import numpy as np
import pandas as pd

dictionary = {"Price":[10, 20, 40, 80], "Weight":[2, 5, 7, np.nan], "Fruit":["Apple", "Banana", "Orange", "Orange"]}
df = pd.DataFrame(dictionary)

df

	Price	Weight	Fruit
0	10	2.0	Apple
1	20	5.0	Banana
2	40	7.0	Orange
3	80	NaN	Orange

df_num = df.loc[:, df.columns != "Fruit"]
df_num

	Price	Weight
0	10	2.0
1	20	5.0
2	40	7.0
3	80	NaN

df_cat = df[["Fruit"]]
df_cat

	Fruit
0	Apple
1	Banana
2	Orange
3	Orange

from sklearn.preprocessing import OneHotEncoder

df_cat_encoder = OneHotEncoder(sparse = False)
df_cat_1hot = df_cat_encoder.fit_transform(df_cat)

print(df_cat_1hot)
print(df_cat_encoder.categories_)

[[1. 0. 0.]
 [0. 1. 0.]
 [0. 0. 1.]
 [0. 0. 1.]]
[array(['Apple', 'Banana', 'Orange'], dtype=object)]

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.impute import SimpleImputer


num_pipeline = Pipeline([
    ('imputer', SimpleImputer(strategy = "median")),
    ('stad_scaler', StandardScaler()),
])

print(num_pipeline.fit_transform(df_num))

[[-1.02575529 -1.54030809]
 [-0.65275337  0.14002801]
 [ 0.09325048  1.26025208]
 [ 1.58525817  0.14002801]]

from sklearn.compose import ColumnTransformer

num_attribs = list(df_num.columns)
cat_attribs = ["Fruit"]

print(num_attribs)
print(cat_attribs)

['Price', 'Weight']
['Fruit']

full_pipeline = ColumnTransformer([
        ("num", num_pipeline, num_attribs),
        ("cat", OneHotEncoder(), cat_attribs),
    ])

df_prepared = full_pipeline.fit_transform(df)

df_prepared

array([[-1.02575529, -1.54030809,  1.        ,  0.        ,  0.        ],
       [-0.65275337,  0.14002801,  0.        ,  1.        ,  0.        ],
       [ 0.09325048,  1.26025208,  0.        ,  0.        ,  1.        ],
       [ 1.58525817,  0.14002801,  0.        ,  0.        ,  1.        ]])

all_attributes = num_attribs + list(df_cat_encoder.categories_[0])

df_prepared = pd.DataFrame(df_prepared, columns = all_attributes)

df_prepared

	Price	Weight	Apple	Banana	Orange
0	-1.025755	-1.540308	1.0	0.0	0.0
1	-0.652753	0.140028	0.0	1.0	0.0
2	0.093250	1.260252	0.0	0.0	1.0
3	1.585258	0.140028	0.0	0.0	1.0