Decision tree regressor

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split

from sklearn.tree import DecisionTreeRegressor

from sklearn.metrics import r2_score, mean_squared_error

# Data load

df = pd.read_csv('./data/xxx.csv')

# Target data separation

y = df['y']

X = df.drop('y', axis = 1)

# Split train : test data set = 7:3 and set random seed

X_train, X_test, y_train, y_test = train_test_split(X,

                                                    y,

                                                    test_size = 0.3,

                                                    random_state = 42)

# Define a model structure

dtr = DecisionTreeRegressor(max_depth = 16, random_state = 42)

# Train model

dtr.fit(X_train, y_train)

# Model prediction

dtr_pred = dtr.predict(X_test)

# Error metric

print("Ridge-r2 score:", r2_score(y_test, dtr_pred))

print("Ridge-RMSE:", np.sqrt(mean_squared_error(y_test, dtr_pred)))

# Plot

plt.bar(X_train.columns, dtr.feature_importances_)

plot_tree(dtr);