Update SentimentAnalyzerUsingDistilbert.py

SentimentAnalyzerUsingDistilbert.py

@@ -1,99 +1,99 @@
-import torch
-import gradio as gr
-import pandas as pd
-import matplotlib.pyplot as plt
-from transformers import pipeline
-from docx import Document
-from PyPDF2 import PdfReader
-
-# Initialize the sentiment analysis pipeline
-analyzer = pipeline("text-classification", model="distilbert/distilbert-base-uncased-finetuned-sst-2-english")
-
-# Function to analyze sentiment for a single sentence
-def sentiment_analyzer(review):
-    sentiment = analyzer(review)
-    return sentiment[0]['label']
-
-# Create a pie chart visualization for the sentiment
-def sentiment_pie_chart(sentiment_labels):
-    sentiment_counts = pd.Series(sentiment_labels).value_counts()
-    
-    fig, ax = plt.subplots()
-    sentiment_counts.plot(kind='pie', autopct='%1.1f%%', colors=['green', 'red'], ax=ax)
-    ax.set_ylabel('')
-    ax.set_title('Sentiment Distribution')
-    
-    return fig
-
-# Function to analyze a single input sentence
-def analyze_single_sentence(sentence):
-    sentiment = sentiment_analyzer(sentence)
-    return f"The sentiment of the sentence is: {sentiment}"
-
-# Function to read and analyze reviews from Excel, PDF, or DOCX files
-def read_reviews_and_analyze_sentiment(file_object):
-    if file_object.name.endswith('.xlsx'):
-        # Load the Excel file into a DataFrame
-        df = pd.read_excel(file_object)
-        if 'Reviews' not in df.columns:
-            raise ValueError("Excel file must contain a 'Reviews' column.")
-        reviews = df['Reviews'].tolist()
-    
-    elif file_object.name.endswith('.docx'):
-        # Read the content of the DOCX file
-        doc = Document(file_object)
-        reviews = [para.text for para in doc.paragraphs if para.text.strip()]
-    
-    elif file_object.name.endswith('.pdf'):
-        # Read the content of the PDF file
-        reader = PdfReader(file_object)
-        text = ""
-        for page in reader.pages:
-            text += page.extract_text()
-        reviews = text.split('\n')  # Assuming reviews are newline-separated
-    
-    else:
-        raise ValueError("Unsupported file format. Please upload .xlsx, .pdf, or .docx files.")
-    
-    # Analyze the sentiment of each review
-    sentiments = [sentiment_analyzer(review) for review in reviews]
-    df = pd.DataFrame({'Reviews': reviews, 'Sentiment': sentiments})
-    
-    # Generate pie chart
-    chart_object = sentiment_pie_chart(sentiments)
-    
-    return df, chart_object
-
-# Gradio interface combining single sentence analysis and file-based review sentiment analysis
-def main_interface(input_option, sentence=None, file=None):
-    if input_option == "Single Sentence":
-        if sentence:
-            result = analyze_single_sentence(sentence)
-            return None, None, result  # Single sentence output
-        else:
-            return None, None, "Please enter a sentence."
-    elif input_option == "File Upload":
-        if file:
-            df, chart_object = read_reviews_and_analyze_sentiment(file)
-            return df, chart_object, None  # File output
-        else:
-            return None, None, "Please upload a file."
-
-# Gradio interface
-demo = gr.Interface(
-    fn=main_interface,
-    inputs=[
-        gr.Radio(label="Choose Input Type", choices=["Single Sentence", "File Upload"], value="Single Sentence"),
-        gr.Textbox(label="Enter a sentence for sentiment analysis (if selected)", placeholder="Type your sentence here..."),
-        gr.File(file_types=["xlsx", "pdf", "docx"], label="Upload your review comment file (if selected)")
-    ],
-    outputs=[
-        gr.Dataframe(label="Sentiment Analysis Results (For File Uploads)"),
-        gr.Plot(label="Sentiment Distribution Chart (For File Uploads)"),
-        gr.Textbox(label="Single Sentence Sentiment Result (For Single Sentence Input)")
-    ],
-    title="@GenAILearniverse Project 3: Sentiment Analyzer",
-    description="This application analyzes the sentiment of either a single sentence or reviews in uploaded files (Excel, PDF, DOCX)."
