Data Analytics II

1. Implement logistic regression using Python to perform classification on

Social_Network_Ads.csv dataset.
2. Compute Confusion matrix to find TP,FP,Tn,FN,Accuracy,Error
rate,Precision,Recall on the given dataset.

Data Link: [Link]

Our dataset contains some information about all of our users in the social
network, including their User ID, Gender, Age, and Estimated Salary. The last
column of the dataset is a vector of booleans describing whether or not each
individual ended up clicking on the advertisement (0 = False, 1 = True).

In [2]: import pandas as pd

import numpy as np
import seaborn as sns
import [Link] as plt

In [3]: data = pd.read_csv('/content/Social_Network_Ads.csv')

In [5]: data

Out[5]: User ID Gender Age EstimatedSalary Purchased

0 15624510 Male 19 19000 0

1 15810944 Male 35 20000 0

2 15668575 Female 26 43000 0

3 15603246 Female 27 57000 0

4 15804002 Male 19 76000 0

... ... ... ... ... ...

395 15691863 Female 46 41000 1

396 15706071 Male 51 23000 1

397 15654296 Female 50 20000 1

398 15755018 Male 36 33000 0

399 15594041 Female 49 36000 1

400 rows × 5 columns

In [6]: [Link](5)
Loading [MathJax]/extensions/[Link]
 Out[6]: User ID Gender Age EstimatedSalary Purchased

0 15624510 Male 19 19000 0

1 15810944 Male 35 20000 0

2 15668575 Female 26 43000 0

3 15603246 Female 27 57000 0

4 15804002 Male 19 76000 0

In [7]: [Link]()

Out[7]: User ID Gender Age EstimatedSalary Purchased

395 15691863 Female 46 41000 1

396 15706071 Male 51 23000 1

397 15654296 Female 50 20000 1

398 15755018 Male 36 33000 0

399 15594041 Female 49 36000 1

In [8]: [Link]

Out[8]: (400, 5)

In [9]: [Link]

Out[9]: Index(['User ID', 'Gender', 'Age', 'EstimatedSalary', 'Purchased'], dtype

='object')

In [10]: [Link]()

Out[10]: User ID Age EstimatedSalary Purchased

count 4.000000e+02 400.000000 400.000000 400.000000

mean 1.569154e+07 37.655000 69742.500000 0.357500

std 7.165832e+04 10.482877 34096.960282 0.479864

min 1.556669e+07 18.000000 15000.000000 0.000000

25% 1.562676e+07 29.750000 43000.000000 0.000000

50% 1.569434e+07 37.000000 70000.000000 0.000000

75% 1.575036e+07 46.000000 88000.000000 1.000000

max 1.581524e+07 60.000000 150000.000000 1.000000

In [4]: [Link]().sum()

Loading [MathJax]/extensions/[Link]
 Out[4]: User ID 0
Gender 0
Age 0
EstimatedSalary 0
Purchased 0
dtype: int64

In [11]: [Link][:,2:4]

Out[11]: Age EstimatedSalary

0 19 19000

1 35 20000

2 26 43000

3 27 57000

4 19 76000

... ... ...

