ajout prediction classification

frontend/pages/prediction_classification.py

@@ -1,7 +1,8 @@
 import streamlit as st
-from sklearn.ensemble import RandomForestClassifier
+from sklearn.linear_model import LogisticRegression
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
 from sklearn.preprocessing import LabelEncoder
-import pandas as pd
 
 st.header("Prediction: Classification")
 
@@ -9,33 +10,54 @@ if "data" in st.session_state:
     data = st.session_state.data
 
     with st.form("classification_form"):
-        st.subheader("Random Forest Parameters")
-        
-        data_name = st.multiselect("Features", data.select_dtypes(include="object").columns, help="Sélectionnez les caractéristiques pour l'entraînement.")
-        target_name = st.selectbox("Target", data.columns, help="Sélectionnez la variable cible pour l'entraînement.")
-        
-        n_estimators = st.number_input("Number of estimators", step=1, min_value=1, value=100, help="Nombre d'arbres dans la forêt.")
-        max_depth = st.number_input("Max depth", step=1, min_value=1, value=10, help="Profondeur maximale des arbres.")
-        
-        submit_button = st.form_submit_button('Train and Predict')
-
-    if submit_button and data_name and target_name:
+        st.subheader("Classification Parameters")
+        data_name = st.multiselect("Features", data.columns)
+        target_name = st.selectbox("Target", data.columns)
+        test_size = st.slider("Test Size", min_value=0.1, max_value=0.5, value=0.2, step=0.1)
+        st.form_submit_button('Train and Predict')
+
+    if data_name and target_name:
+        X = data[data_name]
+        y = data[target_name]
+
+        label_encoders = {}
+        for column in X.select_dtypes(include=['object']).columns:
             le = LabelEncoder()
-        X = data[data_name].apply(le.fit_transform)
-        y = le.fit_transform(data[target_name])
+            X[column] = le.fit_transform(X[column])
+            label_encoders[column] = le
         
-        model = RandomForestClassifier(n_estimators=n_estimators, max_depth=max_depth, random_state=111)
-        model.fit(X, y)
-
-        st.subheader("Enter values for prediction")
+        if y.dtype == 'object':
+            le = LabelEncoder()
+            y = le.fit_transform(y)
+            label_encoders[target_name] = le
 
-        pred_values = [st.selectbox(f"Value for {feature}", options=data[feature].unique(), key=f"value_{feature}") for feature in data_name]
-        pred_values_encoded = [le.transform([val])[0] for val in pred_values]
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=42)
 
-        prediction = model.predict([pred_values_encoded])
+        model = LogisticRegression()
+        model.fit(X_train, y_train)
+        y_pred = model.predict(X_test)
+        accuracy = accuracy_score(y_test, y_pred)
 
-        prediction_decoded = le.inverse_transform(prediction)
+        st.subheader("Model Accuracy")
+        st.write(f"Accuracy on test data: {accuracy:.2f}")
 
-        st.write("Prediction:", prediction_decoded[0])
+        st.subheader("Enter values for prediction")
+        pred_values = []
+        for feature in data_name:
+            if feature in label_encoders:
+                values = list(label_encoders[feature].classes_)
+                value = st.selectbox(f"Value for {feature}", values)
+                value_encoded = label_encoders[feature].transform([value])[0]
+                pred_values.append(value_encoded)
+            else:
+                value = st.number_input(f"Value for {feature}", value=0.0)
+                pred_values.append(value)
+        
+        prediction = model.predict([pred_values])
+
+        if target_name in label_encoders:
+            prediction = label_encoders[target_name].inverse_transform(prediction)
+        
+        st.write("Prediction:", prediction[0])
 else:
     st.error("File not loaded")