Update app.py

app.py

@@ -1,105 +1,126 @@
 import streamlit as st
-from transformers import pipeline
-from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
-import numpy as np
 import pandas as pd
-from datetime import datetime, timedelta
-import plotly.express as px
-from sklearn.linear_model import LinearRegression
-from wordcloud import WordCloud
-import base64
-from io import BytesIO
+import matplotlib.pyplot as plt
+import seaborn as sns
 import nltk
 from textblob import TextBlob
+import numpy as np
+from wordcloud import WordCloud
+import plotly.express as px
+from datetime import datetime, timedelta
+from transformers import pipeline
+from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
 
+# Ensure necessary NLTK data is available
 nltk.download('punkt')
 
-# Initialize sentiment models
-bert_sentiment = pipeline("sentiment-analysis", model="nlptown/bert-base-multilingual-uncased-sentiment")
-vader_analyzer = SentimentIntensityAnalyzer()
-
-# Generate sample past sentiment data
-dates = [datetime.today() - timedelta(days=i) for i in range(14)]
-sentiment_scores = np.random.uniform(-1, 1, len(dates))
-df = pd.DataFrame({"Date": dates, "Sentiment Score": sentiment_scores})
+st.set_page_config(page_title="Advanced Sentiment Analyzer", layout="wide")
 
-# Train a regression model
-X = np.array(range(len(df))).reshape(-1, 1)
-y = df["Sentiment Score"]
-model = LinearRegression()
-model.fit(X, y)
-
-# Predict for next 7 days
-future_dates = [datetime.today() + timedelta(days=i) for i in range(1, 8)]
-X_future = np.array(range(len(df), len(df) + 7)).reshape(-1, 1)
-predictions = model.predict(X_future)
-
-future_df = pd.DataFrame({"Date": future_dates, "Predicted Sentiment": predictions})
-
-# Generate Word Cloud
-def generate_wordcloud(text):
-    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(text)
-    img = BytesIO()
-    wordcloud.to_image().save(img, format='PNG')
-    return base64.b64encode(img.getvalue()).decode()
-
-# Streamlit app setup
-st.title("🌟 Advanced Sentiment Analysis Dashboard")
+st.title("🔍 Advanced Sentiment Analysis Dashboard")
+st.markdown("Analyze sentiments with deep insights and visualizations")
 
