app.py

import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import plot_tree, export_text
import seaborn as sns
from sklearn.preprocessing import LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score, roc_curve

data = pd.read_csv('exported_named_train_good.csv')
data_test = pd.read_csv('exported_named_test_good.csv')
X_train = data.drop("Target", axis=1).values
y_train = data['Target'].values

X_test = data_test.drop('Target', axis=1).values
y_test = data_test['Target'].values

models={
    "Logisitic Regression":LogisticRegression(),
    "Decision Tree":DecisionTreeClassifier(),
    "Random Forest":RandomForestClassifier(),
    "Gradient Boost":GradientBoostingClassifier()
}

for name, model in models.items():

    model.fit(X_train, y_train)

    # Make predictions
    y_train_pred = model.predict(X_train)
    y_test_pred = model.predict(X_test)

    # Training set performance
    model_train_accuracy = accuracy_score(y_train, y_train_pred) # Calculate Accuracy
    model_train_f1 = f1_score(y_train, y_train_pred, average='weighted') # Calculate F1-score
    model_train_precision = precision_score(y_train, y_train_pred) # Calculate Precision
    model_train_recall = recall_score(y_train, y_train_pred) # Calculate Recall
    model_train_rocauc_score = roc_auc_score(y_train, y_train_pred)

    # Test set performance
    model_test_accuracy = accuracy_score(y_test, y_test_pred) # Calculate Accuracy
    model_test_f1 = f1_score(y_test, y_test_pred, average='weighted') # Calculate F1-score
    model_test_precision = precision_score(y_test, y_test_pred) # Calculate Precision
    model_test_recall = recall_score(y_test, y_test_pred) # Calculate Recall
    model_test_rocauc_score = roc_auc_score(y_test, y_test_pred) #Calculate Roc

    print(name)

    print('Model performance for Training set')
    print("- Accuracy: {:.4f}".format(model_train_accuracy))
    print('- F1 score: {:.4f}'.format(model_train_f1))
    
    print('- Precision: {:.4f}'.format(model_train_precision))
    print('- Recall: {:.4f}'.format(model_train_recall))
    print('- Roc Auc Score: {:.4f}'.format(model_train_rocauc_score))

    
    
    print('----------------------------------')
    
    print('Model performance for Test set')
    print('- Accuracy: {:.4f}'.format(model_test_accuracy))
    print('- F1 score: {:.4f}'.format(model_test_f1))
    print('- Precision: {:.4f}'.format(model_test_precision))
    print('- Recall: {:.4f}'.format(model_test_recall))
    print('- Roc Auc Score: {:.4f}'.format(model_test_rocauc_score))

    
    print('='*35)
    print('\n')

def load_model_and_data():

    model = models['Decision Tree']
    data = pd.read_csv('exported_named_train_good.csv')
    X = data.drop("Target", axis=1)
    y = data['Target']

    return model, X, y, X.columns
    
import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import plot_tree, export_text
import seaborn as sns
from sklearn.preprocessing import LabelEncoder
from dtreeviz import trees
from dtreeviz.trees import dtreeviz


def app():
    st.title("Interpréteur d'Arbre de Décision")
    
    # Chargement du modèle et des données
    model, X, y, feature_names = load_model_and_data()
    
    if model is None:
        st.warning("Veuillez charger un modèle pour commencer.")
        return
    
    # Sidebar avec les sections
    st.sidebar.title("Navigation")
    page = st.sidebar.radio(
        "Sélectionnez une section",
        ["Vue globale du modèle", 
         "Explorateur de règles", 
         "Analyse de cohortes",
         "Simulateur de prédictions"]
    )
    
    # Vue globale du modèle
    if page == "Vue globale du modèle":
        st.header("Vue globale du modèle")
        col1, col2 = st.columns(2)
        
        with col1:
            st.subheader("Importance des caractéristiques")
            importance_plot = plt.figure(figsize=(10, 6))
            feature_importance = pd.DataFrame({
                'feature': feature_names,
                'importance': model.feature_importances_
            }).sort_values('importance', ascending=True)
            plt.barh(feature_importance['feature'], feature_importance['importance'])
            st.pyplot(importance_plot)
        
        with col2:
            st.subheader("Statistiques du modèle")
            st.write(f"Profondeur de l'arbre: {model.get_depth()}")
            st.write(f"Nombre de feuilles: {model.get_n_leaves()}")
    
