Pipeline

pipe_1.py

from sklearn.compose import ColumnTransformer

pipe_10.py

df = pd.DataFrame({"col1":["a","b",np.nan,"c"],"col2":[1,2,np.nan,5]})
print(df)

pipe_11.py

ct = ColumnTransformer(transformers=[('mode_impute1',SimpleImputer(strategy="most_frequent"),[0]),
                                    ('one_hot_encode1',OneHotEncoder(),[0]),
                                    ('median_impute2',SimpleImputer(strategy="median"),[1])])
df = ct.fit_transform(df)
print(df)

pipe_12.py

df = pd.DataFrame({"col1":["a","b","d","c"],"col2":[1,2,np.nan,5]})
print(df)

pipe_13.py

ct = ColumnTransformer(transformers=[('ord_encode1',OrdinalEncoder(),[0]),
                                     ('scale1',MinMaxScaler(),[0]),
                                     ('median_impute2',SimpleImputer(strategy="median"),[1])])
df = ct.fit_transform(df)
print(df)

pipe_14.py

from sklearn.pipeline import Pipeline

pipe_15.py

df = pd.DataFrame({"col1":[1,2,np.nan,3],"col2":[1,np.nan,1,5]})
print(df)

pipe_16.py

pipe = Pipeline(steps=[('imputation',SimpleImputer(strategy="median")),
                       ("scaling",MinMaxScaler())])
df = pipe.fit_transform(df)
print(df)

pipe_17.py

df = pd.DataFrame({"col1":[1,2,np.nan,3],"col2":[1,np.nan,1,5]})
print(df)

pipe_18.py

df = SimpleImputer(strategy="median").fit_transform(df)
df = MinMaxScaler().fit_transform(df)
print(df)

pipe_19.py

df = pd.DataFrame({"col1":["a","b",np.nan,"a"],"col2":[1,2,np.nan,5]})
print(df)

pipe_2.py

df = pd.DataFrame({"col1":["a","b","a","c"],"col2":["a","b","a","c"]})
print(df)

pipe_20.py

col1_pipe = Pipeline(steps=[('mode_col1',SimpleImputer(strategy="most_frequent")),
                            ("one_hot_encode",OneHotEncoder())])

col_transform = ColumnTransformer(transformers=[("col1",col1_pipe,[0]),
                                                ("col2",SimpleImputer(strategy="median"),[1])])

df = col_transform.fit_transform(df)
print(df)

pipe_3.py

ohe = OneHotEncoder()
df = ohe.fit_transform(df)
print(df.toarray())

pipe_4.py

df = pd.DataFrame({"col1":["a","b","a","c"],"col2":["a","b","a","c"]})
print(df)

pipe_5.py

ct = ColumnTransformer(transformers = [('ohe_col1',OneHotEncoder(),[0]),
                                       ('ord_col2',OrdinalEncoder(),[1])])
df = ct.fit_transform(df)
print(df)

pipe_6.py

df = pd.DataFrame({"col1":["a","b","a","c"],"col2":["a","b","a","c"]})
print(df)

pipe_7.py

ct = ColumnTransformer(transformers = [('ohe_col1',OneHotEncoder(),[0])])
df = ct.fit_transform(df)
print(df)

pipe_8.py

df = pd.DataFrame({"col1":["a","b","a","c"],"col2":["a","b","a","c"]})
print(df)

pipe_9.py

ct = ColumnTransformer(transformers = [('ohe_col1',OneHotEncoder(),[0])],remainder="passthrough")
df = ct.fit_transform(df)
print(df)