信用卡欺诈检测
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np%matplotlib inlinedata = pd.read_csv('data/data48333/creditcard.csv')
data.head()
| Time | V1 | V2 | V3 | V4 | V5 | V6 | V7 | V8 | V9 | ... | V21 | V22 | V23 | V24 | V25 | V26 | V27 | V28 | Amount | Class | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.0 | -1.359807 | -0.072781 | 2.536347 | 1.378155 | -0.338321 | 0.462388 | 0.239599 | 0.098698 | 0.363787 | ... | -0.018307 | 0.277838 | -0.110474 | 0.066928 | 0.128539 | -0.189115 | 0.133558 | -0.021053 | 149.62 | 0 |
| 1 | 0.0 | 1.191857 | 0.266151 | 0.166480 | 0.448154 | 0.060018 | -0.082361 | -0.078803 | 0.085102 | -0.255425 | ... | -0.225775 | -0.638672 | 0.101288 | -0.339846 | 0.167170 | 0.125895 | -0.008983 | 0.014724 | 2.69 | 0 |
| 2 | 1.0 | -1.358354 | -1.340163 | 1.773209 | 0.379780 | -0.503198 | 1.800499 | 0.791461 | 0.247676 | -1.514654 | ... | 0.247998 | 0.771679 | 0.909412 | -0.689281 | -0.327642 | -0.139097 | -0.055353 | -0.059752 | 378.66 | 0 |
| 3 | 1.0 | -0.966272 | -0.185226 | 1.792993 | -0.863291 | -0.010309 | 1.247203 | 0.237609 | 0.377436 | -1.387024 | ... | -0.108300 | 0.005274 | -0.190321 | -1.175575 | 0.647376 | -0.221929 | 0.062723 | 0.061458 | 123.50 | 0 |
| 4 | 2.0 | -1.158233 | 0.877737 | 1.548718 | 0.403034 | -0.407193 | 0.095921 | 0.592941 | -0.270533 | 0.817739 | ... | -0.009431 | 0.798278 | -0.137458 | 0.141267 | -0.206010 | 0.502292 | 0.219422 | 0.215153 | 69.99 | 0 |
5 rows × 31 columns
# 统计不同分类的样本个数
count_classes = pd.value_counts(data['Class'], sort = True).sort_index()
count_classes
0 284315
1 492
Name: Class, dtype: int64
count_classes.plot(kind = 'bar')
plt.title("Fraud class histogram")
plt.xlabel("Class")
plt.ylabel("Frequency")
Text(0,0.5,'Frequency')
样本不均衡
- 下采样(将多的样本取和少的样本同样的个数集)
- 过采样(将少的样本取增加到和多的样本同样个数)
from sklearn.preprocessing import StandardScaler
# 转换维度并归一化
data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1, 1))
data = data.drop(['Time','Amount'],axis=1)
data.head()
| V1 | V2 | V3 | V4 | V5 | V6 | V7 | V8 | V9 | V10 | ... | V21 | V22 | V23 | V24 | V25 | V26 | V27 | V28 | Class | normAmount | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | -1.359807 | -0.072781 | 2.536347 | 1.378155 | -0.338321 | 0.462388 | 0.239599 | 0.098698 | 0.363787 | 0.090794 | ... | -0.018307 | 0.277838 | -0.110474 | 0.066928 | 0.128539 | -0.189115 | 0.133558 | -0.021053 | 0 | 0.244964 |
| 1 | 1.191857 | 0.266151 | 0.166480 | 0.448154 | 0.060018 | -0.082361 | -0.078803 | 0.085102 | -0.255425 | -0.166974 | ... | -0.225775 | -0.638672 | 0.101288 | -0.339846 | 0.167170 | 0.125895 | -0.008983 | 0.014724 | 0 | -0.342475 |
| 2 | -1.358354 | -1.340163 | 1.773209 | 0.379780 | -0.503198 | 1.800499 | 0.791461 | 0.247676 | -1.514654 | 0.207643 | ... | 0.247998 | 0.771679 | 0.909412 | -0.689281 | -0.327642 | -0.139097 | -0.055353 | -0.059752 | 0 | 1.160686 |
| 3 | -0.966272 | -0.185226 | 1.792993 | -0.863291 | -0.010309 | 1.247203 | 0.237609 | 0.377436 | -1.387024 | -0.054952 | ... | -0.108300 | 0.005274 | -0.190321 | -1.175575 | 0.647376 | -0.221929 | 0.062723 | 0.061458 | 0 | 0.140534 |
| 4 | -1.158233 | 0.877737 | 1.548718 | 0.403034 | -0.407193 | 0.095921 | 0.592941 | -0.270533 | 0.817739 | 0.753074 | ... | -0.009431 | 0.798278 | -0.137458 | 0.141267 | -0.206010 | 0.502292 | 0.219422 | 0.215153 | 0 | -0.073403 |
5 rows × 30 columns
# 特征
X = data.loc[:, data.columns != 'Class']
# 类别
y = data.loc[:, data.columns == 'Class']# Number of data points in the minority class
number_records_fraud = len(data[data.Class == 1])
# 取索引
fraud_indices = np.array(data[data.Class == 1].index)
# print(fraud_indices)# 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)
# 在 normal_indices 中随机取出 number_records_fraud 个值
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
# 合并两个数组
under_sample_indices = np.concatenate([fraud_indices,random_normal_indices])# 下采样
# loc是基于name索引,iloc是基于位置索引
under_sample_data = data.iloc[under_sample_indices,:]X_undersample = under_sample_data.loc[:, under_sample_data.columns != 'Class']
y_undersample = under_sample_data.loc[:, 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.model_selection import train_test_split# 所有数据集
# random_state(随机种子)就是为了保证程序每次运行都分割一样的训练集和测试集。否则，同样的算法模型在不同的训练集和测试集上的效果不一样。
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))# 下采样数据集划分train和test
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: 284807Number transactions train dataset: 688
Number transactions test dataset: 296
