项目实战-交易数据异常检测
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
data = pd.read_csv("creditcard.csv")
data.head()
# value_counts计算当前数据的某一列有多少个不同的属性值
count_classes = pd.value_counts(data['Class'], sort = True).sort_index()
# kind = 'bar'条形图
count_classes.plot(kind = 'bar')
plt.title("Fraud class histogram")
plt.xlabel("Class")
plt.ylabel("Frequency")
可以观察出样本分布很不规则。解决这种问题的两种方案就是:过采样,下采样 下采样:可以让0和1的数量一样少。 过采样:在1号样本的数据中进行生成,生成出的数据跟0号样本一样多。
# 预处理
from sklearn.preprocessing import StandardScaler
# reshape(-1, 1)这个-1是让编译器自动计算;这里不能直接reshape,应该是.values.reshape
data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1, 1))
# 去掉这两列
data = data.drop(['Time','Amount'],axis=1)
data.head()
# 下采样
# 数据选择
X = data.ix[:, data.columns != 'Class']
y = data.ix[:, data.columns == 'Class']
# Number of data points in the minority class
number_records_fraud = len(data[data.Class == 1])
fraud_indices = np.array(data[data.Class == 1].index)
# Picking the indices of the normal classes
normal_indices = data[data.Class == 0].index
# Out of the indices we picked, randomly select "x" number (number_records_fraud)
random_normal_indices = np.random.choice(normal_indices, number_records_fraud, replace = False)
random_normal_indices = np.array(random_normal_indices)
# Appending the 2 indices
under_sample_indices = np.concatenate([fraud_indices,random_normal_indices])
# Under sample dataset
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))
Percentage of normal transactions: 0.5
Percentage of fraud transactions: 0.5
Total number of transactions in resampled data: 984
# 交叉验证
#from sklearn.cross_validation import train_test_split
# sklearn.cross_validation这个包已经不再使用了,被划分到model_selection这个包做交叉验证
from sklearn.model_selection import train_test_split
# Whole dataset
# 切分完整的数据集
# test_size指的是切分的比例,30%是测试集,70%是训练集;
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))
# 切分下采样数据集
# Undersampled dataset
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))
Number transactions train dataset: 199364
Number transactions test dataset: 85443
Total number of transactions: 284807
Number transactions train dataset: 688
Number transactions test dataset: 296
Total number of transactions: 984
#Recall = TP/(TP+FN)
# Recall召回率、查全率,检测模型的效果
from sklearn.linear_model import LogisticRegression
# 第一处报错修改成model_selection
from sklearn.model_selection import KFold, cross_val_score
from sklearn.metrics import confusion_matrix,recall_score,classification_report
def printing_Kfold_scores(x_train_data,y_train_data):
#第二处报错修改,去掉len(y_train_data)这个参数
fold = KFold(5,shuffle=False)
# Different C parameters
# 惩罚参数
c_param_range = [0.01,0.1,1,10,100]
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 = []
# 第三处报错,enumerate(fold,start=1)修改成如下
for iteration, indices in enumerate(fold.split(y_train_data),start=1):
# Call the logistic regression model with a certain C parameter
# 第五处报错,添加solver='liblinear'
lr = LogisticRegression(C = c_param, penalty = 'l1',solver='liblinear')
# 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('')
# 第四处报错,在.idxmax()的前面添加.astype("float64")
best_c = results_table.loc[results_table['Mean recall score'].astype("float64").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)
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.9315068493150684
Iteration 2 : recall score = 0.9178082191780822
Iteration 3 : recall score = 0.9830508474576272
Iteration 4 : recall score = 0.9594594594594594
Iteration 5 : recall score = 0.9545454545454546
Mean recall score 0.9492741659911385
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.8493150684931506
Iteration 2 : recall score = 0.863013698630137
Iteration 3 : recall score = 0.9152542372881356
Iteration 4 : recall score = 0.9324324324324325
Iteration 5 : recall score = 0.8939393939393939
Mean recall score 0.89079096615665
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.863013698630137
Iteration 2 : recall score = 0.8904109589041096
Iteration 3 : recall score = 0.9661016949152542
Iteration 4 : recall score = 0.9324324324324325
Iteration 5 : recall score = 0.9090909090909091
Mean recall score 0.9122099387945685
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.8767123287671232
Iteration 2 : recall score = 0.8904109589041096
Iteration 3 : recall score = 0.9661016949152542
Iteration 4 : recall score = 0.9459459459459459
Iteration 5 : recall score = 0.9393939393939394
Mean recall score 0.9237129735852745
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.8767123287671232
Iteration 2 : recall score = 0.8904109589041096
Iteration 3 : recall score = 0.9661016949152542
Iteration 4 : recall score = 0.9459459459459459
Iteration 5 : recall score = 0.9242424242424242
Mean recall score 0.9206826705549714
*********************************************************************************
Best model to choose from cross validation is with C parameter = 0.01
*********************************************************************************
# 混淆矩阵
def plot_confusion_matrix(cm, classes,
title='Confusion matrix',
cmap=plt.cm.Blues):
"""
This function prints and plots the confusion matrix.
