prediction de regression terminee

frontend/pages/prediction_classification.py

@@ -0,0 +1,41 @@
+import streamlit as st
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.preprocessing import LabelEncoder
+import pandas as pd
+
+st.header("Prediction: Classification")
+
+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:
+        le = LabelEncoder()
+        X = data[data_name].apply(le.fit_transform)
+        y = le.fit_transform(data[target_name])
+
+        model = RandomForestClassifier(n_estimators=n_estimators, max_depth=max_depth, random_state=111)
+        model.fit(X, y)
+
+        st.subheader("Enter values for prediction")
+
+        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]
+
+        prediction = model.predict([pred_values_encoded])
+
+        prediction_decoded = le.inverse_transform(prediction)
+
+        st.write("Prediction:", prediction_decoded[0])
+else:
+    st.error("File not loaded")