102 lines
4.5 KiB
Python
Executable file
102 lines
4.5 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Wed Jun 29 20:29:36 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
import sys, os
|
|
import pandas as pd
|
|
import numpy as np
|
|
import re
|
|
|
|
###############################################################################
|
|
homedir = os.path.expanduser("~")
|
|
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
|
|
sys.path
|
|
###############################################################################
|
|
#====================
|
|
# Import ML functions
|
|
#====================
|
|
from MultClfs import *
|
|
from GetMLData import *
|
|
from SplitTTS import *
|
|
|
|
# param dict for getmldata()
|
|
combined_model_paramD = {'data_combined_model' : False
|
|
, 'use_or' : False
|
|
, 'omit_all_genomic_features': False
|
|
, 'write_maskfile' : False
|
|
, 'write_outfile' : False }
|
|
###############################################################################
|
|
#ml_genes = ["pncA", "embB", "katG", "rpoB", "gid"]
|
|
|
|
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)
|
|
|
|
for split_type in split_types:
|
|
for data_type in split_data_types:
|
|
out_filename = (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(**paramD[k]
|
|
, tts_split_type = split_type
|
|
, skf_cv = skf_cv
|
|
, blind_test_df = tempD['X_bts']
|
|
, blind_test_target = tempD['y_bts']
|
|
, add_cm = True
|
|
, add_yn = True
|
|
, return_formatted_output = True)
|
|
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)
|
|
|