Create app.py

app.py

@@ -0,0 +1,90 @@
+import gradio as gr
+import pandas as pd
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# Load model and tokenizer globally for efficiency
+model_name = "tabularisai/multilingual-sentiment-analysis"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+
+def predict_sentiment(texts):
+    """
+    Predict sentiment for a list of texts
+    """
+    inputs = tokenizer(texts, return_tensors="pt", truncation=True, padding=True, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    sentiment_map = {
+        0: "Very Negative",
+        1: "Negative",
+        2: "Neutral",
+        3: "Positive",
+        4: "Very Positive"
+    }
+    return [sentiment_map[p] for p in torch.argmax(probabilities, dim=-1).tolist()]
+
+
+def process_file(file_obj):
+    """
+    Process the input file and add sentiment analysis results
+    """
+    try:
+        # Read the file based on its extension
+        file_path = file_obj.name
+        if file_path.endswith('.csv'):
+            df = pd.read_csv(file_path)
+        elif file_path.endswith(('.xlsx', '.xls')):
+            df = pd.read_excel(file_path)
+        else:
+            raise ValueError("Unsupported file format. Please upload a CSV or Excel file.")
+
+        # Verify that 'Reviews' column exists
+        if 'Reviews' not in df.columns:
+            raise ValueError("Input file must contain a 'Reviews' column.")
+
+        # Perform sentiment analysis
+        reviews = df['Reviews'].fillna("")  # Handle any missing values
+        sentiments = predict_sentiment(reviews.tolist())
+
+        # Add results to the dataframe
+        df['Sentiment'] = sentiments
+
+        # Save the results to a new Excel file
+        output_path = "output_with_sentiment.xlsx"
+        df.to_excel(output_path, index=False)
+
+        return df, output_path
+
+    except Exception as e:
+        raise gr.Error(str(e))
+
+
+# Create Gradio interface
+with gr.Blocks() as interface:
+    gr.Markdown("# Review Sentiment Analysis")
+    gr.Markdown("Upload an Excel or CSV file with a 'Reviews' column to analyze sentiment.")
+
+    with gr.Row():
+        file_input = gr.File(
+            label="Upload File (CSV or Excel)",
+            file_types=[".csv", ".xlsx", ".xls"]
+        )
+
+    with gr.Row():
+        analyze_btn = gr.Button("Analyze Sentiments")
+
+    with gr.Row():
+        output_df = gr.Dataframe(label="Results Preview")
+        output_file = gr.File(label="Download Results")
+
+    analyze_btn.click(
+        fn=process_file,
+        inputs=[file_input],
+        outputs=[output_df, output_file]
+    )
+
+# Launch the interface
+interface.launch()