undersampling.py

# Shuffle the Dataset.
shuffled_df = credit_df.sample(frac=1,random_state=4)

# Put all the fraud class in a separate dataset.
fraud_df = shuffled_df.loc[shuffled_df['Class'] == 1]

#Randomly select 492 observations from the non-fraud (majority class)
non_fraud_df = shuffled_df.loc[shuffled_df['Class'] == 0].sample(n=492,random_state=42)

# Concatenate both dataframes again
normalized_df = pd.concat([fraud_df, non_fraud_df])

#plot the dataset after the undersampling
plt.figure(figsize=(8, 8))
sns.countplot('Class', data=normalized_df)
plt.title('Balanced Classes')
plt.show()