如何使用 scikit-learn 创建自定义 ColumnTransformer？

Question

鉴于，我有以下数据集：

from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.compose import make_column_transformer
from sklearn.preprocessing import MinMaxScaler
import numpy as np
import pandas as pd

dt = pd.DataFrame( { "time":[ "1/4/2021 0:00","1/4/2021 1:00","1/4/2021 2:00","1/4/2021 3:00","1/4/2021 4:00"],
                 "age":np.random.randint(12,80,5) })

我需要创建一个 自定义 ColumnTransformer 使用 scikit-learn 将数据和时间特征转换为数字特征。

这是我的习惯 ColumnTransformer:

class DateTimeTransformer(BaseEstimator, TransformerMixin):

    def fit(self, X, y = None):
        return self

    def transform(self, X, y = None):
        return np.c_[ [self.date_and_time_to_num(x) for x in X] ]


    def date_and_time_to_num(self,date_and_time):
        date_and_time_in_list = date_and_time.split(" ")
        date_in_seconds = self.date_to_num(date_and_time_in_list[0])
        time_in_seconds = self.time_to_num(date_and_time_in_list[1])
        return date_in_seconds + time_in_seconds

    def date_to_num(self,date):
        yy, mm, dd = map(int, date.split('/'))
        return 10000 * yy + 100 * mm + dd

    def time_to_num(self,time_str):
        hh, mm = map(int, time_str.split(':'))
        return 60 * (mm + 60 * hh)

然后我可以使用以下两个函数转换我的特征：

def process_data(x):
    column_transformer = get_column_transformer()
    column_transformer.fit(X=x)
    return column_transformer.transform(x)

def get_column_transformer():
    return make_column_transformer(
        (MinMaxScaler(),dt["age"].values.tolist()),
        (DateTimeTransformer(),dt["time"].values.tolist())
    )

最后我调用 process_data 来应用更改：

print(process_data(dt))

但是，我遇到了以下错误：

    raise ValueError(
ValueError: all features must be in [0, 1] or [-2, 0]

Answer 1

错误是由于make_column_transformer将列名或列索引作为输入，而不是数据。在您的情况下，正确的语法是

make_column_transformer(
   (MinMaxScaler(), ['age']),
   (DateTimeTransformer(), 'time')
)

或者，等价地，

make_column_transformer(
    (MinMaxScaler(), [1]),
    (DateTimeTransformer(), 0)
)

对于 MinMaxScaler 你应该使用 ['age'] 或 [1] 因为 MinMaxScaler 需要一个二维数组作为输入（例如 pd.DataFrame），而对于 DateTimeTransformer，您可以使用 'time' 或 0，因为 DateTimeTransformer 需要一维数组作为输入（例如 pd.Series）。 documentation.

中对此进行了解释

列名示例：

from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.compose import make_column_transformer
from sklearn.preprocessing import MinMaxScaler
import numpy as np
import pandas as pd
np.random.seed(0)

class DateTimeTransformer(BaseEstimator, TransformerMixin):

    def fit(self, X, y=None):
        return self

    def transform(self, X, y=None):
        return np.c_[[self.date_and_time_to_num(x) for x in X]]

    def date_and_time_to_num(self, date_and_time):
        date_and_time_in_list = date_and_time.split(' ')
        date_in_seconds = self.date_to_num(date_and_time_in_list[0])
        time_in_seconds = self.time_to_num(date_and_time_in_list[1])
        return date_in_seconds + time_in_seconds

    def date_to_num(self, date):
        yy, mm, dd = map(int, date.split('/'))
        return 10000 * yy + 100 * mm + dd

    def time_to_num(self, time_str):
        hh, mm = map(int, time_str.split(':'))
        return 60 * (mm + 60 * hh)

def process_data(x):
    column_transformer = get_column_transformer()
    column_transformer.fit(X=x)
    return column_transformer.transform(x)

def get_column_transformer():
    return make_column_transformer(
        (MinMaxScaler(), ['age']),
        (DateTimeTransformer(), 'time')
    )

df = pd.DataFrame({
    'time': ['1/4/2021 0:00', '1/4/2021 1:00', '1/4/2021 2:00', '1/4/2021 3:00', '1/4/2021 4:00'],
    'age': np.random.randint(12, 80, 5)
})

process_data(df)
# array([[0.00000000e+00, 1.24210000e+04],
#        [1.30434783e-01, 1.60210000e+04],
#        [8.69565217e-01, 1.96210000e+04],
#        [1.00000000e+00, 2.32210000e+04],
#        [1.00000000e+00, 2.68210000e+04]])

列索引示例：

from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.compose import make_column_transformer
from sklearn.preprocessing import MinMaxScaler
import numpy as np
import pandas as pd
np.random.seed(0)

class DateTimeTransformer(BaseEstimator, TransformerMixin):

    def fit(self, X, y=None):
        return self

    def transform(self, X, y=None):
        return np.c_[[self.date_and_time_to_num(x) for x in X]]

    def date_and_time_to_num(self, date_and_time):
        date_and_time_in_list = date_and_time.split(' ')
        date_in_seconds = self.date_to_num(date_and_time_in_list[0])
        time_in_seconds = self.time_to_num(date_and_time_in_list[1])
        return date_in_seconds + time_in_seconds

    def date_to_num(self, date):
        yy, mm, dd = map(int, date.split('/'))
        return 10000 * yy + 100 * mm + dd

    def time_to_num(self, time_str):
        hh, mm = map(int, time_str.split(':'))
        return 60 * (mm + 60 * hh)

def process_data(x):
    column_transformer = get_column_transformer()
    column_transformer.fit(X=x)
    return column_transformer.transform(x)

def get_column_transformer():
    return make_column_transformer(
        (MinMaxScaler(), [1]),
        (DateTimeTransformer(), 0)
    )

df = pd.DataFrame({
    'time': ['1/4/2021 0:00', '1/4/2021 1:00', '1/4/2021 2:00', '1/4/2021 3:00', '1/4/2021 4:00'],
    'age': np.random.randint(12, 80, 5)
})

process_data(df)
# array([[0.00000000e+00, 1.24210000e+04],
#        [1.30434783e-01, 1.60210000e+04],
#        [8.69565217e-01, 1.96210000e+04],
#        [1.00000000e+00, 2.32210000e+04],
#        [1.00000000e+00, 2.68210000e+04]])

如何使用 scikit-learn 创建自定义 ColumnTransformer？

How to create a custom ColumnTransformer using scikit-learn?

python

scikit-learn