From 9e14cefe6538529be364e6f36def9006490efc0d Mon Sep 17 00:00:00 2001
From: Haoran Pan <167847254+TPLin22@users.noreply.github.com>
Date: Thu, 26 Sep 2024 13:43:50 +0800
Subject: [PATCH] feat: random forest for s3e11 (#347)

---
 .../model/model_randomforest.py               | 35 +++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 rdagent/scenarios/kaggle/experiment/playground-series-s3e11_template/model/model_randomforest.py

diff --git a/rdagent/scenarios/kaggle/experiment/playground-series-s3e11_template/model/model_randomforest.py b/rdagent/scenarios/kaggle/experiment/playground-series-s3e11_template/model/model_randomforest.py
new file mode 100644
index 00000000..9618a10e
--- /dev/null
+++ b/rdagent/scenarios/kaggle/experiment/playground-series-s3e11_template/model/model_randomforest.py
@@ -0,0 +1,35 @@
+import pandas as pd
+from sklearn.ensemble import RandomForestRegressor
+
+
+def select(X: pd.DataFrame) -> pd.DataFrame:
+    # Ignore feature selection logic
+    return X
+
+
+def fit(X_train: pd.DataFrame, y_train: pd.DataFrame, X_valid: pd.DataFrame, y_valid: pd.DataFrame):
+    """Define and train the Random Forest model. Merge feature_select"""
+    X_train = select(X_train)
+
+    rf_params = {
+        "n_estimators": 100,
+        "max_depth": 10,
+        "min_samples_split": 2,
+        "min_samples_leaf": 1,
+        "max_features": "sqrt",
+        "random_state": 2023,
+        "n_jobs": -1,
+        "verbose": 1,
+    }
+    model = RandomForestRegressor(**rf_params)
+    model.fit(X_train, y_train)
+    return model
+
+
+def predict(model, X_test):
+    """
+    Keep feature select's consistency.
+    """
+    X_test = select(X_test)
+    y_pred = model.predict(X_test)
+    return y_pred.reshape(-1, 1)