信用卡欺诈检测分析案例

Posted 2020-10-15

data = pd.read_csv("creditcard.csv")
data.head()

count_classes = pd.value_counts(data[‘class‘],sort = True).sort_index() # value_count:计算数值的个数
count_classes.plot(kind = ‘bar‘) # 绘制条形图
plt.title("Fraud class hiistogram")
plt.xlabel("class")
plt.ylabel("Frequency")

样本不平衡解决方案
from sklearn.preprocessing import StandardScaler

data[‘normAmount‘] = StandardScaler().fit_transform(data[‘Amount‘].reshape(-1,1)) # fit_transform对数据进行变换，amount数据值较大，机器算法会把它的数值看得比较
# 重要，所以要进行转换，让它的每一列数据的重要程度看起来一样
# [2,3].reshape(-1,2),   -1:2*3/2    1:变成列向量
data = data.drop([‘Time‘,‘Amount‘],axis=1) # 删除Time,Amount这两列数据
data.head()

下采样策略：
X = data.ix[:,data.columns != ‘Class‘]
y = data.ix[:,data.columns == ‘Class‘]

number_records_fraud = len(data[data.Class == 1]) # class=1的样本函数
fraud_indices = np.array(data[data.Class == 1].index) # 样本等于1的索引值

normal_indices = data[data.Class == 0].index # 样本等于0的索引值

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

under_sample_indices = np.concatenate([fraud_indices,random_normal_indices]) # Appending the 2 indices

under_sample_data = data.iloc[under_sample_indices,:] # Under sample dataset

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

交叉验证
from sklearn.cross_validation import train_test_split
# While dataset
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.3,random_state = 0) # random_state 
# 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)

模型评估方法
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import KFold,cross_val_score
from sklearn.metrics import confusion_matrix,reclll_score,classification_report

def printing_Kfold_scores(x_train_data,y_train_data):
  fold = KFold(len(y_train_data),5,shuffle=False) # 将原始的数据进行切分
  
  c_param_range = [0.01,0.1,1,10,100] # 惩罚力度参数
  results_table = pd.DataFrame(index = range(len(c_param_range),2),columns = ["C_parameter‘，‘Mean recall s’]
  results_table[‘C_parameter‘] = c_param_range
  
  j = 0
  for c_param in c_param_range:
    recall_accs = []
    for iteration,indices in enumerate(fold,start=1):
      lr = LogisticRegression(C=c_param,penalty=‘l1‘)# 建立逻辑回归模型,l1是w的绝对值惩罚，l2是w2的惩罚
      lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())
      y_pred_undersample = lr.predict(x_train_data.iloc[indices[1],:].values)
      recall_acc = recall_score(y_train_data.iloc[indices[1],:].values,y_pred_undersample) # 召回率
      recall_accs.append(recall_acc)
      print("Iteration",iteration,‘:recall score = ‘,recall_acc)
    result_table.ix[j,‘Mean recall score‘] = np.mean(recall_accs)
    j += 1
    print(‘Mean recall score‘,np.mean(recall_accs))

  best_c = results_table.loc[results_table[‘Mean recall score‘].idxmax()][‘C_parameter‘]
  print(“Best model”,best_c)
  return best_c

混淆矩阵

逻辑回归阈值对结果的影响
lr = LogisticRegression(C = 0.01,penalty=‘l1‘)
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_predicttions_high_recall = y_pred_undersample_proba[:,1]> i
  plt.subplot(3,3,j)
  j += 1
  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]))
  class_names = [0,1]
  plot_confusion_matrix(cnf_matrix,classes=class_names,title="Threshold >= %s‘%i)
  

SMOTE样本生成策略（过采样）
import pandas as pd
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
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)
os_features,os_labels = oversampler.fit_sample(features_train,labels_train)

len(os_labels[os_labels==1])

os_features = pd.DataFrame(os_features)
os_labels = pd.DataFrame(os_labels)
best_c = printing_Kfold_scores(os_features,os_labels)

lr = LogisticRegression(C = best_c,penalty=‘l1‘)
lr.fit(os_features,os_labels.values.ravel())
y_pred = lr.predict(features_test.values)

cnf_matrix = confusiion_matrix(labels_test,y_pred)
np.set_printopotions(precision=2)
print(‘recall metric:‘,cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
class_names[0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix,classes=class_names,title=‘Confusion matrix‘)
plt.show()