【机器学习】使用sklearn的model

首先：文中有废话，有缺失是必然的，大家听我bb几分钟，不如看看

• 官方文档

比如我们现在有一颗决策树了，我们看了看模型得分，嚯，太磕碜了
必须得作出一些改变了
这里的调参指调超参，
一般参数，是拟合出一个模型后，比如说用回归树，拟合出一条一次直线，有了几个斜率和一个截距，这是参数
超参是参数的参数，比如得出这条直线用到的：树的最大深度、节点拆分策略是随机拆分呀还是最佳拆分这些

dtm = DecisionTreeRegressor(max_depth=4,
                           min_samples_split=5,
                           max_leaf_nodes=10)
dtm.fit(X,y)
dtm.fit(X_test,y_test)   

print("R-Squared on train dataset={}".format(dtm.score(X_test,y_test)))
print("R-Squaredon test dataset={}".format(dtm.score(X_test,y_test)))

怎么改变呢，如果动手能力强，可以写点for循环，让他慢慢跑
当然sklearn也有现成的包可以调
那就优雅地调包吧

from sklearn.metrics import make_scorer
from sklearn.model_selection import GridSearchCV

clf = DecisionTreeClassifier(random_state=42)

# TODO: Create the parameters list you wish to tune.
parameters = {'max_depth':[2,4,6,8,10],
			  'min_samples_leaf':[2,4,6,8,10], 
			  'min_samples_split':[2,4,6,8,10]}

# TODO: Make an fbeta_score scoring object.
scorer = make_scorer(f1_score)

# TODO: Perform grid search on the classifier using 'scorer' as the scoring method.
grid_obj =  GridSearchCV(clf, parameters, scoring=scorer)

# TODO: Fit the grid search object to the training data and find the optimal parameters.
best_clf= grid_obj.fit(X_train, y_train)

# Let's also explore what parameters ended up being used in the new model.
best_clf

>>> Best Hyperparameters::
	{'criterion': 'mse', 'max_depth': 8, 'max_leaf_nodes': 100, 
	 'min_samples_leaf': 20, 'min_samples_split': 10}