sgsg704

df_card = pd.read_csv("https://cainvas-static.s3.amazonaws.com/media/user_data/hrithikgupta/creditcard.csv")
df_card.head(10)

sgsg704

print(df_card.shape)
print(df_card.size)

sgsg704

df_card.info()

sgsg704

df_card.drop(columns = ['Time'], inplace= True)

# Standardizing the amount column
from sklearn import preprocessing
scaler = preprocessing.StandardScaler()
#standard scaling
df_card['Stand_Amount'] = scaler.fit_transform(df_card['Amount'].values.reshape (-1,1))

#removing Amount
df = df_card.drop("Amount", axis=1)

sgsg704

sns.countplot(x="Class", data=df_card)

sgsg704

import imblearn
from imblearn.under_sampling import RandomUnderSampler 

undersample = RandomUnderSampler(sampling_strategy=0.5)
cols = df.columns.tolist()
cols = [c for c in cols if c not in ["Class"]]
target = "Class"

sgsg704

# Define X and Y
X = df[cols]
Y = df[target]

# Undersampling
X_sample, Y_sample = undersample.fit_resample(X, Y)
test = pd.DataFrame(Y_sample, columns = ['Class'])

sgsg704

#visualizing undersampling results
fig, axs = plt.subplots(ncols=2, figsize=(13,4.5))
sns.countplot(x="Class", data=df, ax=axs[0])
sns.countplot(x="Class", data=test, ax=axs[1])

fig.suptitle("Class repartition before and after undersampling")
a1=fig.axes[0]
a1.set_title("Before")
a2=fig.axes[1]
a2.set_title("After")

sgsg704

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X_sample, Y_sample, test_size=0.3, random_state=1)

print(len(X_train))
print(len(y_train))
print(len(X_test))
print(len(y_test))

sgsg704

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import Dense
from tensorflow.keras import layers
from tensorflow.keras import regularizers
from sklearn import metrics

model = Sequential()