机器学习算法基础七 XGBoost

Harmony ·

更新时间:2024-09-21

· 635 次阅读

XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework. XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way.
Git

所用练习数据已上传https://download.csdn.net/download/qq_22096121/12201850

xgboost.DMatrix是此包的核心数据结构
在这里插入图片描述

train()函数为训练操作

在这里插入图片描述

predict()函数为预测操作
在这里插入图片描述

练习1

# /usr/bin/python
# -*- encoding:utf-8 -*-
import xgboost as xgb
import numpy as np
# 1、xgBoost的基本使用
# 2、自定义损失函数的梯度和二阶导
# 3、binary:logistic/logitraw
# 定义f: theta * x
def log_reg(y_hat, y):
    p = 1.0 / (1.0 + np.exp(-y_hat))
    g = p - y.get_label()
    h = p * (1.0-p)
    return g, h
def error_rate(y_hat, y):
    return 'error', float(sum(y.get_label() != (y_hat > 0.5))) / len(y_hat)
if __name__ == "__main__":
    # 读取数据
    data_train = xgb.DMatrix('agaricus_train.txt')
    data_test = xgb.DMatrix('agaricus_test.txt')
    print(data_train)
    print(type(data_train))
    # 设置参数
    param = {'max_depth': 3, 'eta': 1, 'silent': 1, 'objective': 'binary:logistic'} # logitraw
    # param = {'max_depth': 3, 'eta': 0.3, 'silent': 1, 'objective': 'reg:logistic'}
    watchlist = [(data_test, 'eval'), (data_train, 'train')]
    n_round = 7
    # bst = xgb.train(param, data_train, num_boost_round=n_round, evals=watchlist)
    bst = xgb.train(param, data_train, num_boost_round=n_round, evals=watchlist, obj=log_reg, feval=error_rate)
    # 计算错误率
    y_hat = bst.predict(data_test)
    y = data_test.get_label()
    print(y_hat)
    print(y)
    error = sum(y != (y_hat > 0.5))
    error_rate = float(error) / len(y_hat)
    print('样本总数：\t', len(y_hat))
    print('错误数目：\t%4d' % error)
    print('错误率：\t%.5f%%' % (100*error_rate))

Output:
[00:08:28] 6513x126 matrix with 143286 entries loaded from agaricus_train.txt
[00:08:28] 1611x126 matrix with 35442 entries loaded from agaricus_test.txt

[0] eval-error:0.01614 train-error:0.01443 eval-error:0.01614 train-error:0.01443
[1] eval-error:0.01614 train-error:0.01443 eval-error:0.01614 train-error:0.01443
[2] eval-error:0.01614 train-error:0.01443 eval-error:0.01614 train-error:0.01443
[3] eval-error:0.01614 train-error:0.01443 eval-error:0.01614 train-error:0.01443
[4] eval-error:0.00248 train-error:0.00307 eval-error:0.00248 train-error:0.00307
[5] eval-error:0.00248 train-error:0.00307 eval-error:0.00248 train-error:0.00307
[6] eval-error:0.00248 train-error:0.00307 eval-error:0.00248 train-error:0.00307
[6.0993789e-06 9.8472750e-01 6.0993789e-06 … 9.9993265e-01 4.4560062e-07
9.9993265e-01]
[0. 1. 0. … 1. 0. 1.]
样本总数： 1611
错误数目： 4
错误率： 0.24829%

