这个项目实战系列主要是跟着网络上的教程来做的,主要参考《跟着迪哥学习机器学习》中的思路和具体实现代码,但是书中使用到的应该是python2的版本,有一些代码也有问题,有的是省略了一些关键的步骤,有的是语法的问题,总之就是并不是直接照着敲就能够一路运行下来的。这里整理了能够运行的代码和数据集(链接容易挂,需要请私聊)。
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
data = pd.read_csv("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
count_classes = pd.value_counts(data['Class'], sort=True).sort_index()
count_classes.plot(kind='bar')
plt.title("class analysis")
plt.xlabel("classes")
plt.ylabel("frequency")
Text(0, 0.5, 'frequency')
解决数据标签不平衡问题
各个列的单位不一样,变化程度不一样,需要对数据进行改善。数据经过处理之后得到的每一个特征的数值都在较小的范围内浮动
Z = X − X m e a n s t d ( X ) Z = \frac{X-X_{mean}}{std(X)} Z=std(X)X−Xmean
from sklearn.preprocessing import StandardScaler
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
X = data.iloc[:,data.columns!='Class']
y = data.iloc[:,data.columns=='Class']
number_records_fraud = len(data[data.Class==1]) # 异常值数据长度
fraud_indices = np.array(data[data.Class==1].index) # 异常值的数据的索引
normal_indices = data[data.Class==0].index
# 对正常样本随即采用指定长度
random_normal_indices = np.random.choice(normal_indices,number_records_fraud,replace=False)
random_normal_indices = np.array(random_normal_indices)
# 合并新的索引项
under_sample_indices = np.concatenate([fraud_indices,random_normal_indices])
# 根据索引得到下采样的所有的样本点
under_sample_data = data.iloc[under_sample_indices,:]
X_undersample = under_sample_data.iloc[:,under_sample_data.columns!='Class']
y_undersample = under_sample_data.iloc[:,under_sample_data.columns=='Class']
#打印比例
print("正常样本比例:",len(under_sample_data[under_sample_data.Class==0])/len(under_sample_data))
print("异常样本比例:",len(under_sample_data[under_sample_data.Class==1])/len(under_sample_data))
print("下采样的总样本:",len(under_sample_data))
正常样本比例: 0.5
异常样本比例: 0.5
下采样的总样本: 984
目的:交叉验证
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("原始数据集包含样本:",len(X_train))
print("原始测试集包含样本数量:",len(X_test))
print("原始样本总数:",len(X_train)+len(X_test))
# 对下采样的数据集进行划分
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("下采样训练集包含样本:",len(X_train_undersample))
print("下采样测试集包含样本数量:",len(X_test_undersample))
print("下采样总数:",len(X_train_undersample)+len(X_test_undersample))
原始数据集包含样本: 199364
原始测试集包含样本数量: 85443
原始样本总数: 284807
下采样训练集包含样本: 688
下采样测试集包含样本数量: 296
下采样总数: 984
from sklearn.model_selection import KFold
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import recall_score
def printing_Kfold_scores(x_train_data,y_train_data):
fold = KFold(n_splits=5,shuffle=False)
c_param_range = [0.01,0.1,1,10,100] # 惩罚力度
result_table = pd.DataFrame(index = range(len(c_param_range),2),columns=['C_parameter','Mean recall score'])
result_table['C_parameter'] = c_param_range
j = 0
for c_param in c_param_range:
print("==================")
print('正则化惩罚力度:',c_param)
print('==================')
print()
recall_accs = []
for iteration,indices in enumerate(fold.split(x_train_data),start=1):
Ir = LogisticRegression(C = c_param, penalty='l2')
Ir.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())
y_pred_undersample = Ir.predict(x_train_data.iloc[indices[1],:].values)
recall_acc = recall_score(y_train_data.iloc[indices[1],:].values,y_pred_undersample)
