File size: 2,101 Bytes
5cbc1e9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
import pandas as pd
from sklearn.ensemble import (
GradientBoostingRegressor,
RandomForestRegressor,
StackingRegressor,
)
from sklearn.linear_model import LinearRegression, RidgeCV
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_error
from sklearn.preprocessing import StandardScaler
# Load the data
train_data = pd.read_csv("./input/train.csv")
test_data = pd.read_csv("./input/test.csv")
# Prepare the data
X = train_data.drop(["id", "yield"], axis=1)
y = train_data["yield"]
X_test = test_data.drop("id", axis=1)
# Split the data into training and validation sets
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
# Scale the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_val_scaled = scaler.transform(X_val)
X_test_scaled = scaler.transform(X_test)
# Initialize base models
estimators = [
(
"gbr",
GradientBoostingRegressor(
n_estimators=200, learning_rate=0.1, max_depth=4, random_state=42
),
),
("rf", RandomForestRegressor(n_estimators=200, random_state=42)),
("lr", LinearRegression()),
]
# Initialize the StackingRegressor with a RidgeCV final estimator
stacking_regressor = StackingRegressor(estimators=estimators, final_estimator=RidgeCV())
# Train the StackingRegressor on the scaled training data
stacking_regressor.fit(X_train_scaled, y_train)
# Predict on the scaled validation set using the StackingRegressor
y_val_pred = stacking_regressor.predict(X_val_scaled)
# Evaluate the model
mae = mean_absolute_error(y_val, y_val_pred)
print(f"Mean Absolute Error on validation set with StackingRegressor: {mae}")
# Train the StackingRegressor on the full scaled training data and predict on the scaled test set
stacking_regressor.fit(scaler.transform(X), y)
test_predictions = stacking_regressor.predict(X_test_scaled)
# Save the predictions to a CSV file
submission = pd.DataFrame({"id": test_data["id"], "yield": test_predictions})
submission.to_csv("./working/submission.csv", index=False)
|