Update app.py

app.py

@@ -41,6 +41,14 @@ with open('engagement_metrics.json', 'r') as f:
 # Convert engagement metrics to DataFrame
 engagement_df = pd.json_normalize(engagement_metrics)
 
+# Load solved.json (hashtags and captions)
+logging.info("Loading solved.json...")
+with open('solved.json', 'r') as f:
+    solved_data = json.load(f)
+
+# Convert solved.json to DataFrame
+solved_df = pd.json_normalize(solved_data)
+
 # Check for required columns in engagement data
 required_columns = ['posting_time', 'likes', 'comments', 'shares']
 missing_columns = [col for col in required_columns if col not in engagement_df.columns]
@@ -102,17 +110,12 @@ label_encoder = LabelEncoder()
 data['content_type_encoded'] = label_encoder.fit_transform(data['content_type'])
 data['media_type_encoded'] = label_encoder.fit_transform(data['media_type'])
 
-# Ensure 'comments' column is treated as a string column
-data['comments'] = data['comments'].astype(str)
-
 # Calculate sentiment for captions in the main dataset
+logging.info("Performing sentiment analysis on captions...")
 data['caption_sentiment'] = data['caption'].apply(lambda x: TextBlob(x).sentiment.polarity)
 
-# Calculate sentiment for comments in the main dataset
-data['comments_sentiment'] = data['comments'].apply(lambda x: TextBlob(x).sentiment.polarity)
-
-# Combine caption and comments sentiment (e.g., average)
-data['sentiment'] = (data['caption_sentiment'] + data['comments_sentiment']) / 2
+# Use caption sentiment as the overall sentiment
+data['sentiment'] = data['caption_sentiment']
 
 # Feature Engineering in the main dataset
 logging.info("Performing feature engineering...")
@@ -211,7 +214,7 @@ else:
     print(recommend_hashtags(0))
 
 # Sentiment Analysis: Audience Reactions (using main dataset)
-logging.info("Performing sentiment analysis on captions and comments...")
+logging.info("Performing sentiment analysis on captions...")
 data['sentiment_category'] = data['sentiment'].apply(lambda x: 'Positive' if x > 0 else 'Negative' if x < 0 else 'Neutral')
 logging.info("Sentiment Analysis Results:")
 print(data['sentiment_category'].value_counts())