ML Assignment 4

Uploaded by

bhargavianjaneya

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

5 views7 pages

ML Assignment 4

Uploaded by

bhargavianjaneya

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

You are on page 1/ 7

# Import necessary libraries

import pandas as pd
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.metrics import confusion_matrix, classification_report,
accuracy_score

# 1. Load the dataset

credit_data = pd.read_csv("C:\\Users\\bharg\\Downloads\\
creditcardfraud.csv")

# 2. Preprocess the data

# Drop the Time column
credit_data.drop("Time", axis=1, inplace=True)

# Scale the Amount column using a standard scaler

scaler = StandardScaler()
credit_data['Amount'] = scaler.fit_transform(credit_data[['Amount']])

# 3. Split the data into training and test sets

X = credit_data.drop("Class", axis=1)
y = credit_data["Class"]
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.2, random_state=42)

# 4. Train a logistic regression model on the training set

logistic_model = LogisticRegression()
logistic_model.fit(X_train, y_train)

LogisticRegression()

# 5. Evaluate the logistic regression model's performance on the test

set
y_pred_logistic = logistic_model.predict(X_test)
print("Logistic Regression Metrics:")
print("Confusion Matrix:\n", confusion_matrix(y_test,
y_pred_logistic))
print("Classification Report:\n", classification_report(y_test,
y_pred_logistic))
print("Accuracy Score:", accuracy_score(y_test, y_pred_logistic))

Logistic Regression Metrics:

Confusion Matrix:
[[59 3]
[ 4 54]]
Classification Report:
precision recall f1-score support

0 0.94 0.95 0.94 62

1 0.95 0.93 0.94 58

accuracy 0.94 120

macro avg 0.94 0.94 0.94 120
weighted avg 0.94 0.94 0.94 120

Accuracy Score: 0.9416666666666667

# 6. Train an SVM model on the training set

svm_model = SVC()
svm_model.fit(X_train, y_train)

SVC()

# 7. Evaluate the SVM model's performance on the test set

y_pred_svm = svm_model.predict(X_test)
print("\nSVM Metrics:")
print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred_svm))
print("Classification Report:\n", classification_report(y_test,
y_pred_svm))
print("Accuracy Score:", accuracy_score(y_test, y_pred_svm))

SVM Metrics:
Confusion Matrix:
[[62 0]
[ 6 52]]
Classification Report:
precision recall f1-score support

0 0.91 1.00 0.95 62

1 1.00 0.90 0.95 58

accuracy 0.95 120

macro avg 0.96 0.95 0.95 120
weighted avg 0.95 0.95 0.95 120

Accuracy Score: 0.95

# 8. Tune hyperparameters using grid search cross-validation for both

models
param_grid_logistic = {'C': [0.001, 0.01, 0.1, 1, 10, 100]}
grid_logistic = GridSearchCV(LogisticRegression(),
param_grid_logistic, cv=5, scoring='accuracy')
grid_logistic.fit(X_train, y_train)

param_grid_svm = {'C': [0.1, 1, 10], 'gamma': [0.1, 1, 10]}

grid_svm = GridSearchCV(SVC(), param_grid_svm, cv=5,
scoring='accuracy')
grid_svm.fit(X_train, y_train)

C:\Users\bharg\anaconda3\Lib\site-packages\sklearn\linear_model\
_logistic.py:460: ConvergenceWarning: lbfgs failed to converge
(status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.