#關於 OneVsRestClassifier(LogisticRegression(太慢了，要用超過的機器)

#關於 OneVsRestClassifier
#注意以下代碼中，有三個類
from sklearn import datasets
X, y = datasets.make_classification(n_samples=10000, n_classes=3)
from sklearn.tree import DecisionTreeClassifier
dt = DecisionTreeClassifier()
dt.fit(X, y)
print(dt.predict(X))
print ("Accuracy:\t", (y == dt.predict(X)).mean())

#利用 OneVsRestClassifier，進行分類
#它好像是個外殼，還是利用里面的分類器進行分類
#只不過加快了速度（並行）

from sklearn.multiclass import OneVsRestClassifier
from sklearn.linear_model import LogisticRegression
'''
Now, we'll override the LogisticRegression classifier.
Also, notice that we can parallelize this.
If we think about how OneVsRestClassifier works,
it's just training separate models and then comparing them.
So, we can train the data separately at the same time:
'''
#LogisticRegression 速度很慢
mlr = OneVsRestClassifier(LogisticRegression(), n_jobs=2)
mlr.fit(X, y)
print(mlr.predict(X))
print ("Accuracy:\t", (y == mlr.predict(X)).mean())