PerSent 0.1.0__py3-none-any.whl

PerSent/__init__.py

@@ -0,0 +1,4 @@
+from .analyzer import PersianSentimentAnalyzer
+
+__version__ = "0.1.0"
+__all__ = ['PersianSentimentAnalyzer']

PerSent/analyzer.py

@@ -0,0 +1,113 @@
+import pandas as pd
+from hazm import Normalizer, word_tokenize, Stemmer, stopwords_list
+import re
+from tqdm import tqdm
+from gensim.models import Word2Vec
+import numpy as np
+from sklearn.linear_model import LogisticRegression
+from sklearn.model_selection import train_test_split
+import os
+import joblib
+
+class PersianSentimentAnalyzer:
+    def __init__(self, model_dir='persian_sentiment/model'):
+        self.normalizer = Normalizer()
+        self.stemmer = Stemmer()
+        self.stopwords = set(stopwords_list())
+        self.model_dir = model_dir
+        self.vectorizer = None
+        self.classifier = None
+        
+        # ایجاد پوشه مدل اگر وجود نداشته باشد
+        os.makedirs(self.model_dir, exist_ok=True)
+        
+    def _preprocess_text(self, text):
+        """پیشپردازش متن فارسی"""
+        # نرمال‌سازی
+        text = self.normalizer.normalize(str(text))
+        
+        # حذف اعداد و علائم
+        text = re.sub(r'[!()-\[\]{};:\'",؟<>./?@#$%^&*_~۰-۹\d]+', ' ', text)
+        text = re.sub(r'\s+', ' ', text).strip()
+        
+        # توکن‌سازی و ریشه‌یابی
+        tokens = word_tokenize(text)
+        processed_tokens = [
+            self.stemmer.stem(token)
+            for token in tokens
+            if token not in self.stopwords and len(token) > 1
+        ]
+        
+        return processed_tokens
+    
+    def _sentence_vector(self, sentence, model):
+        """تبدیل جمله به بردار با استفاده از مدل Word2Vec"""
+        vectors = []
+        for word in sentence:
+            try:
+                vectors.append(model.wv[word])
+            except KeyError:
+                vectors.append(np.zeros(100))
+        return np.mean(vectors, axis=0) if vectors else np.zeros(100)
+    
+    def train(self, train_csv, test_size=0.2, vector_size=100, window=5):
+        """آموزش مدل از داده‌های CSV"""
+        # خواندن داده‌ها
+        df = pd.read_csv(train_csv)
+        df['tokens'] = df['body'].apply(self._preprocess_text)
+        
+        # آموزش مدل Word2Vec
+        self.vectorizer = Word2Vec(
+            sentences=df['tokens'],
+            vector_size=vector_size,
+            window=window,
+            min_count=1,
+            workers=4
+        )
+        
+        # تبدیل جملات به بردار
+        X = np.array([self._sentence_vector(s, self.vectorizer) for s in df['tokens']])
+        y = df['recommendation_status'].map({
+            "no_idea": 2,
+            "recommended": 1,
+            "not_recommended": 0
+        }).values
+        
+        # تقسیم داده‌ها
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size)
+        
+        # آموزش طبقه‌بند
+        self.classifier = LogisticRegression(max_iter=1000)
+        self.classifier.fit(X_train, y_train)
+        
+        # ذخیره مدل
+        self.save_model()
+        
+        # ارزیابی
+        accuracy = self.classifier.score(X_test, y_test)
+        return accuracy
+    
+    def predict(self, text):
+        """پیش‌بینی احساس متن"""
+        if not self.classifier or not self.vectorizer:
+            raise Exception("Model not trained! Call train() first or load a pretrained model.")
+            
+        tokens = self._preprocess_text(text)
+        vector = self._sentence_vector(tokens, self.vectorizer)
+        prediction = self.classifier.predict([vector])[0]
+        
+        return {
+            0: "not_recommended",
+            1: "recommended",
+            2: "no_idea"
+        }[prediction]
+    
+    def save_model(self):
+        """ذخیره مدل آموزش دیده"""
+        joblib.dump(self.classifier, os.path.join(self.model_dir, 'classifier.joblib'))
+        self.vectorizer.save(os.path.join(self.model_dir, 'word2vec.model'))
+    
+    def load_model(self):
+        """بارگذاری مدل از فایل"""
+        self.classifier = joblib.load(os.path.join(self.model_dir, 'classifier.joblib'))
+        self.vectorizer = Word2Vec.load(os.path.join(self.model_dir, 'word2vec.model'))

