机器学习算法进阶学习笔记——xgboost实践

进阶学习笔记——xgboost实践"/>

机器学习算法进阶学习笔记——xgboost实践

机器学习算法进阶学习笔记——xgboost实践

• 泰坦尼克号生存预测

泰坦尼克号生存预测

首先切换到python2.7，然后在运行

# /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 csvdef show_accuracy(a, b, tip):'''显示正确率:param a: :param b: :param tip: :return:acc_rate '''acc = a.ravel() == b.ravel()acc_rate = 100 * float(acc.sum()) / a.sizeprint '%s正确率：%.3f%%' % (tip, acc_rate)return acc_ratedef load_data(file_name, is_train):'''读取数据，预处理数据，返回训练集:param file_name: :param is_train: :return: '''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 2data.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_ageif 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_existx = 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_hatdata.loc[(data.Age.isnull()), 'Age'] = age_hatprint '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_existx = 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_hatdata.loc[(data.Age.isnull()), 'Age'] = age_hatprint '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 = Noneif '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, yreturn x, data['PassengerId']def write_result(c, c_type):'''将预测结果输出到文件:param c: :param c_type: :return: '''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] = 1y[~(y > 0.5)] = 0predictions_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)# XGBoostdata_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] = 1y_hat[~(y_hat > 0.5)] = 0xgb_acc = accuracy_score(y_test, y_hat)print 'Logistic回归：%.3f%%' % lr_accprint '随机森林：%.3f%%' % rfc_accprint 'XGBoost：%.3f%%' % xgb_acc