Update app.py

app.py

@@ -1,65 +1,75 @@
-import gradio as gr
 import torch
+import gradio as gr
 import pandas as pd
+import matplotlib.pyplot as plt
 
 # Use a pipeline as a high-level helper
 from transformers import pipeline
-analyzer = pipeline("text-classification", model="distilbert/distilbert-base-uncased-finetuned-sst-2-english")
+# model_path = ("../Models/models--distilbert--distilbert-base-uncased-finetuned-sst-2-english"
+#               "/snapshots/714eb0fa89d2f80546fda750413ed43d93601a13")
+
+analyzer = pipeline("text-classification",
+                model="distilbert/distilbert-base-uncased-finetuned-sst-2-english")
+
+# analyzer = pipeline("text-classification",
+#                 model=model_path)
+
+
+
+# print(analyzer(["This production is good", "This product was quite expensive"]))
+
+def sentiment_analyzer(review):
+    sentiment = analyzer(review)
+    return sentiment[0]['label']
+
+def sentiment_bar_chart(df):
+    sentiment_counts = df['Sentiment'].value_counts()
+
+    # Create a bar chart
+    fig, ax = plt.subplots()
+    sentiment_counts.plot(kind='pie', ax=ax, autopct='%1.1f%%', color=['green', 'red'])
+    ax.set_title('Review Sentiment Counts')
+    ax.set_xlabel('Sentiment')
+    ax.set_ylabel('Count')
+    # ax.set_xticklabels(['Positive', 'Negative'], rotation=0)
 
-# Load model directly
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+    # Return the figure object
+    return fig
 
-def sentiment_analyzer(reviews):
-    sentiment = analyzer(reviews)
-    return sentiment
 
-# Read Reviews & Analyzer Sentiments
 def read_reviews_and_analyze_sentiment(file_object):
-    """
-    Reads reviews from an Excel file, analyzes their sentiment, and returns a DataFrame
-    with the reviews, sentiment, and sentiment score.
-
-    Parameters:
-        input_excel (str): Path to the input Excel file.
-
-    Returns:
-        pd.DataFrame: DataFrame containing reviews, sentiment, and sentiment score.
-    """
-    # Read the Excel file
-    df = pd.read_xlsx(file_object)
-    
-
-    # Check if 'reviews' column exists
-    if 'review' not in df.columns:
-        raise ValueError("The input Excel file must contain a column named 'reviews'.")
-
-    # Analyze sentiment for each review
-    sentiments = []
-    scores = []
-    for review in df['review']:
-        obj = sentiment_analyzer(review[0])
-        sentiment = obj[0]['label']
-        score = obj[0]['score']
-        sentiments.append(sentiment)
-        scores.append(score)
-
-    # Add sentiment and score to the DataFrame
-    df['sentiment'] = sentiments
-    df['sentiment_score'] = scores
-
-    return df
-
-# file_path = '/content/sample_data/amazon customer reviews.csv'
-# result = read_reviews_and_analyze_sentiment(file_path)
-# print(result)
+    # Load the Excel file into a DataFrame
+    df = pd.read_excel(file_object)
+
+    # Check if 'Review' column is in the DataFrame
+    if 'Reviews' not in df.columns:
+        raise ValueError("Excel file must contain a 'Review' column.")
 
+    # Apply the get_sentiment function to each review in the DataFrame
+    df['Sentiment'] = df['Reviews'].apply(sentiment_analyzer)
+    chart_object = sentiment_bar_chart(df)
+    return df, chart_object
+
+# result = read_reviews_and_analyze_sentiment("../Files/Prod-review.xlsx")
+# print(result)
+# Example usage:
+# df = read_reviews_and_analyze_sentiment('path_to_your_excel_file.xlsx')
+# print(df)
 
-gr.close_all()
 
 demo = gr.Interface(fn=read_reviews_and_analyze_sentiment,
-                    inputs=[gr.File(file_types=['xlsx'], label="Upload review file")],
-                    outputs=[gr.Dataframe(label="Analyze the sentiment of the reviews")],
-                    title = "Gen AI Sentiment Analyzer",
-                    description= "Review is positive negative."
-                    )
-demo.launch(share=True)
+                    inputs=[gr.File(file_types=["xlsx"], label="Upload your review comment file")],
+                    outputs=[gr.Dataframe(label="Sentiments"), gr.Plot(label="Sentiment Analysis")],
+                    title="@GenAILearniverse Project 3: Sentiment Analyzer",
+                    description="THIS APPLICATION WILL BE USED TO ANALYZE THE SENTIMENT BASED ON FILE UPLAODED.")
+demo.launch()
+
+
+
+
+
+
+# Example usage:
+# Assuming you have a dataframe `df` with appropriate data
+# fig = sentiment_bar_chart(df)
+# fig.show()  # This line is just to visualize the plot in a local environment