sklearn 常用api（一）
import numpy as np
np.set_printoptions(precision=4)类别的编码
将类别变为从0开始计数；
from sklearn.preprocessing import LabelEncoder>>> y = np.array(['r', 'g', 'g', 'b'])
>>> enc = LabelEncoder()
>>> enc.fit(y)
>>> y = enc.transform(y)
>>> y
array([2, 1, 1, 0], dtype=int32)
>>> enc.transform(['r', 'g', 'b'])
[2 1 0]或者fit、transform两步并作一步fit_transform：
>>> y = np.array(['r', 'g', 'g', 'b'])
>>> enc = LabelEncoder()
>>> y = enc.fit_transform(y)
>>> y
array([2, 1, 1, 0], dtype=int32)自然也有求逆的转换 (inverse_transform)（我们为了操作的 方便，将原本内含丰富的类别标签转换为以0开始的数字型标签，操作完成之后，我们希望能转换为原始的标签形态）：
>>> enc.inverse_transform(y)
['r', 'g', 'g', 'b']clone：同时保存原始和fitted后的模型
from sklearn.base import cloneself.classifiers_ = []
for clf in self.classifiers:
fitted_clf = clone(clf).fit(X, self.enc.transform(y))
self.classifiers_.append(fitted_clf)clf.predict_proba()
from sklearn.naive_bayes import BernoulliNB>>> classes = ['one','two','three','one','three']
>>> feature = [[0,1,1,0],[0,1,0,1],[1,1,0,0],[0,0,0,0],[0,1,1,1]]
>>> clf = BernoulliNB()
>>> clf.fit(feature, classes)
>>> P = clf.predict_proba(feature)
>>> P
[[ 0.5428 0.3619 0.0953]
[ 0.1958 0.3916 0.4126]
[ 0.2835 0.5671 0.1494]
[ 0.7154 0.159 0.1256]
[ 0.2467 0.4934 0.2599]]
>>> P.shape
(5, 3)
# n_samples * n_classes
>>> P.dot(np.ones(len(np.unique(classes))))
[ 1. 1. 1. 1. 1.]
# P的行和为1
# 也即P的每一行代表当前样本属于每一类的概率分布scikit-learn uses the predict_proba method (if applicable) to compute the ROC AUC score. 关于ROC AUC 理解及实践的详细信息，见[ROC曲线与AUC区域的理解与实践]，[分类模型的精确率（precision）与召回率（recall）（Python）]
fit
模型（model）从训练数据集中学习得到（模型所需）参数的过程即为 fit
class MajVoteClf(BaseEstimator, ClassifierMixin):
def __init__(self, classifiers):
self.classifiers = classifiers
def fit(self, X, y):
self.enc = LabelEncoder()
self.enc.fit(y)
self.classes = self.enc.classes
self.classifiers_ = []
for clf in self.classifiers:
fitted_clf = clone(clf).fit(X, self.enc.transform(y))
self.classifiers_.append(fitted_clf)
_name_estimators
from sklearn.pipeline import _name_estimators>>> from sklearn.pipeline import _name_estimators
>>> help(_name_estimators)
Generate names for estimators.（及参数信息）以二元tuple构成的list的形式返回，每一个list中的元素（二元tuple）对应于一个classifier。
>>> from sklearn.svm import SVC
>>> from sklearn.linear_model import LogisticRegression
>>> _name_estimators([SVC(), LogisticRegression()])
[
(
'logisticregression',
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True, intercept_scaling=1, max_iter=100, multi_class='ovr', penalty='l2', random_state=None, solver='liblinear', tol=0.0001, verbose=0)
),
(
'svc',
SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0, degree=3, gamma=0.0, kernel='rbf', max_iter=-1, probability=False, random_state=None, shrinking=True, tol=0.001, verbose=False)
)
]接下来，我们将这些二元tuple构成的list转换为dict类型（非常实用的一种转换）：
>>> named_clfs = {k:v for k, v in _name_classifiers([LogisticRegression(), SVC()])}
{
'logisticregression':
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True, intercept_scaling=1, max_iter=100, multi_class='ovr', penalty='l2', random_state=None, solver='liblinear', tol=0.0001, verbose=0),
'svc':
SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0, degree=3, gamma=0.0, kernel='rbf', max_iter=-1, probability=False, random_state=None, shrinking=True, tol=0.001, verbose=False)
}