练习2

# /usr/bin/python
# -*- encoding:utf-8 -*-
import numpy as np
import pandas as pd
import xgboost as xgb
from sklearn.model_selection import train_test_split   # cross_validation
from sklearn.linear_model import LogisticRegressionCV
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
def iris_type(s):
    it = {b'Iris-setosa': 0, b'Iris-versicolor': 1, b'Iris-virginica': 2}
    return it[s]
if __name__ == "__main__":
    path = u'..\\8.Regression\\iris.data'  # 数据文件路径
    # data = np.loadtxt(path, dtype=float, delimiter=',', converters={4: iris_type})
    data = pd.read_csv(path, header=None)
    x, y = data[range(4)], data[4]
    y = pd.Categorical(y).codes
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, test_size=50)
    data_train = xgb.DMatrix(x_train, label=y_train)
    data_test = xgb.DMatrix(x_test, label=y_test)
    watch_list = [(data_test, 'eval'), (data_train, 'train')]
    param = {'max_depth': 2, 'eta': 0.3, 'silent': 1, 'objective': 'multi:softmax', 'num_class': 3}
    bst = xgb.train(param, data_train, num_boost_round=6, evals=watch_list)
    y_hat = bst.predict(data_test)
    result = y_test.reshape(1, -1) == y_hat
    print('正确率:\t', float(np.sum(result)) / len(y_hat))
    print('END.....\n')
    models = [('LogisticRegression', LogisticRegressionCV(Cs=10 ,cv=3)),
              ('RandomForest', RandomForestClassifier(n_estimators=30, criterion='gini'))]
    for name, model in models:
        model.fit(x_train, y_train)
        print(name, '训练集正确率：', accuracy_score(y_train, model.predict(x_train)))
        print(name, '测试机正确率：', accuracy_score(y_test, model.predict(x_test)))

Output:
[0] eval-merror:0.04000 train-merror:0.04000
[1] eval-merror:0.04000 train-merror:0.04000
[2] eval-merror:0.02000 train-merror:0.02000
[3] eval-merror:0.02000 train-merror:0.02000
[4] eval-merror:0.02000 train-merror:0.02000
[5] eval-merror:0.02000 train-merror:0.02000
正确率: 0.98
END…
LogisticRegression 训练集正确率： 0.97
LogisticRegression 测试机正确率： 0.96
RandomForest 训练集正确率： 1.0
RandomForest 测试机正确率： 0.96
LogisticRegression精度不足但相对简单

练习3 葡萄酒类型分类

# !/usr/bin/python
# -*- encoding:utf-8 -*-
import xgboost as xgb
import numpy as np
from sklearn.model_selection import train_test_split   # cross_validation
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
if __name__ == "__main__":
    # 作业：尝试用Pandas读取试试？
    data = np.loadtxt('wine.data', dtype=float, delimiter=',')
    y, x = np.split(data, (1,), axis=1)
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, test_size=0.5)
    # Logistic回归
    lr = LogisticRegression(penalty='l2')
    lr.fit(x_train, y_train.ravel())
    y_hat = lr.predict(x_test)
    print('Logistic回归正确率：', accuracy_score(y_test, y_hat))
    # XGBoost
    # 要求标记为0， 做转换
    y_train[y_train == 3] = 0
    y_test[y_test == 3] = 0
    data_train = xgb.DMatrix(x_train, label=y_train)
    data_test = xgb.DMatrix(x_test, label=y_test)
    watch_list = [(data_test, 'eval'), (data_train, 'train')]
    params = {'max_depth': 3, 'eta': 1, 'silent': 0, 'objective': 'multi:softmax', 'num_class': 3}
    bst = xgb.train(params, data_train, num_boost_round=2, evals=watch_list)
    y_hat = bst.predict(data_test)
    print('XGBoost正确率：', accuracy_score(y_test, y_hat))

Output:
Logistic回归正确率： 0.9438202247191011
[0] eval-merror:0.01124 train-merror:0.00000
[1] eval-merror:0.00000 train-merror:0.00000
XGBoost正确率： 1.0

练习4

# /usr/bin/python
# -*- coding:utf-8 -*-
import xgboost as xgb
import numpy as np
import scipy.sparse
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
def read_data(path):
    y = []
    row = []
    col = []
    values = []
    r = 0       # 首行
    for d in open(path):
        d = d.strip().split()      # 以空格分开
        y.append(int(d[0]))
        d = d[1:]
        for c in d:
            key, value = c.split(':')
            row.append(r)
            col.append(int(key))
            values.append(float(value))
        r += 1
    x = scipy.sparse.csr_matrix((values, (row, col))).toarray()
    y = np.array(y)
    return x, y
if __name__ == '__main__':
    x, y = read_data('agaricus_train.txt')
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, train_size=0.6)
    # Logistic回归
    lr = LogisticRegression(penalty='l2')
    lr.fit(x_train, y_train.ravel())
    y_hat = lr.predict(x_test)
    print('Logistic回归正确率：', accuracy_score(y_test, y_hat))
    # XGBoost
    data_train = xgb.DMatrix(x_train, label=y_train)
    data_test = xgb.DMatrix(x_test, label=y_test)
    watch_list = [(data_test, 'eval'), (data_train, 'train')]
    param = {'max_depth': 3, 'eta': 1, 'silent': 0, 'objective': 'multi:softmax', 'num_class': 3}
    bst = xgb.train(param, data_train, num_boost_round=4, evals=watch_list)
    y_hat = bst.predict(data_test)
    print('XGBoost正确率：', accuracy_score(y_test, y_hat))

Output:
Logistic回归正确率： 1.0
[0] eval-merror:0.03569 train-merror:0.04070
[1] eval-merror:0.00729 train-merror:0.00998
[2] eval-merror:0.00077 train-merror:0.00051
[3] eval-merror:0.00077 train-merror:0.00051
XGBoost正确率： 0.9992325402916347