persent-0.1.0.dist-info/METADATA

@@ -0,0 +1,162 @@
+Metadata-Version: 2.4
+Name: PerSent
+Version: 0.1.0
+Summary: Persian Sentiment Analysis Toolkit
+Home-page: https://github.com/RezaGooner/PerSent
+Author: RezaGooner
+Author-email: RezaAsadiProgrammer@Gmail.com
+Keywords: persian sentiment analysis nlp
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: hazm>=0.7.0
+Requires-Dist: gensim>=4.0.0
+Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: pandas>=1.3.0
+Requires-Dist: tqdm>=4.62.0
+Requires-Dist: joblib>=1.1.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Persian Sentiment Analyzer
+
+[![Python Version](https://img.shields.io/badge/python-3.6%2B-blue)](https://www.python.org/)
+[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+
+A Python library for sentiment analysis of Persian (Farsi) text, capable of classifying opinions as "recommended", "not_recommended", or "no_idea".
+
+## Features
+
+- **Text Preprocessing**: Normalization, tokenization, stemming, and stopword removal for Persian text
+- **Word Embeddings**: Built-in Word2Vec implementation for Persian language
+- **Sentiment Classification**: Logistic Regression classifier trained on Persian sentiment data
+- **Model Persistence**: Save and load trained models for future use
+- **Batch Processing**: Analyze sentiment for multiple texts at once
+
+## Installation
+
+```bash
+pip install persian-sentiment-analyzer
+```
+
+## Dependencies
+- Python 3.6+
+
+- hazm
+
+- gensim
+
+- scikit-learn
+
+- numpy
+
+- pandas
+
+## Usage
+
+### Basic Usage
+
+``` bash
+from persian_sentiment_analyzer import SentimentAnalyzer
+
+# Initialize with a pre-trained model
+analyzer = SentimentAnalyzer(model_path="path/to/pretrained_model")
+
+# Predict sentiment
+result = analyzer.predict("این محصول بسیار عالی است")
+print(result)  # Output: 'recommended'
+```
+
+### Training Your Own Model
+
+``` bash
+from persian_sentiment_analyzer import SentimentAnalyzer
+import pandas as pd
+
+# Load your dataset
+data = pd.read_csv("persian_reviews.csv")
+texts = data['text'].tolist()
+labels = data['label'].values  # 0: not_recommended, 1: recommended, 2: no_idea
+
+# Initialize analyzer
+analyzer = SentimentAnalyzer()
+
+# Preprocess and tokenize texts
+tokenized_texts = [analyzer.preprocessor.preprocess_text(text) for text in texts]
+
+# Train Word2Vec model
+analyzer.train_word2vec(tokenized_texts, vector_size=100)
+
+# Prepare feature vectors
+X = np.array([analyzer.sentence_vector(tokens) for tokens in tokenized_texts])
+
+# Train classifier
+analyzer.train_classifier(X, labels)
+
+# Save the trained model
+analyzer.save_model("my_persian_model")
+```
+
+### Batch Processing
+
+```bash
+from persian_sentiment_analyzer import predict_sentiments_for_file
+
+# Process a CSV file containing Persian comments
+results_summary = predict_sentiments_for_file(
+    analyzer,
+    input_file="comments.csv",
+    output_file="results.csv",
+    summary_file="summary.csv"
+)
+
+print(results_summary)
+```
+
+## Model Architecture
+1- Text Preprocessing:
+
+- Normalization (Hazm)
+
+- Tokenization
+
+- Stemming
+
+- Stopword removal
+
+2- Feature Extraction:
+
+- Word2Vec embeddings (100 dimensions)
+
+- Sentence vectors (average of word vectors)
+
+3- Classification:
+
+- Logistic Regression with L2 regularization
+
+## Performance
+The pre-trained model achieves the following performance on our test set:
+
+Metric	Value
+Accuracy	85.2%
+Precision	84.7%
+Recall	85.0%
+F1-score	84.8%
+
+License
+This project is licensed under the MIT [License](https://github.com/RezaGooner/Sentiment-Survey-Analyzer/blob/main/LICENSE) - see the LICENSE file for details
+
+
+> Github : RezaGooner

persent-0.1.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+PerSent/__init__.py,sha256=k1I222LsqgD_RW7iq3V_8RnDPFi6Y7MhWpPCsDX_RBw,113
+PerSent/analyzer.py,sha256=V5JqyyxaF6WuPLpblZ7gz8opYngprYIi5HJIJFCd3uw,4277
+persent-0.1.0.dist-info/licenses/LICENSE.txt,sha256=CcwwQLrmZxKhQzpzoKLRDut_IlthYUCqNyWZfsE4RAo,1094
+persent-0.1.0.dist-info/METADATA,sha256=yz5uOPUAlZC81Ma0U_owVhuAuKF1qqEKdvnpf8mkFcA,4078
+persent-0.1.0.dist-info/WHEEL,sha256=DK49LOLCYiurdXXOXwGJm6U4DkHkg4lcxjhqwRa0CP4,91
+persent-0.1.0.dist-info/top_level.txt,sha256=D-YZBGOvL3FdEaLI9OwoTXniE26IUqE_dX3w8XEiDms,8
+persent-0.1.0.dist-info/RECORD,,

persent-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (78.0.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

persent-0.1.0.dist-info/licenses/LICENSE.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 𝐑𝐞𝐳𝐚 𝐀𝐬𝐚𝐝𝐢
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

persent-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+PerSent