"""
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=0)
plt.yticks(tick_marks, classes)
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(j, i, cm[i, j],
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')
# 下采样数据集
import itertools
lr = LogisticRegression(C = best_c, penalty = 'l1',solver='liblinear')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample = lr.predict(X_test_undersample.values)
# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test_undersample,y_pred_undersample)
np.set_printoptions(precision=2)
print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()
Recall metric in the testing dataset: 0.9251700680272109
# 全部数据集
lr = LogisticRegression(C = best_c, penalty = 'l1',solver='liblinear')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred = lr.predict(X_test.values)
# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test,y_pred)
np.set_printoptions(precision=2)
print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()
Recall metric in the testing dataset: 0.9115646258503401
# 如果原始数据没有采样操作,直接用最开始的样本不均衡的数据,实验的模型效果很差
best_c = printing_Kfold_scores(X_train,y_train)
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.4925373134328358
Iteration 2 : recall score = 0.6027397260273972
Iteration 3 : recall score = 0.6833333333333333
Iteration 4 : recall score = 0.5692307692307692
Iteration 5 : recall score = 0.45
Mean recall score 0.5595682284048672
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.5671641791044776
Iteration 2 : recall score = 0.6164383561643836
Iteration 3 : recall score = 0.6833333333333333
Iteration 4 : recall score = 0.5846153846153846
Iteration 5 : recall score = 0.525
Mean recall score 0.5953102506435158
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.5522388059701493
Iteration 2 : recall score = 0.6164383561643836
Iteration 3 : recall score = 0.7166666666666667
Iteration 4 : recall score = 0.6153846153846154
Iteration 5 : recall score = 0.5625
Mean recall score 0.612645688837163
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.5522388059701493
Iteration 2 : recall score = 0.6164383561643836
Iteration 3 : recall score = 0.7333333333333333
Iteration 4 : recall score = 0.6153846153846154
Iteration 5 : recall score = 0.575
Mean recall score 0.6184790221704963
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.5522388059701493
Iteration 2 : recall score = 0.6164383561643836
Iteration 3 : recall score = 0.7333333333333333
Iteration 4 : recall score = 0.6153846153846154
Iteration 5 : recall score = 0.575
Mean recall score 0.6184790221704963
*********************************************************************************
Best model to choose from cross validation is with C parameter = 10.0
*********************************************************************************
# 观察阈值对结果的影响
lr = LogisticRegression(C = 0.01, penalty = 'l1',solver='liblinear')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample_proba = lr.predict_proba(X_test_undersample.values)
thresholds = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]
plt.figure(figsize=(10,10))
j = 1
for i in thresholds:
y_test_predictions_high_recall = y_pred_undersample_proba[:,1] > i
plt.subplot(3,3,j)
j += 1
# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test_undersample,y_test_predictions_high_recall)
np.set_printoptions(precision=2)
print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Threshold >= %s'%i)
Recall metric in the testing dataset: 1.0
Recall metric in the testing dataset: 1.0
Recall metric in the testing dataset: 1.0
Recall metric in the testing dataset: 0.9727891156462585
Recall metric in the testing dataset: 0.9251700680272109
Recall metric in the testing dataset: 0.8639455782312925
Recall metric in the testing dataset: 0.8163265306122449
Recall metric in the testing dataset: 0.7687074829931972
Recall metric in the testing dataset: 0.5782312925170068
# SMOTE样本生成策略(过采样)
import pandas as pd
# 这里会报错,需要安装,执行命令pip install imblearn
from imblearn.over_sampling import SMOTE
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split
credit_cards=pd.read_csv('creditcard.csv')
columns=credit_cards.columns
# The labels are in the last column ('Class'). Simply remove it to obtain features columns
features_columns=columns.delete(len(columns)-1)
features=credit_cards[features_columns]
labels=credit_cards['Class']
features_train, features_test, labels_train, labels_test = train_test_split(features,
labels,
test_size=0.2,
random_state=0)
oversampler=SMOTE(random_state=0)
# 会出错,将fit_sample改为fit_resample
# 传入训练集的x,y,自动平衡
os_features,os_labels=oversampler.fit_resample(features_train,labels_train)
len(os_labels[os_labels==1])
227454
os_features = pd.DataFrame(os_features)
os_labels = pd.DataFrame(os_labels)
best_c = printing_Kfold_scores(os_features,os_labels)
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9688170853159235
Iteration 4 : recall score = 0.9578483419615085
Iteration 5 : recall score = 0.9585407942317626
Mean recall score 0.9340531288519237
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9704105344694036
Iteration 4 : recall score = 0.9596728987370989
Iteration 5 : recall score = 0.9604752640661237
Mean recall score 0.93512362400461
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9704769281841319
Iteration 4 : recall score = 0.9600356118310417
Iteration 5 : recall score = 0.9607940119365582
Mean recall score 0.9352731949404312
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9705654531371031
Iteration 4 : recall score = 0.9541332805750651
Iteration 5 : recall score = 0.9607170727954188
Mean recall score 0.9340950458516023
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9705433218988603
Iteration 4 : recall score = 0.9585627768435168
Iteration 5 : recall score = 0.9608599597718205
Mean recall score 0.9350050962529244
*********************************************************************************
Best model to choose from cross validation is with C parameter = 1.0
*********************************************************************************
lr = LogisticRegression(C = best_c, penalty = 'l1',solver='liblinear')
lr.fit(os_features,os_labels.values.ravel())
y_pred = lr.predict(features_test.values)
# Compute confusion matrix
cnf_matrix = confusion_matrix(labels_test,y_pred)
np.set_printoptions(precision=2)
print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()
Recall metric in the testing dataset: 0.9108910891089109
问题解决
做这个项目的时候遇到几个问题,以下是解决方案
ModuleNotFoundError: No module named 'sklearn.cross_validation’
https://blog.csdn.net/weixin_40283816/article/details/83242777
TypeError: init() got multiple values for argument 'shuffle’
https://blog.csdn.net/weixin_40283816/article/details/83242777
TypeError:‘KFold’ object is not iterable
https://blog.csdn.net/weixin_40283816/article/details/83242777
ValueError: Solver lbfgs supports only ‘l2’ or ‘none’ penalties, got l1 pena https://www.cnblogs.com/peijz/p/13611602.html
TypeError: reduction operation ‘argmax’ not allowed for this dtype
https://www.cnblogs.com/hum0ro/p/9696418.html