Total number of transactions: 984
召回率（Recall）
- 表示的是样本中的正例有多少被预测正确了。那也有两种可能，一种是把原来的正类预测成正类(TP)，另一种就是把原来的正类预测为负类(FN)
- TP:正例检索对的
- FP:负例预测为正例
- FN:把原来的正例预测为负例
- 例如:
50个人,20个女生,30个男生,检测出来50个女生
TP:20
FP:30
FN:0
#Recall = TP/(TP+FN)
from sklearn.linear_model import LogisticRegression
# KFold 做多少次的交叉验证
from sklearn.model_selection import KFold,cross_val_score
from sklearn.metrics import confusion_matrix,recall_score,classification_report
正则化：
（1）防止过拟合；
（2）正则化项的引入其实是利用了先验知识，体现了人对问题的解的认知程度或者对解的估计；例如正则化最小二乘问题如下：
（3）引入正则化项之后，会降低条件数，提高抗干扰能力，提高泛化能力
超参数α控制权重
L1：
f(w;X,y)=α∣w1?∣+J(w;X,y)
对应的梯度就变为
▽w?f(w;X,y)=αsign(w)+▽w?J(w;X,y)
L2：
正则化的目标函数为
f(w;X,y)=1/2?(wTw+J(w;X,y)?)
对应的梯度就变为
▽w?f(w;X,y)=αw+▽w?J(w;X,y)
# 计算召回率
def printing_Kfold_scores(x_train_data,y_train_data):# fold = KFold(len(y_train_data),5,shuffle=False) # KFold 做多少次的交叉验证,此处为5次fold = KFold(5,shuffle=False)# Different C parameters# 不同的正则化权重值(a)c_param_range = [0.01,0.1,1,10,100]# print(fold)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# 不同的正则化权重值for c_param in c_param_range:print('-------------------------------------------')print('C parameter: ', c_param)print('-------------------------------------------')print('')recall_accs = []# 循环进行交叉验证for iteration, indices in enumerate(fold.split(x_train_data)):# Call the logistic regression model with a certain C parameter# 指定逻辑回归模型,正则化为L1,权重值为c_paramlr = 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 datay_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 召回率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.# 召回率的平均值results_table.loc[j,'Mean recall score'] = np.mean(recall_accs)j += 1print('')print('Mean recall score ', np.mean(recall_accs))print('')# best_c = results_table.loc[results_table['Mean recall score'].idxmax()]['C_parameter']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 0 : recall score = 0.9315068493150684
Iteration 1 : recall score = 0.9178082191780822
Iteration 2 : recall score = 0.9830508474576272
Iteration 3 : recall score = 0.972972972972973
Iteration 4 : recall score = 0.9545454545454546Mean recall score 0.9519768686938409-------------------------------------------
C parameter: 0.1
-------------------------------------------Iteration 0 : recall score = 0.8493150684931506
Iteration 1 : recall score = 0.8767123287671232
Iteration 2 : recall score = 0.9322033898305084
Iteration 3 : recall score = 0.9324324324324325
Iteration 4 : recall score = 0.9090909090909091Mean recall score 0.8999508257228248-------------------------------------------
C parameter: 1
-------------------------------------------Iteration 0 : recall score = 0.863013698630137
Iteration 1 : recall score = 0.8904109589041096
Iteration 2 : recall score = 0.9661016949152542
Iteration 3 : recall score = 0.9459459459459459
Iteration 4 : recall score = 0.9090909090909091Mean recall score 0.9149126414972711-------------------------------------------
C parameter: 10
-------------------------------------------Iteration 0 : recall score = 0.863013698630137
Iteration 1 : recall score = 0.9041095890410958
Iteration 2 : recall score = 0.9661016949152542
Iteration 3 : recall score = 0.9459459459459459/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 4 : recall score = 0.9090909090909091Mean recall score 0.9176523675246685-------------------------------------------
C parameter: 100
-------------------------------------------Iteration 0 : recall score = 0.863013698630137
Iteration 1 : recall score = 0.8904109589041096
Iteration 2 : recall score = 0.9661016949152542
Iteration 3 : recall score = 0.9459459459459459
Iteration 4 : recall score = 0.9090909090909091Mean recall score 0.9149126414972711*********************************************************************************
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')import itertools
lr = LogisticRegression(C = best_c, penalty = 'l1')
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/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)
lr = LogisticRegression(C = best_c, penalty = 'l1')
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()
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Recall metric in the testing dataset: 0.9251700680272109
best_c = printing_Kfold_scores(X_train,y_train)
-------------------------------------------
C parameter: 0.01
