In [1]:

    

import pandas as pd
import numpy as np


    

In [2]:

    

import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline


    

In [3]:

    

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


    

In [4]:

    

ad_data.head()


    

    
Out[4]:







  

    

      

      
Daily Time Spent on Site
      
Age
      
Area Income
      
Daily Internet Usage
      
Ad Topic Line
      
City
      
Male
      
Country
      
Timestamp
      
Clicked on Ad
    
  
  

    

      
0
      
68.95
      
35
      
61833.90
      
256.09
      
Cloned 5thgeneration orchestration
      
Wrightburgh
      
0
      
Tunisia
      
2016-03-27 00:53:11
      
0
    
    

      
1
      
80.23
      
31
      
68441.85
      
193.77
      
Monitored national standardization
      
West Jodi
      
1
      
Nauru
      
2016-04-04 01:39:02
      
0
    
    

      
2
      
69.47
      
26
      
59785.94
      
236.50
      
Organic bottom-line service-desk
      
Davidton
      
0
      
San Marino
      
2016-03-13 20:35:42
      
0
    
    

      
3
      
74.15
      
29
      
54806.18
      
245.89
      
Triple-buffered reciprocal time-frame
      
West Terrifurt
      
1
      
Italy
      
2016-01-10 02:31:19
      
0
    
    

      
4
      
68.37
      
35
      
73889.99
      
225.58
      
Robust logistical utilization
      
South Manuel
      
0
      
Iceland
      
2016-06-03 03:36:18
      
0
    
  

In [5]:

    

ad_data.describe()


    

    
Out[5]:







  

    

      

      
Daily Time Spent on Site
      
Age
      
Area Income
      
Daily Internet Usage
      
Male
      
Clicked on Ad
    
  
  

    

      
count
      
1000.000000
      
1000.000000
      
1000.000000
      
1000.000000
      
1000.000000
      
1000.00000
    
    

      
mean
      
65.000200
      
36.009000
      
55000.000080
      
180.000100
      
0.481000
      
0.50000
    
    

      
std
      
15.853615
      
8.785562
      
13414.634022
      
43.902339
      
0.499889
      
0.50025
    
    

      
min
      
32.600000
      
19.000000
      
13996.500000
      
104.780000
      
0.000000
      
0.00000
    
    

      
25%
      
51.360000
      
29.000000
      
47031.802500
      
138.830000
      
0.000000
      
0.00000
    
    

      
50%
      
68.215000
      
35.000000
      
57012.300000
      
183.130000
      
0.000000
      
0.50000
    
    

      
75%
      
78.547500
      
42.000000
      
65470.635000
      
218.792500
      
1.000000
      
1.00000
    
    

      
max
      
91.430000
      
61.000000
      
79484.800000
      
269.960000
      
1.000000
      
1.00000
    
  

In [6]:

    

ad_data["Age"].hist(bins = 30)


    

    
Out[6]:





<matplotlib.axes._subplots.AxesSubplot at 0x1b1f065ae48>






    

In [7]:

    

sns.jointplot(ad_data["Age"], ad_data["Area Income"])


    

    
Out[7]:





<seaborn.axisgrid.JointGrid at 0x1b1f067e2b0>






    

In [8]:

    

sns.jointplot(ad_data["Age"], ad_data["Daily Time Spent on Site"], kind="kde")


    

    
Out[8]:





<seaborn.axisgrid.JointGrid at 0x1b1f1f7c5c0>






    

In [9]:

    

sns.jointplot(ad_data["Daily Internet Usage"], ad_data["Daily Time Spent on Site"])


    

    
Out[9]:





<seaborn.axisgrid.JointGrid at 0x1b1f2148b38>






    

In [10]:

    

sns.pairplot(ad_data, hue="Clicked on Ad")


    

    
Out[10]:





<seaborn.axisgrid.PairGrid at 0x1b1f2148940>






    

In [13]:

    

from sklearn.model_selection import train_test_split


    

In [22]:

    

preX = ad_data.drop(["Ad Topic Line", "City", "Country", "Timestamp"], axis = 1, )
X = preX.drop("Clicked on Ad", axis = 1)
y = ad_data["Clicked on Ad"]


    

In [23]:

    

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 42)


    

In [24]:

    

from sklearn.linear_model import LogisticRegression


    

In [25]:

    

logreg = LogisticRegression()


    

In [26]:

    

logreg.fit(X_train, y_train)


    

    
Out[26]:





LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)

In [27]:

    

predictions = logreg.predict(X_test)


    

In [29]:

    

from sklearn.metrics import classification_report


    

In [30]:

    

print(classification_report(y_test, predictions))


    

    




             precision    recall  f1-score   support

          0       0.84      0.97      0.90       146
          1       0.96      0.82      0.89       154

avg / total       0.90      0.89      0.89       300

In [ ]: