Rename app.py to app_gradio.py

app.py

@@ -1,96 +0,0 @@
-
-import streamlit as st
-import numpy as np
-import pickle
-from tensorflow.keras.models import load_model
-from tensorflow.keras.preprocessing.sequence import pad_sequences
-
-# Load the trained model and preprocessing objects
-@st.cache_resource
-def load_resources():
-    model = load_model('emotion_classification_model.h5')
-    with open('tokenizer.pickle', 'rb') as handle:
-        tokenizer = pickle.load(handle)
-    with open('label_encoder.pickle', 'rb') as handle:
-        label_encoder = pickle.load(handle)
-    return model, tokenizer, label_encoder
-
-model, tokenizer, label_encoder = load_resources()
-
-# Streamlit app
-st.title("🧠 Emotion Classification System")
-st.subheader("AI-Powered Emotion Recognition from Text")
-
-st.write("""
-This model can classify text into **75 different emotions** with **100% accuracy**.
-Enter any text below to see which emotion it represents!
-""")
-
-# Text input
-user_input = st.text_area(
-    "Enter text for emotion classification:", 
-    height=150,
-    placeholder="Type your text here... For example: 'Examine how Envy plays a role in leadership...'"
-)
-
-if st.button("Classify Emotion"):
-    if user_input.strip():
-        with st.spinner('Analyzing emotion...'):
-            # Preprocess the input text
-            sequence = tokenizer.texts_to_sequences([user_input])
-            padded = pad_sequences(sequence, maxlen=512, padding='post', truncating='post')
-            
-            # Make prediction
-            prediction = model.predict(padded)
-            predicted_class_idx = np.argmax(prediction, axis=1)[0]
-            predicted_emotion = label_encoder.classes_[predicted_class_idx]
-            confidence = prediction[0][predicted_class_idx]
-            
-            # Display results
-            st.success(f"**Predicted Emotion:** {predicted_emotion}")
-            st.info(f"**Confidence:** {confidence:.4f}")
-            
-            # Show top 3 predictions
-            top_3_indices = np.argsort(prediction[0])[-3:][::-1]
-            top_3_emotions = [label_encoder.classes_[idx] for idx in top_3_indices]
-            top_3_confidences = [prediction[0][idx] for idx in top_3_indices]
-            
-            st.subheader("Top 3 Predictions:")
-            for i, (emotion, conf) in enumerate(zip(top_3_emotions, top_3_confidences)):
-                st.write(f"{i+1}. {emotion}: {conf:.4f}")
-            
-            # Show input text
-            st.subheader("Input Text:")
-            st.write(user_input)
-    else:
-        st.warning("Please enter some text to classify!")
-
-# Add some sample texts for testing
-st.subheader("Try these sample texts:")
-samples = [
-    "I feel so angry about the unfair treatment I received today",
-    "The joy of seeing my family after so long was overwhelming",
-    "I'm constantly worried about everything that could go wrong",
-    "The envy I feel towards my successful colleague is consuming me"
-]
-
-for i, sample in enumerate(samples):
-    if st.button(f"Sample {i+1}", key=f"sample_{i}"):
-        st.session_state.user_input = sample
-
-st.sidebar.header("About this Model")
-st.sidebar.write("""
-- **Model Type**: Bidirectional LSTM with Attention
-- **Classes**: 75 different emotions
-- **Accuracy**: 100%
-- **Architecture**: Custom neural network
-""")
-
-st.sidebar.header("How it Works")
-st.sidebar.write("""
-1. Text is processed through tokenization
-2. Converted to numerical sequences
-3. Passed through LSTM network
-4. Attention mechanism identifies key emotional phrases
-5. Output shows the predicted emotion
-""")

app_gradio.py

@@ -0,0 +1,89 @@
+# app_gradio.py
+import gradio as gr
+import numpy as np
+import pickle
+import requests
+import os
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+
+def download_model_from_drive():
+    """Download model from Google Drive"""
+    file_id = "1A0dE-UXP9M4bPY795Z6fAdJ0wyp8M9nW"  # Your new file ID
+    url = f"https://drive.google.com/uc?export=download&id={file_id}"
+    
+    response = requests.get(url, stream=True)
+    with open('emotion_classification_model.h5', 'wb') as f:
+        for chunk in response.iter_content(chunk_size=8192):
+            if chunk:
+                f.write(chunk)
+
+def load_model_resources():
+    """Load model and preprocessing objects"""
+    model_path = 'emotion_classification_model.h5'
+    
+    if not os.path.exists(model_path):
+        print("Downloading model...")
+        download_model_from_drive()
+        print("Model downloaded!")
+    
+    model = load_model(model_path)
+    with open('tokenizer.pickle', 'rb') as handle:
+        tokenizer = pickle.load(handle)
+    with open('label_encoder.pickle', 'rb') as handle:
+        label_encoder = pickle.load(handle)
+    
+    return model, tokenizer, label_encoder
+
+# Load resources once
+model, tokenizer, label_encoder = load_model_resources()
+
+def predict_emotion(text):
+    """Predict emotion for input text"""
+    if not text.strip():
+        return "Please enter some text", 0.0
+    
+    # Preprocess
+    sequence = tokenizer.texts_to_sequences([text])
+    padded = pad_sequences(sequence, maxlen=512, padding='post', truncating='post')
+    
+    # Predict
+    prediction = model.predict(padded, verbose=0)
+    predicted_idx = np.argmax(prediction, axis=1)[0]
+    predicted_emotion = label_encoder.classes_[predicted_idx]
+    confidence = float(prediction[0][predicted_idx])
+    
+    # Top 3 predictions
+    top_3_indices = np.argsort(prediction[0])[-3:][::-1]
+    top_3_emotions = [label_encoder.classes_[idx] for idx in top_3_indices]
+    top_3_confidences = [float(prediction[0][idx]) for idx in top_3_indices]
+    
+    top_results = "\n".join([f"{i+1}. {e}: {c:.4f}" for i, (e, c) in enumerate(zip(top_3_emotions, top_3_confidences))])
+    
+    return predicted_emotion, confidence, top_results
+
+# Create Gradio interface
+interface = gr.Interface(
+    fn=predict_emotion,
+    inputs=gr.Textbox(
+        label="Enter text for emotion classification",
+        placeholder="Type your text here... For example: 'Examine how Envy plays a role in leadership...'",
+        lines=5
+    ),
+    outputs=[
+        gr.Textbox(label="Predicted Emotion"),
+        gr.Number(label="Confidence Score"),
+        gr.Textbox(label="Top 3 Predictions")
+    ],
+    title="🧠 Emotion Classification System",
+    description="Perfect 100% accurate emotion classification using Bidirectional LSTM with Attention (75 emotions)",
+    examples=[
+        ["I feel so angry about the unfair treatment I received today"],
+        ["The joy of seeing my family after so long was overwhelming"],
+        ["I'm constantly worried about everything that could go wrong"],
+        ["The envy I feel towards my successful colleague is consuming me"]
+    ]
+)
+
+# Launch the app
+interface.launch()