395 46 41000

396 51 23000

397 50 20000

398 36 33000

399 49 36000

400 rows × 2 columns

In [12]: [Link][:,2:4].values

Loading [MathJax]/extensions/[Link]
 Out[12]: array([[ 19, 19000],
[ 35, 20000],
[ 26, 43000],
[ 27, 57000],
[ 19, 76000],
[ 27, 58000],
[ 27, 84000],
[ 32, 150000],
[ 25, 33000],
[ 35, 65000],
[ 26, 80000],
[ 26, 52000],
[ 20, 86000],
[ 32, 18000],
[ 18, 82000],
[ 29, 80000],
[ 47, 25000],
[ 45, 26000],
[ 46, 28000],
[ 48, 29000],
[ 45, 22000],
[ 47, 49000],
[ 48, 41000],
[ 45, 22000],
[ 46, 23000],
[ 47, 20000],
[ 49, 28000],
[ 47, 30000],
[ 29, 43000],
[ 31, 18000],
[ 31, 74000],
[ 27, 137000],
[ 21, 16000],
[ 28, 44000],
[ 27, 90000],
[ 35, 27000],
[ 33, 28000],
[ 30, 49000],
[ 26, 72000],
[ 27, 31000],
[ 27, 17000],
[ 33, 51000],
[ 35, 108000],
[ 30, 15000],
[ 28, 84000],
[ 23, 20000],
[ 25, 79000],
[ 27, 54000],
[ 30, 135000],
[ 31, 89000],
[ 24, 32000],
[ 18, 44000],
[ 29, 83000],
[ 35, 23000],
[ 27, 58000],
[
Loading [MathJax]/extensions/[Link] 24, 55000],
 [ 23, 48000],
[ 28, 79000],
[ 22, 18000],
[ 32, 117000],
[ 27, 20000],
[ 25, 87000],
[ 23, 66000],
[ 32, 120000],
[ 59, 83000],
[ 24, 58000],
[ 24, 19000],
[ 23, 82000],
[ 22, 63000],
[ 31, 68000],
[ 25, 80000],
[ 24, 27000],
[ 20, 23000],
[ 33, 113000],
[ 32, 18000],
[ 34, 112000],
[ 18, 52000],
[ 22, 27000],
[ 28, 87000],
[ 26, 17000],
[ 30, 80000],
[ 39, 42000],
[ 20, 49000],
[ 35, 88000],
[ 30, 62000],
[ 31, 118000],
[ 24, 55000],
[ 28, 85000],
[ 26, 81000],
[ 35, 50000],
[ 22, 81000],
[ 30, 116000],
[ 26, 15000],
[ 29, 28000],
[ 29, 83000],
[ 35, 44000],
[ 35, 25000],
[ 28, 123000],
[ 35, 73000],
[ 28, 37000],
[ 27, 88000],
[ 28, 59000],
[ 32, 86000],
[ 33, 149000],
[ 19, 21000],
[ 21, 72000],
[ 26, 35000],
[ 27, 89000],
[ 26, 86000],
[ 38, 80000],
[ 39, 71000],
[
Loading [MathJax]/extensions/[Link] 37, 71000],
 [ 38, 61000],
[ 37, 55000],
[ 42, 80000],
[ 40, 57000],
[ 35, 75000],
[ 36, 52000],
[ 40, 59000],
[ 41, 59000],
[ 36, 75000],
[ 37, 72000],
[ 40, 75000],
[ 35, 53000],
[ 41, 51000],
[ 39, 61000],
[ 42, 65000],
[ 26, 32000],
[ 30, 17000],
[ 26, 84000],
[ 31, 58000],
[ 33, 31000],
[ 30, 87000],
[ 21, 68000],
[ 28, 55000],
[ 23, 63000],
[ 20, 82000],
[ 30, 107000],
[ 28, 59000],
[ 19, 25000],
[ 19, 85000],
[ 18, 68000],
[ 35, 59000],
[ 30, 89000],
[ 34, 25000],
[ 24, 89000],
[ 27, 96000],
[ 41, 30000],
[ 29, 61000],
[ 20, 74000],
[ 26, 15000],
[ 41, 45000],
[ 31, 76000],
[ 36, 50000],
[ 40, 47000],
[ 31, 15000],
[ 46, 59000],
[ 29, 75000],
[ 26, 30000],
[ 32, 135000],
[ 32, 100000],
[ 25, 90000],
[ 37, 33000],
[ 35, 38000],
[ 33, 69000],
[ 18, 86000],
[ 22, 55000],
[
Loading [MathJax]/extensions/[Link] 35, 71000],
 [ 29, 148000],
[ 29, 47000],
[ 21, 88000],
[ 34, 115000],
[ 26, 118000],
[ 34, 43000],
[ 34, 72000],
[ 23, 28000],
[ 35, 47000],
[ 25, 22000],
[ 24, 23000],
[ 31, 34000],
[ 26, 16000],
[ 31, 71000],
[ 32, 117000],
[ 33, 43000],
[ 33, 60000],
[ 31, 66000],
[ 20, 82000],
[ 33, 41000],
[ 35, 72000],
[ 28, 32000],
[ 24, 84000],
[ 19, 26000],
[ 29, 43000],
[ 19, 70000],
[ 28, 89000],
[ 34, 43000],
