import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# importing data

transaction_dataset= pd.read_csv("/content/drive/MyDrive/google_collab/creditcard.csv")
transaction_dataset.head(10)

legit = transaction_dataset[transaction_dataset.Class == 0]
fraud = transaction_dataset[transaction_dataset.Class == 1]

# comparing the values for both transaction 
transaction_dataset.groupby('Class').mean()

plt.figure(figsize = (20,11))
# heatmap size in ration 16:9

sns.heatmap(new_transaction_dataset2.corr(), annot = True, cmap = 'coolwarm')
# heatmap parameters

plt.title("Heatmap for correlation matrix for credit card data ", fontsize = 22)
plt.show()

X = new_transaction_dataset2.drop(columns = 'Class', axis = 1)
Y = new_transaction_dataset2['Class']

X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size = 0.2, stratify = Y, random_state = 2)

model = LogisticRegression()
model.fit(X_train, Y_train)

print("\nAccuracy on Training data ",traning_data_accuracy,"\n")
print("Accuracy on Training data ",test_data_accuracy)