Hyperparameter optimization with Scikit-Learn GridSearchCV using different models

import pandas as pd
import numpy as np

from sklearn.model_selection import GridSearchCV

class EstimatorSelectionHelper:

    def __init__(self, models, params):
        if not set(models.keys()).issubset(set(params.keys())):
            missing_params = list(set(models.keys()) - set(params.keys()))
            raise ValueError("Some estimators are missing parameters: %s" % missing_params)
        self.models = models
        self.params = params
        self.keys = models.keys()
        self.grid_searches = {}

    def fit(self, X, y, cv=3, n_jobs=3, verbose=1, scoring=None, refit=False):
        for key in self.keys:
            print("Running GridSearchCV for %s." % key)
            model = self.models[key]
            params = self.params[key]
            gs = GridSearchCV(model, params, cv=cv, n_jobs=n_jobs,
                              verbose=verbose, scoring=scoring, refit=refit,
                              return_train_score=True)
            gs.fit(X,y)
            self.grid_searches[key] = gs    

    def score_summary(self, sort_by='mean_score'):
        def row(key, scores, params):
            d = {
                 'estimator': key,
                 'min_score': min(scores),
                 'max_score': max(scores),
                 'mean_score': np.mean(scores),
                 'std_score': np.std(scores),
            }
            return pd.Series({**params,**d})

        rows = []
        for k in self.grid_searches:
            print(k)
            params = self.grid_searches[k].cv_results_['params']
            scores = []
            for i in range(self.grid_searches[k].cv):
                key = "split{}_test_score".format(i)
                r = self.grid_searches[k].cv_results_[key]        
                scores.append(r.reshape(len(params),1))

            all_scores = np.hstack(scores)
            for p, s in zip(params,all_scores):
                rows.append((row(k, s, p)))

        df = pd.concat(rows, axis=1).T.sort_values([sort_by], ascending=False)

        columns = ['estimator', 'min_score', 'mean_score', 'max_score', 'std_score']
        columns = columns + [c for c in df.columns if c not in columns]

        return df[columns]

from sklearn import datasets

breast_cancer = datasets.load_breast_cancer()
X_cancer = breast_cancer.data
y_cancer = breast_cancer.target

from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.svm import SVC

models1 = {
    'ExtraTreesClassifier': ExtraTreesClassifier(),
    'RandomForestClassifier': RandomForestClassifier(),
    'AdaBoostClassifier': AdaBoostClassifier(),
    'GradientBoostingClassifier': GradientBoostingClassifier(),
    'SVC': SVC()
}

params1 = {
    'ExtraTreesClassifier': { 'n_estimators': [16, 32] },
    'RandomForestClassifier': { 'n_estimators': [16, 32] },
    'AdaBoostClassifier':  { 'n_estimators': [16, 32] },
    'GradientBoostingClassifier': { 'n_estimators': [16, 32], 'learning_rate': [0.8, 1.0] },
    'SVC': [
        {'kernel': ['linear'], 'C': [1, 10]},
        {'kernel': ['rbf'], 'C': [1, 10], 'gamma': [0.001, 0.0001]},
    ]
}

helper1 = EstimatorSelectionHelper(models1, params1)
helper1.fit(X_cancer, y_cancer, scoring='f1', n_jobs=2)

Running GridSearchCV for ExtraTreesClassifier.
Fitting 3 folds for each of 2 candidates, totalling 6 fits

Running GridSearchCV for RandomForestClassifier.
Fitting 3 folds for each of 2 candidates, totalling 6 fits

Running GridSearchCV for GradientBoostingClassifier.
Fitting 3 folds for each of 4 candidates, totalling 12 fits

Running GridSearchCV for AdaBoostClassifier.
Fitting 3 folds for each of 2 candidates, totalling 6 fits

Running GridSearchCV for SVC.
Fitting 3 folds for each of 6 candidates, totalling 18 fits

helper1.score_summary(sort_by='max_score')

from sklearn.base import BaseEstimator
from sklearn.linear_model import SGDClassifier

class ClfSwitcher(BaseEstimator):

    def __init__(
            self,
            estimator=SGDClassifier(),
    ):
        """
        A Custom BaseEstimator that can switch between classifiers.
        :param estimator: sklearn object - The classifier
        """
        self.estimator = estimator

    def fit(self, X, y=None, **kwargs):
        self.estimator.fit(X, y)
        return self

    def predict(self, X, y=None):
        return self.estimator.predict(X)

    def predict_proba(self, X):
        return self.estimator.predict_proba(X)

    def score(self, X, y):
        return self.estimator.score(X, y)

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.linear_model import SGDClassifier
from sklearn.pipeline import Pipeline
from sklearn.model_selection import GridSearchCV

pipeline = Pipeline([
    ('tfidf', TfidfVectorizer()),
    ('clf', ClfSwitcher()),
])

parameters = [
    {
        'clf__estimator': [SGDClassifier()], # SVM if hinge loss / logreg if log loss
        'tfidf__max_df': (0.25, 0.5, 0.75, 1.0),
        'tfidf__stop_words': ['english', None],
        'clf__estimator__penalty': ('l2', 'elasticnet', 'l1'),
        'clf__estimator__max_iter': [50, 80],
        'clf__estimator__tol': [1e-4],
        'clf__estimator__loss': ['hinge', 'log', 'modified_huber'],
    },
    {
        'clf__estimator': [MultinomialNB()],
        'tfidf__max_df': (0.25, 0.5, 0.75, 1.0),
        'tfidf__stop_words': [None],
        'clf__estimator__alpha': (1e-2, 1e-3, 1e-1),
    },
]

gscv = GridSearchCV(pipeline, parameters, cv=5, n_jobs=12, return_train_score=False, verbose=3)
gscv.fit(train_data, train_labels)

import pandas as pd
pd.DataFrame(gscv.cv_results_)