python 多分类 recall_使用sklearn对多分类的每个类别进行指标评价操作

import numpy as np

import pandas as pd

import sklearn

from sklearn.cross_validation import train_test_split,cross_val_score

from xgboost.sklearn import XGBClassifier

from sklearn.metrics import precision_score,roc_auc_score

min_max_scaler = sklearn.preprocessing.MinMaxScaler(feature_range=(-1,1))

resultX = []

resultY = []

with open("./train_data/train2.txt",'r') as rf:

train_lines = rf.readlines()

for train_line in train_lines:

train_line_temp = train_line.split(",")

train_line_temp = map(float, train_line_temp)

line_x = train_line_temp[1:-1]

line_y = train_line_temp[-1]

resultX.append(line_x)

resultY.append(line_y)

X = np.array(resultX)

Y = np.array(resultY)

X = min_max_scaler.fit_transform(X)

X_train,X_test, Y_train, Y_test = train_test_split(X,Y,test_size=0.3)

xgbc = XGBClassifier()

xgbc.fit(X_train,Y_train)

pre_test = xgbc.predict(X_test)

auc_score = roc_auc_score(Y_test,pre_test)

pre_score = precision_score(Y_test,pre_test)

print("xgb_auc_score:",auc_score)

print("xgb_pre_score:",pre_score)

多分类：有19种分类其中正常0，异常1~18种。数据格式如下：

# -*- coding:utf-8 -*-

from sklearn import datasets

from sklearn.multiclass import OneVsRestClassifier

from sklearn.svm import LinearSVC

from sklearn.cross_validation import train_test_split,cross_val_score

from sklearn.svm import SVC

from sklearn.linear_model import LogisticRegression

from xgboost.sklearn import XGBClassifier

import sklearn

import numpy as np

from sklearn.preprocessing import OneHotEncoder

from sklearn.metrics import precision_score,roc_auc_score

min_max_scaler = sklearn.preprocessing.MinMaxScaler(feature_range=(-1,1))

resultX = []

resultY = []

with open("../train_data/train_multi_class.txt",'r') as rf:

train_lines = rf.readlines()

for train_line in train_lines:

train_line_temp = train_line.split(",")

train_line_temp = map(float, train_line_temp) # 转化为浮点数

line_x = train_line_temp[1:-1]

line_y = train_line_temp[-1]

resultX.append(line_x)

resultY.append(line_y)

X = np.array(resultX)

Y = np.array(resultY)

#fit_transform(partData)对部分数据先拟合fit，找到该part的整体指标，如均值、方差、最大值最小值等等(根据具体转换的目的)，然后对该partData进行转换transform，从而实现数据的标准化、归一化等等。。

X = min_max_scaler.fit_transform(X)

#通过OneHotEncoder函数将Y值离散化成19维，例如3离散成000000···100

Y = OneHotEncoder(sparse = False).fit_transform(Y.reshape(-1,1))

X_train,X_test, Y_train, Y_test = train_test_split(X,Y,test_size=0.2)

model = OneVsRestClassifier(XGBClassifier(),n_jobs=2)

clf = model.fit(X_train, Y_train)

pre_Y = clf.predict(X_test)

test_auc2 = roc_auc_score(Y_test,pre_Y)#验证集上的auc值

print ("xgb_muliclass_auc:",test_auc2)

以上这篇使用sklearn对多分类的每个类别进行指标评价操作就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持python博客。