Update app.py

app.py

@@ -1,87 +1,49 @@
-# import streamlit as st
-
-# from transformers import pipeline
-
-# model_name = "peace4ever/roberta-large-finetuned-mongolian_v4"
-# pipeline = pipeline(task="sentiment-analysis", model=model_name)  # Load pre-trained pipeline
-
-# st.title("Эерэг? Сөрөг эсвэл аль нь ч биш?")
-# text = st.text_area("Өгүүлбэр оруулна уу?")
-
-# if text is not None:
-#     predictions = pipeline(text)
-#     label = predictions[0]["label"]
-#     probability = predictions[0]["score"]
-#     col1, col2 = st.columns(2)
-#     col1.header("Sentiment")
-#     col2.header("Probability")
-
-#     if label == "entailment":
-#         sentiment = "Negative"
-#     elif label == "contradiction":
-#         sentiment = "Neutral"
-#     elif label == "neutral":
-#         sentiment = "Positive" 
-
-#     col1.write(sentiment)
-#     col2.write(f"{probability:.2f}") 
-    
+from flask import Flask, request, jsonify
 from transformers import pipeline
-from tkinter import *
+import os
+
+# Initialize Flask app
+app = Flask(__name__)
 
-# Load pre-trained sentiment analysis pipeline (replace with your actual model name)
+# Load pre-trained sentiment analysis pipeline
 model_name = "peace4ever/roberta-large-finetuned-mongolian_v4"
-pipeline = pipeline(task="sentiment-analysis", model=model_name)
+nlp_pipeline = pipeline(task="sentiment-analysis", model=model_name)
 
 def analyze_sentiment(text):
-  """
-  This function takes user input, performs sentiment analysis using your fine-tuned model,
-  maps the predicted labels to desired sentiment categories, and returns the sentiment.
-  """
-  predictions = pipeline(text)
-  label = predictions[0]["label"]
-  probability = predictions[0]["score"]
-
-  sentiment_map = {
-      "entailment": "Negative",  # Map based on your fine-tuned model's labels
-      "contradiction": "Neutral",
-      "neutral": "Positive",
-      # Add more mappings if needed
-  }
-
-  sentiment = sentiment_map.get(label.upper(), "Unknown")  
-  return sentiment
-
-def main():
-  """
-  This function creates the main window and handles user interaction.
-  """
-  window = Tk()
-  window.title("Эерэг? Сөрөг эсвэл аль нь ч биш?")
-
-  # Text box for user input
-  text_box = Text(window)
-  text_box.pack(padx=10, pady=10)
-
-  # Button to trigger sentiment analysis
-  analyze_button = Button(window, text="Анализ хийх", command=lambda: update_sentiment(text_box.get("1.0", END)))
-  analyze_button.pack(pady=10)
-
-  # Label to display sentiment result
-  sentiment_label = Label(window, text="")
-  sentiment_label.pack()
-
-  def update_sentiment(text):
     """
-    This function performs sentiment analysis and updates the sentiment label.
+    This function takes user input, performs sentiment analysis using your fine-tuned model,
+    maps the predicted labels to desired sentiment categories, and returns the sentiment.
+    """
+    predictions = nlp_pipeline(text)
+    label = predictions[0]["label"]
+    probability = predictions[0]["score"]
+
+    sentiment_map = {
+        "entailment": "Negative",  # Map based on your fine-tuned model's labels
+        "contradiction": "Neutral",
+        "neutral": "Positive",
+        # Add more mappings if needed
+    }
+
+    sentiment = sentiment_map.get(label.lower(), "Unknown")  
+    return {"sentiment": sentiment, "label": label, "probability": probability}
+
+@app.route('/analyze', methods=['POST'])
+def analyze():
     """
-    sentiment = analyze_sentiment(text)
-    sentiment_label.config(text=f"Sentiment: {sentiment}")
+    This endpoint receives text data and returns the sentiment analysis result.
+    """
+    data = request.json
+    if 'text' not in data:
+        return jsonify({"error": "No text provided"}), 400
+    text = data['text']
+    result = analyze_sentiment(text)
+    return jsonify(result)
 
-  window.mainloop()
+@app.route('/')
+def home():
+    return "Welcome to the Sentiment Analysis API!"
 
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=int(os.environ.get("PORT", 7860)))
-
-
-
+    port = int(os.environ.get("PORT", 7860))
+    app.run(host="0.0.0.0", port=port)