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

changed ml output dirs and ready to run fs

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-01 21:40:14 +01:00
parent 57348f1874
commit 11af00f1db
5 changed files with 67 additions and 152 deletions
Download patch file Download diff file Expand all files Collapse all files

82
scripts/ml/ml_iterator_fs.py Normal file → Executable file
View file

@ -15,6 +15,8 @@ homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
sys.path
###############################################################################
outdir = homedir + '/git/LSHTM_ML/output/fs/'
#====================
# Import ML functions
#====================
@ -31,7 +33,8 @@ combined_model_paramD = {'data_combined_model' : False
, 'write_outfile' : False }
###############################################################################
#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'
# , 'embB' : 'ethambutol'
# , 'katG' : 'isoniazid'
@ -39,26 +42,27 @@ ml_gene_drugD = {'pncA' : 'pyrazinamide'
# , 'gid' : 'streptomycin'
}
gene_dataD={}
#split_types = ['70_30', '80_20', 'sl']
#split_data_types = ['actual', 'complete']
split_types = ['70_30']
split_types = ['70_30', '80_20', 'sl']
split_data_types = ['actual', 'complete']
#split_types = ['70_30']
#split_data_types = ['actual', 'complete']
fs_models = [('Logistic Regression' , LogisticRegression(**rs) )]
# fs_models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
# , ('Decision Tree' , DecisionTreeClassifier(**rs) )
# , ('Extra Tree' , ExtraTreeClassifier(**rs) )
# , ('Extra Trees' , ExtraTreesClassifier(**rs) )
# , ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
# , ('LDA' , LinearDiscriminantAnalysis() )
# , ('Logistic Regression' , LogisticRegression(**rs) )
# , ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
# , ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
# , ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000 ) )
# , ('Ridge Classifier' , RidgeClassifier(**rs) )
# , ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
# , ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
# ]
#fs_models = [('Logistic Regression' , LogisticRegression(**rs) )]
fs_models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Decision Tree' , DecisionTreeClassifier(**rs) )
, ('Extra Tree' , ExtraTreeClassifier(**rs) )
, ('Extra Trees' , ExtraTreesClassifier(**rs) )
, ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
, ('LDA' , LinearDiscriminantAnalysis() )
, ('Logistic Regression' , LogisticRegression(**rs) )
, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
, ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000 ) )
, ('Ridge Classifier' , RidgeClassifier(**rs) )
, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
]
for gene, drug in ml_gene_drugD.items():
print ('\nGene:', gene
@ -88,26 +92,28 @@ for gene, drug in ml_gene_drugD.items():
, 'target' : tempD['y']
, 'var_type' : 'mixed'
, 'resampling_type': 'none'}
,'smnc_paramD': { 'input_df' : tempD['X_smnc']
, 'target' : tempD['y_smnc']
, 'var_type' : 'mixed'
, 'resampling_type' : 'smnc'}
# , 'ros_paramD': { 'input_df' : tempD['X_ros']
# , 'target' : tempD['y_ros']
# , 'var_type' : 'mixed'
# , 'resampling_type' : 'ros'}
# , 'rus_paramD' : { 'input_df' : tempD['X_rus']
# , 'target' : tempD['y_rus']
# , 'var_type' : 'mixed'
# , 'resampling_type' : 'rus'}
# , 'rouC_paramD' : { 'input_df' : tempD['X_rouC']
# , 'target' : tempD['y_rouC']
# , 'var_type' : 'mixed'
# , 'resampling_type': 'rouC'}
, 'smnc_paramD' : { 'input_df' : tempD['X_smnc']
, 'target' : tempD['y_smnc']
, 'var_type' : 'mixed'
, 'resampling_type' : 'smnc'}
, 'ros_paramD' : { 'input_df' : tempD['X_ros']
, 'target' : tempD['y_ros']
, 'var_type' : 'mixed'
, 'resampling_type' : 'ros'}
, 'rus_paramD' : { 'input_df' : tempD['X_rus']
, 'target' : tempD['y_rus']
, 'var_type' : 'mixed'
, 'resampling_type' : 'rus'}
, 'rouC_paramD' : { 'input_df' : tempD['X_rouC']
, 'target' : tempD['y_rouC']
, 'var_type' : 'mixed'
, 'resampling_type': 'rouC'}
}
#for m in fs_models:
# print(m)
out_fsD = {}
index = 1
for model_name, model_fn in fs_models: