Big Data Analytics Project

Credit Card Fraud Detection

</center> By:
SOUBHIK SINHA (19BIT0303)
AASHISH BANSAL (19BIT0346)

Component: K-MEANS CLUSTERING

Import the packages¶

In [ ]:
import numpy as ny
import pandas as ps
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import normalize
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score
from sklearn.metrics import f1_score
import time
In [ ]:
tic=time.time()
In [ ]:
from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive

Importing dataset¶

In [ ]:
cred=ps.read_csv("/content/drive/MyDrive/Project - ITE2013 - Big Data - Credit Card Fraud Detection/dataset/creditcard.csv")

cred.head()
Out[ ]:
Time V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13 V14 V15 V16 V17 V18 V19 V20 V21 V22 V23 V24 V25 V26 V27 V28 Amount Class
0 0.0 -1.359807 -0.072781 2.536347 1.378155 -0.338321 0.462388 0.239599 0.098698 0.363787 0.090794 -0.551600 -0.617801 -0.991390 -0.311169 1.468177 -0.470401 0.207971 0.025791 0.403993 0.251412 -0.018307 0.277838 -0.110474 0.066928 0.128539 -0.189115 0.133558 -0.021053 149.62 0
1 0.0 1.191857 0.266151 0.166480 0.448154 0.060018 -0.082361 -0.078803 0.085102 -0.255425 -0.166974 1.612727 1.065235 0.489095 -0.143772 0.635558 0.463917 -0.114805 -0.183361 -0.145783 -0.069083 -0.225775 -0.638672 0.101288 -0.339846 0.167170 0.125895 -0.008983 0.014724 2.69 0
2 1.0 -1.358354 -1.340163 1.773209 0.379780 -0.503198 1.800499 0.791461 0.247676 -1.514654 0.207643 0.624501 0.066084 0.717293 -0.165946 2.345865 -2.890083 1.109969 -0.121359 -2.261857 0.524980 0.247998 0.771679 0.909412 -0.689281 -0.327642 -0.139097 -0.055353 -0.059752 378.66 0
3 1.0 -0.966272 -0.185226 1.792993 -0.863291 -0.010309 1.247203 0.237609 0.377436 -1.387024 -0.054952 -0.226487 0.178228 0.507757 -0.287924 -0.631418 -1.059647 -0.684093 1.965775 -1.232622 -0.208038 -0.108300 0.005274 -0.190321 -1.175575 0.647376 -0.221929 0.062723 0.061458 123.50 0
4 2.0 -1.158233 0.877737 1.548718 0.403034 -0.407193 0.095921 0.592941 -0.270533 0.817739 0.753074 -0.822843 0.538196 1.345852 -1.119670 0.175121 -0.451449 -0.237033 -0.038195 0.803487 0.408542 -0.009431 0.798278 -0.137458 0.141267 -0.206010 0.502292 0.219422 0.215153 69.99 0

