Update app.py

app.py

@@ -138,6 +138,123 @@ def main():
     else:
         st.warning("No se pudieron cargar los datos. Por favor, verifica la instalación.")
 
+if __name__ == "__main__":
+    try:
+        main()
+    finally:
+        gc.collect()
+
+import streamlit as st
+from transformers import pipeline
+import pandas as pd
+import plotly.express as px
+import nltk
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+import re
+import gc
+
+st.set_page_config(page_title="Análisis de Reseñas de Amazon", page_icon="📊", layout="wide")
+
+@st.cache_resource
+def load_sentiment_analyzer():
+    return pipeline("sentiment-analysis", model="nlptown/bert-base-multilingual-uncased-sentiment")
+
+@st.cache_resource
+def download_nltk_resources():
+    nltk.download('punkt')
+    nltk.download('stopwords')
+    nltk.download('wordnet')
+
+@st.cache_data
+def load_data():
+    try:
+        return pd.read_csv('sample_reviews.csv')
+    except Exception as e:
+        st.error(f"Error cargando datos: {str(e)}")
+        return None
+
+def analyze_sentiment(text):
+    analyzer = load_sentiment_analyzer()
+    result = analyzer(text)[0]
+    rating = int(result['label'].split()[0])
+    if rating >= 4:
+        sentiment = "POSITIVO"
+        color = "green"
+    elif rating == 3:
+        sentiment = "NEUTRAL"
+        color = "blue"
+    else:
+        sentiment = "NEGATIVO"
+        color = "red"
+    return sentiment, result['score'], color
+
+def main():
+    st.title("📊 Análisis de Reseñas de Amazon")
+    
+    # Sección de Análisis de Texto en Tiempo Real
+    st.header("🔍 Análisis de Sentimiento en Tiempo Real")
+    user_text = st.text_area("Escribe o pega un texto para analizar:", height=150)
+    
+    if user_text:
+        with st.spinner('Analizando sentimiento...'):
+            sentiment, confidence, color = analyze_sentiment(user_text)
+            
+            col1, col2 = st.columns(2)
+            col1.metric("Sentimiento", sentiment)
+            col2.metric("Confianza", f"{confidence:.2%}")
+            
+            st.markdown(f"<h3 style='color: {color};'>Resultado: {sentiment}</h3>", unsafe_allow_html=True)
+    
+    # Separador
+    st.markdown("---")
+    
+    # Dashboard Original
+    download_nltk_resources()
+    df = load_data()
+    
+    if df is not None:
+        categories = ['Todas'] + sorted(df['product_category'].unique().tolist())
+        selected_category = st.sidebar.selectbox("Categoría de Producto", categories)
+        
+        df_filtered = df[df['product_category'] == selected_category] if selected_category != 'Todas' else df
+        
+        col1, col2 = st.columns(2)
+        
+        with col1:
+            sentiment_counts = df_filtered['sentiment'].value_counts()
+            fig_sentiment = px.pie(
+                values=sentiment_counts.values,
+                names=sentiment_counts.index,
+                title="Distribución de Sentimientos"
+            )
+            st.plotly_chart(fig_sentiment, use_container_width=True)
+        
+        with col2:
+            rating_counts = df_filtered['star_rating'].value_counts().sort_index()
+            fig_ratings = px.bar(
+                x=rating_counts.index,
+                y=rating_counts.values,
+                title="Distribución de Ratings",
+                labels={'x': 'Rating', 'y': 'Cantidad'}
+            )
+            st.plotly_chart(fig_ratings, use_container_width=True)
+        
+        col1, col2, col3 = st.columns(3)
+        col1.metric("Total de Reseñas", f"{len(df_filtered):,}")
+        col2.metric("Rating Promedio", f"{df_filtered['star_rating'].mean():.2f}⭐")
+        col3.metric("% Positivas", f"{(df_filtered['sentiment'] == 'positive').mean():.1%}")
+        
+        if selected_category == 'Todas':
+            st.header("📊 Análisis por Categoría")
+            category_stats = df.groupby('product_category').agg({
+                'star_rating': 'mean',
+                'sentiment': lambda x: (x == 'positive').mean()
+            }).round(3)
+            category_stats.columns = ['Rating Promedio', '% Positivas']
+            st.dataframe(category_stats)
+
 if __name__ == "__main__":
     try:
         main()