标签：实例 data age XGBoost print train test hat
1. 自定义随时函数
下面的代码自定义了XGBoost的随时函数。XGBoost要求我们在自定义随时函数的时候，给出其一阶导函数和二阶导函数的值的表达式。同时，XGBoost也允许使用者给出自定义的评价函数，用以评价训练出来的模型的性能。
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)
2. 读入数据的一些小操作
我们的原始数据在txt中是这样的
XGBoost其实可以直接读入这种数据，不需要进行下述操作。下述操作只是展示一下如何把这种数据改成我们常见的系数矩阵形式。
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)
3. Titanic数据的实操
这段代码的主要关注点在于数据的预处理部分。展示了多种缺失值的处理办法，第一，直接用平均值或者是中位数进行缺失值替换。但是即使是这种比较简练的替换方法，也有可深入探索的地方，比如在替换年龄时，选取同一性别的人的年龄平均值进行替换，而不是用所有人的年龄平均值进行替换。第二，用机器学习模型，比如随机森林，进行缺失值替换。具体方法是，选取处缺失变量的其他变量作为解释变量，缺失变量作为反应变量，使用模型进行训练并做相应预测，进而替换缺失的部分。当然代码的数据预处理还要其他关注点，比如独热编码部分。
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
标签：实例,data,age,XGBoost,print,train,test,hat 来源： https://blog.csdn.net/hello_JeremyWang/article/details/120106035
本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享； 2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关； 3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关； 4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除； 5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。