    # Explorateur de règles
    elif page == "Explorateur de règles":
        st.header("Explorateur de règles de décision")
        
        viz_type = st.radio(
            "Type de visualisation",
            ["Texte", "Graphique interactif"]
        )
        
        max_depth = st.slider("Profondeur maximale à afficher", 1, model.get_depth(), 3)
        
        if viz_type == "Texte":
            tree_text = export_text(model, feature_names=list(feature_names), max_depth=max_depth)
            st.text(tree_text)
        else:
            # Création de la visualisation dtreeviz
            viz = dtreeviz(
                model,
                X,
                y,
                target_name="target",
                feature_names=list(feature_names),
                class_names=list(map(str, model.classes_)),
                max_depth=max_depth
            )
            
            # Sauvegarde temporaire et affichage
            st.set_option('deprecation.showPyplotGlobalUse', False)
            fig = viz.view()
            st.pyplot(fig)
    
    # Analyse de cohortes
    elif page == "Analyse de cohortes":
        st.header("Analyse de cohortes")
        
        selected_features = st.multiselect(
            "Sélectionnez les caractéristiques pour définir les cohortes",
            feature_names,
            max_selections=2
        )
        
        if len(selected_features) > 0:
            def create_cohorts(X, features):
                cohort_def = X[features].copy()
                for feat in features:
                    if X[feat].dtype == 'object' or len(X[feat].unique()) < 10:
                        cohort_def[feat] = X[feat]
                    else:
                        cohort_def[feat] = pd.qcut(X[feat], q=4, labels=['Q1', 'Q2', 'Q3', 'Q4'])
                return cohort_def.apply(lambda x: ' & '.join(x.astype(str)), axis=1)
            
            cohorts = create_cohorts(X, selected_features)
            
            cohort_analysis = pd.DataFrame({
                'Cohorte': cohorts,
                'Prédiction': model.predict(X)
            })
            
            cohort_stats = cohort_analysis.groupby('Cohorte')['Prédiction'].agg(['count', 'mean'])
            cohort_stats.columns = ['Nombre d\'observations', 'Taux de prédiction positive']
            
            st.write("Statistiques par cohorte:")
            st.dataframe(cohort_stats)
            
            cohort_viz = plt.figure(figsize=(10, 6))
            sns.barplot(data=cohort_analysis, x='Cohorte', y='Prédiction')
            plt.xticks(rotation=45)
            st.pyplot(cohort_viz)
    
    # Simulateur de prédictions
    else:
        st.header("Simulateur de prédictions")
        
        input_values = {}
        for feature in feature_names:
            if X[feature].dtype == 'object':
                input_values[feature] = st.selectbox(
                    f"Sélectionnez {feature}",
                    options=X[feature].unique()
                )
            else:
                input_values[feature] = st.slider(
                    f"Valeur pour {feature}",
                    float(X[feature].min()),
                    float(X[feature].max()),
                    float(X[feature].mean())
                )
        
        if st.button("Prédire"):
            input_df = pd.DataFrame([input_values])
            
            prediction = model.predict_proba(input_df)
            
            st.write("Probabilités prédites:")
            st.write({f"Classe {i}": f"{prob:.2%}" for i, prob in enumerate(prediction[0])})
            
            st.subheader("Chemin de décision")
            node_indicator = model.decision_path(input_df)
            leaf_id = model.apply(input_df)
            
            node_index = node_indicator.indices[node_indicator.indptr[0]:node_indicator.indptr[1]]
            
            rules = []
            for node_id in node_index:
                if node_id != leaf_id[0]:
                    threshold = model.tree_.threshold[node_id]
                    feature = feature_names[model.tree_.feature[node_id]]
                    if input_df.iloc[0][feature] <= threshold:
                        rules.append(f"{feature} ≤ {threshold:.2f}")
                    else:
                        rules.append(f"{feature} > {threshold:.2f}")
            
            for rule in rules:
                st.write(rule)

if __name__ == "__main__":
    app()