

In [8]:

    
%matplotlib inline
import matplotlib

Linear Regression

This is one of the simplest models to use, since it has uses linearly correlated data to 'predict' a value given



In [9]:

    
import pandas as pd
from sklearn import linear_model
import matplotlib.pyplot as plt

We will use pandas to handle reading of the data, pandas is pretty much the de facto standard for data manipulation in python.



In [13]:

    
df = pd.read_fwf('brain_body.txt')
x_values = df[['Brain']]
y_values = df[['Body']]
df.head()

now lets train the model using the data



In [11]:

    
import warnings
warnings.filterwarnings(action="ignore", module="scipy", message="^internal gelsd")

body_regression = linear_model.LinearRegression()
body_regression.fit(x_values, y_values)









    Out[11]:





LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)



In [25]:

    
fig = plt.figure()

plt.scatter(x_values, y_values)
plt.plot(x_values, body_regression.predict(x_values))

#add some axes and labelling
fig.suptitle('Linear Regression', fontsize=14, fontweight='bold')
ax = fig.add_subplot(111)

ax.set_title('Body vs Brain')
fig.subplots_adjust(top=0.85)
ax.set_xlabel('Body weight (kg)')
ax.set_ylabel('Brain weight (kg)')

plt.show()



In [ ]:

	Brain	Body
0	3.385	44.5
1	0.480	15.5
2	1.350	8.1
3	465.000	423.0
4	36.330	119.5