polynomial_regression in datascience using python

#polynomial regression









In [7]:



from scipy.stats import norm
import matplotlib.pyplot as plt
import numpy as np

np.random.seed(2)
page_speeds = np.random.normal(3.0,1.0,1000)
purchase_amount = np.random.normal(50.0,10.0,1000)/page_speeds

plt.scatter(page_speeds,purchase_amount)









Out[7]:

<matplotlib.collections.PathCollection at 0x1f82b374588>














In [13]:



x= np.array(page_speeds)
y = np.array(purchase_amount)

p4 = np.poly1d(np.polyfit(x,y,3))









In [14]:



xp = np.linspace(0,7,100)
plt.scatter(x,y)
plt.plot(xp,p4(xp), c='r')
plt.show()



















In [ ]:



xp = np.linspace(0,7,100)
plt.scatter(x,y)
plt.plot(xp,p4(xp), c='r')
plt.show()

linear regression in matplotlib in python

Linear regression

This is the topic related to Linear regression using python

In [4]:

from scipy.stats import norm
import matplotlib.pyplot as plt
import numpy as np


page_speeds = np.random.normal(3.0,1.0,1000)
purchase_amount = 100 - (page_speeds + np.random.normal(0,0.1, 1000))*3

plt.scatter(page_speeds,purchase_amount)

Out[4]:

<matplotlib.collections.PathCollection at 0x277ffa83348>

In [5]:

from scipy import stats 

slope, intercept, r_value, p_value, std_err = stats.linregress(page_speeds,purchase_amount)

In [6]:

r_value**2

Out[6]:

0.9904525550737715

In [7]:

import matplotlib.pyplot as plt

def predict(x):
    return slope * x + intercept

fit_line = predict(page_speeds)
plt.scatter(page_speeds,purchase_amount)
plt.plot(page_speeds,fit_line, c='r')
plt.show()