4. Apply oversampling to balance an imbalanced dataset by increasing by number of minority class samples. Classify it using Decision Tree Classifier. (Dataset: creditcard.xls)¶

In [1]:
import numpy as np
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
In [2]:
data = pd.read_csv("dataset/creditcard.xls")
data.head()
Out[2]:
Time V1 V2 V3 V4 V5 V6 V7 V8 V9 ... V21 V22 V23 V24 V25 V26 V27 V28 Amount target
0 0.0 -1.359807 -0.072781 2.536347 1.378155 -0.338321 0.462388 0.239599 0.098698 0.363787 ... -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 ... -0.225775 -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 ... 0.247998 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 ... -0.108300 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 ... -0.009431 0.798278 -0.137458 0.141267 -0.206010 0.502292 0.219422 0.215153 69.99 0

5 rows × 31 columns

In [3]:
x = data.drop(['target'], axis = 1)
y = data['target']
In [4]:
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2)
In [5]:
classifier = DecisionTreeClassifier()
classifier.fit(x_train, y_train)
Out[5]:
DecisionTreeClassifier()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
Parameters
criterion  'gini'
splitter  'best'
max_depth  None
min_samples_split  2
min_samples_leaf  1
min_weight_fraction_leaf  0.0
max_features  None
random_state  None
max_leaf_nodes  None
min_impurity_decrease  0.0
class_weight  None
ccp_alpha  0.0
monotonic_cst  None
In [6]:
pred = classifier.predict(x_test)
In [7]:
from sklearn.metrics import accuracy_score, classification_report
accuracy_score(y_test, pred)
Out[7]:
0.9991397773954567
In [8]:
targets = ['0', '1']
print(classification_report(y_test, pred, target_names = targets))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00     56865
           1       0.77      0.71      0.74        97

    accuracy                           1.00     56962
   macro avg       0.88      0.86      0.87     56962
weighted avg       1.00      1.00      1.00     56962
In [9]:
legit = data[data['target'] == 0]
fraud = data[data['target'] == 1]
In [10]:
legit.shape
Out[10]:
(284315, 31)
In [11]:
fraud.shape
Out[11]:
(492, 31)
In [12]:
fraud_sample = fraud.sample(n = 284315, replace = True)
fraud_sample.shape
Out[12]:
(284315, 31)
In [13]:
new_dataset = pd.concat([legit, fraud_sample], axis = 0)
new_dataset['target'].value_counts()
Out[13]:
target
0    284315
1    284315
Name: count, dtype: int64
In [14]:
x = new_dataset.drop(['target'], axis = 1)
y = new_dataset['target']
In [15]:
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2)
classifier = DecisionTreeClassifier()
classifier.fit(x_train, y_train)
Out[15]:
DecisionTreeClassifier()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
Parameters
criterion  'gini'
splitter  'best'
max_depth  None
min_samples_split  2
min_samples_leaf  1
min_weight_fraction_leaf  0.0
max_features  None
random_state  None
max_leaf_nodes  None
min_impurity_decrease  0.0
class_weight  None
ccp_alpha  0.0
monotonic_cst  None
In [16]:
y_pred = classifier.predict(x_test)
In [17]:
accuracy_score(y_test, y_pred)
Out[17]:
0.9997362080790673
In [18]:
targets = ['0', '1']
print(classification_report(y_test, y_pred, target_names = targets))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00     56715
           1       1.00      1.00      1.00     57011

    accuracy                           1.00    113726
   macro avg       1.00      1.00      1.00    113726
weighted avg       1.00      1.00      1.00    113726
In [ ]: