tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

iterator

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-10 12:33:17 +01:00
parent 01ff9d5be6
commit 4d5b848471
1 changed files with 36 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

67
scripts/ml/feature_selection_iterator.py
View file

@ -9,7 +9,7 @@ import sys, os
import pandas as pd import pandas as pd
import numpy as np import numpy as np
import re import re
#import prettyprint as pp #import prettyprint as pp
############################################################################### ###############################################################################
homedir = os.path.expanduser("~") homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions') sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
@ -18,7 +18,7 @@ sys.path
outdir = homedir + '/git/LSHTM_ML/output/fs/' outdir = homedir + '/git/LSHTM_ML/output/fs/'
#==================== #====================
# Import ML functions # Import ML functions
#==================== #====================
from MultClfs import * from MultClfs import *
@ -27,43 +27,45 @@ from SplitTTS import *
from FS import * from FS import *
# param dict for getmldata() # param dict for getmldata()
combined_model_paramD = {'data_combined_model' : False combined_model_paramD = {'data_combined_model' : False
, 'use_or' : False , 'use_or' : False
, 'omit_all_genomic_features': False , 'omit_all_genomic_features': False
, 'write_maskfile' : False , 'write_maskfile' : False
, 'write_outfile' : False } , 'write_outfile' : False }
############################################################################### ###############################################################################
#ml_genes = ["pncA", "embB", "katG", "rpoB", "gid"] #ml_genes = ["pncA", "embB", "katG", "rpoB", "gid"]
# outdir = homedir + '/git/Data/ml_combined/fs/' # outdir = homedir + '/git/Data/ml_combined/fs/'
ml_gene_drugD = {'pncA' : 'pyrazinamide' ml_gene_drugD = {
# , 'embB' : 'ethambutol' 'pncA' : 'pyrazinamide', # NOTE: may need re-run for 80_20 and sl
# , 'katG' : 'isoniazid' #'embB' : 'ethambutol',
# , 'rpoB' : 'rifampicin' #'katG' : 'isoniazid', #NOTE: RF only for all split-types actual
# , 'gid' : 'streptomycin' #'rpoB' : 'rifampicin',
} #'gid' : 'streptomycin' # NOTE: for gid, run 'actual' on 80/20 and sl only
}
gene_dataD={} gene_dataD={}
# NOTE: for gid, run 'actual' on 80/20 and sl only
split_types = ['70_30', '80_20', 'sl'] #split_types = ['70_30', '80_20', 'sl']
split_data_types = ['actual', 'complete']
#split_types = ['70_30']
#split_data_types = ['actual', 'complete'] #split_data_types = ['actual', 'complete']
#fs_models = [('Logistic Regression' , LogisticRegression(**rs) )] split_types = ['70_30']
#split_data_types = ['actual', 'complete']
split_data_types = ['actual']
fs_models = [ fs_models = [
('Logistic Regression' , LogisticRegression(**rs) ) #('Ridge Classifier' , RidgeClassifier(**rs) ),
, ('Ridge Classifier' , RidgeClassifier(**rs) ) #('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) ),
#, ('AdaBoost Classifier' , AdaBoostClassifier(**rs) ) #('Logistic Regression' , LogisticRegression(**rs, **njobs) ),
#, ('Decision Tree' , DecisionTreeClassifier(**rs) ) #('AdaBoost Classifier' , AdaBoostClassifier(**rs) ),
#, ('Extra Tree' , ExtraTreeClassifier(**rs) ) #('Gradient Boosting' , GradientBoostingClassifier(**rs) ),
#, ('Extra Trees' , ExtraTreesClassifier(**rs) ) #('Stochastic GDescent' , SGDClassifier(**rs, **njobs) ),
#, ('Gradient Boosting' , GradientBoostingClassifier(**rs) ) #('Decision Tree' , DecisionTreeClassifier(**rs) ),
#, ('LDA' , LinearDiscriminantAnalysis() ) #('Extra Trees' , ExtraTreesClassifier(**rs, **njobs) ),
#, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs)) #('Extra Tree' , ExtraTreeClassifier(**rs) ),
#, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) ) #('LDA' , LinearDiscriminantAnalysis() ),
#, ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000 ) ) #('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs, **njobs) ),
#, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) ) #('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
#, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) ) #('Random Forest' , RandomForestClassifier(n_estimators = 1000, verbose=3, **rs, **njobs ) )
('XGBoost' , XGBClassifier(verbosity=3, use_label_encoder=False, **rs, **njobs) )
] ]
for gene, drug in ml_gene_drugD.items(): for gene, drug in ml_gene_drugD.items():
@ -122,9 +124,10 @@ for gene, drug in ml_gene_drugD.items():
index = index+1 index = index+1
#out_fsD[model_name] = {} #out_fsD[model_name] = {}
current_model = {} current_model = {}
model_name_clean = model_name.replace(' ','-')
for k, v in paramD.items(): for k, v in paramD.items():
out_filename = gene.lower() + '_' + split_type + '_' + data_type + '_' + model_name + '_' + k + '.json' out_filename = outdir + gene.lower() + '_' + split_type + '_' + data_type + '_' + model_name_clean + '_' + k + '.json'
fsD_params=paramD[k] fsD_params=paramD[k]
#out_fsD[model_name][k] = fsgs_rfecv( #out_fsD[model_name][k] = fsgs_rfecv(
@ -145,6 +148,8 @@ for gene, drug in ml_gene_drugD.items():
# write current model to disk # write current model to disk
#print(current_model) #print(current_model)
print("⚠️ ⚠️ ⚠️ WRITING TO FILE: ", out_filename, "⚠️ ⚠️ ⚠️'")
out_json = json.dumps(current_model) out_json = json.dumps(current_model)
with open(out_filename, 'w', encoding="utf-8") as file: with open(out_filename, 'w', encoding="utf-8") as file:
file.write(out_json) file.write(out_json)
print("⚠️ ⚠️ ⚠️ Finished writing to: ", out_filename, "⚠️ ⚠️ ⚠️'")