project1day15_py.py

# -*- coding: utf-8 -*-
"""project1day15.py

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1RAngly3f8zFseiKS9RLuxT1cZVQOvOvD
"""

import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv("advertising.csv")

data.head()

fig , axs = plt.subplots(1 , 3 , sharey = True)
data.plot( kind='scatter' , x='TV' , y = 'Sales' , ax=axs[0] , figsize=(14,7))
data.plot( kind='scatter' , x='Radio' , y = 'Sales' , ax=axs[1])
data.plot( kind='scatter' , x='Newspaper' , y = 'Sales' , ax=axs[2])



feature_cols = ['TV']
X = data[feature_cols]
y = data.Sales

from sklearn.linear_model import LinearRegression
lr = LinearRegression()
lr.fit(X,y)

print(lr.intercept_)
print(lr.coef_)

#y = a+bx

result = 6.974821488229891+0.05546477*50
print(result)

X_new = pd.DataFrame({'TV':[data.TV.min(),data.TV.max()]})
X_new.head()

preds = lr.predict(X_new)
preds




data.plot(kind = 'scatter',x = 'TV',y='Sales')
plt.plot(X_new,preds,c='red',linewidth=5)


import statsmodels.formula.api as smf
lm = smf.ols(formula = 'Sales ~ TV',data=data).fit()
lm.conf_int()

lm.pvalues

print(lm.rsquared)

feature_cols = ['TV','Radio']
X = data[feature_cols]
y = data.Sales

lr = LinearRegression()
lr.fit(X, y)

print(lr.intercept_)
print(lr.coef_)

lm = smf.ols(formula = 'Sales ~ TV+Radio+Newspaper',data=data).fit()
lm.conf_int()
lm.summary()