Randomize the dataset¶

In [ ]:
cred = cred.sample(frac=1)
cred
Out[ ]:
Time V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13 V14 V15 V16 V17 V18 V19 V20 V21 V22 V23 V24 V25 V26 V27 V28 Amount Class
178103 123475.0 -5.907829 4.495036 -3.682879 -2.626879 -0.198306 3.447705 -2.558034 3.446840 2.201571 2.332888 -0.730184 1.157248 0.159355 0.692754 0.724211 0.482909 0.141694 -0.297332 -0.606919 0.645331 -0.095417 -0.823894 0.512631 0.608003 0.364096 -0.373512 -1.393714 -0.222022 1.77 0
261925 160243.0 -2.783865 1.596824 -2.084844 2.512986 -1.446749 -0.828496 -0.732262 -0.203329 -0.347046 -2.162061 1.966123 -3.127456 0.506574 -5.926131 0.931091 -2.499307 -3.712752 -1.142133 0.626241 -0.515001 0.203563 0.293268 0.199568 0.146868 0.163602 -0.624085 -1.333100 0.428634 156.00 1
194951 130837.0 -1.150428 -0.791315 0.565064 -2.139782 1.352664 -0.059039 0.260391 0.125684 -1.596782 -0.091853 -0.230739 -0.685829 -0.270623 -0.019917 -1.300188 1.093228 -0.182027 -0.804988 1.560827 0.533215 0.057807 -0.366581 -0.154412 -0.313439 0.914807 -0.196511 -0.076915 0.047318 90.70 0
197961 132257.0 2.086916 -0.842936 -3.973379 -1.698370 2.540840 2.677246 -0.276120 0.497714 -0.974467 0.342742 0.364130 -0.759274 -0.257962 -0.826524 -0.072530 0.534962 1.416166 -1.382954 0.482206 0.206675 0.296118 0.673546 -0.137164 0.675475 0.507282 0.122100 -0.052114 -0.047698 91.40 0
111956 72448.0 -0.795972 -0.337945 1.868059 1.050754 -1.120475 0.087213 -1.124932 0.708030 -1.023988 0.285413 -0.667877 0.441433 0.751321 -0.250259 0.470302 -2.091935 0.891401 1.006323 -0.498712 -0.275143 -0.172551 -0.152472 0.226367 0.365930 -0.484788 -0.311035 0.039018 -0.114734 40.00 0
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
160326 113237.0 1.624383 -1.005744 0.412692 1.615982 -1.085810 0.945635 -1.166649 0.368163 1.954861 -0.125110 -1.596324 0.606588 0.206027 -0.902252 -0.464850 0.204302 -0.410422 0.368665 -0.506987 0.040387 0.247959 0.817079 0.063272 0.618675 -0.228784 -0.559651 0.092650 0.011391 139.00 0
46718 42899.0 -1.213732 1.688825 -0.755056 -0.912420 3.124243 3.518855 -0.720185 -1.732199 -1.137526 -1.860717 0.036458 -0.395282 -0.530655 -0.915168 0.640247 1.222133 0.340463 1.171805 -0.883744 0.655440 -1.324803 -0.018077 -0.477582 0.836884 0.728877 -0.413261 0.029606 0.135440 1.00 0
59846 49032.0 -2.032651 0.409651 0.736766 -1.862659 1.526845 0.499899 -0.262421 -2.474291 -1.007222 -1.590705 0.276773 1.103023 0.890970 0.441409 -0.650635 1.128877 -1.287067 -0.204933 -1.089240 0.400198 -1.434896 0.022223 0.391344 -1.322870 0.684427 0.550036 0.009533 -0.036957 26.22 0
272256 164988.0 1.643815 -2.152240 0.613898 0.277621 -2.363581 0.597806 -1.773400 0.319186 1.632011 0.397138 -2.235965 0.090129 -0.397398 -1.318790 -1.546596 -1.557987 0.357367 1.408143 -0.528242 -0.273783 -0.194241 0.022026 0.081441 -0.068532 -0.576502 0.730318 0.027644 -0.001285 200.00 0
19645 30431.0 -1.361328 1.332937 0.419559 1.178256 -0.808321 1.358962 -1.425060 1.802502 -0.007368 -0.564927 -0.850215 0.472257 -0.984551 0.798282 -0.578186 -0.007858 0.449377 0.657700 1.406890 -0.445492 0.127248 0.136341 0.079341 -1.183486 -0.833094 -0.389425 -0.352892 -0.009522 0.76 0

284807 rows × 31 columns

Data Preparation¶

In [ ]:
#We don't need Time and Class feature as they are unused - saw in other algorithm models

features = cred.drop(["Time","Class"],axis=1)
features
Out[ ]:
V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13 V14 V15 V16 V17 V18 V19 V20 V21 V22 V23 V24 V25 V26 V27 V28 Amount
178103 -5.907829 4.495036 -3.682879 -2.626879 -0.198306 3.447705 -2.558034 3.446840 2.201571 2.332888 -0.730184 1.157248 0.159355 0.692754 0.724211 0.482909 0.141694 -0.297332 -0.606919 0.645331 -0.095417 -0.823894 0.512631 0.608003 0.364096 -0.373512 -1.393714 -0.222022 1.77
261925 -2.783865 1.596824 -2.084844 2.512986 -1.446749 -0.828496 -0.732262 -0.203329 -0.347046 -2.162061 1.966123 -3.127456 0.506574 -5.926131 0.931091 -2.499307 -3.712752 -1.142133 0.626241 -0.515001 0.203563 0.293268 0.199568 0.146868 0.163602 -0.624085 -1.333100 0.428634 156.00
194951 -1.150428 -0.791315 0.565064 -2.139782 1.352664 -0.059039 0.260391 0.125684 -1.596782 -0.091853 -0.230739 -0.685829 -0.270623 -0.019917 -1.300188 1.093228 -0.182027 -0.804988 1.560827 0.533215 0.057807 -0.366581 -0.154412 -0.313439 0.914807 -0.196511 -0.076915 0.047318 90.70
197961 2.086916 -0.842936 -3.973379 -1.698370 2.540840 2.677246 -0.276120 0.497714 -0.974467 0.342742 0.364130 -0.759274 -0.257962 -0.826524 -0.072530 0.534962 1.416166 -1.382954 0.482206 0.206675 0.296118 0.673546 -0.137164 0.675475 0.507282 0.122100 -0.052114 -0.047698 91.40
111956 -0.795972 -0.337945 1.868059 1.050754 -1.120475 0.087213 -1.124932 0.708030 -1.023988 0.285413 -0.667877 0.441433 0.751321 -0.250259 0.470302 -2.091935 0.891401 1.006323 -0.498712 -0.275143 -0.172551 -0.152472 0.226367 0.365930 -0.484788 -0.311035 0.039018 -0.114734 40.00
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
160326 1.624383 -1.005744 0.412692 1.615982 -1.085810 0.945635 -1.166649 0.368163 1.954861 -0.125110 -1.596324 0.606588 0.206027 -0.902252 -0.464850 0.204302 -0.410422 0.368665 -0.506987 0.040387 0.247959 0.817079 0.063272 0.618675 -0.228784 -0.559651 0.092650 0.011391 139.00
46718 -1.213732 1.688825 -0.755056 -0.912420 3.124243 3.518855 -0.720185 -1.732199 -1.137526 -1.860717 0.036458 -0.395282 -0.530655 -0.915168 0.640247 1.222133 0.340463 1.171805 -0.883744 0.655440 -1.324803 -0.018077 -0.477582 0.836884 0.728877 -0.413261 0.029606 0.135440 1.00
59846 -2.032651 0.409651 0.736766 -1.862659 1.526845 0.499899 -0.262421 -2.474291 -1.007222 -1.590705 0.276773 1.103023 0.890970 0.441409 -0.650635 1.128877 -1.287067 -0.204933 -1.089240 0.400198 -1.434896 0.022223 0.391344 -1.322870 0.684427 0.550036 0.009533 -0.036957 26.22
272256 1.643815 -2.152240 0.613898 0.277621 -2.363581 0.597806 -1.773400 0.319186 1.632011 0.397138 -2.235965 0.090129 -0.397398 -1.318790 -1.546596 -1.557987 0.357367 1.408143 -0.528242 -0.273783 -0.194241 0.022026 0.081441 -0.068532 -0.576502 0.730318 0.027644 -0.001285 200.00
19645 -1.361328 1.332937 0.419559 1.178256 -0.808321 1.358962 -1.425060 1.802502 -0.007368 -0.564927 -0.850215 0.472257 -0.984551 0.798282 -0.578186 -0.007858 0.449377 0.657700 1.406890 -0.445492 0.127248 0.136341 0.079341 -1.183486 -0.833094 -0.389425 -0.352892 -0.009522 0.76

