In [14]:

#Import the libraries and packages we need
import numpy as np
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt

In [3]:

#we are going to create two arrays that have our data. These should be the same length

x = np.array([10,40,25,30,55,18,7]).reshape(-1,1) #we have to use reshape because we are required to pass in x 
                                                  #as a 2-dimensional array. One column and as many rows as necessary
y = np.array([5,18,22,45,60,34,19])

In [4]:

print(x)
print(y)

[[10]
 [40]
 [25]
 [30]
 [55]
 [18]
 [ 7]]
[ 5 18 22 45 60 34 19]

In [5]:

print(x.shape)
print(y.shape)

(7, 1)
(7,)

In [8]:

#we now create our model instance. We are just going to use the default parameters
#we also are going to fit the model
#this calculates the values for the slope and intercept in our regression equation
model = LinearRegression().fit(x,y) 

In [11]:

#now we can see the results
#first our r-squared
r_sq = model.score(x,y)
print("r-squared: ",r_sq)

r-squared:  0.5034536744482078

In [13]:

#we can also find our intercept and slope
intercept = model.intercept_
slope = model.coef_
print("intercept: ",intercept)
print("slope: ",slope)

intercept:  8.420731707317064
slope:  [0.77867502]

In [15]:

#now we can find our predicted values
y_predicted = model.predict(x)

In [16]:

y_predicted

Out[16]:

array([16.20748187, 39.56773237, 27.88760712, 31.7809822 , 51.24785761,
       22.436882  , 13.87145682])

In [17]:

#we can now create our regression equation
y_predicted = intercept + slope*x

In [20]:

#now we can plot the 
fig,ax = plt.subplots(figsize=(10,10))
plt.scatter(x,y)
plt.plot(x,y_predicted)

Out[20]:

[<matplotlib.lines.Line2D at 0x1114dcd0>]

In [ ]: