Machine Learning Model 2
Basically the Multiple Linear regression is same as the linear equation only difference is the having many independent variable and in linear regression only on independent variable is there.
Y = @ + # X ( Linear regression )
Y is dependent Variable
X is independent variable
@ is slope
# is linear regression constant
Y = @ + #1 .X1 + #2 .X2 + #3X3 + #4 .X4
Y is dependent Variable X1,X2 ,X3 ,X4 is independent variable
@ is slope
#1 , #2 , #3 , #4 is MULTIPLE linear regression constant
In multiple regression we compare many items that independent variable to dependent variable and predict the result
We Process the data firstly and then we work on the regression
data preprocessing
# template is heavnly need and also feature scaling is not need for mant time but if required we usedimport numpy as npimport matplotlib.pyplot as plotimport pandas as pd#import the data setsdataset = pd.read_csv('data.csv')X = dataset.iloc[: , :-1].valuesY = dataset.iloc[: ,:3].values#split the set to traning and test setsfrom sklearn.model_selection import train_test_splitX_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.2) # test size should be displayed#scalingfrom sklearn.preprocessing import StandardScalersc_X = StandardScaler()X_train = sc_X.fit_transform(X_train)X_test = sc_X.transform(X_test)# scale dumay vriable
now we do an Multiple linear Rgression
# the multiple linear regression is having many component independent , Y = a+ax1+ax2....
# we need to remove the coloum which is noy useful $ garbage in and out
# in = out ... ifthe variable which not impact on
# 5 method of building models 2,3 ,4 are step wise regression ...
#1 all in : - if you know that important varaible or just gave you and make model
# 2 : -
# 3
# 4
# 5
import numpy as np
import matplotlib.pyplot as plot
import pandas as pd
dataset = pd.read_csv('data.csv')
# all expect the last is independ variable
# 4 is dependent variable which is the last coloum and
X = dataset.iloc[:, :-1].values
Y = dataset.iloc[:, :4].values
# categorial data
from sklearn.preprocessing import LabelEncoder ,OneHotEncoder
X = X.reshape(1,-3)
labelencoder_X = LabelEncoder() # index gaves which has coloum which has diff data type than int...
X[:, 0]=labelencoder_X.fit_transform(X[:,0])
onehotencoder = OneHotEncoder(OneHotEncoder(categories='auto', sparse=False))
#dummy create pasiing index
X = onehotencoder.fit_transform(X[0]).toarray()
#split the set to traning and test sets
#dumay variable the type , this used to remove the trap
#removing tthe first index
X = X [: ,:-1]
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) # test size should be displayed
# Mutiple Rehression
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train,Y_train)
# now we learn all the model the traing set now we have to test the model using some variables
Y_pred = regressor.predict(X_test)
print(Y_pred)