笔记：Preprocessing data — scikit-learn 0.22.2 documentation
from sklearn import preprocessing
import numpy as np
X_train=np.array([[1.,-1.,2.],
[1.,0.,0.],
[0.,1.0,-1.]])
help(preprocessing.scale)
scale(X, axis=0, with_mean=True, with_std=True, copy=True)
axis=0:默认是按照每一个特征(即按照列)进行标准化；
axis=1:则为行，按照样本进本进行标准化
X_scaled=preprocessing.scale(X_train)
X_scaled
array([[ 0.70710678, -1.22474487, 1.33630621],
[ 0.70710678, 0. , -0.26726124],
[-1.41421356, 1.22474487, -1.06904497]])
X_scaled.mean(axis=0)
array([7.40148683e-17, 0.00000000e+00, 0.00000000e+00])
X_scaled.std(axis=0)
array([1., 1., 1.])
#与之类似的是StandarScaler()
scaler=preprocessing.StandardScaler().fit(X_train)
scaler.mean_
array([0.66666667, 0. , 0.33333333])
#标准差
scaler.scale_
#等价于X_train.std(axis=0)
array([0.47140452, 0.81649658, 1.24721913])
scaler.transform(X_train)
array([[ 0.70710678, -1.22474487, 1.33630621],
[ 0.70710678, 0. , -0.26726124],
[-1.41421356, 1.22474487, -1.06904497]])
#对新数据
X_test=[[-1.,1.,0.]]
scaler.transform(X_test)
array([[-3.53553391, 1.22474487, -0.26726124]])
help(preprocessing.MinMaxScaler)：
X_std = (X - X.min(axis=0)) / (X.max(axis=0) - X.min(axis=0))
X_scaled = X_std * (max - min) + min
preprocessing.MinMaxScaler(feature_range=(min,max),copy=True)
min_max_scaler=preprocessing.MinMaxScaler()
X_train_minmax=min_max_scaler.fit_transform(X_train)
X_train_minmax
array([[1. , 0. , 1. ],
[1. , 0.5 , 0.33333333],
[0. , 1. , 0. ]])
#对于新数据的处理
X_test=np.array([[-3.,-1.,4.]])
X_test_minmax=min_max_scaler.transform(X_test)
X_test_minmax
array([[-3. , 0. , 1.66666667]])
min_max_scaler.scale_
array([1. , 0.5 , 0.33333333])
min_max_scaler.min_
array([0. , 0.5 , 0.33333333])
help(preprocessing.MaxAbsScaler)：
class MaxAbsScaler(sklearn.base.TransformerMixin, sklearn.base.BaseEstimator)
Scale each feature by its maximum absolute(最大值的绝对值) value.
max_abs_scaler=preprocessing.MaxAbsScaler()
X_train=np.array([[1.,-1.,-2.],
[2.,0.,0.],
[0.,1.,-1.]])
X_train_maxabs=max_abs_scaler.fit_transform(X_train)
X_train_maxabs
array([[ 0.5, -1. , -1. ],
[ 1. , 0. , 0. ],
[ 0. , 1. , -0.5]])
help(preprocessing.QuantileTransformer)
class QuantileTransformer(sklearn.base.TransformerMixin, sklearn.base.BaseEstimator)
Transform features using quantiles information(使用分位数信息变换特征).
preprocessing.QuantileTransformer(n_quantiles=1000, output_distribution=‘uniform‘, ignore_implicit_zeros=False, subsample=100000, random_state=None, copy=True)[source]?
Marginal distribution for the transformed data. The choices are ‘uniform’ (default) or ‘normal’.
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
X,y=load_iris(return_X_y=True)
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
quantile_transformer=preprocessing.QuantileTransformer(random_state=0)
X_train_trans=quantile_transformer.fit_transform(X_train)
d:\software\python\lib\site-packages\sklearn\preprocessing\_data.py:2357: UserWarning: n_quantiles (1000) is greater than the total number of samples (112). n_quantiles is set to n_samples.
% (self.n_quantiles, n_samples))
X_test_trans=quantile_transformer.transform(X_test)
np.percentile(X_train[:,0],[0,25,50,75,100])
array([4.3, 5.1, 5.8, 6.5, 7.9])
np.percentile(X_train_trans[:,0],[0,25,50,75,100])
array([0. , 0.23873874, 0.50900901, 0.74324324, 1. ])
#### 映射到高斯分布
help(preprocessing.PowerTransformer)
class PowerTransformer(sklearn.base.TransformerMixin, sklearn.base.BaseEstimator)
| Apply a power transform featurewise to make data more Gaussian-like.