-)
-
-demo.launch()
+import torch
+import gradio as gr
+import pandas as pd
+import matplotlib.pyplot as plt
+from transformers import pipeline
+from docx import Document
+from PyPDF2 import PdfReader
+
+# Initialize the sentiment analysis pipeline
+analyzer = pipeline("text-classification", model="distilbert/distilbert-base-uncased-finetuned-sst-2-english")
+
+# Function to analyze sentiment for a single sentence
+def sentiment_analyzer(review):
+    sentiment = analyzer(review)
+    return sentiment[0]['label']
+
+# Create a pie chart visualization for the sentiment
+def sentiment_pie_chart(sentiment_labels):
+    sentiment_counts = pd.Series(sentiment_labels).value_counts()
+    
+    fig, ax = plt.subplots()
+    sentiment_counts.plot(kind='pie', autopct='%1.1f%%', colors=['green', 'red'], ax=ax)
+    ax.set_ylabel('')
+    ax.set_title('Sentiment Distribution')
+    
+    return fig
+
+# Function to analyze a single input sentence
+def analyze_single_sentence(sentence):
+    sentiment = sentiment_analyzer(sentence)
+    return f"The sentiment of the sentence is: {sentiment}"
+
+# Function to read and analyze reviews from Excel, PDF, or DOCX files
+def read_reviews_and_analyze_sentiment(file_object):
+    if file_object.name.endswith('.xlsx'):
+        # Load the Excel file into a DataFrame
+        df = pd.read_excel(file_object)
+        if 'Reviews' not in df.columns:
+            raise ValueError("Excel file must contain a 'Reviews' column.")
+        reviews = df['Reviews'].tolist()
+    
+    elif file_object.name.endswith('.docx'):
+        # Read the content of the DOCX file
+        doc = Document(file_object)
+        reviews = [para.text for para in doc.paragraphs if para.text.strip()]
+    
+    elif file_object.name.endswith('.pdf'):
+        # Read the content of the PDF file
+        reader = PdfReader(file_object)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text()
+        reviews = text.split('\n')  # Assuming reviews are newline-separated
+    
+    else:
+        raise ValueError("Unsupported file format. Please upload .xlsx, .pdf, or .docx files.")
+    
+    # Analyze the sentiment of each review
+    sentiments = [sentiment_analyzer(review) for review in reviews]
+    df = pd.DataFrame({'Reviews': reviews, 'Sentiment': sentiments})
+    
+    # Generate pie chart
+    chart_object = sentiment_pie_chart(sentiments)
+    
+    return df, chart_object
+
+# Gradio interface combining single sentence analysis and file-based review sentiment analysis
+def main_interface(input_option, sentence=None, file=None):
+    if input_option == "Single Sentence":
+        if sentence:
+            result = analyze_single_sentence(sentence)
+            return None, None, result  # Single sentence output
+        else:
+            return None, None, "Please enter a sentence."
+    elif input_option == "File Upload":
+        if file:
+            df, chart_object = read_reviews_and_analyze_sentiment(file)
+            return df, chart_object, None  # File output
+        else:
+            return None, None, "Please upload a file."
+
+# Gradio interface
+demo = gr.Interface(
+    fn=main_interface,
+    inputs=[
+        gr.Radio(label="Choose Input Type", choices=["Single Sentence", "File Upload"], value="Single Sentence"),
+        gr.Textbox(label="Enter a sentence for sentiment analysis (if selected)", placeholder="Type your sentence here..."),
+        gr.File(file_types=["xlsx", "pdf", "docx"], label="Upload your review comment file (if selected)")
+    ],
+    outputs=[
+        gr.Dataframe(label="Sentiment Analysis Results (For File Uploads)"),
+        gr.Plot(label="Sentiment Distribution Chart (For File Uploads)"),
+        gr.Textbox(label="Single Sentence Sentiment Result (For Single Sentence Input)")
+    ],
+    title="Sentiment Analyzer",
+    description="This application analyzes the sentiment of either a single sentence or reviews in uploaded files (Excel, PDF, DOCX)."
+)
+
+demo.launch()