Credit_Card_Fraud_Detection

-- coding: utf-8 --

"""Final_project_of_Credit_Card_Fraud_Detection(1).ipynb

Automatically generated by Colaboratory.

Original file is located at https://colab.research.google.com/drive/1PSHcV_bp0wcT0Kl_f2n5QwtlOZj3M5BV """

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

data=pd.read_csv('/content/data4.csv')

data.head()

data.shape

data.isnull().sum().sum()

data.keys()

data.info()

data=data.drop(['Unnamed: 0','nameOrig','nameDest'],axis=1)

data.shape

data['isFraud'].value_counts()

plt.pie(data['isFraud'].value_counts(),labels=['Not_Fraud','Fraud'],autopct='%0.2f%%') plt.show()

#sns.countplot('isFraud',data=data) sns.countplot(data=data, x="type", hue="isFraud") plt.show()

plt.figure(figsize=(6,8)) sns.countplot(data=data, x="isFraud", hue="type") plt.show()

data.tail()

data['type'].value_counts()

dict1={'CASH_OUT':0,'TRANSFER':1,'PAYMENT':2,'CASH_IN':3,'DEBIT':4}

data['type']=data['type'].map(dict1)

data.head()

X=data.drop('isFraud',axis=1)

X

y=data['isFraud']

y

from sklearn.model_selection import train_test_split

X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.30,random_state=0)

print(X_train.shape) print(X_test.shape) print(y_train.shape) print(y_test.shape)

from sklearn.preprocessing import StandardScaler

sc=StandardScaler()

X_train_sc=sc.fit_transform(X_train) X_test_sc=sc.transform(X_test)

X_train_sc

X_test_sc

from sklearn.linear_model import LogisticRegression

model1=LogisticRegression()

model1.fit(X_train_sc,y_train)

y_pred1=model1.predict(X_test_sc)

from sklearn.metrics import classification_report

print(classification_report(y_test,y_pred1))

from sklearn.naive_bayes import GaussianNB

model2=GaussianNB()

model2.fit(X_train_sc,y_train)

y_pred2=model2.predict(X_test_sc)

print(classification_report(y_test,y_pred2))

from sklearn.neighbors import KNeighborsClassifier

model3=KNeighborsClassifier()

model3.fit(X_train_sc,y_train)

y_pred3=model3.predict(X_test_sc)

print(classification_report(y_test,y_pred3))

from sklearn.tree import DecisionTreeClassifier

model4=DecisionTreeClassifier()

model4.fit(X_train_sc,y_train)

y_pred4=model4.predict(X_test_sc)

print(classification_report(y_test,y_pred4))

from sklearn import tree

plt.figure(figsize=(10,10)) tree.plot_tree(model4,filled=True) plt.show()

from sklearn.ensemble import RandomForestClassifier,AdaBoostClassifier

model5=RandomForestClassifier()

model5.fit(X_train_sc,y_train)

y_pred5=model5.predict(X_test_sc)

print(classification_report(y_test,y_pred5))

model6=AdaBoostClassifier()

model6.fit(X_train_sc,y_train)

y_pred6=model6.predict(X_test_sc)

print(classification_report(y_test,y_pred6))

model5.predict([[239,2,5178.72,400705.00,395526.28,0.00,0.00]])

model5.predict([[369,0,89596.79,89596.79,0.0,0.00,89596.79]])