Create Model Creation with Optuna.py

pages/Model Creation with Optuna.py

@@ -0,0 +1,58 @@
+import streamlit as st
+import pandas as pd
+import optuna
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split, cross_val_score
+from sklearn.metrics import classification_report
+
+# Title
+st.title("Model Creation and Hyperparameter Tuning with Optuna")
+st.markdown("""
+Upload your dataset, select features and target, and let Optuna optimize hyperparameters 
+to train the best Random Forest model.
+""")
+
+# File uploader
+uploaded_file = st.file_uploader("Upload your prepared dataset (CSV format):", type=["csv"])
+
+if uploaded_file is not None:
+    data = pd.read_csv(uploaded_file)
+    st.write("### Dataset:")
+    st.dataframe(data)
+
+    # Feature and target selection
+    features = st.multiselect("Select Features:", options=data.columns)
+    target = st.selectbox("Select Target:", options=data.columns)
+
+    if features and target:
+        X = data[features]
+        y = data[target]
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+
+        def objective(trial):
+            model = RandomForestClassifier(
+                n_estimators=trial.suggest_int("n_estimators", 10, 200),
+                max_depth=trial.suggest_int("max_depth", 2, 32, log=True),
+                min_samples_split=trial.suggest_int("min_samples_split", 2, 20),
+                min_samples_leaf=trial.suggest_int("min_samples_leaf", 1, 20),
+                random_state=42,
+            )
+            return cross_val_score(model, X_train, y_train, cv=3, scoring="accuracy").mean()
+
+        st.write("### Hyperparameter Tuning")
+        n_trials = st.slider("Number of Trials:", 10, 100, 20)
+        if st.button("Start Tuning"):
+            study = optuna.create_study(direction="maximize")
+            study.optimize(objective, n_trials=n_trials)
+
+            st.write("#### Best Parameters:")
+            st.json(study.best_params)
+
+            model = RandomForestClassifier(**study.best_params, random_state=42)
+            model.fit(X_train, y_train)
+
+            y_pred = model.predict(X_test)
+            st.write("### Model Performance:")
+            st.text(classification_report(y_test, y_pred))
+else:
+    st.warning("Upload a dataset to start.")