In 

[12]:
import pandas as pd

from sklearn import linear_model

from matplotlib import pyplot as plt

In [13]:
ca=pd.read_csv(r"C:\Users\Chromsy\Downloads\canada_per_capita_income.csv")

In [14]:
ca.head()

Out[14]: year per capita income (US$)

0 1970 3399.299037

1 1971 3768.297935

2 1972 4251.175484

3 1973 4804.463248

4 1974 5576.514583

In [15]:
inc=ca['per capita income (US$)']

In [23]:
plt.scatter(ca.year,inc, marker='+', color='red',s=100)

plt.title('Canada per Capita Income',fontsize=30)

plt.xlabel('Year',fontsize=20)

plt.ylabel('per capita income (US$)',fontsize=20)

plt.show()

In [29]:
reg = linear_model.LinearRegression()

reg.fit(ca[['year']],inc)

Out[29]: LinearRegression()

In [34]:
reg.predict([[2017]])

Out[34]: array([38803.29886875])

In [56]:
df=(1968,1969,2017,2018,2019,2020,2021,2022)

In [57]:
nxt=pd.DataFrame({"year":df})

nxt

Out[57]: year

0 1968

1 1969

2 2017

3 2018

4 2019

5 2020

6 2021

7 2022

In [58]:
jh=reg.predict(nxt)

jh

Out[58]: array([-1791.48981716, -963.02474194, 38803.29886875, 39631.76394397,

40460.22901919, 41288.69409442, 42117.15916964, 42945.62424486])

In [61]:
plt.scatter(ca.year,inc, marker='+', color='red',s=100)

plt.plot(df,jh,color="green")

plt.scatter(df,jh, marker='*', color='yellow',s=200)

plt.title('Canada per Capita Income',fontsize=30)

plt.xlabel('Year',fontsize=20)

plt.ylabel('per capita income (US$)',fontsize=20)

plt.show()

In [ ]: