Random Forest Tree with test train split

 # -*- coding: utf-8 -*-

"""

Created on Tue Nov 14 13:20:09 2023

@author: Syed Kamran Bukhari

"""

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

dataset=pd.read_csv("possum.csv")

from sklearn.preprocessing import LabelEncoder

label_encoder= LabelEncoder()

dataset["sex"]=label_encoder.fit_transform(dataset["sex"])

selected_feature_X = ["Pop", "sex", "age", "chest"]

selected_feature_Y = ["belly"]

X=dataset[selected_feature_X]

Y=dataset[selected_feature_Y]

from sklearn.compose import ColumnTransformer

from sklearn.preprocessing import OneHotEncoder

ct = ColumnTransformer(transformers=[('encoders', OneHotEncoder(),["Pop"])], remainder="passthrough")

X=np.array(ct.fit_transform(X))

from sklearn.impute import SimpleImputer

imputer = SimpleImputer(missing_values=np.nan , strategy="most_frequent")

imputer.fit(X)

X=imputer.fit_transform(X)

imputer.fit(Y)

Y=imputer.fit_transform(Y)

from sklearn.model_selection import train_test_split

X_train, X_test , Y_train, Y_test = train_test_split(X, Y, test_size= 0.2 , random_state=0)

#randomforest

from sklearn.ensemble import RandomForestRegressor

forest_regressor = RandomForestRegressor(n_estimators=90 , random_state= 0)

forest_regressor.fit(X_train, Y_train)

Y_pred = forest_regressor.predict(X_test)

Y_pred_abs = Y_pred.reshape(len(Y_pred), 1)

#RMSE

residual = abs(Y_test - Y_pred_abs)

ss=residual**2

ss=ss.sum()/len(Y_test)

from math import sqrt

ss= sqrt(ss)

print("RMSE score is = ", ss)

#R2 Score

from sklearn.metrics import r2_score

R2 = r2_score(Y_test, Y_pred)

print ("R2 Score is = ", R2)

#Durbin watson

from statsmodels.stats.stattools import durbin_watson

DB = durbin_watson(residual)

print("Durbin Watson Score is = ", DB)