ta

?

白酒、泰坦尼克號例子? ?

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_scoreif __name__ == "__main__":data = np.loadtxt('wine.data', dtype=float, delimiter=',')y, x = np.split(data, (1,), axis=1) #從0開始到1不包含1x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, test_size=0.5)# Logistic回歸lr = LogisticRegression(penalty='l2')lr.fit(x_train, y_train.ravel())y_hat = lr.predict(x_test)print('Logistic回歸正確率：',accuracy_score(y_test, y_hat))# XGBoost# 必須有第0類y_train[y_train == 3] = 0y_test[y_test == 3] = 0# DataMatrixdata_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')]#softmax三分類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正確率：', accuracy_score(y_test, y_hat)) 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):acc = a.ravel() == b.ravel()acc_rate = 100 * float(acc.sum()) / a.sizeprint('%s正確率：%.3f%%' % (tip, acc_rate))return acc_ratedef load_data(file_name, is_train):data = pd.read_csv(file_name) # 數據文件路徑# print 'data.describe() = \n', data.describe()# 性別data['Sex'] = data['Sex'].map({'female': 0, 'male': 1}).astype(int)# 補齊船票價格缺失值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]# 年齡：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:# 年齡：使用隨機森林預測年齡缺失值print('隨機森林預測缺失年齡：--start--')data_for_age = data[['Age', 'Survived', 'Fare', 'Parch', 'SibSp', 'Pclass']]age_exist = data_for_age.loc[(data.Age.notnull())] # 年齡不缺失的數據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('隨機森林預測缺失年齡：--over--')else:print('隨機森林預測缺失年齡2：--start--')data_for_age = data[['Age', 'Fare', 'Parch', 'SibSp', 'Pclass']]age_exist = data_for_age.loc[(data.Age.notnull())] # 年齡不缺失的數據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('隨機森林預測缺失年齡2：--over--')# 起始城市data.loc[(data.Embarked.isnull()), 'Embarked'] = 'S' # 保留缺失出發城市# 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)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):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回歸：%.3f%%' % lr_acc)print('隨機森林：%.3f%%' % rfc_acc)print('XGBoost：%.3f%%' % xgb_acc)

總結

以上是生活随笔為你收集整理的机器学习算法加强——XGBoost实践的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。