Parameters
| method : str, (default=‘yeo-johnson‘)
| The power transform method. Available methods are:
|
| - ‘yeo-johnson‘ [1]_, works with positive and negative values
| - ‘box-cox‘ [2]_, only works with strictly positive values
pt=preprocessing.PowerTransformer(method=‘box-cox‘,standardize=False)
X_lognormal=np.random.RandomState(616).lognormal(size=(3,3))
X_lognormal
array([[1.28331718, 1.18092228, 0.84160269],
[0.94293279, 1.60960836, 0.3879099 ],
[1.35235668, 0.21715673, 1.09977091]])
pt.fit_transform(X_lognormal)
array([[ 0.49024349, 0.17881995, -0.1563781 ],
[-0.05102892, 0.58863195, -0.57612414],
[ 0.69420009, -0.84857822, 0.10051454]])
help(preprocessing.normalize)
normalize(X, norm=‘l2‘, axis=1, copy=True, return_norm=False)
Scale input vectors individually to unit norm (vector length).
norm : ‘l1‘, ‘l2‘, or ‘max‘, optional (‘l2‘ by default)
The norm to use to normalize each non zero sample (or each non-zero feature if axis is 0).
axis : 0 or 1, optional (1 by default)
axis used to normalize the data along. If 1, independently normalize each sample, otherwise (if 0) normalize each feature.
X_train=np.array([[1.,-1.,-2.],
[2.,0.,0.],
[0.,1.,-1.]])
X_train_normalized=preprocessing.normalize(X_train,norm=‘l2‘)
X_train_normalized
array([[ 0.40824829, -0.40824829, -0.81649658],
[ 1. , 0. , 0. ],
[ 0. , 0.70710678, -0.70710678]])
#使用管道函数:sklearn.pipeline.Pipeline
normalizer=preprocessing.Normalizer().fit(X_train)
normalizer
Normalizer(copy=True, norm=‘l2‘)
normalizer.transform(X_train)
array([[ 0.40824829, -0.40824829, -0.81649658],
[ 1. , 0. , 0. ],
[ 0. , 0.70710678, -0.70710678]])
#### 编码
help(preprocessing.OrdinalEncoder):
class OrdinalEncoder(_BaseEncoder)
| Encode categorical features as an integer array.
| The input to this transformer should be an array-like of integers or strings, denoting the values taken on by categorical (discrete) features.
| The features are converted to ordinal integers. This results in a single column of integers (0 to n_categories - 1) per feature.
enc = preprocessing.OrdinalEncoder()
X = [[‘male‘, ‘from US‘, ‘uses Safari‘], [‘female‘, ‘from Europe‘, ‘uses Firefox‘]]
enc.fit(X)
OrdinalEncoder(categories=‘auto‘, dtype=<class ‘numpy.float64‘>)
enc.transform([[‘female‘, ‘from US‘, ‘uses Safari‘]])
array([[0., 1., 1.]])
genders = [‘female‘, ‘male‘]
locations = [‘from Africa‘, ‘from Asia‘, ‘from Europe‘, ‘from US‘]
browsers = [‘uses Chrome‘, ‘uses Firefox‘, ‘uses IE‘, ‘uses Safari‘]
enc = preprocessing.OneHotEncoder(categories=[genders, locations, browsers])
X = [[‘male‘, ‘from US‘, ‘uses Safari‘], [‘female‘, ‘from Europe‘, ‘uses Firefox‘]]
enc.fit(X)
OneHotEncoder(categories=[[‘female‘, ‘male‘],
[‘from Africa‘, ‘from Asia‘, ‘from Europe‘,
‘from US‘],
[‘uses Chrome‘, ‘uses Firefox‘, ‘uses IE‘,
‘uses Safari‘]],
drop=None, dtype=<class ‘numpy.float64‘>, handle_unknown=‘error‘,
sparse=True)
enc.transform([[‘female‘, ‘from Asia‘, ‘uses Chrome‘]]).toarray()
#逆操作
enc.inverse_transform(np.array([[1., 0., 0., 1., 0., 0., 1., 0., 0., 0.]]))
array([[‘female‘, ‘from Asia‘, ‘uses Chrome‘]], dtype=object)
enc.categories_
[array([‘female‘, ‘male‘], dtype=object),
array([‘from Africa‘, ‘from Asia‘, ‘from Europe‘, ‘from US‘], dtype=object),
array([‘uses Chrome‘, ‘uses Firefox‘, ‘uses IE‘, ‘uses Safari‘],
dtype=object)]
enc.get_feature_names()
array([‘x0_female‘, ‘x0_male‘, ‘x1_from Africa‘, ‘x1_from Asia‘,
‘x1_from Europe‘, ‘x1_from US‘, ‘x2_uses Chrome‘,
‘x2_uses Firefox‘, ‘x2_uses IE‘, ‘x2_uses Safari‘], dtype=object)
#### K-bins离散化
help(preprocessing.KBinsDiscretizer):
class KBinsDiscretizer(sklearn.base.TransformerMixin,sklearn.base.BaseEstimator) Bin continuous data into intervals.
