sklearn_parallel_example.py

## Adapted from https://www.featureranking.com/tutorials/machine-learning-tutorials/sk-part-5-advanced-topics-pipelines-statistical-model-comparison-and-model-deployment/
## by Ista

import numpy as np
from sklearn.datasets import load_breast_cancer
from sklearn import preprocessing
from sklearn.pipeline import Pipeline
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import RepeatedStratifiedKFold, GridSearchCV
from sklearn.feature_selection import SelectKBest, f_classif, mutual_info_classif


cancer_df = load_breast_cancer()
Data_unscaled, target = cancer_df.data, cancer_df.target
data_scaler = preprocessing.MinMaxScaler().fit(Data_unscaled)
Data = data_scaler.transform(Data_unscaled)

cv_method = RepeatedStratifiedKFold(n_splits=5, 
                                    n_repeats=2, 
                                    random_state=999)

pipe_KNN = Pipeline([('fselector', SelectKBest()), 
                     ('knn', KNeighborsClassifier())])

params_pipe_KNN = {'fselector__score_func': [f_classif, mutual_info_classif],
                   'fselector__k': [10, 20, Data.shape[1]],
                   'knn__n_neighbors': [1, 2, 3, 4, 5],
                   'knn__p': [1, 2]}
 
gs_pipe_KNN = GridSearchCV(estimator=pipe_KNN, 
                           param_grid=params_pipe_KNN, 
                           cv=cv_method,
                           n_jobs=16,
                           scoring='roc_auc',
                           verbose=1) 

gs_pipe_KNN.fit(Data, target)