In [ ]:

    

import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
import numpy as np


    

In [ ]:

    

df = pd.read_csv("data/hanford.csv")


    

In [ ]:

    

df


    

In [ ]:

    

lm = LinearRegression()


    

In [ ]:

    

data = np.asarray(df[['Mortality','Exposure']])
x = data[:,1:]
y = data[:,0]


    

In [ ]:

    

data


    

In [ ]:

    

x


    

In [ ]:

    

lm.fit(x,y)


    

In [ ]:

    

lm.coef_


    

In [ ]:

    

lm.score(x,y)


    

In [ ]:

    

slope = lm.coef_[0]


    

In [ ]:

    

intercept = lm.intercept_


    

In [ ]:

    

df.plot(kind='scatter',x='Exposure',y='Mortality')
plt.plot(df['Exposure'],slope*df['Exposure']+intercept,'-')


    

In [ ]:

    

lm.predict(10)


    

In [ ]: