数据分离与混淆矩阵 好坏质检分类

好坏质检分类实战task：

1. 基于data_class_raw.csv数据，根据高斯分布概率密度函数，寻找异常点并剔除

• 基于data_class_processed.csv数据，进行PCA处理，确定重要数据维度及成分
• 完成数据分离，数据分离参数：random_state=4,test_size=0.4
• 建立KNN模型完成分类，n_neighbors取10，计算分类准确率，可视化分类边界
• 计算测试数据集对应的混淆矩阵，计算准确率、召回率、特异度、精确率、F1分数
• 尝试不同的n_neighbors（1-20）,计算其在训练数据集、测试数据集上的准确率并作图

#加载数据
import pandas as pd
import numpy as np
data = pd.read_csv('data_class_raw.csv')
data.head()

#define X and y
X = data.drop(['y'],axis=1)
y = data.loc[:,'y']

#可视化数据
%matplotlib inline
from matplotlib import pyplot as plt
fig1 = plt.figure(figsize=(10,10))
bad = plt.scatter(X.loc[:,'x1'][y==0],X.loc[:,'x2'][y==0])
good = plt.scatter(X.loc[:,'x1'][y==1],X.loc[:,'x2'][y==1])
plt.legend((good,bad),('good','bad'))
plt.title('raw data')
plt.xlabel('x1')
plt.ylabel('x2')
plt.show()

#异常检测
from sklearn.covariance import EllipticEnvelope
ad_model = EllipticEnvelope(contamination=0.02)
ad_model.fit(X[y==0])#只给坏的数据样本学习
y_predict_bad = ad_model.predict(X[y==0])#预测异常点
print(y_predict_bad)

-1 是异常点

#可视化异常点
fig2 = plt.figure(figsize=(5,5))
bad = plt.scatter(X.loc[:,'x1'][y==0],X.loc[:,'x2'][y==0])
good = plt.scatter(X.loc[:,'x1'][y==1],X.loc[:,'x2'][y==1])
#画异常点
plt.scatter(X.loc[:,'x1'][y==0][y_predict_bad==-1],X.loc[:,'x2'][y==0][y_predict_bad==-1],marker='x',s=150)

plt.legend((good,bad),('good','bad'))
plt.title('raw data')
plt.xlabel('x1')
plt.ylabel('x2')
plt.show()

2

data = pd.read_csv('data_class_processed.csv')
data.head()
#define X and y
X = data.drop(['y'],axis=1)
y = data.loc[:,'y']

#pca 
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
X_norm = StandardScaler().fit_transform(X)
pca = PCA(n_components=2)
X_reduced = pca.fit_transform(X_norm)
var_ratio = pca.explained_variance_ratio_
print(var_ratio) #标准差比例
fig4 = plt.figure(figsize=(5,5))
plt.bar([1,2],var_ratio)
plt.show()
#两个数据都要保留

3 数据分离

#数据分离
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,random_state=4,test_size=0.4) 
print(X_train.shape,X_test.shape,X.shape)#数据维度

原始数据被拆成了测试数据和训练数据

根据训练数据集建立KNN模型

from sklearn.neighbors import KNeighborsClassifier
knn_10=KNeighborsClassifier(n_neighbors=10)
knn_10.fit(X_train,y_train)
y_train_predict=knn_10.predict(X_train)
y_test_predict=knn_10.predict(X_test)

#计算准确率
from sklearn.metrics import accuracy_score
accuracy_train=accuracy_score(y_train,y_train_predict)
accuracy_test=accuracy_score(y_test,y_test_predict)
print("training accuracy:",accuracy_train)
print("testing accuracy:",accuracy_test)

可视化分类边界

#生成填充数据
xx,yy=np.meshgrid(np.arange(0,10,0.05),np.arange(0,10,0.05)) #生成对应的数据组合
print(yy.shape)

#转换成两列
x_range = np.c_[xx.ravel(),yy.ravel()] 
print(x_range.shape)

#预测
y_range_predict=knn_10.predict(x_range)

#画图
fig4 = plt.figure(figsize=(10,10))
knn_bad = plt.scatter(x_range[:,0][y_range_predict==0],x_range[:,1][y_range_predict==0])
knn_good = plt.scatter(x_range[:,0][y_range_predict==1],x_range[:,1][y_range_predict==1])


bad = plt.scatter(X.loc[:,'x1'][y==0],X.loc[:,'x2'][y==0])
good = plt.scatter(X.loc[:,'x1'][y==1],X.loc[:,'x2'][y==1])
plt.legend((good,bad,knn_good,knn_bad),('good','bad','knn_good','knn_bad'))
plt.title('prediction result')
plt.xlabel('x1')
plt.ylabel('x2')
plt.show()

5 混淆矩阵

from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test,y_test_predict)
print(cm)
TP = cm[1,1]
TN = cm[0,0]
FP = cm[0,1]
FN = cm[1,0]
print(TP,TN,FP,FN)

#准确率
accuracy = (TP + TN)/(TP + TN + FP + FN)
print(accuracy)

#灵敏度
recall = TP/(TP + FN)
print(recall)

#特异度
specificity = TN/(TN + FP)
print(specificity)

#精确率
precision = TP/(TP + FP)
print(precision)

#F1分数
F1 = 2*precision*recall/(precision+recall)
print(F1)

调整参数看准确率

#尝试不同的n_neighbors（1-20）,计算其在训练数据集、测试数据集上的准确率并作图
n = [i for i in range(1,21)]
accuracy_train = []
accuracy_test = []
for i in n:
    knn = KNeighborsClassifier(n_neighbors=i)
    knn.fit(X_train,y_train)
    y_train_predict = knn.predict(X_train)
    y_test_predict = knn.predict(X_test)
    accuracy_train_i = accuracy_score(y_train,y_train_predict)
    accuracy_test_i = accuracy_score(y_test,y_test_predict)
    accuracy_train.append(accuracy_train_i)
    accuracy_test.append(accuracy_test_i)
print(accuracy_train,accuracy_test)

fig5 = plt.figure(figsize=(12,5))
plt.subplot(121)
plt.plot(n,accuracy_train,marker='o')
plt.title('training accuracy vs n_neighbors')
plt.xlabel('n_neighbors')
plt.ylabel('accuracy')
plt.subplot(122)
plt.plot(n,accuracy_test,marker='o')
plt.title('testing accuracy vs n_neighbors')
plt.xlabel('n_neighbors')
plt.ylabel('accuracy')
plt.show()