In [1]:

    

import numpy as np
from sklearn import linear_model
import matplotlib.pyplot as plt


    

In [2]:

    

# get the dataset using numpy's genfromtxt
data = np.genfromtxt('challenge_dataset.txt', delimiter = ',')


    

In [3]:

    

# split the values
x_values = data[:, 0]
y_values = data[:, 1]


    

In [4]:

    

# visualize the data on a scatter plot
plt.scatter(x_values, y_values)
plt.show()


    

In [5]:

    

# reshape the data
x_values = np.reshape(x_values, (97, 1))
y_values = np.reshape(y_values, (97, 1))


    

In [6]:

    

# get the linear regression model
model = linear_model.LinearRegression()


    

In [7]:

    

# train the model with the data
out = model.fit(x_values, y_values)


    

In [8]:

    

# test the data and plot it out
plt.scatter(x_values, y_values)
plt.plot(x_values, out.predict(x_values))
plt.show()


    

In [ ]: