1/11/25, 6:16 PM TP4_ISI_KEF_24_25.

ipynb - Colab

keyboard_arrow_down Imports
# Mount Drive
from google.colab import drive
drive.mount('/content/drive')

Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).

import matplotlib.pyplot as plt

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.compose import make_column_selector, make_column_transformer
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import accuracy_score, recall_score, precision_score, \
f1_score, classification_report, confusion_matrix
from sklearn.metrics import ConfusionMatrixDisplay
from sklearn import metrics

import sklearn
print(sklearn.__version__)

1.2.2

from sklearn.metrics import RocCurveDisplay

Here is the link for where the data is found: https://www.kaggle.com/mlg-ulb/creditcardfraud

This dataset is on credit card fraud from kaggle.

# Load in Data
df = pd.read_csv('/content/drive/MyDrive/datasets/creditcard.csv')

df.head()

Time V1 V2 V3 V4 V5 V6 V7 V8 V9 ... V21 V22 V23

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

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

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

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

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

5 rows × 31 columns

# Look at info from data

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 284807 entries, 0 to 284806
Data columns (total 31 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Time 284807 non-null float64
1 V1 284807 non-null float64
2 V2 284807 non-null float64
3 V3 284807 non-null float64
4 V4 284807 non-null float64
5 V5 284807 non-null float64
6 V6 284807 non-null float64
7 V7 284807 non-null float64
8 V8 284807 non-null float64
9 V9 284807 non-null float64
10 V10 284807 non-null float64
https://colab.research.google.com/drive/1ewnFbr_xMraYUy3Hri4N_6QUsbjypW-b#scrollTo=9SK9D3ac-N8U&printMode=true 1/6
1/11/25, 6:16 PM TP4_ISI_KEF_24_25.ipynb - Colab
11 V11 284807 non-null float64
12 V12 284807 non-null float64
13 V13 284807 non-null float64
14 V14 284807 non-null float64
15 V15 284807 non-null float64
16 V16 284807 non-null float64
17 V17 284807 non-null float64
18 V18 284807 non-null float64
19 V19 284807 non-null float64
20 V20 284807 non-null float64
21 V21 284807 non-null float64
22 V22 284807 non-null float64
23 V23 284807 non-null float64
24 V24 284807 non-null float64
25 V25 284807 non-null float64
26 V26 284807 non-null float64
27 V27 284807 non-null float64
28 V28 284807 non-null float64
29 Amount 284807 non-null float64
30 Class 284807 non-null int64
dtypes: float64(30), int64(1)
memory usage: 67.4 MB

# Check for duplicates

df.duplicated().sum()

1081

df.drop_duplicates(inplace=True)

df.duplicated().sum()

# Check class balance numbers

df['Class'].value_counts()

0 283253
1 473
Name: Class, dtype: int64

# Check class balance percentages

df['Class'].value_counts(normalize=True)

0 0.998333
1 0.001667
Name: Class, dtype: float64

# Define X features and y target

X = df.drop(columns = 'Class')
y = df['Class']

# Train Test Split

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

# Instantiate standard scaler

scaler = StandardScaler()

# Define a function that takes in arguments and prints out a classification report, confusion matrix and ROC AUC
def evaluate_classification(model, X_test, y_test, cmap='Greens',
normalize='true', classes=None, figsize=(20, 5)):
test_preds = model.predict(X_test)
print(metrics.classification_report(y_test, test_preds, target_names=classes))

fig, ax = plt.subplots(ncols=3, figsize=figsize)

ConfusionMatrixDisplay.from_estimator(model, X_test, y_test, cmap=cmap,
display_labels=classes,
ax=ax[0])

ConfusionMatrixDisplay.from_estimator(model, X_test, y_test, cmap=cmap,

display_labels=classes, normalize='true',
ax=ax[1])

curve = RocCurveDisplay.from_estimator(model, X_test, y_test, ax=ax[2])

https://colab.research.google.com/drive/1ewnFbr_xMraYUy3Hri4N_6QUsbjypW-b#scrollTo=9SK9D3ac-N8U&printMode=true 2/6
1/11/25, 6:16 PM TP4_ISI_KEF_24_25.ipynb - Colab
curve.ax_.grid()
curve.ax_.plot([0,1],[0,1], ls=':')

# Evaluate function on the dummy pipe

evaluate_classification(dummy_pipe, X_test, y_test)

precision recall f1-score support

0 1.00 1.00 1.00 70814

1 0.00 0.00 0.00 118

accuracy 1.00 70932

macro avg 0.50 0.50 0.50 70932
weighted avg 1.00 1.00 1.00 70932

keyboard_arrow_down Logistic Regression Model

# Instantiate a logistic regression model
# Make a pipeline with the model
logreg = LogisticRegression()

logreg_pipe = make_pipeline(scaler, logreg)

# Fit the logistic regression pipe

logreg_pipe.fit(X_train, y_train)

▸ Pipeline
▸ StandardScaler

▸ LogisticRegression

# Look at the predictions using .predict()

preds = logreg_pipe.predict(X_train[:5])
preds

array([0, 0, 0, 0, 0])

# Take a look at the predicted probabilities using .predict_proba

probs = logreg_pipe.predict_proba(X_train[:5])
np.set_printoptions(suppress=True)
probs

array([[0.99803098, 0.00196902],
[0.99972247, 0.00027753],
[0.99972296, 0.00027704],
[0.99992753, 0.00007247],
[0.9999754 , 0.0000246 ]])

https://colab.research.google.com/drive/1ewnFbr_xMraYUy3Hri4N_6QUsbjypW-b#scrollTo=9SK9D3ac-N8U&printMode=true 3/6
1/11/25, 6:16 PM TP4_ISI_KEF_24_25.ipynb - Colab
# Evaluate the logistic regression pipe using function
evaluate_classification(logreg_pipe, X_test, y_test)

precision recall f1-score support

0 1.00 1.00 1.00 70814

1 0.84 0.59 0.70 118

accuracy 1.00 70932

macro avg 0.92 0.80 0.85 70932
weighted avg 1.00 1.00 1.00 70932

keyboard_arrow_down GridSearchCV
logreg2 = LogisticRegression()

logreg_pipe2 = make_pipeline(scaler, logreg2)

Sklearn metrics documentation for scoring Gridsearch parameter https://scikit-learn.org/stable/modules/model_evaluation.html

# Create a paramater grid for GridSearchCV and instantiate object

params = {'logisticregression__C': [1,10],
'logisticregression__penalty':['l1', 'l2'],
'logisticregression__solver':['liblinear']}

logreg_grid = GridSearchCV(logreg_pipe2, params)

logreg_grid

▸ GridSearchCV
▸ estimator: Pipeline
▸ StandardScaler

▸ LogisticRegression

# Fit gridsearch object on the X_train and y_train

logreg_grid.fit(X_train, y_train)

▸ GridSearchCV
▸ estimator: Pipeline
▸ StandardScaler

▸ LogisticRegression

# Get out the best parameters

logreg_grid.best_params_

https://colab.research.google.com/drive/1ewnFbr_xMraYUy3Hri4N_6QUsbjypW-b#scrollTo=9SK9D3ac-N8U&printMode=true 4/6
1/11/25, 6:16 PM TP4_ISI_KEF_24_25.ipynb - Colab

{'logisticregression__C': 10,
'logisticregression__penalty': 'l1',
'logisticregression__solver': 'liblinear'}

# Get out the best model

best_logreg = logreg_grid.best_estimator_

# Evaluate GridSearch Object using function

evaluate_classification(best_logreg, X_test, y_test)

precision recall f1-score support

0 1.00 1.00 1.00 70814

1 0.84 0.59 0.70 118

accuracy 1.00 70932

macro avg 0.92 0.80 0.85 70932
weighted avg 1.00 1.00 1.00 70932

keyboard_arrow_down SMOTE
from imblearn.over_sampling import SMOTE

pd.Series(y_train).value_counts()

0 212439
1 355
Name: Class, dtype: int64

smote = SMOTE(sampling_strategy = 'auto')

X_train_smote, y_train_smote = smote.fit_resample(X_train, y_train)

pd.Series(y_train_smote).value_counts()

0 212439
1 212439
Name: Class, dtype: int64

smote_logreg = LogisticRegression(max_iter=1000)
smote_logreg.fit(X_train_smote, y_train_smote)

▾ LogisticRegression
LogisticRegression(max_iter=1000)

evaluate_classification(smote_logreg, X_test, y_test)

https://colab.research.google.com/drive/1ewnFbr_xMraYUy3Hri4N_6QUsbjypW-b#scrollTo=9SK9D3ac-N8U&printMode=true 5/6
1/11/25, 6:16 PM TP4_ISI_KEF_24_25.ipynb - Colab

precision recall f1-score support

0 1.00 0.98 0.99 70814

1 0.08 0.88 0.15 118

accuracy 0.98 70932

macro avg 0.54 0.93 0.57 70932
weighted avg 1.00 0.98 0.99 70932

https://colab.research.google.com/drive/1ewnFbr_xMraYUy3Hri4N_6QUsbjypW-b#scrollTo=9SK9D3ac-N8U&printMode=true 6/6