recall_accs.append(recall_acc)
print('Iteration',iteration,':召回率 = ',recall_accs[-1])
result_table.loc[j,'Mean recall score'] = np.mean(recall_accs)
j += 1
print()
print("平均召回率:",np.mean(recall_accs))
print()
best_c = result_table.iloc[result_table['Mean recall score'].astype('float32').idxmax()]['C_parameter']
print(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>")
print('效果最好的模型选择的参数=',best_c)
print(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>")
return best_c
best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample)
==================
正则化惩罚力度: 0.01
==================
Iteration 1 :召回率 = 0.821917808219178
Iteration 2 :召回率 = 0.8493150684931506
Iteration 3 :召回率 = 0.9152542372881356
Iteration 4 :召回率 = 0.9324324324324325
Iteration 5 :召回率 = 0.8939393939393939
平均召回率: 0.882571788074458
==================
正则化惩罚力度: 0.1
==================
Iteration 1 :召回率 = 0.8493150684931506
Iteration 2 :召回率 = 0.863013698630137
Iteration 3 :召回率 = 0.9322033898305084
Iteration 4 :召回率 = 0.9459459459459459
Iteration 5 :召回率 = 0.8939393939393939
平均召回率: 0.8968834993678272
==================
正则化惩罚力度: 1
==================
Iteration 1 :召回率 = 0.863013698630137
Iteration 2 :召回率 = 0.8904109589041096
Iteration 3 :召回率 = 0.9830508474576272
Iteration 4 :召回率 = 0.9459459459459459
Iteration 5 :召回率 = 0.9090909090909091
平均召回率: 0.9183024720057457
==================
正则化惩罚力度: 10
==================
Iteration 1 :召回率 = 0.8767123287671232
Iteration 2 :召回率 = 0.8767123287671232
Iteration 3 :召回率 = 0.9830508474576272
Iteration 4 :召回率 = 0.9459459459459459
Iteration 5 :召回率 = 0.9090909090909091
平均召回率: 0.9183024720057457
==================
正则化惩罚力度: 100
==================
Iteration 1 :召回率 = 0.8767123287671232
Iteration 2 :召回率 = 0.8767123287671232
Iteration 3 :召回率 = 0.9830508474576272
Iteration 4 :召回率 = 0.9459459459459459
Iteration 5 :召回率 = 0.9090909090909091
平均召回率: 0.9183024720057457
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
效果最好的模型选择的参数= 1.0
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
猜想这里为什么和书上得出了不一样的答案:
from sklearn.metrics import confusion_matrix
from itertools import product as product
def plot_confusion_matrix(cm,classes,title='Confusion matrix',cmap=plt.cm.Blues):
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 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")
Ir = LogisticRegression(C=best_c,penalty='l2')
Ir.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample = Ir.predict(X_test_undersample.values)
cnf_matrix = confusion_matrix(y_test_undersample,y_pred_undersample)
np.set_printoptions(precision=2)
print("召回率:",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()
召回率: 0.9251700680272109
Ir = LogisticRegression(C=best_c,penalty='l2')
Ir.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred = Ir.predict(X_test.values)
cnf_matrix = confusion_matrix(y_test,y_pred)
np.set_printoptions(precision=2)
print("模型应用于原始数据的召回率:",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()
模型应用于原始数据的召回率: 0.9319727891156463
分析:左下角说明了遗漏分类Neg数据的数目可以接受,而右上角的数目代表错误分类为Neg的数目过多,需要改正!
