python信用卡欺诈_有关信用卡欺诈的那个例子

#信用卡欺诈检测

import pandas as pd

import matplotlib.pyplot as plt

import numpy as np

#%matplotlib inline 魔法方法ipython中用

data = pd.read_csv(r"D:\储存\学习\唐宇迪python\01、python数据分析与机器学习实战\课程资料\唐宇迪-机器学习课程资料\机器学习算法配套案例实战\逻辑回归-信用卡欺诈检测\creditcard.csv")

count_classes = pd.value_counts(data['Class'], sort = True).sort_index()

count_classes.plot(kind = 'bar')                #建立柱状图

plt.title("Fraud class histogram")

plt.xlabel("Class")

plt.ylabel("Frequency")

from sklearn.preprocessing import StandardScaler

data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1, 1))

data = data.drop(['Time','Amount'],axis=1)

X = data.ix[:, data.columns != 'Class']

y = data.ix[:, data.columns == 'Class']

number_records_fraud = len(data[data.Class == 1])

fraud_indices = np.array(data[data.Class == 1].index)

normal_indices = data[data.Class == 0].index

random_normal_indices = np.random.choice(normal_indices, number_records_fraud, replace = False)

random_normal_indices = np.array(random_normal_indices)

under_sample_indices = np.concatenate([fraud_indices,random_normal_indices])

under_sample_data = data.iloc[under_sample_indices,:]

X_undersample = under_sample_data.ix[:, under_sample_data.columns != 'Class']

y_undersample = under_sample_data.ix[:, under_sample_data.columns == 'Class']

# Showing ratio

print("Percentage of normal transactions: ", len(under_sample_data[under_sample_data.Class == 0])/len(under_sample_data))

print("Percentage of fraud transactions: ", len(under_sample_data[under_sample_data.Class == 1])/len(under_sample_data))

print("Total number of transactions in resampled data: ", len(under_sample_data))

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size = 0.3, random_state = 0)

print("Number transactions train dataset: ", len(X_train))

print("Number transactions test dataset: ", len(X_test))

print("Total number of transactions: ", len(X_train)+len(X_test))

# 下采样

X_train_undersample, X_test_undersample, y_train_undersample, y_test_undersample = train_test_split(X_undersample,y_undersample,test_size = 0.3,random_state = 0)

print("")

print("Number transactions train dataset: ", len(X_train_undersample))

print("Number transactions test dataset: ", len(X_test_undersample))

print("Total number of transactions: ", len(X_train_undersample)+len(X_test_undersample))

#Recall = TP/(TP+FN)

from sklearn.linear_model import LogisticRegression

from sklearn.model_selection import KFold

from sklearn.model_selection import cross_val_score

from sklearn.metrics import confusion_matrix,recall_score,classification_report

#交叉验证

def printing_Kfold_scores(x_train_data,y_train_data):

fold = KFold(5,shuffle=False)

#    fold.get_n_splits(len(y_train_data))

# 定义不同正则化惩罚力度

c_param_range = [0.01,0.1,1,10,100]

#可视化显示

results_table = pd.DataFrame(index = range(len(c_param_range),2), columns = ['C_parameter','Mean recall score'])

results_table['C_parameter'] = c_param_range

# the k-fold will give 2 lists: train_indices = indices[0], test_indices = indices[1]

j = 0

for c_param in c_param_range:

print('-------------------------------------------')

print('C parameter: ', c_param)

print('-------------------------------------------')

print('')

recall_accs = []

for iteration, indices in fold.split(X):

lr = LogisticRegression(C = c_param, penalty = 'l1')

# Use the training data to fit the model. In this case, we use the portion of the fold to train the model

# with indices[0]. We then predict on the portion assigned as the 'test cross validation' with indices[1]

lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())

# Predict values using the test indices in the training data

y_pred_undersample = lr.predict(x_train_data.iloc[indices[1],:].values)

# Calculate the recall score and append it to a list for recall scores representing the current c_parameter

recall_acc = recall_score(y_train_data.iloc[indices[1],:].values,y_pred_undersample)

recall_accs.append(recall_acc)

print('Iteration ', iteration,': recall score = ', recall_acc)

# The mean value of those recall scores is the metric we want to save and get hold of.

results_table.ix[j,'Mean recall score'] = np.mean(recall_accs)

j += 1

print('')

print('Mean recall score ', np.mean(recall_accs))

print('')

best_c = results_table.loc[results_table['Mean recall score'].idxmax()]['C_parameter']

# Finally, we can check which C parameter is the best amongst the chosen.

print('*********************************************************************************')

print('Best model to choose from cross validation is with C parameter = ', best_c)

print('*********************************************************************************')

return best_c

best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample)

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值