eda.py

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# Load dataset
df = pd.read_csv('c:/card/creditcard.csv')

# Basic info
print("Dataset Shape:", df.shape)
print("\nFirst 5 rows:")
print(df.head())

# Check for missing values
print("\nMissing values:")
print(df.isnull().sum().max())

# Class distribution
print("\nClass Distribution (0: Normal, 1: Fraud):")
print(df['Class'].value_counts())
print("\nPercentage:")
print(df['Class'].value_counts(normalize=True) * 100)

# Statistics
print("\nSummary Statistics:")
print(df.describe())

# Plotting class distribution
plt.figure(figsize=(8, 6))
sns.countplot(x='Class', data=df, palette='viridis')
plt.title('Class Distribution (0: Normal, 1: Fraud)')
plt.savefig('c:/card/class_distribution.png')

# Plotting distributions of Time and Amount
plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)
sns.histplot(df['Amount'], bins=50, kde=True, color='blue')
plt.title('Transaction Amount Distribution')

plt.subplot(1, 2, 2)
sns.histplot(df['Time'], bins=50, kde=True, color='red')
plt.title('Transaction Time Distribution')
plt.savefig('c:/card/distributions.png')