One Hot Encoder and Linear Regression

 # -*- coding: utf-8 -*-

"""

Created on Thu Nov  9 23:39:19 2023

@author: Syed Kamran Bukhari

"""

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

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

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

selected_features_y=["belly"]

X=dataset[selected_features_x]

Y=dataset[selected_features_y]

from sklearn.compose import ColumnTransformer

from sklearn.preprocessing import OneHotEncoder

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

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

from sklearn.impute import SimpleImputer

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

imputer.fit(X)

X=imputer.fit_transform(X)

imputer.fit(Y)

Y=imputer.fit_transform(Y)

from sklearn.preprocessing import PolynomialFeatures

poly_reg=PolynomialFeatures(degree=4)

poly_reg.fit_transform(X,Y)

from sklearn.linear_model import LinearRegression

linear_regression = LinearRegression()

linear_regression.fit(X, Y)

Y_pred=linear_regression.predict([[1, 0, 0, 1, 8, 28]])

print("\n")

#RMSE score

residual = abs(Y)- abs(linear_regression.predict(X))

ss= residual**2

ss=ss.sum()

import math

RMSE=math.sqrt(ss)

print('The RMSE score is =', RMSE)

#R2 score

from sklearn.metrics import r2_score

R2= r2_score(Y, linear_regression.predict(X))

print('The R2 score is =',R2)

#Durbin Watson Statistics

from statsmodels.stats.stattools import durbin_watson

DW = durbin_watson(residual)

print('Durbin Watson Statistics =',DW)