Update app.py

app.py

@@ -1,61 +1,134 @@
 import streamlit as st
-import joblib
+import pickle
 import nltk
 from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize
 
-# Ensure NLTK resources are downloaded
-nltk.download('punkt')
-nltk.download('stopwords')
+# Download NLTK resources
+nltk.download('punkt', quiet=True)
+nltk.download('stopwords', quiet=True)
 
-# Load the trained KNN model
-knn_classifier = joblib.load('knn_model.pkl')
-
-# Load the TF-IDF vectorizer
-tfidf_vectorizer = joblib.load('tfidf_vectorizer.pkl')
-
-# Text Preprocessing Function
-stop_words = set(stopwords.words('english'))
+# Load the pre-trained model and vectorizer
+@st.cache_resource
+def load_model():
+    try:
+        # Load TF-IDF Vectorizer
+        with open('tfidf_vectorizer.pkl', 'rb') as vectorizer_file:
+            tfidf_vectorizer = pickle.load(vectorizer_file)
+        
+        # Load KNN Classifier
+        with open('knn_model.pkl', 'rb') as model_file:
+            knn_classifier = pickle.load(model_file)
+        
+        return tfidf_vectorizer, knn_classifier
+    except Exception as e:
+        st.error(f"Error loading model: {e}")
+        return None, None
 
+# Preprocess text function
 def preprocess_text(text):
+    # Tokenization and preprocessing
+    stop_words = set(stopwords.words('english'))
     words = word_tokenize(text.lower())
     words = [word for word in words if word.isalpha() and word not in stop_words]
     return ' '.join(words)
 
-# Inference function
-def predict_disease(symptom):
-    preprocessed_symptom = preprocess_text(symptom)
-    symptom_tfidf = tfidf_vectorizer.transform([preprocessed_symptom])
-    predicted_disease = knn_classifier.predict(symptom_tfidf)
-    return predicted_disease[0]
-
-# Streamlit UI
-st.title("Disease Classification using Symptoms")
-st.markdown("Enter your symptoms to predict the disease.")
-
-# Input box for symptoms
-symptom = st.text_input("Enter symptoms:", "")
-
-# Predict button
-if st.button("Predict Disease"):
-    if symptom:
-        predicted_disease = predict_disease(symptom)
-        st.success(f"Predicted Disease: {predicted_disease}")
-    else:
-        st.warning("Please enter symptoms.")
-
-# Add some styling
-st.markdown(
-    """
-    <style>
-    .main .block-container {
-        max-width: 600px;
-        padding-top: 2rem;
-        padding-right: 2rem;
-        padding-left: 2rem;
-        padding-bottom: 2rem;
-    }
-    </style>
-    """,
-    unsafe_allow_html=True
-)
+# Main Streamlit App
+def main():
+    # Set page title and favicon
+    st.set_page_config(
+        page_title="Disease Classification by Symptoms", 
+        page_icon=":medical_symbol:",
+        layout="centered"
+    )
+
+    # Title and description
+    st.title("🩺 Disease Classification Predictor")
+    st.markdown("""
+    ### Predict Potential Diseases Based on Symptoms
+    
+    Enter your symptoms below, and our AI model will help predict possible diseases.
+    """)
+
+    # Load model and vectorizer
+    tfidf_vectorizer, knn_classifier = load_model()
+
+    # Input form for symptoms
+    with st.form(key='symptom_form'):
+        symptoms = st.text_area(
+            "Enter your symptoms:", 
+            placeholder="Example: low appetite, fever, headache",
+            help="Provide a detailed description of your symptoms"
+        )
+        
+        submit_button = st.form_submit_button(label="Predict Disease")
+
+    # Prediction logic
+    if submit_button:
+        if not symptoms:
+            st.warning("Please enter some symptoms.")
+            return
+
+        try:
+            # Preprocess input symptoms
+            preprocessed_symptoms = preprocess_text(symptoms)
+
+            # Transform symptoms using TF-IDF vectorizer
+            symptoms_tfidf = tfidf_vectorizer.transform([preprocessed_symptoms])
+
+            # Predict disease
+            predicted_disease = knn_classifier.predict(symptoms_tfidf)
+
+            # Display prediction
+            st.success(f"Predicted Disease: {predicted_disease[0]}")
+
+            # Additional information (optional)
+            st.info("""
+            ### Disclaimer
+            - This is an AI-based prediction and should not replace professional medical advice
+            - Always consult with a healthcare professional for accurate diagnosis
+            - The prediction is based on machine learning analysis of symptom patterns
+            """)
+
+        except Exception as e:
+            st.error(f"An error occurred during prediction: {e}")
+
+    # Sidebar with additional information
+    st.sidebar.title("About the Model")
+    st.sidebar.markdown("""
+    ### Disease Classification Model
+    - **Algorithm**: K-Nearest Neighbors (KNN)
+    - **Features**: TF-IDF Vectorization
+    - **Trained on**: Symptom to Disease Dataset
+    
+    #### How it works:
+    1. Transform symptoms into numerical features
+    2. Compare with known disease patterns
+    3. Predict most likely disease
+    """)
+
+# Run the app
+if __name__ == "__main__":
+    main()
+
+# Additional requirements.txt content
+"""
+streamlit
+scikit-learn
+nltk
+pickle5
+"""
+
+# Deployment Notes
+"""
+Deployment Steps:
+1. Install requirements:
+   pip install -r requirements.txt
+   
+2. Download NLTK resources:
+   python -m nltk.downloader punkt
+   python -m nltk.downloader stopwords
+
+3. Run the Streamlit app:
+   streamlit run app.py
+"""