new update

app.py

@@ -0,0 +1,96 @@
+import pandas as pd
+import gradio as gr
+import joblib
+import numpy as np
+import plotly.express as px
+from sklearn.preprocessing import StandardScaler
+from sklearn.decomposition import PCA
+from sklearn.cluster import KMeans
+
+# Charger les modèles
+try:
+    model = joblib.load("C:\\Users\\karballah\\Documents\\APP_Class_Clustering_ML_L3\\lg.joblib")
+    model_cluster = joblib.load("C:\\Users\\karballah\\Documents\\APP_Class_Clustering_ML_L3\\kmeans_model.joblib")
+    print("Modèles chargés avec succès.")
+except FileNotFoundError:
+    print("Erreur: Le fichier n'a pas été trouvé.")
+    exit(1)
+
+# Fonction de prédiction du diabète
+def predict_diabetes(pregnancies, glucose, blood_pressure, skin_thickness, insulin, bmi, dpf, age):
+    input_data = np.array([[pregnancies, glucose, blood_pressure, skin_thickness, insulin, bmi, dpf, age]])
+    prediction = model.predict(input_data)[0]
+    return "Diabétique" if prediction == 1 else "Non diabétique"
+
+# Fonction de visualisation des clusters
+def plot_clusters(selected_cluster):
+    np.random.seed(42)
+    pca_features = np.random.randn(100, 2)
+    clusters = np.random.randint(0, 5, size=100)
+
+    pca_df = pd.DataFrame(pca_features, columns=['PC1', 'PC2'])
+    pca_df['Cluster'] = clusters
+
+    if selected_cluster == "Tous":
+        selected_data = pca_df
+    else:
+        selected_data = pca_df[pca_df['Cluster'] == int(selected_cluster)]
+    
+    if selected_data.empty:
+        return px.scatter(title="Aucun point à afficher")
+
+    fig = px.scatter(selected_data, x='PC1', y='PC2', color=selected_data['Cluster'].astype(str),
+                     title=f"Visualisation du Cluster {selected_cluster}", labels={'color': 'Cluster'})
+    
+    return fig
+
+# Fonction pour télécharger les clusters en CSV
+def download_clusters():
+    cluster_data = {
+        'PC1': np.random.randn(100),
+        'PC2': np.random.randn(100),
+        'Cluster': np.random.randint(0, 5, 100)
+    }
+    df_clusters = pd.DataFrame(cluster_data)
+    return df_clusters.to_csv(index=False), "clusters.csv"
+
+# Interface utilisateur avec Gradio
+with gr.Blocks() as app:
+    gr.Markdown("## Application Machine Learning : Classification et Clustering")
+    
+    # Section Classification
+    gr.Markdown("### Prédiction du Diabète")
+    with gr.Row():
+        pregnancies = gr.Number(label="Grossesses")
+        glucose = gr.Number(label="Glucose")
+        blood_pressure = gr.Number(label="Pression artérielle")
+    with gr.Row():
+        skin_thickness = gr.Number(label="Épaisseur de peau")
+        insulin = gr.Number(label="Insuline")
+        bmi = gr.Number(label="IMC")
+    with gr.Row():
+        dpf = gr.Number(label="DPF")
+        age = gr.Number(label="Âge")
+    
+    predict_button = gr.Button("Prédire")
+    output_label = gr.Textbox(label="Résultat")
+    
+    predict_button.click(fn=predict_diabetes, 
+                         inputs=[pregnancies, glucose, blood_pressure, skin_thickness, insulin, bmi, dpf, age], 
+                         outputs=output_label)
+    
+    # Section Clustering
+    gr.Markdown("### Visualisation des Clusters des Réactions en Ligne")
+    cluster_selector = gr.Dropdown(["Tous"] + [str(i) for i in range(5)], label="Sélectionner un cluster")
+    cluster_plot = gr.Plot()
+
+    def update_plot(selected_cluster):
+        return plot_clusters(selected_cluster)
+
+    cluster_selector.change(fn=update_plot, inputs=[cluster_selector], outputs=[cluster_plot])
+
+    # Téléchargement des clusters
+    download_button = gr.Button("Télécharger les clusters")
+    download_button.click(fn=download_clusters, outputs=gr.File())
+
+app.launch()

kmeans_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98fc30ca548f15395c506815965c7efe98d09c95306d7ce8d6abde4229584721
+size 29791

lg.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3044d65ebb0fcff67f20e7610636909c9a5a73f6b6a2e95504f48a47b0eccc6c
+size 927

requirements.txt

@@ -0,0 +1,26 @@
+gradio==5.10.0
+Flask==3.1.0
+Flask-SQLAlchemy==3.1.1
+Flask-Bootstrap==3.3.7.1
+Flask-WTF==1.2.1
+joblib==1.4.2
+scikit-learn==1.5.1
+numpy==2.2.2
+pandas==2.2.3
+matplotlib==3.8.4
+seaborn==0.13.2
+scipy==1.13.0
+statsmodels==0.14.4
+streamlit==1.41.1
+google-api-core==2.24.0
+google-auth==2.37.0
+google-auth-httplib2==0.2.0
+huggingface-hub==0.27.1
+gunicorn==22.0.0
+uvicorn==0.34.0
+Werkzeug==3.1.3
+requests==2.32.3
+beautifulsoup4==4.12.3
+pytest==7.2.2
+pytest-flask==1.2.0
+pytest-gradio==0.0.1