“columnTransformer in randomizedSearchCV” Code-Antworten

columnTransformer in randomizedSearchCV

import seaborn as sns
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder, KBinsDiscretizer, MinMaxScaler
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression

df = sns.load_dataset('titanic')[['survived', 'age', 'embarked']]
X_train, X_test, y_train, y_test = train_test_split(df.drop(columns='survived'), df['survived'], test_size=0.2, 
                                                    random_state=123)
num = ['age']
cat = ['embarked']

num_transformer = Pipeline(steps=[('imputer', SimpleImputer()), 
                                  ('discritiser', KBinsDiscretizer(encode='ordinal', strategy='uniform')),
                                  ('scaler', MinMaxScaler())])

cat_transformer = Pipeline(steps=[('imputer', SimpleImputer(strategy='constant', fill_value='missing')),
                                  ('onehot', OneHotEncoder(handle_unknown='ignore'))])

preprocessor = ColumnTransformer(transformers=[('num', num_transformer, num),
                                               ('cat', cat_transformer, cat)])

pipe = Pipeline(steps=[('preprocessor', preprocessor),
                       ('classiffier', LogisticRegression(random_state=1, max_iter=10000))])

param_grid = {'preprocessor__num__imputer__strategy' : ['mean', 'median'],
              'preprocessor__num__discritiser__n_bins' : range(5,10),
              'classiffier__C' : [0.1, 10, 100],
              'classiffier__solver' : ['liblinear', 'saga']}
grid_search = GridSearchCV(pipe, param_grid=param_grid, cv=10)
grid_search.fit(X_train, y_train)