Parameters
n_bins : int or array-like, shape (n_features,) (default=5)
The number of bins to produce. Raises ValueError if n_bins < 2.
encode : {‘onehot‘, ‘onehot-dense‘, ‘ordinal‘}, (default=‘onehot‘)Method used to encode the transformed result.
onehot：Encode the transformed result with one-hot encoding and return a sparse matrix. Ignored features are always stacked to the right.
onehot-dense：Encode the transformed result with one-hot encoding and return a dense array. Ignored features are always stacked to the right.
ordinal：Return the bin identifier encoded as an integer value.
strategy : {‘uniform‘, ‘quantile‘, ‘kmeans‘}, (default=‘quantile‘)
Strategy used to define the widths of the bins.
X=np.array([[-3,5.,15],
[0.,6.,14],
[6.,3.,11]])
est=preprocessing.KBinsDiscretizer(n_bins=[3,2,2],encode=‘ordinal‘).fit(X)
#生成的箱是左闭右开
"""
特征1：[-3,-1)-->0;
[-1,2)-->1；
[2,6]-->3
"""
est.bin_edges_
array([array([-3., -1., 2., 6.]), array([3., 5., 6.]),
array([11., 14., 15.])], dtype=object)
est.transform(X)
array([[0., 1., 1.],
[1., 1., 1.],
[2., 0., 0.]])
help(preprocessing.Binarizer):二值编码(默认阈值为0)
class Binarizer(sklearn.base.TransformerMixin, sklearn.base.BaseEstimator)
| Binarize data (set feature values to 0 or 1) according to a threshold
| Values greater than the threshold map to 1, while values less than or equal to the threshold map to 0. With the default threshold of 0,
| only positive values map to 1.
| Binarization is a common operation on text count data where the analyst can decide to only consider the presence or absence of a
| feature rather than a quantified number of occurrences for instance.
| It can also be used as a pre-processing step for estimators that consider boolean random variables (e.g. modelled using the Bernoulli
| distribution in a Bayesian setting).
Parameters
| threshold : float, optional (0.0 by default)
| Feature values below or equal to this are replaced by 0, above it by 1.
| Threshold may not be less than 0 for operations on sparse matrices.
binarizer = preprocessing.Binarizer(threshold=5.5).fit(X) # fit does nothing
binarizer.transform(X)
array([[0., 0., 1.],
[0., 1., 1.],
[1., 0., 1.]])
#### 生成多项式特征
help(preprocessing.PolynomialFeatures)
class PolynomialFeatures(sklearn.base.TransformerMixin,sklearn.base.BaseEstimator)
| Generate polynomial and interaction features.
|
| Generate a new feature matrix consisting of all polynomial combinations of the features with degree less than or equal to the specified degree.
| For example, if an input sample is two dimensional and of the form [a, b], the degree-2 polynomial features are [1, a, b, a^2, ab, b^2].
Parameters
degreeinteger:The degree of the polynomial features. Default = 2.
interaction_onlyboolean, default = False
If true, only interaction features are produced: features that are products of at most degree distinct input features (so not x[1] ** 2, x[0] * x[2] ** 3, etc.).
include_biasboolean:
If True (default), then include a bias column, the feature in which all polynomial powers are zero (i.e. a column of ones -acts as an intercept term in a linear model).
X=np.arange(6).reshape(3,2)
X
array([[0, 1],
[2, 3],
[4, 5]])
poly=preprocessing.PolynomialFeatures(2)
poly.fit_transform(X)
array([[ 1., 0., 1., 0., 0., 1.],
[ 1., 2., 3., 4., 6., 9.],
[ 1., 4., 5., 16., 20., 25.]])
poly1=preprocessing.PolynomialFeatures(1)
poly1.fit_transform(X)
array([[1., 0., 1.],
[1., 2., 3.],
[1., 4., 5.]])
#交互项设置
X=np.arange(9).reshape(3,3)
X
array([[0, 1, 2],
[3, 4, 5],
[6, 7, 8]])
poly=preprocessing.PolynomialFeatures(degree=3,interaction_only=True)
poly.fit_transform(X)
#X的特征已经从(x1,x2,x3)到(1,x1,x2,x3,x1x2,x1x3,x2x3,x1x2x3)
array([[ 1., 0., 1., 2., 0., 0., 2., 0.],
[ 1., 3., 4., 5., 12., 15., 20., 60.],
[ 1., 6., 7., 8., 42., 48., 56., 336.]])
#### 自定义编码
help(preprocessing.FunctionTransformer)
transformer=preprocessing.FunctionTransformer(np.log1p,validate=True)
#np.log1p:在整个数组上逐个元素操作的函数,Calculates ``log(1 + x)``.。
X=np.array([[0,1],[2,3]])
transformer.transform(X)
array([[0. , 0.69314718],
[1.09861229, 1.38629436]])原文：https://www.cnblogs.com/B-Hanan/p/12774056.html