Upload 2 files

app.py

@@ -0,0 +1,123 @@
+import streamlit as st
+from sklearn.metrics.pairwise import cosine_similarity
+from sklearn.preprocessing import normalize
+from sklearn.decomposition import TruncatedSVD
+from sklearn.feature_extraction.text import TfidfVectorizer
+import pandas as pd
+
+# Load the dataset
+dataset = pd.read_csv('avito_cars.csv')
+
+# Combine relevant columns into 'content'
+dataset['content'] = (
+    dataset['Marque'] + " " +
+    dataset['Modèle'] + " " +
+    dataset['Type de carburant'] + " " +
+    dataset['Boite de vitesses']
+)
+dataset = dataset.drop_duplicates(subset=['content'])  # Remove duplicates
+
+# Preprocess and build TF-IDF and LSI
+vectorizer = TfidfVectorizer(stop_words=None)
+tfidf_matrix = vectorizer.fit_transform(dataset['content'])
+
+n_components = 50  # Number of LSI dimensions
+svd = TruncatedSVD(n_components=n_components)
+lsi_matrix = svd.fit_transform(tfidf_matrix)
+lsi_matrix = normalize(lsi_matrix)
+
+# Search function
+def search(query, top_n=100):
+    query_tfidf = vectorizer.transform([query])
+    query_lsi = svd.transform(query_tfidf)
+    query_lsi = normalize(query_lsi)
+    similarities = cosine_similarity(query_lsi, lsi_matrix).flatten()
+    top_indices = similarities.argsort()[-top_n:][::-1]
+    results = dataset.iloc[top_indices]
+    return results, similarities[top_indices]
+
+# Streamlit Interface
+st.title("Moteur de recherche de voitures basé sur le LSI (Latent Semantic Indexing)")
+st.write("Recherchez des voitures en utilisant des mots-clés (par ex. : 'Peugeot Diesel Manuelle').")
+
+# User input
+query = st.text_input("Entrez votre requête de recherche :")
+top_n = st.slider("Nombre de résultats à afficher par page :", min_value=3, max_value=12, step=3, value=6)
+
+# Pagination logic
+if "page" not in st.session_state:
+    st.session_state.page = 1
+
+#if st.button("Previous Page"):
+#    st.session_state.page = max(1, st.session_state.page - 1)
+
+#if st.button("Next Page"):
+#    st.session_state.page += 1
+
+# Search and display
+if st.button("Search") or query.strip():
+    results, similarities = search(query)
+    total_results = len(results)
+    results_per_page = top_n
+    total_pages = (total_results // results_per_page) + (1 if total_results % results_per_page != 0 else 0)
+
+    # Paginate results
+    start_idx = (st.session_state.page - 1) * results_per_page
+    end_idx = start_idx + results_per_page
+    paginated_results = results.iloc[start_idx:end_idx]
+    st.write(f"Showing results {start_idx + 1}-{min(end_idx, total_results)} of {total_results} (Page {st.session_state.page}/{total_pages}):")
+
+    # Start the grid layout
+   # Display cards in rows using Streamlit's `st.columns()`
+    for i, (index, row) in enumerate(paginated_results.iterrows()):
+        if i % 3 == 0:  # Create a new row every 3 cards
+            cols = st.columns(3)  # 3 cards per row
+        
+        # Use the appropriate column in the row
+        with cols[i % 3]:
+            link = row['Lien']
+            st.markdown(
+                f"""
+                <div style="
+                    border: 1px solid green;
+                    border-radius: 10px;
+                    padding: 10px;
+                    background-color: #f9f9f9;
+                    text-align: left;
+                    height: auto;
+                    margin-bottom: 20px;
+                ">
+                    <h5>{row['content']}</h5>
+                    <p><strong>Année-Modèle:</strong> {row['Année-Modèle']}</p>
+                    <p><strong>Price:</strong> {row['Prix']} MAD</p>
+                    <p><strong>City:</strong> {row['Ville']}</p>
+                    <p><strong>Kilométrage:</strong> {row['Kilométrage']} km</p>
+                    <a href="{link}" target="_blank" style="
+                        display: block;
+                        margin: 10px auto 0 auto; 
+                        background-color: #4CAF50; 
+                        color: white; 
+                        padding: 5px 10px; 
+                        text-align: center; 
+                        text-decoration: none; 
+                        border-radius: 5px;">
+                        View Details
+                    </a>
+                </div>
+                """,
+                unsafe_allow_html=True,
+            )
+
+        
+
+    
+    
+    # Pagination controls
+    st.write("Navigation:")
+    col1, col2, col3 = st.columns(3)
+    with col1:
+        if st.button("Previous"):
+            st.session_state.page = max(1, st.session_state.page - 1)
+    with col3:
+        if st.button("Next"):
+            st.session_state.page += 1