#Salary_Database
import numpy as nm
import matplotlib.pyplot as mtp
import pandas as pd
data_set = pd.read_csv('Salary_Data.csv')
data_set
1.1 39343
0 1.3 46205
1 1.5 37731
2 2.0 43525
3 2.2 39891
4 2.9 56642
5 3.0 60150
6 3.2 54445
7 3.2 64445
8 3.7 57189
9 3.9 63218
10 4.0 55794
11 4.0 56957
12 4.1 57081
13 4.5 61111
14 4.9 67938
15 5.1 66029
16 5.3 83088
17 5.9 81363
18 6.0 93940
19 6.8 91738
20 7.1 98273
21 7.9 101302
22 8.2 113812
23 8.7 109431
24 9.0 105582
25 9.5 116969
26 9.6 112635
27 10.3 122391
28 10.5 121872
x = data_set.iloc[:, :-1].values
y = data_set.iloc[:, 1].values
x
array([[ 1.3],
[ 1.5],
[ 2. ],
[ 2.2],
[ 2.9],
[ 3. ],
[ 3.2],
[ 3.2],
[ 3.7],
[ 3.9],
[ 4. ],
[ 4. ],
[ 4.1],
[ 4.5],
[ 4.9],
[ 5.1],
[ 5.3],
[ 5.9],
[ 6. ],
[ 6.8],
[ 7.1],
[ 7.9],
[ 8.2],
[ 8.7],
[ 9. ],
[ 9.5],
[ 9.6],
[10.3],
[10.5]])
array([ 46205, 37731, 43525, 39891, 56642, 60150, 54445, 64445,
57189, 63218, 55794, 56957, 57081, 61111, 67938, 66029,
83088, 81363, 93940, 91738, 98273, 101302, 113812, 109431,
105582, 116969, 112635, 122391, 121872], dtype=int64)
#Splitting the dataset into training and test set.
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)
x_test
array([[2. ],
[7.1],
[8.7],
[4.5],
[4. ],
[9.5]])
#Fitting the simple linear regression model to the training dataset
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(x_train, y_train)
▾ LinearRegression
LinearRegression()
#Prediction of Test and Training set result
y_pred = regressor.predict(x_test)
x_pred = regressor.predict(x_train)
x_pred
array([ 54560.25600817, 72489.8086666 , 61165.8806718 , 76264.45133154,
103630.61065232, 81926.41532894, 40405.34601466, 63996.8626705 ,
125334.80597569, 56447.57734063, 53616.59534193, 82870.07599517,
90419.36132504, 63053.20200427, 56447.57734063, 111179.89598218,
47010.9706783 , 38518.02468219, 100799.62865361, 74377.12999907,
64940.52333674])
mtp.scatter(x_train, y_train, color="green")
mtp.plot(x_train, x_pred, color="red")
mtp.title("Salary vs Experience(Training DataSet)")
mtp.xlabel("Year of Experience")
mtp.ylabel("Salary(In Rupees)")
mtp.show()
mtp.scatter(x_test, y_test, color="blue")
mtp.plot(x_train, x_pred, color="red")
mtp.title("Salary vs Experience(Training DataSet)")
mtp.xlabel("Year of Experience")
mtp.ylabel("Salary(In Rupees)")
mtp.show()
Loading [MathJax]/jax/output/CommonHTML/fonts/TeX/fontdata.js
