shayaf84

!ls "/content/drive/My Drive/Credit_Fraud"
data = pd.read_csv("/content/drive/My Drive/Credit_Fraud/creditcard.csv")

shayaf84

print(data.head(),"\n"*3)

data.shape

shayaf84

sns.countplot(x=data['Class'])
data["Class"].value_counts()

shayaf84

# Adjusting figuresize, and fontsize
plt.rcParams["figure.figsize"] = "8,6"
font = {'size': 12}
plt.rc('font', **font)

# Adding titles to the plots and axes
plt.title("Distribution of Amount over Both Classes")
plt.xlabel("Amount")
plt.ylabel("Class")

shayaf84

# Adjusting figuresize, and fontsize
plt.rcParams["figure.figsize"] = "8,6"
font = {'size': 12}
plt.rc('font', **font)

# Adding titles to the plots and axes
plt.title("Distribution of Time over Both Classes")
plt.xlabel("Time")
plt.ylabel("Class")

shayaf84

correlation = data.corr()
fig = plt.subplots(figsize=(15,15)) 
sns.heatmap(correlation, vmax= 1 )

shayaf84

X = data.drop(["Class","Time"],axis=1).values 
y = data["Class"].values 


X_train_Before, X_test, y_train_Before, y_test = train_test_split(
    X, y, test_size = 0.3, 
    random_state = 42)

shayaf84

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
for i in X_train_Before:
    scaler = StandardScaler()
    X_train_Before[i] = scaler.fit_transform(X_train_Before[i].values.reshape(-1,1))
    X_test[i] = scaler.transform(X_test[i].values.reshape(-1,1))

shayaf84

borderlineSMOTE = BorderlineSMOTE(k_neighbors = 10, random_state = 42)
X_train, y_train = borderlineSMOTE.fit_resample(X_train_Before,y_train_Before)

shayaf84

#Random Forest Classifier

rf = RandomForestClassifier(n_estimators = 15,random_state=42)

rf.fit(X_train, y_train)

y_pred = rf.predict(X_test)


precision = precision_score(y_test, y_pred)