[ 30, 79000],
[ 20, 36000],
[ 26, 80000],
[ 35, 22000],
[ 35, 39000],
[ 49, 74000],
[ 39, 134000],
[ 41, 71000],
[ 58, 101000],
[ 47, 47000],
[ 55, 130000],
[ 52, 114000],
[ 40, 142000],
[ 46, 22000],
[ 48, 96000],
[ 52, 150000],
[ 59, 42000],
[ 35, 58000],
[ 47, 43000],
[ 60, 108000],
[ 49, 65000],
[ 40, 78000],
[ 46, 96000],
[ 59, 143000],
[ 41, 80000],
[ 35, 91000],
[ 37, 144000],
[
Loading [MathJax]/extensions/[Link] 60, 102000],
 [ 35, 60000],
[ 37, 53000],
[ 36, 126000],
[ 56, 133000],
[ 40, 72000],
[ 42, 80000],
[ 35, 147000],
[ 39, 42000],
[ 40, 107000],
[ 49, 86000],
[ 38, 112000],
[ 46, 79000],
[ 40, 57000],
[ 37, 80000],
[ 46, 82000],
[ 53, 143000],
[ 42, 149000],
[ 38, 59000],
[ 50, 88000],
[ 56, 104000],
[ 41, 72000],
[ 51, 146000],
[ 35, 50000],
[ 57, 122000],
[ 41, 52000],
[ 35, 97000],
[ 44, 39000],
[ 37, 52000],
[ 48, 134000],
[ 37, 146000],
[ 50, 44000],
[ 52, 90000],
[ 41, 72000],
[ 40, 57000],
[ 58, 95000],
[ 45, 131000],
[ 35, 77000],
[ 36, 144000],
[ 55, 125000],
[ 35, 72000],
[ 48, 90000],
[ 42, 108000],
[ 40, 75000],
[ 37, 74000],
[ 47, 144000],
[ 40, 61000],
[ 43, 133000],
[ 59, 76000],
[ 60, 42000],
[ 39, 106000],
[ 57, 26000],
[ 57, 74000],
[ 38, 71000],
[ 49, 88000],
[ 52, 38000],
[
Loading [MathJax]/extensions/[Link] 50, 36000],
 [ 59, 88000],
[ 35, 61000],
[ 37, 70000],
[ 52, 21000],
[ 48, 141000],
[ 37, 93000],
[ 37, 62000],
[ 48, 138000],
[ 41, 79000],
[ 37, 78000],
[ 39, 134000],
[ 49, 89000],
[ 55, 39000],
[ 37, 77000],
[ 35, 57000],
[ 36, 63000],
[ 42, 73000],
[ 43, 112000],
[ 45, 79000],
[ 46, 117000],
[ 58, 38000],
[ 48, 74000],
[ 37, 137000],
[ 37, 79000],
[ 40, 60000],
[ 42, 54000],
[ 51, 134000],
[ 47, 113000],
[ 36, 125000],
[ 38, 50000],
[ 42, 70000],
[ 39, 96000],
[ 38, 50000],
[ 49, 141000],
[ 39, 79000],
[ 39, 75000],
[ 54, 104000],
[ 35, 55000],
[ 45, 32000],
[ 36, 60000],
[ 52, 138000],
[ 53, 82000],
[ 41, 52000],
[ 48, 30000],
[ 48, 131000],
[ 41, 60000],
[ 41, 72000],
[ 42, 75000],
[ 36, 118000],
[ 47, 107000],
[ 38, 51000],
[ 48, 119000],
[ 42, 65000],
[ 40, 65000],
[ 57, 60000],
[
Loading [MathJax]/extensions/[Link] 36, 54000],
 [ 58, 144000],
[ 35, 79000],
[ 38, 55000],
[ 39, 122000],
[ 53, 104000],
[ 35, 75000],
[ 38, 65000],
[ 47, 51000],
[ 47, 105000],
[ 41, 63000],
[ 53, 72000],
[ 54, 108000],
[ 39, 77000],
[ 38, 61000],
[ 38, 113000],
[ 37, 75000],
[ 42, 90000],
[ 37, 57000],
[ 36, 99000],
[ 60, 34000],
[ 54, 70000],
[ 41, 72000],
[ 40, 71000],
[ 42, 54000],
[ 43, 129000],
[ 53, 34000],
[ 47, 50000],
[ 42, 79000],
[ 42, 104000],
[ 59, 29000],
[ 58, 47000],
[ 46, 88000],
[ 38, 71000],
[ 54, 26000],
[ 60, 46000],
[ 60, 83000],
[ 39, 73000],
[ 59, 130000],
[ 37, 80000],
[ 46, 32000],
[ 46, 74000],
[ 42, 53000],
[ 41, 87000],
[ 58, 23000],
[ 42, 64000],
[ 48, 33000],
[ 44, 139000],
[ 49, 28000],
[ 57, 33000],
[ 56, 60000],
[ 49, 39000],
[ 39, 71000],
[ 47, 34000],
[ 48, 35000],
[ 48, 33000],
[
Loading [MathJax]/extensions/[Link] 47, 23000],
 [ 45, 45000],
[ 60, 42000],
[ 39, 59000],
[ 46, 41000],
[ 51, 23000],
[ 50, 20000],
[ 36, 33000],
[ 49, 36000]])

