
+        :param text: Input text to classify
+        :return: Dictionary with toxicity scores
+        """
+        # Preprocess text
+        seq = self.tokenizer.texts_to_sequences([text])
+        padded = pad_sequences(seq, maxlen=MAXLEN)
+
+        # Predict toxicity scores
+        preds = self.model.predict(padded)[0]
+
+        # Return results as a dictionary
+        return {LIST_CLASSES[i]: float(preds[i]) for i in range(len(LIST_CLASSES))}

toxic_comment_classifier-0.1.0/toxic_classifier/utils.py

@@ -0,0 +1,13 @@
+import re
+
+
+def clean_text(text: str) -> str:
+    """
+    Cleans text by removing special characters and multiple spaces.
+
+    :param text: Raw text
+    :return: Cleaned text
+    """
+    text = re.sub(r"\s+", " ", text)  # Remove extra spaces
+    text = re.sub(r"[^a-zA-Z0-9!?.,]", " ", text)  # Remove special chars
+    return text.strip()

toxic_comment_classifier-0.1.0/toxic_comment_classifier.egg-info/PKG-INFO

@@ -0,0 +1,27 @@
+Metadata-Version: 2.4
+Name: toxic_comment_classifier
+Version: 0.1.0
+Summary: A Python library for classifying toxic comments using deep learning.
+Author-email: Md Irfan Ali <irfanali29@hotmail.com>
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: numpy
+Requires-Dist: tensorflow
+Requires-Dist: pandas
+Requires-Dist: scikit-learn
+
+# toxic_comment_classifier
+
+# Toxic Comment Classifier
+
+A Python library for classifying toxic comments using deep learning.
+
+## Installation
+
+```bash
+pip install toxic_comment_classifier
+```

toxic_comment_classifier-0.1.0/toxic_comment_classifier.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+toxic_classifier/__init__.py
+toxic_classifier/model.py
+toxic_classifier/utils.py
+toxic_comment_classifier.egg-info/PKG-INFO
+toxic_comment_classifier.egg-info/SOURCES.txt
+toxic_comment_classifier.egg-info/dependency_links.txt
+toxic_comment_classifier.egg-info/requires.txt
+toxic_comment_classifier.egg-info/top_level.txt

toxic_comment_classifier-0.1.0/toxic_comment_classifier.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

toxic_comment_classifier-0.1.0/toxic_comment_classifier.egg-info/requires.txt

@@ -0,0 +1,4 @@
+numpy
+tensorflow
+pandas
+scikit-learn

toxic_comment_classifier-0.1.0/toxic_comment_classifier.egg-info/top_level.txt

@@ -0,0 +1 @@
+toxic_classifier