In [1]:
!pip install imbalanced-learn

Requirement already satisfied: imbalanced-learn in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (0.14.0)
Requirement already satisfied: numpy<3,>=1.25.2 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from imbalanced-learn) (2.3.2)
Requirement already satisfied: scipy<2,>=1.11.4 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from imbalanced-learn) (1.16.1)
Requirement already satisfied: scikit-learn<2,>=1.4.2 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from imbalanced-learn) (1.7.1)
Requirement already satisfied: joblib<2,>=1.2.0 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from imbalanced-learn) (1.5.1)
Requirement already satisfied: threadpoolctl<4,>=2.0.0 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from imbalanced-learn) (3.6.0)
In [2]:
import pandas as pd
import numpy as np
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report
from imblearn.over_sampling import SMOTE
In [3]:
dataset = pd.read_csv("dataset/creditcard.xls")
dataset.head()
Out[3]:
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 [4]:
x = dataset.drop(['target'], axis=1)
y = dataset['target']
In [5]:
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2)
In [6]:
classifier = DecisionTreeClassifier()
classifier.fit(x_train, y_train)
Out[6]:
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 [7]:
y_pred = classifier.predict(x_test)
accuracy_score(y_test, y_pred)
Out[7]:
0.9992275552122467
In [8]:
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     56879
           1       0.73      0.73      0.73        83

    accuracy                           1.00     56962
   macro avg       0.87      0.87      0.87     56962
weighted avg       1.00      1.00      1.00     56962
In [9]:
from sklearn.metrics import confusion_matrix, precision_score, recall_score
cm = confusion_matrix(y_test, y_pred)
print("Confusion Matrix:\n", cm)
tn, fp, fn, tp = cm.ravel()
print(f"True Negatives: {tn}")
print(f"False Negatives: {fp}")
print(f"False Positives: {fn}")
print(f"True Positives: {tp}")

precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
print(f"Precision: {precision:.4f}")
print(f"Recall: {recall:.4f}")

Confusion Matrix:
 [[56857    22]
 [   22    61]]
True Negatives: 56857
False Negatives: 22
False Positives: 22
True Positives: 61
Precision: 0.7349
Recall: 0.7349