106 lines
4.1 KiB
Python
106 lines
4.1 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Wed Mar 16 16:55:06 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
# https://stackoverflow.com/questions/57248072/gridsearchcv-gives-different-result
|
|
# https://stackoverflow.com/questions/44947574/what-is-the-meaning-of-mean-test-score-in-cv-result
|
|
#https://stackoverflow.com/questions/47257952/how-to-get-average-score-of-k-fold-cross-validation-with-sklearn
|
|
|
|
|
|
#https://stackoverflow.com/questions/47257952/how-to-get-average-score-of-k-fold-cross-validation-with-sklearn
|
|
# If you only want accuracy, then you can simply use cross_val_score()
|
|
# kf = KFold(n_splits=10)
|
|
# clf_tree=DecisionTreeClassifier()
|
|
# scores = cross_val_score(clf_tree, X, y, cv=kf)
|
|
# avg_score = np.mean(score_array)
|
|
# print(avg_score)
|
|
# Here cross_val_score will take as input your original X and y (without splitting into train and test). cross_val_score will automatically split them into train and test, fit the model on train data and score on test data. And those scores will be returned in the scores variable.
|
|
# So when you have 10 folds, 10 scores will be returned in scores variable. You can then just take an average of that.
|
|
|
|
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
|
|
|
|
scoring_refit_recall = {'scoring': 'recall'
|
|
,'refit': 'recall'}
|
|
|
|
scoring_refit_recall = {'scoring': 'precision'
|
|
,'refit': 'precision'}
|
|
|
|
scoring_refit_mcc = {'scoring': mcc_score_fn
|
|
,'refit': 'mcc'}
|
|
#n_jobs = 10 # my desktop has 12 cores
|
|
#cv = {'cv': 10}#%%
|
|
|
|
njobs = {'n_jobs': 10}
|
|
skf_cv = StratifiedKFold(n_splits = 10, shuffle = True)
|
|
|
|
#%% GSCV: RandomForest
|
|
gs_rf = GridSearchCV(estimator=RandomForestClassifier(n_jobs=-1, oob_score = True
|
|
#,class_weight = {1: 10/11, 0: 1/11}
|
|
)
|
|
, param_grid=[{'max_depth': [4, 6, 8, 10, None]
|
|
, 'max_features': ['auto', 'sqrt']
|
|
, 'min_samples_leaf': [2, 4, 8]
|
|
, 'min_samples_split': [10, 20]}]
|
|
, cv = skf_cv
|
|
, **njobs
|
|
, **scoring_refit_recall
|
|
#, **scoring_refit_mcc
|
|
#, scoring = scoring_fn, refit = False
|
|
)
|
|
#gs_rf.fit(X_train, y_train)
|
|
#gs_rf_fit = gs_rf.fit(X_train y_train)
|
|
|
|
gs_rf.fit(X, y)
|
|
gs_rf_fit = gs_rf.fit(X, y)
|
|
gs_rf_res = gs_rf_fit.cv_results_
|
|
print('Best model:\n', gs_rf.best_params_)
|
|
print('Best models score:\n', gs_rf.best_score_)
|
|
print('Check mean models score:\n', mean(gs_rf_res['mean_test_score']))
|
|
|
|
#%% Proof of concept: manual inspection to see how best score is calcualted!
|
|
# SATISFIED!
|
|
# Best_model example: recall, Best model's score: 0.8059288537549408
|
|
# {'max_depth': 4, 'max_features': 'sqrt', 'min_samples_leaf': 2, 'min_samples_split': 10}
|
|
|
|
# Best model example: mcc, Best models score: 0.42504894661702863
|
|
# {'max_depth': 4, 'max_features': 'auto', 'min_samples_leaf': 4, 'min_samples_split': 20}
|
|
|
|
# Best model example: precision, Best models score: 0.7144745254745255
|
|
# {'max_depth': 6, 'max_features': 'sqrt', 'min_samples_leaf': 8, 'min_samples_split': 10}
|
|
|
|
best_model = [{'max_depth': 6, 'max_features': 'sqrt', 'min_samples_leaf': 8, 'min_samples_split': 10 }]
|
|
|
|
gs_results_df = pd.DataFrame(gs_rf_res)
|
|
gs_results_df.shape
|
|
|
|
gs_best_df = gs_results_df.loc[gs_results_df['params'].isin(best_model)]
|
|
gs_best_df.shape
|
|
|
|
gs_best_df_test = gs_best_df.filter(like = 'test_', axis = 1)
|
|
gs_best_df_test.shape
|
|
|
|
gs_best_df_test_recall = gs_best_df_test.filter(like = '_score', axis = 1)
|
|
gs_best_df_test_recall.shape
|
|
|
|
f = gs_best_df_test_recall.filter(like='split', axis = 1)
|
|
f.shape
|
|
#gs_best_df_test_mcc = gs_best_df_test.filter(like = '_mcc', axis = 1)
|
|
#f = gs_best_df_test_mcc.filter(like='split', axis = 1)
|
|
|
|
f.iloc[:,[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]].mean(axis = 1)
|
|
# recall: 0.801186 vs 0.8059288537549408
|
|
# mcc: 0.425049 vs 0.42504894661702863
|
|
# precision: 0.714475 vs 0.7144745254745255
|
|
|
|
#%%
|
|
|
|
#%% Check the scores:
|
|
print([(len(train), len(test)) for train, test in skf_cv.split(X, y)])
|
|
gs_rf_fit.cv_results_
|
|
#its the weighted average!?
|
|
#%%
|
|
|
|
|