Create app.py

app.py

@@ -0,0 +1,132 @@
+import streamlit as st
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+import numpy as np
+import pickle
+import re
+
+# Set page config
+st.set_page_config(
+    page_title="Next Word Predictor",
+    page_icon="🔮",
+    layout="centered"
+)
+
+# Custom CSS for styling
+st.markdown("""
+    <style>
+    .main {
+        background-color: #f5f5f5;
+    }
+    .stTextInput>div>div>input {
+        background-color: #ffffff;
+        color: #000000;
+    }
+    .prediction-box {
+        background-color: #e6f7ff;
+        padding: 15px;
+        border-radius: 10px;
+        border-left: 5px solid #1890ff;
+        margin-top: 20px;
+    }
+    </style>
+    """, unsafe_allow_html=True)
+
+@st.cache_resource
+def load_models():
+    """Load the model and tokenizer with caching"""
+    try:
+        model = load_model('nextword_lstm_model.h5')
+        with open('tokenizer.pkl', 'rb') as f:
+            tokenizer = pickle.load(f)
+        return model, tokenizer
+    except Exception as e:
+        st.error(f"Error loading model: {str(e)}")
+        return None, None
+
+def predict_next_word(model, tokenizer, seed_text, max_seq_len):
+    """Predict the next word given a seed text"""
+    try:
+        # Clean and preprocess the input text
+        seed_text = re.sub(r'[^\w\s]', '', seed_text.lower()).strip()
+        
+        # Convert text to sequence
+        token_list = tokenizer.texts_to_sequences([seed_text])
+        
+        if not token_list or not token_list[0]:
+            return "Please enter more meaningful text"
+            
+        token_list = token_list[0]
+        token_list = pad_sequences([token_list], maxlen=max_seq_len-1, padding='pre')
+        
+        # Make prediction
+        predicted = model.predict(token_list, verbose=0)
+        predicted_word_index = np.argmax(predicted, axis=-1)[0]
+        
+        # Find the word corresponding to the predicted index
+        for word, index in tokenizer.word_index.items():
+            if index == predicted_word_index:
+                return word.capitalize()
+                
+        return "No prediction available"
+    except Exception as e:
+        return f"Error in prediction: {str(e)}"
+
+def main():
+    st.title("🔮 Next Word Predictor")
+    st.markdown("Enter some text and I'll predict the next word using an LSTM model trained on a large corpus.")
+    
+    # Load model and tokenizer
+    model, tokenizer = load_models()
+    
+    if model is None or tokenizer is None:
+        st.error("Failed to load the model. Please check if model files are available.")
+        return
+    
+    # Calculate max sequence length (you might want to set this based on your training)
+    max_seq_len = 20  # Adjust based on your model's training parameters
+    
+    # Input section
+    st.subheader("Enter your text")
+    seed_text = st.text_input(
+        "Start typing...", 
+        placeholder="Type something like 'I am going to'",
+        key="text_input"
+    )
+    
+    # Prediction button
+    if st.button("Predict Next Word", type="primary"):
+        if seed_text.strip():
+            with st.spinner("Predicting..."):
+                next_word = predict_next_word(model, tokenizer, seed_text, max_seq_len)
+                
+                # Display result
+                st.markdown(f"""
+                <div class="prediction-box">
+                    <h3>Prediction</h3>
+                    <p style="font-size: 20px; margin-bottom: 0;"><strong>{seed_text} <span style="color: #1890ff;">{next_word}</span></strong></p>
+                </div>
+                """, unsafe_allow_html=True)
+        else:
+            st.warning("Please enter some text first!")
+
+    # Information section
+    st.markdown("---")
+    st.subheader("About")
+    st.markdown("""
+    This app uses an LSTM neural network trained on a large text corpus to predict the next word in a sequence.
+    
+    **How it works:**
+    - The model was trained on 20,000 text samples
+    - Uses word embeddings and LSTM layers
+    - Predicts the most likely next word based on context
+    
+    **Try phrases like:**
+    - "I am going to"
+    - "The weather is"
+    - "Machine learning is"
+    """)
+
+if __name__ == "__main__":
+    main()