156 lines
7.4 KiB
Python
156 lines
7.4 KiB
Python
#!/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
|
|
#import prettyprint as pp
|
|
###############################################################################
|
|
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 *
|
|
from FS 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"]
|
|
outdir = homedir + '/git/Data/ml_combined/fs/'
|
|
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']
|
|
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) )
|
|
# ]
|
|
|
|
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:
|
|
# unused per-split outfile
|
|
out_filename = outdir + gene.lower() + '_'+split_type+'_' + data_type + '.json'
|
|
tempD=split_tts(gene_dataD[gene_low]
|
|
, data_type = data_type
|
|
, split_type = split_type
|
|
, oversampling = True # TURN IT ON TO RUN THE OTHERS BIS
|
|
, 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'}
|
|
}
|
|
#for m in fs_models:
|
|
# print(m)
|
|
|
|
out_fsD = {}
|
|
index = 1
|
|
for model_name, model_fn in fs_models:
|
|
print('\nRunning classifier with FS:', index
|
|
, '\nModel_name:' , model_name
|
|
, '\nModel func:' , model_fn)
|
|
#, '\nList of models:', models)
|
|
index = index+1
|
|
|
|
out_fsD[model_name] = {}
|
|
# current_model = {}
|
|
for k, v in paramD.items():
|
|
# out_filename = (gene.lower() + '_' + split_type + '_' + data_type + '_' + k + '.json')
|
|
fsD_params=paramD[k]
|
|
# print("XXXXXX THIS: ", len(fsD_params['input_df']) )
|
|
# print("XXXXXX THIS: ", out_filename )
|
|
|
|
# current_model[k] = fsgs_rfecv(
|
|
out_fsD[model_name][k] = fsgs_rfecv(
|
|
**fsD_params
|
|
, param_gridLd = [{'fs__min_features_to_select': [1]}]
|
|
, blind_test_df = tempD['X_bts']
|
|
, blind_test_target = tempD['y_bts']
|
|
, estimator = model_fn
|
|
, use_fs = False # uses estimator as the RFECV parameter for fs. Set to TRUE if you want to supply custom_fs as shown below
|
|
, custom_fs = RFECV(DecisionTreeClassifier(**rs), cv = skf_cv, scoring = 'matthews_corrcoef')
|
|
, cv_method = skf_cv
|
|
)
|
|
# write per-resampler outfile here
|
|
# with open(out_filename, 'w') as f:
|
|
# f.write(json.dumps(current_model
|
|
# , cls = NpEncoder )
|
|
# )
|
|
|
|
# write per-split outfile here
|
|
with open(out_filename, 'w') as f:
|
|
f.write(json.dumps(out_fsD
|
|
#, cls = NpEncoder
|
|
))
|
|
#%%############################################################################
|
|
# # Read output json
|
|
# testF = outdir + 'pnca_70_30_actual.json'
|
|
# testF = outdir + 'pnca_70_30_complete.json'
|
|
|
|
# with open(testF, 'r') as f:
|
|
# data = json.load(f)
|