Simple Pipeline

[1]:

import pandas as pd
import numpy as np
from skpipes.pipeline import SkPipeline

[2]:

data = [{"x1": 1, "x2": 400, "x3": np.nan},
        {"x1": 4.8, "x2": 250, "x3": 50},
        {"x1": 3, "x2": 140, "x3": 43},
        {"x1": 1.4, "x2": 357, "x3": 75},
        {"x1": 2.4, "x2": np.nan, "x3": 42},
        {"x1": 4, "x2": 287, "x3": 21}]

df = pd.DataFrame(data)
df.head()

[2]:

	x1	x2	x3
0	1.0	400.0	NaN
1	4.8	250.0	50.0
2	3.0	140.0	43.0
3	1.4	357.0	75.0
4	2.4	NaN	42.0

[3]:

pipe = SkPipeline(name='median_imputer-minmax',
                  data_type="numerical")
pipe.steps

[3]:

[('imputer', SimpleImputer(strategy='median')), ('scaler', MinMaxScaler())]

[4]:

str(pipe)

[4]:

'Median imputer with MinMax Scaler'

[5]:

pipe.fit(df)

[5]:

SkPipeline(data_type='numerical', name='median_imputer-minmax')

[6]:

pipe.transform(df)

[6]:

array([[0.        , 1.        , 0.40740741],
       [1.        , 0.42307692, 0.53703704],
       [0.52631579, 0.        , 0.40740741],
       [0.10526316, 0.83461538, 1.        ],
       [0.36842105, 0.56538462, 0.38888889],
       [0.78947368, 0.56538462, 0.        ]])

[7]:

pipe.fit_transform(df)

[7]:

array([[0.        , 1.        , 0.40740741],
       [1.        , 0.42307692, 0.53703704],
       [0.52631579, 0.        , 0.40740741],
       [0.10526316, 0.83461538, 1.        ],
       [0.36842105, 0.56538462, 0.38888889],
       [0.78947368, 0.56538462, 0.        ]])