 # Sidebar for user input
-st.sidebar.header("🔍 Sentiment Analysis Controls")
-user_input = st.sidebar.text_area("Enter text for sentiment analysis")
-
-# Display sentiment analysis results
-def display_sentiment_analysis(vader_score, bert_result, textblob_score):
-    st.subheader("📊 Sentiment Analysis Results:")
-    st.write(f"**VADER Sentiment Score**: {vader_score:.2f}")
-    st.write(f"**BERT Sentiment**: {bert_result['label']} ({bert_result['score']:.2f})")
-    st.write(f"**TextBlob Sentiment Polarity**: {textblob_score:.2f}")
-
-    sentiment_data = {'Positive': max(0, vader_score), 'Negative': min(0, vader_score), 'Neutral': 1 - abs(vader_score)}
-    sentiment_df = pd.DataFrame(list(sentiment_data.items()), columns=["Sentiment", "Score"])
-    st.bar_chart(sentiment_df.set_index("Sentiment"))
-
-    wordcloud_img = f'data:image/png;base64,{generate_wordcloud(user_input)}'
-    st.image(wordcloud_img, use_column_width=True)
-
-if st.sidebar.button("Analyze Sentiment"):
-    if user_input:
-        with st.spinner("Analyzing text..."):
-            vader_score = vader_analyzer.polarity_scores(user_input)['compound']
-            bert_result = bert_sentiment(user_input)[0]
-            textblob_score = TextBlob(user_input).sentiment.polarity
-            display_sentiment_analysis(vader_score, bert_result, textblob_score)
+st.sidebar.header("Upload your dataset")
+uploaded_file = st.sidebar.file_uploader("Upload a CSV file", type=["csv"])
+
+if uploaded_file is not None:
+    df = pd.read_csv(uploaded_file)
+    st.sidebar.success("File uploaded successfully!")
+else:
+    st.sidebar.warning("Please upload a CSV file to proceed.")
+
+# Sample Text Input
+st.sidebar.subheader("Enter Text for Sentiment Analysis")
+user_input = st.sidebar.text_area("Type or paste text here", "The product is amazing!")
+
+# Initialize sentiment analyzers
+analyzer = SentimentIntensityAnalyzer()
+bert_sentiment = pipeline("sentiment-analysis")
+
+def analyze_vader_sentiment(text):
+    score = analyzer.polarity_scores(text)['compound']
+    return "Positive" if score > 0.05 else "Negative" if score < -0.05 else "Neutral"
+
+def analyze_bert_sentiment(text):
+    result = bert_sentiment(text)[0]
+    return result['label']
+
+if user_input:
+    vader_result = analyze_vader_sentiment(user_input)
+    bert_result = analyze_bert_sentiment(user_input)
+    st.sidebar.markdown(f"**VADER Sentiment:** {vader_result}")
+    st.sidebar.markdown(f"**BERT Sentiment:** {bert_result}")
+
+# If dataset is uploaded, analyze sentiments
+if uploaded_file is not None:
+    df['VADER Sentiment'] = df['text'].apply(analyze_vader_sentiment)
+    df['BERT Sentiment'] = df['text'].apply(analyze_bert_sentiment)
+    
+    # Sentiment Distribution
+    st.subheader("📊 Sentiment Distribution")
+    fig, ax = plt.subplots()
+    sns.countplot(x=df['VADER Sentiment'], palette="coolwarm", ax=ax)
+    st.pyplot(fig)
+    
+    # Word Cloud
+    st.subheader("☁️ Word Cloud")
+    sentiment_filter = st.selectbox("Filter Word Cloud by Sentiment", ["All", "Positive", "Neutral", "Negative"])
+    if sentiment_filter != "All":
+        filtered_df = df[df['VADER Sentiment'] == sentiment_filter]
     else:
-        st.warning("⚠️ Please enter some text for analysis.")
-
-# Past sentiment trends
-st.subheader("📅 Past Sentiment Trends (Last 14 Days)")
-fig1 = px.line(df, x='Date', y='Sentiment Score', title='Sentiment Over Time', markers=True, line_shape='spline')
-st.plotly_chart(fig1)
-
-# Future sentiment predictions
-st.subheader("🔮 Sentiment Prediction for Next 7 Days")
-fig2 = px.line(future_df, x='Date', y='Predicted Sentiment', title='Predicted Sentiment Trend', markers=True, line_shape='spline')
-st.plotly_chart(fig2)
-
-# Sentiment distribution pie chart
-st.subheader("📊 Sentiment Distribution")
-fig3 = px.pie(values=[sum(df['Sentiment Score'] > 0), sum(df['Sentiment Score'] <= 0)], names=['Positive', 'Negative'], title='Sentiment Distribution', hole=0.3)
-st.plotly_chart(fig3)
-
-# Sentiment scatter plot
-st.subheader("🔎 Sentiment Scatter Plot (Last 14 Days)")
-fig4 = px.scatter(df, x='Date', y='Sentiment Score', title='Sentiment Over Time')
-st.plotly_chart(fig4)
-
-# Rolling average sentiment
-st.subheader("📈 Rolling Average of Sentiment (7-Day Window)")
-df['Rolling Avg Sentiment'] = df['Sentiment Score'].rolling(window=7).mean()
-fig5 = px.line(df, x='Date', y='Rolling Avg Sentiment', title="7-Day Rolling Average Sentiment")
-st.plotly_chart(fig5)
-
-# Reset button
-if st.sidebar.button('🔄 Reset Analysis'):
-    st.experimental_rerun()
+        filtered_df = df
+    all_text = " ".join(filtered_df['text'].dropna().astype(str))
+    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(all_text)
+    st.image(wordcloud.to_array(), use_column_width=True)
+    
+    # Sentiment Over Time (Simulated for Demo)
+    st.subheader("📈 Sentiment Trend Over Time")
+    df['date'] = pd.date_range(end=datetime.today(), periods=len(df), freq='D')
+    sentiment_map = {'Positive': 1, 'Neutral': 0, 'Negative': -1}
+    df['sentiment_score'] = df['VADER Sentiment'].map(sentiment_map)
+    
+    fig = px.line(df, x='date', y='sentiment_score', title='Sentiment Trend')
+    st.plotly_chart(fig)
+    
+    # Regression Model for Sentiment Prediction
+    st.subheader("📈 Sentiment Prediction")
+    label_encoder = LabelEncoder()
+    df['sentiment_encoded'] = label_encoder.fit_transform(df['VADER Sentiment'])
+    X = np.array(range(len(df))).reshape(-1, 1)
+    y = df['sentiment_encoded']
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    model = LinearRegression()
+    model.fit(X_train, y_train)
+    future_days = np.array(range(len(df), len(df) + 30)).reshape(-1, 1)
+    predicted_sentiments = model.predict(future_days)
+    
+    fig_pred = px.line(x=range(len(df), len(df) + 30), y=predicted_sentiments, title='Predicted Sentiment Trend')
+    st.plotly_chart(fig_pred)
+    
+    # Interactive Pie Chart
+    st.subheader("📝 Sentiment Breakdown")
+    sentiment_counts = df['VADER Sentiment'].value_counts()
+    fig_pie = px.pie(names=sentiment_counts.index, values=sentiment_counts.values, title="Sentiment Breakdown")
+    st.plotly_chart(fig_pie)
+    
+    # Sentiment Heatmap
+    st.subheader("🔥 Sentiment Heatmap")
+    heatmap_df = df.pivot_table(index=df['date'].dt.date, columns='VADER Sentiment', aggfunc='size', fill_value=0)
+    fig_heatmap = px.imshow(heatmap_df.T, title="Sentiment Heatmap", labels=dict(x="Date", y="Sentiment", color="Count"))
+    st.plotly_chart(fig_heatmap)
+    
+    # Keyword Sentiment Analysis
+    st.subheader("🔍 Keyword Sentiment Analysis")
+    keyword = st.text_input("Enter a keyword to analyze sentiment", "great")
+    keyword_df = df[df['text'].str.contains(keyword, case=False, na=False)]
+    st.write(keyword_df[['text', 'VADER Sentiment']])
+    
+    # Download Report as CSV
+    st.subheader("📄 Download Report")
+    csv = df.to_csv(index=False).encode('utf-8')
+    st.download_button(label="Download CSV", data=csv, file_name="sentiment_analysis.csv", mime='text/csv')
+
+st.sidebar.markdown("Developed with ❤️")