Update app.py

app.py

@@ -4,48 +4,49 @@ import gradio as gr
 import seaborn as sns
 import matplotlib.pyplot as plt
 from fuzzywuzzy import fuzz
- 
-# تحميل البيانات
+
+# Load the restaurant reviews dataset
 reviews_df = pd.read_csv('Restaurant_reviews.csv')
- 
-# تحميل نموذج التصنيف العاطفي
+
+# Load the Hugging Face sentiment analysis model
 sentiment_model = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
- 
-# وظيفة لتصنيف المراجعة
+
+# Function to classify a user's review based on dataset matching and sentiment analysis
 def classify_review(user_review):
     try:
         if not user_review.strip():
             return "Please enter a valid review."
- 
+
         best_match = None
         best_score = 0
- 
+
         for _, row in reviews_df.iterrows():
             if pd.isna(row['Review']):
                 continue
- 
+
+            # Use fuzzy matching to find the most similar review in the dataset
             score = fuzz.token_sort_ratio(user_review.lower(), str(row['Review']).lower())
             if score > best_score:
                 best_score = score
                 best_match = row
- 
-        if best_score > 80:
+
+        if best_score > 80:  # If the fuzzy match score is greater than 80
             rating = best_match['Rating']
             rating_based_classification = f"Positive review based on rating: {rating}" if int(rating) >= 4 else f"Negative review based on rating: {rating}"
- 
+
             sentiment_result = sentiment_model(user_review)[0]
             sentiment = sentiment_result['label']
             confidence = sentiment_result['score']
             sentiment_based_classification = f"Model prediction: {sentiment} with confidence: {confidence:.2f}"
- 
+
             return f"{rating_based_classification}\n{sentiment_based_classification}\nMatching Score: {best_score}%"
         else:
             return "Review not found in the dataset."
- 
+
     except Exception as e:
         return f"An error occurred: {str(e)}"
- 
-# وظيفة لرسم توزيع التقييمات
+
+# Function to plot the distribution of ratings from the dataset
 def plot_rating_distribution():
     plt.figure(figsize=(8, 6))
     sns.countplot(x='Rating', data=reviews_df, order=[1, 2, 3, 4, 5])
@@ -54,8 +55,16 @@ def plot_rating_distribution():
     plt.ylabel('Count')
     plt.tight_layout()
     return plt.gcf()
- 
-# إنشاء واجهات Gradio
+
+# Function to allow users to preview the dataset (first 10 rows)
+def preview_dataset():
+    return reviews_df.head(10)  # Return the first 10 rows of the dataset
+
+# Function to download the dataset
+def download_dataset():
+    return 'Restaurant_reviews.csv'  # Provide the path to the dataset for download
+
+# Create the Gradio interface for classifying reviews
 review_interface = gr.Interface(
     fn=classify_review,
     inputs=gr.Textbox(lines=2, placeholder="Enter your review here", label="Reviews"),
@@ -63,7 +72,8 @@ review_interface = gr.Interface(
     title="Review Classifier Based on Rating and Hugging Face Model",
     description="Enter a restaurant review. The system will classify it based on the dataset rating and use a sentiment analysis model."
 )
- 
+
+# Create the Gradio interface for plotting the rating distribution
 plot_interface = gr.Interface(
     fn=plot_rating_distribution,
     inputs=[],
@@ -71,9 +81,30 @@ plot_interface = gr.Interface(
     title="Rating Distribution",
     description="Shows the distribution of ratings in the dataset."
 )
- 
-# دمج الواجهتين باستخدام تبويبات
-tabbed_interface = gr.TabbedInterface([review_interface, plot_interface], ["Review Classifier", "Rating Distribution"])
- 
-# إطلاق الواجهات
-tabbed_interface.launch()
+
+# Create the Gradio interface for previewing the dataset
+preview_interface = gr.Interface(
+    fn=preview_dataset,
+    inputs=[],
+    outputs="dataframe",
+    title="Preview Restaurant Reviews Dataset",
+    description="Displays the first 10 rows of the dataset for preview."
+)
+
+# Create the Gradio interface for downloading the dataset
+download_interface = gr.Interface(
+    fn=download_dataset,
+    inputs=[],
+    outputs=gr.File(),
+    title="Download Restaurant Reviews Dataset",
+    description="Download the full restaurant reviews dataset in CSV format."
+)
+
+# Combine all interfaces (Review Classifier, Rating Distribution, Dataset Preview, Dataset Download) into tabs
+tabbed_interface = gr.TabbedInterface(
+    [review_interface, plot_interface, preview_interface, download_interface],
+    ["Review Classifier", "Rating Distribution", "Dataset Preview", "Download Dataset"]
+)
+
+# Launch the Gradio interface
+tabbed_interface.launch()