multiple changes
This commit is contained in:
parent
2fda32901b
commit
dccd3c8eb2
7 changed files with 82 additions and 122 deletions
|
|
@ -15,13 +15,15 @@ homedir = os.path.expanduser("~")
|
|||
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
|
||||
sys.path
|
||||
###############################################################################
|
||||
outdir = homedir + '/git/LSHTM_ML/output/combined/
|
||||
outdir = homedir + '/git/LSHTM_ML/output/combined/'
|
||||
|
||||
#====================
|
||||
# Import ML functions
|
||||
#====================
|
||||
#from MultClfs import *
|
||||
from MultClfs_logo_skf import *
|
||||
#from MultClfs_logo_skf import *
|
||||
from MultClfs_logo_skf_split import *
|
||||
|
||||
from GetMLData import *
|
||||
from SplitTTS import *
|
||||
|
||||
|
|
@ -29,73 +31,59 @@ from SplitTTS import *
|
|||
from ml_data_combined import *
|
||||
|
||||
###############################################################################
|
||||
#ml_genes = ["pncA", "embB", "katG", "rpoB", "gid"]
|
||||
print('\nUsing data with 5 genes:', len(cm_input_df5))
|
||||
|
||||
###############################################################################
|
||||
|
||||
ml_gene_drugD = {'pncA' : 'pyrazinamide'
|
||||
, 'embB' : 'ethambutol'
|
||||
, 'katG' : 'isoniazid'
|
||||
, 'rpoB' : 'rifampicin'
|
||||
, 'gid' : 'streptomycin'
|
||||
}
|
||||
gene_dataD={}
|
||||
split_types = ['70_30', '80_20', 'sl']
|
||||
split_data_types = ['actual', 'complete']
|
||||
|
||||
for gene, drug in ml_gene_drugD.items():
|
||||
print ('\nGene:', gene
|
||||
, '\nDrug:', drug)
|
||||
gene_low = gene.lower()
|
||||
gene_dataD[gene_low] = getmldata(gene, drug
|
||||
, data_combined_model = False # this means it doesn't include 'gene_name' as a feauture as a single gene-target shouldn't have it.
|
||||
, use_or = False
|
||||
, omit_all_genomic_features = False
|
||||
, write_maskfile = False
|
||||
, write_outfile = False)
|
||||
for split_type in split_types:
|
||||
for data_type in split_data_types:
|
||||
|
||||
for split_type in split_types:
|
||||
for data_type in split_data_types:
|
||||
out_filename = outdir + gene.lower()+ '_' + split_type + '_' + data_type + '.csv'
|
||||
tempD=split_tts(gene_dataD[gene_low]
|
||||
, data_type = data_type
|
||||
, split_type = split_type
|
||||
, oversampling = True
|
||||
, dst_colname = 'dst'
|
||||
, target_colname = 'dst_mode'
|
||||
, include_gene_name = True
|
||||
)
|
||||
paramD = {
|
||||
'baseline_paramD': { 'input_df' : tempD['X']
|
||||
, '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'}
|
||||
}
|
||||
|
||||
mmDD = {}
|
||||
for k, v in paramD.items():
|
||||
scoresD = MultModelsCl_logo_skf(**paramD[k]
|
||||
XXXXXXXXXXXXXXXXXXXXXXX
|
||||
mmDD[k] = scoresD
|
||||
out_filename = outdir + 'cm_' + split_type + '_' + data_type + '.csv'
|
||||
print(out_filename)
|
||||
tempD = split_tts(cm_input_df5
|
||||
, data_type = data_type
|
||||
, split_type = split_type
|
||||
, oversampling = True
|
||||
, dst_colname = 'dst'
|
||||
, target_colname = 'dst_mode'
|
||||
, include_gene_name = True
|
||||
)
|
||||
paramD = {
|
||||
'baseline_paramD': { 'input_df' : tempD['X']
|
||||
, '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'}
|
||||
}
|
||||
|
||||
mmDD = {}
|
||||
for k, v in paramD.items():
|
||||
scoresD = MultModelsCl_logo_skf(**paramD[k]
|
||||
XXXXXXXXXXXXXXXXXXXXXXX
|
||||
mmDD[k] = scoresD
|
||||
|
||||
# Extracting the dfs from within the dict and concatenating to output as one df
|
||||
for k, v in mmDD.items():
|
||||
out_wf= pd.concat(mmDD, ignore_index = True)
|
||||
|
||||
out_wf_f = out_wf.sort_values(by = ['resampling', 'source_data', 'MCC'], ascending = [True, True, False], inplace = False)
|
||||
out_wf_f.to_csv(('/home/tanu/git/Data/ml_combined/genes/'+out_filename), index = False)
|
||||
# Extracting the dfs from within the dict and concatenating to output as one df
|
||||
for k, v in mmDD.items():
|
||||
out_wf= pd.concat(mmDD, ignore_index = True)
|
||||
|
||||
out_wf_f = out_wf.sort_values(by = ['resampling', 'source_data', 'MCC'], ascending = [True, True, False], inplace = False)
|
||||
out_wf_f.to_csv(('/home/tanu/git/Data/ml_combined/genes/'+out_filename), index = False)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue