Create app.py

app.py

@@ -0,0 +1,102 @@
+import pandas as pd
+import numpy as np
+import streamlit as st
+import faiss
+from sentence_transformers import SentenceTransformer
+from symspellpy import SymSpell, Verbosity
+
+# ----------------------
+# Data Preparation
+# ----------------------
+def preprocess_data(file_path):
+    # Load dataset
+    df = pd.read_csv(file_path)
+    
+    # Combine multi-value columns
+    def combine_columns(row, prefix):
+        values = [str(row[col]) for col in df.columns if col.startswith(prefix) and pd.notna(row[col])]
+        return ', '.join(values)
+    
+    df['uses'] = df.apply(lambda x: combine_columns(x, 'use'), axis=1)
+    df['substitutes'] = df.apply(lambda x: combine_columns(x, 'substitute'), axis=1)
+    df['side_effects'] = df.apply(lambda x: combine_columns(x, 'sideEffect'), axis=1)
+    
+    # Clean text
+    text_columns = ['name', 'uses', 'Chemical Class', 'Therapeutic Class']
+    for col in text_columns:
+        df[col] = df[col].str.lower().str.replace('[^\w\s]', '', regex=True)
+    
+    return df[['id', 'name', 'uses', 'substitutes', 'side_effects',
+               'Habit Forming', 'Therapeutic Class', 'Action Class']]
+
+# ----------------------
+# Embedding & FAISS Setup
+# ----------------------
+def setup_faiss(df):
+    model = SentenceTransformer('all-MiniLM-L6-v2')
+    embeddings = model.encode(df['uses'].tolist(), show_progress_bar=True)
+    
+    # Create FAISS index
+    dimension = embeddings.shape[1]
+    index = faiss.IndexFlatL2(dimension)
+    index.add(embeddings)
+    return model, index
+
+# ----------------------
+# Spelling Correction
+# ----------------------
+def setup_spell_checker():
+    sym_spell = SymSpell(max_dictionary_edit_distance=2, prefix_length=7)
+    sym_spell.load_dictionary('frequency_dictionary_en_82_765.txt', 
+                             term_index=0, count_index=1)
+    return sym_spell
+
+# ----------------------
+# Streamlit App
+# ----------------------
+def main():
+    st.title("🧬 MedSearch NLP: Medicine Recommender System")
+    
+    # Load data and models
+    df = preprocess_data('medicine_dataset.csv')
+    model, faiss_index = setup_faiss(df)
+    sym_spell = setup_spell_checker()
+    
+    # User input
+    query = st.text_input("Describe your symptoms or medical need:")
+    therapeutic_class = st.selectbox(
+        "Filter by Therapeutic Class (optional):",
+        ['All'] + sorted(df['Therapeutic Class'].dropna().unique().tolist())
+    )
+    
+    if query:
+        # Spelling correction
+        suggestions = sym_spell.lookup(query, Verbosity.CLOSEST, max_edit_distance=2)
+        if suggestions:
+            query = suggestions[0].term
+            st.info(f"Did you mean: '{query}'?")
+        
+        # Semantic search
+        query_embedding = model.encode([query])
+        D, I = faiss_index.search(query_embedding, k=5)
+        
+        # Filter results
+        results = df.iloc[I[0]].copy()
+        if therapeutic_class != 'All':
+            results = results[results['Therapeutic Class'] == therapeutic_class]
+        
+        # Display results
+        st.subheader("Recommended Medicines")
+        for _, row in results.iterrows():
+            with st.expander(f"💊 {row['name']}"):
+                cols = st.columns(3)
+                cols[0].write(f"**Uses:** {row['uses']}")
+                cols[1].write(f"**Substitutes:** {row['substitutes']}")
+                cols[2].write(f"**Side Effects:** {row['side_effects']}")
+                
+                cols2 = st.columns(2)
+                cols2[0].write(f"Therapeutic Class: {row['Therapeutic Class']}")
+                cols2[1].write(f"Habit Forming: {row['Habit Forming']}")
+
+if __name__ == "__main__":
+    main()