train.py

#importing train_test_split class from scikit-learn module/library
from sklearn.model_selection import train_test_split
#importing Linear regression class from scikit-learn module/library
from sklearn.linear_model import LinearRegression
#Radomly shuffling the X and y columns data into training and testing data and with test size of 30 percent and training data is of 70 percent
#random_state= some number is to keep same data for train and test to evaluate our algorithm when called with same number(in our case '15')
X_train, X_test, y_train, y_test = train_test_split(df[['X']],df.y,test_size=0.3, random_state=15)

print('Training input data: ',X_train)
print('Testing input data: ',X_test)
print('Testing output data: ',y_train)
print('Testing output data: ',y_test)

#data output of train and test stored in respective variables as above
'''
Training input data:       X
                      6    7
                      11  12
                      3    4
                      10  11
                      0    1
                      7    8
                      12  13
                      5    6
                      8    9
Testing input data:       X
                      13  14
                      2    3
                      9   10
                      4    5
                      1    2
Training output data:  6      77
                      11    132
                      3      44
                      10    121
                      0      11
                      7      88
                      12    143
                      5      66
                      8      99
Name: y, dtype: int64
Testing output data:  13    154
                      2      33
                      9     110
                      4      55
                      1      22
'''
#load linearregression object into a variable. This is the algorithm we are training our data with.
lr = LinearRegression()
#fit our training data of both X and y. by calling fit method on lr object.
lr.fit(X_train,y_train)
#we are done with training our data.