这章很多东西背后理论都很熟悉了，主要熟悉包和函数
linear regression：
from sklearn.linear_model import LinearRegression
model = LinearRegression(normalize=True)
model = model.fit(train_X, train_y)
cross validation：
from sklearn.model_selection import cross_val_score
from sklearn.metrics import mean_absolute_error, make_scorer
scores = cross_val_score(model, X=train_X, y=train_y, verbose=1, cv = 5, scoring=make_scorer(mean_absolute_error))
学习率曲线和验证曲线
from sklearn.model_selection import learning_curve, validation_curve
L1，L2 regularization
from sklearn.linear_model import Ridge
from sklearn.linear_model import Lasso
非线性模型
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.neural_network import MLPRegressor
from xgboost.sklearn import XGBRegressor
from lightgbm.sklearn import LGBMRegressor
调参：
贪心算法：按顺序找局部最优，代替为全局最优
网格寻优：按固定步长在范围内遍历一遍，省力耗时
objective = ['regression', 'regression_l1', 'mape', 'huber', 'fair']
num_leaves = [3,5,10,15,20,40, 55]
max_depth = [3,5,10,15,20,40, 55]
from sklearn.model_selection import GridSearchCV
parameters = {'objective': objective , 'num_leaves': num_leaves, 'max_depth': max_depth}
model = LGBMRegressor()
clf = GridSearchCV(model, parameters, cv=5)
clf = clf.fit(train_X, train_y)
贝叶斯寻优：按之前步骤的结果给出概率函数，以此为依据更新参数
Python中有几个贝叶斯优化库，它们目标函数的替代函数不一样。在本文中，我们将使用Hyperopt，它使用Tree Parzen Estimator（TPE）。其他Python库包括Spearmint（高斯过程代理）和SMAC（随机森林回归）
from bayes_opt import BayesianOptimization
def rf_cv(num_leaves, max_depth, subsample, min_child_samples):
val = cross_val_score(
LGBMRegressor(objective = 'regression_l1',
num_leaves=int(num_leaves),
max_depth=int(max_depth),
subsample = subsample,
min_child_samples = int(min_child_samples)
),
X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)
).mean()
return 1 - val
rf_bo = BayesianOptimization(
rf_cv,
{
'num_leaves': (2, 100),
'max_depth': (2, 100),
'subsample': (0.1, 1),
'min_child_samples' : (2, 100)
}
)
rf_bo.maximize()
