PerSent 0.1.0__tar.gz → 0.1.2__tar.gz

{persent-0.1.0 → persent-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PerSent
-Version: 0.1.0
+Version: 0.1.2
 Summary: Persian Sentiment Analysis Toolkit
 Home-page: https://github.com/RezaGooner/PerSent
 Author: RezaGooner

{persent-0.1.0 → persent-0.1.2}/PerSent/__init__.py

@@ -1,4 +1,4 @@
 from .analyzer import PersianSentimentAnalyzer
 
-__version__ = "0.1.0"
+__version__ = "0.1.2"
 __all__ = ['PersianSentimentAnalyzer']

{persent-0.1.0 → persent-0.1.2}/PerSent/analyzer.py

@@ -1,7 +1,7 @@
 import pandas as pd
 from hazm import Normalizer, word_tokenize, Stemmer, stopwords_list
 import re
-from tqdm import tqdm
+from tqdm import tqdm  
 from gensim.models import Word2Vec
 import numpy as np
 from sklearn.linear_model import LogisticRegression
@@ -17,31 +17,31 @@ class PersianSentimentAnalyzer:
         self.model_dir = model_dir
         self.vectorizer = None
         self.classifier = None
+        self.emotion_keywords = {
+            'Fear': ['ترس', 'وحشت', 'هراس'],
+            'Surprise': ['تعجب', 'شگفت', 'حیرت'],
+            'Anger': ['خشم', 'عصبانیت', 'خشونت'],
+            'Contempt': ['تحقیر', 'توهین', 'حقارت'],
+            'Joy': ['شادی', 'خوشحالی', 'خنده'],
+            'Sadness': ['غم', 'اندوه', 'ناراحتی'],
+            'Disgust': ['انزجار', 'تهوع', 'نفرت']
+        }
         
-        # 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:
@@ -50,13 +50,19 @@ class PersianSentimentAnalyzer:
                 vectors.append(np.zeros(100))
         return np.mean(vectors, axis=0) if vectors else np.zeros(100)
     
+    def _emotion_analysis(self, tokens):
+        """تحلیل احساسات بر اساس کلیدواژه‌های از پیش تعریف شده"""
+        emotions = {emotion: 0 for emotion in self.emotion_keywords.keys()}
+        for word in tokens:
+            for emotion, keywords in self.emotion_keywords.items():
+                if word in keywords:
+                    emotions[emotion] += 1
+        return emotions
+    
     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,
@@ -65,7 +71,6 @@ class PersianSentimentAnalyzer:
             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,
@@ -73,41 +78,47 @@ class PersianSentimentAnalyzer:
             "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"""
+    def predict(self, text, mode=0):
+        """پیش‌بینی احساس متن با قابلیت انتخاب حالت تحلیل
+        
+        پارامترها:
+            mode (int): 
+                0 = تحلیل توصیه (پیش‌فرض)
+                1 = تحلیل احساسات (Fear, Joy, etc.)
+        """
         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]
+        if mode == 0:
+            vector = self._sentence_vector(tokens, self.vectorizer)
+            prediction = self.classifier.predict([vector])[0]
+            return {
+                0: "not_recommended",
+                1: "recommended",
+                2: "no_idea"
+            }[prediction]
+            
+        elif mode == 1:
+            return self._emotion_analysis(tokens)
+            
+        else:
+            raise ValueError("Invalid mode. Use 0 (recommendation analysis) or 1 (emotion analysis)")
     
     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 → persent-0.1.2}/PerSent.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PerSent
-Version: 0.1.0
+Version: 0.1.2
 Summary: Persian Sentiment Analysis Toolkit
 Home-page: https://github.com/RezaGooner/PerSent
 Author: RezaGooner

{persent-0.1.0 → persent-0.1.2}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 
 setup(
     name="PerSent",
-    version="0.1.0",
+    version="0.1.2",
     author="RezaGooner",
     author_email="RezaAsadiProgrammer@Gmail.com",
     description="Persian Sentiment Analysis Toolkit",