-------------------------------------------/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 0 : recall score = 0.4925373134328358/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 1 : recall score = 0.6027397260273972/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 2 : recall score = 0.6833333333333333/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 3 : recall score = 0.5692307692307692/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 4 : recall score = 0.45Mean recall score 0.5595682284048672-------------------------------------------
C parameter: 0.1
-------------------------------------------/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 0 : recall score = 0.5671641791044776/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 1 : recall score = 0.6164383561643836/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 2 : recall score = 0.6833333333333333/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 3 : recall score = 0.5846153846153846/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 4 : recall score = 0.525Mean recall score 0.5953102506435158-------------------------------------------
C parameter: 1
-------------------------------------------/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 0 : recall score = 0.5522388059701493/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 1 : recall score = 0.6164383561643836/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 2 : recall score = 0.7166666666666667/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 3 : recall score = 0.6153846153846154/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 4 : recall score = 0.5625Mean recall score 0.612645688837163-------------------------------------------
C parameter: 10
-------------------------------------------/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 0 : recall score = 0.5522388059701493/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 1 : recall score = 0.6164383561643836/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 2 : recall score = 0.7333333333333333/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 3 : recall score = 0.6153846153846154/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 4 : recall score = 0.575Mean recall score 0.6184790221704963-------------------------------------------
C parameter: 100
-------------------------------------------/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 0 : recall score = 0.5522388059701493/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 1 : recall score = 0.6164383561643836/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 2 : recall score = 0.7333333333333333/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 3 : recall score = 0.6153846153846154/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Iteration 4 : recall score = 0.575Mean recall score 0.6184790221704963*********************************************************************************
Best model to choose from cross validation is with C parameter = 10.0
*********************************************************************************
lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train,y_train.values.ravel())
y_pred_undersample = lr.predict(X_test.values)# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test,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()
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Recall metric in the testing dataset: 0.6190476190476191
lr = LogisticRegression(C = 0.01, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
# 取出概率值
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] > iplt.subplot(3,3,j)j += 1# Compute confusion matrixcnf_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 matrixclass_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: 0.9931972789115646
Recall metric in the testing dataset: 0.9727891156462585
Recall metric in the testing dataset: 0.9251700680272109/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.FutureWarning)Recall metric in the testing dataset: 0.8843537414965986
Recall metric in the testing dataset: 0.8299319727891157
Recall metric in the testing dataset: 0.7687074829931972
Recall metric in the testing dataset: 0.5918367346938775
pip install imbalanced-learn
Looking in indexes: https://pypi.mirrors.ustc.edu.cn/simple/
Collecting imbalanced-learn
import pandas as pd
from imblearn.over_sampling import SMOTE
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix
s.ustc.edu.cn/simple/Collecting imbalanced-learn```python
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