训练5 Titanci幸存预测

# /usr/bin/python
# -*- encoding:utf-8 -*-
import xgboost as xgb
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
import pandas as pd
import csv
def show_accuracy(a, b, tip):
    acc = a.ravel() == b.ravel()
    acc_rate = 100 * float(acc.sum()) / a.size
    print('%s正确率：%.3f%%' % (tip, acc_rate))
    return acc_rate
def load_data(file_name, is_train):
    data = pd.read_csv(file_name)  # 数据文件路径
    # print 'data.describe() = \n', data.describe()
    # 性别
    data['Sex'] = data['Sex'].map({'female': 0, 'male': 1}).astype(int)
    # 补齐船票价格缺失值
    if len(data.Fare[data.Fare.isnull()]) > 0:
        fare = np.zeros(3)
        for f in range(0, 3):
            fare[f] = data[data.Pclass == f + 1]['Fare'].dropna().median()
        for f in range(0, 3):  # loop 0 to 2
            data.loc[(data.Fare.isnull()) & (data.Pclass == f + 1), 'Fare'] = fare[f]
    # 年龄：使用均值代替缺失值
    # mean_age = data['Age'].dropna().mean()
    # data.loc[(data.Age.isnull()), 'Age'] = mean_age
    if is_train:
        # 年龄：使用随机森林预测年龄缺失值
        print('随机森林预测缺失年龄：--start--')
        data_for_age = data[['Age', 'Survived', 'Fare', 'Parch', 'SibSp', 'Pclass']]
        age_exist = data_for_age.loc[(data.Age.notnull())]   # 年龄不缺失的数据
        age_null = data_for_age.loc[(data.Age.isnull())]
        # print age_exist
        x = age_exist.values[:, 1:]
        y = age_exist.values[:, 0]
        rfr = RandomForestRegressor(n_estimators=1000)
        rfr.fit(x, y)
        age_hat = rfr.predict(age_null.values[:, 1:])
        # print age_hat
        data.loc[(data.Age.isnull()), 'Age'] = age_hat
        print('随机森林预测缺失年龄：--over--')
    else:
        print('随机森林预测缺失年龄2：--start--')
        data_for_age = data[['Age', 'Fare', 'Parch', 'SibSp', 'Pclass']]
        age_exist = data_for_age.loc[(data.Age.notnull())]  # 年龄不缺失的数据
        age_null = data_for_age.loc[(data.Age.isnull())]
        # print age_exist
        x = age_exist.values[:, 1:]
        y = age_exist.values[:, 0]
        rfr = RandomForestRegressor(n_estimators=1000)
        rfr.fit(x, y)
        age_hat = rfr.predict(age_null.values[:, 1:])
        # print age_hat
        data.loc[(data.Age.isnull()), 'Age'] = age_hat
        print('随机森林预测缺失年龄2：--over--')
    # 起始城市
    data.loc[(data.Embarked.isnull()), 'Embarked'] = 'S'  # 保留缺失出发城市
    # data['Embarked'] = data['Embarked'].map({'S': 0, 'C': 1, 'Q': 2, 'U': 0}).astype(int)
    # print data['Embarked']
    embarked_data = pd.get_dummies(data.Embarked)
    print(embarked_data)
    # embarked_data = embarked_data.rename(columns={'S': 'Southampton', 'C': 'Cherbourg', 'Q': 'Queenstown', 'U': 'UnknownCity'})
    embarked_data = embarked_data.rename(columns=lambda x: 'Embarked_' + str(x))
    data = pd.concat([data, embarked_data], axis=1)
    print(data.describe())
    data.to_csv('New_Data.csv')
    x = data[['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked_C', 'Embarked_Q', 'Embarked_S']]
    # x = data[['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']]
    y = None
    if 'Survived' in data:
        y = data['Survived']
    x = np.array(x)
    y = np.array(y)
    # 思考：这样做，其实发生了什么？
    x = np.tile(x, (5, 1))
    y = np.tile(y, (5, ))
    if is_train:
        return x, y
    return x, data['PassengerId']
def write_result(c, c_type):
    file_name = 'Titanic.test.csv'
    x, passenger_id = load_data(file_name, False)
    if type == 3:
        x = xgb.DMatrix(x)
    y = c.predict(x)
    y[y > 0.5] = 1
    y[~(y > 0.5)] = 0
    predictions_file = open("Prediction_%d.csv" % c_type, "wb")
    open_file_object = csv.writer(predictions_file)
    open_file_object.writerow(["PassengerId", "Survived"])
    open_file_object.writerows(zip(passenger_id, y))
    predictions_file.close()
if __name__ == "__main__":
    x, y = load_data('Titanic.train.csv', True)
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=1)
    #
    lr = LogisticRegression(penalty='l2')
    lr.fit(x_train, y_train)
    y_hat = lr.predict(x_test)
    lr_acc = accuracy_score(y_test, y_hat)
    # write_result(lr, 1)
    rfc = RandomForestClassifier(n_estimators=100)
    rfc.fit(x_train, y_train)
    y_hat = rfc.predict(x_test)
    rfc_acc = accuracy_score(y_test, y_hat)
    # write_result(rfc, 2)
    # XGBoost
    data_train = xgb.DMatrix(x_train, label=y_train)
    data_test = xgb.DMatrix(x_test, label=y_test)
    watch_list = [(data_test, 'eval'), (data_train, 'train')]
    param = {'max_depth': 6, 'eta': 0.8, 'silent': 1, 'objective': 'binary:logistic'}
             # 'subsample': 1, 'alpha': 0, 'lambda': 0, 'min_child_weight': 1}
    bst = xgb.train(param, data_train, num_boost_round=100, evals=watch_list)
    y_hat = bst.predict(data_test)
    # write_result(bst, 3)
    y_hat[y_hat > 0.5] = 1
    y_hat[~(y_hat > 0.5)] = 0
    xgb_acc = accuracy_score(y_test, y_hat)
    print('Logistic回归：%.3f%%' % lr_acc)
    print('随机森林：%.3f%%' % rfc_acc)
    print('XGBoost：%.3f%%' % xgb_acc)

作者：不可描述的两脚兽

xgboost 学习机器学习算法

1024 个赞