In [13]: sns.set_style('whitegrid')
data['Age'].hist(bins=30)
[Link]('Age')

Out[13]: Text(0.5, 0, 'Age')

In [14]: [Link](x='Age', y='EstimatedSalary', data = data)

Out[14]: <[Link] at 0x7febe788e2c0>

Loading [MathJax]/extensions/[Link]
 In [15]: [Link](x='Age',y='EstimatedSalary',data= data,color='green')

Out[15]: <[Link] at 0x7febe7852bc0>

Loading [MathJax]/extensions/[Link]
 In [16]: [Link](data,hue='Purchased',palette='bwr')

Out[16]: <[Link] at 0x7febe5322170>

Loading [MathJax]/extensions/[Link]
 Logistic Regression
In [17]: # ** Split the data into training set and testing set using train_test_split

from sklearn.model_selection import train_test_split

In [18]: X = data[['Age','EstimatedSalary']]
y = data['Purchased']

In [19]: X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, ra

In [20]: X_train.shape

Out[20]: (300, 2)

In [21]: X_test.shape

Out[21]: (100, 2)

In [MathJax]/extensions/[Link]
Loading [22]: y_train.shape
 Out[22]: (300,)

In [23]: y_test.shape

Out[23]: (100,)

** Train and fit a logistic regression model on the

training set.**
In [24]: from sklearn.linear_model import LogisticRegression

In [25]: logmodel = LogisticRegression()

[Link](X_train,y_train)

Out[25]: ▾ LogisticRegression

LogisticRegression()

Predictions and Evaluations

In [26]: predictions = [Link](X_test)

Create a classification report for the model.

In [27]: from [Link] import classification_report

In [28]: print(classification_report(y_test,predictions))

precision recall f1-score support

0 0.68 1.00 0.81 68

1 0.00 0.00 0.00 32

accuracy 0.68 100

macro avg 0.34 0.50 0.40 100
weighted avg 0.46 0.68 0.55 100

Loading [MathJax]/extensions/[Link]
 /usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1
344: UndefinedMetricWarning: Precision and F-score are ill-defined and being
set to 0.0 in labels with no predicted samples. Use `zero_division` paramete
r to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1
344: UndefinedMetricWarning: Precision and F-score are ill-defined and being
set to 0.0 in labels with no predicted samples. Use `zero_division` paramete
r to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1
344: UndefinedMetricWarning: Precision and F-score are ill-defined and being
set to 0.0 in labels with no predicted samples. Use `zero_division` paramete
r to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))

In [29]: from [Link] import confusion_matrix

cm = confusion_matrix(y_test, predictions)
print(cm)

[[68 0]
[32 0]]

This Confusion Matrix tells us that there were 68 correct predictions and 32
incorrect ones, meaning the model overall accomplished an 68% accuracy
rating.

Loading [MathJax]/extensions/[Link]