284807 rows × 29 columns

In [ ]:
labels = ps.DataFrame(cred[["Class"]])
labels
Out[ ]:
Class
178103 0
261925 1
194951 0
197961 0
111956 0
... ...
160326 0
46718 0
59846 0
272256 0
19645 0

284807 rows × 1 columns

In [ ]:
features_array = features.values
features_array
Out[ ]:
array([[-5.90782921e+00,  4.49503625e+00, -3.68287879e+00, ...,
        -1.39371378e+00, -2.22022345e-01,  1.77000000e+00],
       [-2.78386549e+00,  1.59682358e+00, -2.08484399e+00, ...,
        -1.33309976e+00,  4.28633994e-01,  1.56000000e+02],
       [-1.15042772e+00, -7.91315138e-01,  5.65063609e-01, ...,
        -7.69154290e-02,  4.73183520e-02,  9.07000000e+01],
       ...,
       [-2.03265075e+00,  4.09650644e-01,  7.36766099e-01, ...,
         9.53257400e-03, -3.69568310e-02,  2.62200000e+01],
       [ 1.64381529e+00, -2.15224043e+00,  6.13898230e-01, ...,
         2.76443020e-02, -1.28499500e-03,  2.00000000e+02],
       [-1.36132758e+00,  1.33293714e+00,  4.19559452e-01, ...,
        -3.52891758e-01, -9.52247000e-03,  7.60000000e-01]])
In [ ]:
labels_array = labels.values
labels_array
Out[ ]:
array([[0],
       [1],
       [0],
       ...,
       [0],
       [0],
       [0]])

Splitting the Dataset¶

In [ ]:
train_feat, test_feat, train_lab, test_lab = train_test_split(features_array,labels_array, train_size=0.90)

Normalizing Dataset¶

In [ ]:
train_feat = normalize(train_feat)
test_feat = normalize(test_feat)

Creating the Model¶

In [ ]:
#KNN (K-NEAREST NEIGHBOUR) CLASSIFICATION

KNN=KNeighborsClassifier(n_neighbors=5,algorithm="kd_tree",n_jobs=-1)
KNN.fit(train_feat,train_lab.ravel())
KNN_predicted_test_lab=KNN.predict(test_feat)

Confusion matrix for KNN¶

In [ ]:
trueNeg,falsePos,falseNeg,truePos=confusion_matrix(test_lab,KNN_predicted_test_lab).ravel()

Evaluation Metrics for KNN¶

In [ ]:
accuracy = accuracy_score(test_lab,KNN_predicted_test_lab)
precison = precision_score(test_lab,KNN_predicted_test_lab)
recall = recall_score(test_lab,KNN_predicted_test_lab)
f1_score = f1_score(test_lab,KNN_predicted_test_lab)

Results from Training¶

In [ ]:
print("Confusion Matrix of KNN")
print("True Negative = ",trueNeg," || False Positive = ",falsePos)
print("False Negative = ",falseNeg," || True Positive = ",truePos)
print(" ")
print("SCORES VIA METRICS --")
print("Accuracy ==>",accuracy)
print("Precison ==>",precison)
print("Recall ==>",recall)
print("F1_Score ==>",f1_score)

Confusion Matrix of KNN
True Negative =  28423  || False Positive =  4
False Negative =  19  || True Positive =  35
 
SCORES VIA METRICS --
Accuracy ==> 0.9991924440855307
Precison ==> 0.8974358974358975
Recall ==> 0.6481481481481481
F1_Score ==> 0.7526881720430108

Summary¶

Accuracy = 99.91%
Precision = 89.74%
ReCall = 64.81%
F1_Score = 75.26%