7

我正在 sci-kit learn 中构建线性回归模型，并将输入缩放作为 sci-kit learn Pipeline 中的预处理步骤。有什么办法可以避免缩放二进制列？发生的事情是这些列与其他列一起缩放，导致值以 0 为中心，而不是 0 或 1，所以我得到像 [-0.6, 0.3] 这样的值，这导致输入值为 0影响我的线性模型中的预测。

基本代码来说明：

>>> import numpy as np
>>> from sklearn.pipeline import Pipeline
>>> from sklearn.preprocessing import StandardScaler
>>> from sklearn.linear_model import Ridge
>>> X = np.hstack( (np.random.random((1000, 2)),
                np.random.randint(2, size=(1000, 2))) )
>>> X
array([[ 0.30314072,  0.22981496,  1.        ,  1.        ],
       [ 0.08373292,  0.66170678,  1.        ,  0.        ],
       [ 0.76279599,  0.36658793,  1.        ,  0.        ],
       ...,
       [ 0.81517519,  0.40227095,  0.        ,  0.        ],
       [ 0.21244587,  0.34141014,  0.        ,  0.        ],
       [ 0.2328417 ,  0.14119217,  0.        ,  0.        ]])
>>> scaler = StandardScaler()
>>> scaler.fit_transform(X)
array([[-0.67768374, -0.95108883,  1.00803226,  1.03667198],
       [-1.43378124,  0.53576375,  1.00803226, -0.96462528],
       [ 0.90632643, -0.48022732,  1.00803226, -0.96462528],
       ...,
       [ 1.08682952, -0.35738315, -0.99203175, -0.96462528],
       [-0.99022572, -0.56690563, -0.99203175, -0.96462528],
       [-0.91994001, -1.25618613, -0.99203175, -0.96462528]])

我希望最后一行的输出是：

>>> scaler.fit_transform(X, dont_scale_binary_or_something=True)
array([[-0.67768374, -0.95108883,  1.        ,  1.        ],
       [-1.43378124,  0.53576375,  1.        ,  0.        ],
       [ 0.90632643, -0.48022732,  1.        ,  0.        ],
       ...,
       [ 1.08682952, -0.35738315,  0.        ,  0.        ],
       [-0.99022572, -0.56690563,  0.        ,  0.        ],
       [-0.91994001, -1.25618613,  0.        ,  0.        ]])

我有什么办法可以做到这一点？我想我可以只选择不是二进制的列，只转换这些列，然后将转换后的值替换回数组，但我希望它与 sci-kit 学习管道工作流很好地配合，所以我可以做类似的事情：

clf = Pipeline([('scaler', StandardScaler()), ('ridge', Ridge())])
clf.set_params(scaler__dont_scale_binary_features=True, ridge__alpha=0.04).fit(X, y)
4

6 回答 6

6

我发布了根据@miindlek 的回复改编的代码，以防万一它对其他人有帮助。当我没有包含 BaseEstimator 时遇到错误。再次感谢@miindlek。下面， bin_vars_index 是二进制变量的列索引数组，而 cont_vars_index 与要缩放的连续变量相同。

from sklearn.preprocessing import StandardScaler
from sklearn.base import BaseEstimator, TransformerMixin
import numpy as np

class CustomScaler(BaseEstimator,TransformerMixin): 
    # note: returns the feature matrix with the binary columns ordered first  
    def __init__(self,bin_vars_index,cont_vars_index,copy=True,with_mean=True,with_std=True):
        self.scaler = StandardScaler(copy,with_mean,with_std)
        self.bin_vars_index = bin_vars_index
        self.cont_vars_index = cont_vars_index

    def fit(self, X, y=None):
        self.scaler.fit(X[:,self.cont_vars_index], y)
        return self

    def transform(self, X, y=None, copy=None):
        X_tail = self.scaler.transform(X[:,self.cont_vars_index],y,copy)
        return np.concatenate((X[:,self.bin_vars_index],X_tail), axis=1)
于 2016-12-29T00:42:56.207 回答
6

您应该创建一个自定义缩放器，在缩放时忽略最后两列。

from sklearn.base import TransformerMixin
import numpy as np

class CustomScaler(TransformerMixin): 
    def __init__(self):
        self.scaler = StandardScaler()

    def fit(self, X, y):
        self.scaler.fit(X[:, :-2], y)
        return self

    def transform(self, X):
        X_head = self.scaler.transform(X[:, :-2])
        return np.concatenate(X_head, X[:, -2:], axis=1)
于 2016-06-07T17:38:51.023 回答
5

您的管道应更改为：

from sklearn.preprocessing import StandardScaler,FunctionTransformer
from sklearn.pipeline import Pipeline,FeatureUnion


pipeline=Pipeline(steps= [
    ('feature_processing', FeatureUnion(transformer_list = [
            ('categorical', FunctionTransformer(lambda data: data[:, cat_indices])),

            #numeric
            ('numeric', Pipeline(steps = [
                ('select', FunctionTransformer(lambda data: data[:, num_indices])),
                ('scale', StandardScaler())
                        ]))
        ])),
    ('clf', Ridge())
    ]
)
于 2018-03-12T09:52:10.630 回答
4

我已经对 @J_C 代码进行了一些调整，以使用 pandas 数据框。您可以传递要缩放的列名，并获得初始列顺序的结果。

enter code here
from sklearn.preprocessing import StandardScaler
from sklearn.base import BaseEstimator, TransformerMixin
import pandas as pd

class CustomScaler(BaseEstimator,TransformerMixin): 
    def __init__(self,columns,copy=True,with_mean=True,with_std=True):
        self.scaler = StandardScaler(copy,with_mean,with_std)
        self.columns = columns

    def fit(self, X, y=None):
        self.scaler.fit(X[self.columns], y)
        return self

    def transform(self, X, y=None, copy=None):
        init_col_order = X.columns
        X_scaled = pd.DataFrame(self.scaler.transform(X[self.columns]), columns=self.columns)
        X_not_scaled = X.ix[:,~X.columns.isin(self.columns)]
        return pd.concat([X_not_scaled, X_scaled], axis=1)[init_col_order]

用法：

scale = CustomScaler(columns=['duration', 'num_operations'])
scaled = scale.fit_transform(churn_d)
于 2017-01-04T10:42:10.303 回答
3

我发现@Vitaliy Grabovets 数据框版本中的连接无法正常工作，除非您指定 X_scaled 的索引。因此，相关行现在显示为：

X_scaled = pd.DataFrame(self.scaler.transform(X[self.columns]), columns=self.columns, index=X.index)
于 2017-02-09T15:25:52.723 回答
2

这可能会让你更容易

    import pandas as pd
    import numpy as np

    X = np.hstack((np.random.random((1000, 2)),np.random.randint(2, size=        (1000, 2))))

    df=pd.DataFrame(X,columns=["num_1","num_2","binary_1","binary_2"])

    from sklearn.pipeline import Pipeline
    from sklearn.compose import ColumnTransformer
    from sklearn.preprocessing import OneHotEncoder

    num_pipeline = Pipeline([            
        ('std_scaler', StandardScaler()),
    ])

    num_attribs=["num_1","num_2"]
    binary_attribs=["binary_1","binary_2"]


    full_pipeline = ColumnTransformer([
        ("num_cols", num_pipeline, num_attribs),
        ("binary_cols",OneHotEncoder(drop="first"),binary_attribs),
    ])

    full_pipeline.fit_transform(df)
于 2020-08-29T08:00:07.463 回答