Ir = LogisticRegression(C=best_c,penalty='l2')
Ir.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample_proba = Ir.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
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)
Recall metric in the testing dataset: 0.9591836734693877
Recall metric in the testing dataset: 0.9455782312925171
Recall metric in the testing dataset: 0.9319727891156463
Recall metric in the testing dataset: 0.9319727891156463
Recall metric in the testing dataset: 0.9251700680272109
Recall metric in the testing dataset: 0.891156462585034
Recall metric in the testing dataset: 0.8775510204081632
Recall metric in the testing dataset: 0.8707482993197279
Recall metric in the testing dataset: 0.8571428571428571
对于混淆矩阵,可以如此记忆:
左上:追求最大的(代表分类为真的正确的样本)
右上:追求最小的(代表分类为假的错误的样本)分类错误 误杀的样本
右下:追求最大的(代表分类为假的正确的样本)
左下:追求最小的(代表分类为真的错误的样本)分类错误 捡漏的样本
自己生成不够的样本
具体流程
# 过采样, 使用 smote算法生成样本
# 引入逻辑回归模型
# 加载数据
data = pd.read_csv("creditcard.csv")
# Amount特征值太大,进行正规化
data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1, 1))
# 删除无用的Time列和原 Amount列
data = data.drop(['Time', 'Amount'], axis=1)
# 获取特征列,所有行,列名不是Class的列
features = data.loc[:, data.columns != 'Class']
# 获取标签列,所有行,列名是Class的列
labels = data.loc[:, data.columns == 'Class']
# 分离训练集和测试集
features_train, features_test, labels_train, labels_test = train_test_split(features, labels, test_size=0.2, random_state=0)
from imblearn.over_sampling import SMOTE
oversampler = SMOTE(random_state=0)
os_features,os_labels=oversampler.fit_resample(features_train,labels_train)
os_features = pd.DataFrame(os_features)
os_labels = pd.DataFrame(os_labels)
best_c = printing_Kfold_scores(os_features,os_labels)
==================
正则化惩罚力度: 0.01
==================
Iteration 1 :召回率 = 0.9161290322580645
Iteration 2 :召回率 = 0.9144736842105263
Iteration 3 :召回率 = 0.9105676662609273
Iteration 4 :召回率 = 0.8931754981809389
Iteration 5 :召回率 = 0.893626141721898
平均召回率: 0.905594404526471
==================
正则化惩罚力度: 0.1
==================
Iteration 1 :召回率 = 0.9161290322580645
Iteration 2 :召回率 = 0.9144736842105263
Iteration 3 :召回率 = 0.9115857032200951
Iteration 4 :召回率 = 0.8943295852980293
Iteration 5 :召回率 = 0.895120959321177
平均召回率: 0.9063277928615785
==================
正则化惩罚力度: 1
==================
Iteration 1 :召回率 = 0.9161290322580645
Iteration 2 :召回率 = 0.9144736842105263
Iteration 3 :召回率 = 0.911807015602523
Iteration 4 :召回率 = 0.8945384201096932
Iteration 5 :召回率 = 0.8952528549917016
平均召回率: 0.9064402014345017
==================
正则化惩罚力度: 10
==================
Iteration 1 :召回率 = 0.9161290322580645
Iteration 2 :召回率 = 0.9144736842105263
Iteration 3 :召回率 = 0.9118734093172512
Iteration 4 :召回率 = 0.8945713940273244
Iteration 5 :召回率 = 0.8952528549917016
平均召回率: 0.9064600749609737
==================
正则化惩罚力度: 100
==================
Iteration 1 :召回率 = 0.9161290322580645
Iteration 2 :召回率 = 0.9144736842105263
Iteration 3 :召回率 = 0.9118734093172512
Iteration 4 :召回率 = 0.8945713940273244
Iteration 5 :召回率 = 0.8952638462975786
平均召回率: 0.906462273222149
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
效果最好的模型选择的参数= 100.0
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Ir = LogisticRegression(C=best_c,penalty='l2')
Ir.fit(os_features,os_labels.values.ravel())
y_pred = Ir.predict(features_test.values)
cnf_matrix = confusion_matrix(labels_test,y_pred)
np.set_printoptions(precision=2)
print("混淆矩阵:",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()
混淆矩阵: 0.9405940594059405
发现:这次的模型结果的误杀比例大大下降,因为可以利用的数据信息更多,使得模型更加符合实际的任务需求,对于不同的任务和数据源来说,并没有一成不变的答案,任何结果都需要通过实验证明。