#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Wed May 18 06:03:24 2022 @author: tanu """ #cv = rskf_cv cv = skf_cv # RandomForestClassifier: Feature Selelction + GridSearch CV + Pipeline ############################################################################### # Define estimator estimator = [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)](**rs) # Define pipleline with steps pipe_rf = Pipeline([ ('pre', MinMaxScaler()) , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef')) # , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef')) , ('clf', estimator) ]) # Define hyperparmeter space to search for param_grid_rf = [ { 'fs__min_features_to_select' : [1,2] # , 'fs__cv': [cv] }, { # 'clf': [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)], 'clf__max_depth': [4, 6, 8, 10, 12, 16, 20, None] , 'clf__class_weight':['balanced','balanced_subsample'] , 'clf__n_estimators': [10, 25, 50, 100, 200, 300] # go upto a 100 , 'clf__criterion': ['gini', 'entropy', 'log_loss'] , 'clf__max_features': ['sqrt', 'log2', None] #deafult is sqrt , 'clf__min_samples_leaf': [1, 2, 3, 4, 5, 10] , 'clf__min_samples_split': [2, 5, 15, 20] } ] # Define GridSearch CV gscv_fs = GridSearchCV(pipe_rf , param_grid_rf , cv = cv , scoring = mcc_score_fn , refit = 'mcc' , verbose = 3 , return_train_score = True , **njobs) ############################################################################### #------------------------------ # Fit gscv containing pipeline #------------------------------ gscv_fs.fit(X, y) #Fitting 10 folds for each of 4 candidates, totalling 80 fits # QUESTION: HOW?? gscv_fs.best_params_ gscv_fs.best_score_ # Training best score corresponds to the max of the mean_test train_bscore = round(gscv_fs.best_score_, 2); train_bscore print('\nTraining best score (MCC):', train_bscore) round(gscv_fs.cv_results_['mean_test_mcc'].max(),2) # Training results gscv_tr_resD = gscv_fs.cv_results_ mod_refit_param = gscv_fs.refit # sanity check if train_bscore == round(gscv_tr_resD['mean_test_mcc'].max(),2): print('\nVerified training score (MCC):', train_bscore ) else: print('\nTraining score could not be internatlly verified. Please check training results dict') # Blind test: REAL check! tp = gscv_fs.predict(X_bts) print('\nMCC on Blind test:' , round(matthews_corrcoef(y_bts, tp),2)) print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, tp),2)) ############ # info extraction ############ # gives input vals?? gscv_fs._check_n_features # gives gscv params used gscv_fs._get_param_names() # gives ?? gscv_fs.best_estimator_ gscv_fs.best_params_ # gives best estimator params as a dict gscv_fs.best_estimator_._final_estimator # similar to above, doesn't contain max_iter gscv_fs.best_estimator_.named_steps['fs'].get_support() gscv_fs.best_estimator_.named_steps['fs'].ranking_ # array of ranks for the features gscv_fs.best_estimator_.named_steps['fs'].grid_scores_.mean() gscv_fs.best_estimator_.named_steps['fs'].grid_scores_.max() #gscv_fs.best_estimator_.named_steps['fs'].grid_scores_ ############################################################################### #============ # FS results #============ # Now get the features out all_features = gscv_fs.feature_names_in_ n_all_features = gscv_fs.n_features_in_ #all_features = gsfit.feature_names_in_ sel_features = X.columns[gscv_fs.best_estimator_.named_steps['fs'].get_support()] n_sf = gscv_fs.best_estimator_.named_steps['fs'].n_features_ # get model name model_name = gscv_fs.best_estimator_.named_steps['clf'] b_model_params = gscv_fs.best_params_ print('\n========================================' , '\nRunning model:' , '\nModel name:', model_name , '\n===============================================' , '\nRunning feature selection with RFECV for model' , '\nTotal no. of features in model:', len(all_features) , '\nThese are:\n', all_features, '\n\n' , '\nNo of features for best model: ', n_sf , '\nThese are:', sel_features, '\n\n' , '\nBest Model hyperparams:', b_model_params ) ############################################################################### ############################## OUTPUT ######################################### ############################################################################### #========================= # Blind test: BTS results #========================= # Build the final results with all scores for a feature selected model bts_predict = gscv_fs.predict(X_bts) print('\nMCC on Blind test:' , round(matthews_corrcoef(y_bts, bts_predict),2)) print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, bts_predict),2)) # create a dict with all scores lr_btsD = {#'best_model': list(gscv_lr_fit_be_mod.items()) 'bts_fscore':None , 'bts_mcc':None , 'bts_precision':None , 'bts_recall':None , 'bts_accuracy':None , 'bts_roc_auc':None , 'bts_jaccard':None } lr_btsD lr_btsD['bts_fscore'] = round(f1_score(y_bts, bts_predict),2) lr_btsD['bts_mcc'] = round(matthews_corrcoef(y_bts, bts_predict),2) lr_btsD['bts_precision'] = round(precision_score(y_bts, bts_predict),2) lr_btsD['bts_recall'] = round(recall_score(y_bts, bts_predict),2) lr_btsD['bts_accuracy'] = round(accuracy_score(y_bts, bts_predict),2) lr_btsD['bts_roc_auc'] = round(roc_auc_score(y_bts, bts_predict),2) lr_btsD['bts_jaccard'] = round(jaccard_score(y_bts, bts_predict),2) lr_btsD #=========================== # Add FS related model info #=========================== output_modelD = {'model_name': model_name , 'model_refit_param': mod_refit_param , 'Best_model_params': b_model_params , 'n_all_features': n_all_features , 'fs_method': gscv_fs.best_estimator_.named_steps['fs'] # FIXME: doesn't tell you which it has chosen , 'fs_res_array': gscv_fs.best_estimator_.named_steps['fs'].get_support() , 'fs_res_array_rank': gscv_fs.best_estimator_.named_steps['fs'].ranking_ , 'all_feature_names': all_features , 'n_sel_features': n_sf , 'sel_features_names': sel_features , 'train_score (MCC)': train_bscore} output_modelD #======================================== # Update output_modelD with bts_results #======================================== output_modelD.update(lr_btsD) output_modelD #======================================== # Write final output file # https://stackoverflow.com/questions/19201290/how-to-save-a-dictionary-to-a-file #======================================== # output final dict as a json # outFile = 'LR_FS.json' # with open(outFile, 'w') as f: # json.dump(output_modelD, f) # # # with open(file, 'r') as f: # data = json.load(f)