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

added all run scripts for diffferent splits

Browse source
This commit is contained in:
Tanushree Tunstall 2022-06-24 20:39:50 +01:00
parent e2bc384155
commit 5d38cde912
6 changed files with 948 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

141
scripts/ml/run_8020.py Executable file
View file

@ -0,0 +1,141 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Jun 20 13:05:23 2022
@author: tanu
"""
#%%Imports ####################################################################
import re
import argparse
import os, sys
# gene = 'pncA'
# drug = 'pyrazinamide'
#total_mtblineage_uc = 8
###############################################################################
#%% command line args: case sensitive
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('-d', '--drug', help = 'drug name', default = '')
arg_parser.add_argument('-g', '--gene', help = 'gene name', default = '')
args = arg_parser.parse_args()
drug = args.drug
gene = args.gene
###############################################################################
homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml')
###############################################################################
#==================
# Import data
#==================
from ml_data_8020 import *
setvars(gene,drug)
from ml_data_8020 import *
# from YC run_all_ML: run locally
#from UQ_yc_RunAllClfs import run_all_ML
#====================
# Import ML functions
#====================
from MultClfs import *
#==================
# other vars
#==================
tts_split_8020 = '80_20'
OutFile_suffix = '8020'
#==================
# Specify outdir
#==================
outdir_ml = outdir + 'ml/tts_8020/'
print('\nOutput directory:', outdir_ml)
#outFile_wf = outdir_ml + gene.lower() + '_baselineC_' + OutFile_suffix + '.csv'
outFile_wf = outdir_ml + gene.lower() + '_baselineC_noOR' + OutFile_suffix + '.csv'
#%% Running models ############################################################
print('\n#####################################################################\n'
, '\nStarting--> Running ML analysis: Baseline modes (No FS)'
, '\nGene name:', gene
, '\nDrug name:', drug
, '\n#####################################################################\n')
paramD = {
'baseline_paramD': { 'input_df' : X
, 'target' : y
, 'var_type' : 'mixed'
, 'resampling_type': 'none'}
, 'smnc_paramD': { 'input_df' : X_smnc
, 'target' : y_smnc
, 'var_type' : 'mixed'
, 'resampling_type' : 'smnc'}
, 'ros_paramD': { 'input_df' : X_ros
, 'target' : y_ros
, 'var_type' : 'mixed'
, 'resampling_type' : 'ros'}
, 'rus_paramD' : { 'input_df' : X_rus
, 'target' : y_rus
, 'var_type' : 'mixed'
, 'resampling_type' : 'rus'}
, 'rouC_paramD' : { 'input_df' : X_rouC
, 'target' : y_rouC
, 'var_type' : 'mixed'
, 'resampling_type' : 'rouC'}
}
##==============================================================================
## Dict with no CV BT formatted df
## mmD = {}
## for k, v in paramD.items():
## # print(mmD[k])
## scores_8020D = MultModelsCl(**paramD[k]
## , tts_split_type = tts_split_8020
## , skf_cv = skf_cv
## , blind_test_df = X_bts
## , blind_test_target = y_bts
## , add_cm = True
## , add_yn = True
## , return_formatted_output = False)
## mmD[k] = scores_8020D
##==============================================================================
## Initial run to get the dict of dicts for each sampling type containing CV, BT and metadata DFs
mmDD = {}
for k, v in paramD.items():
scores_8020D = MultModelsCl(**paramD[k]
, tts_split_type = tts_split_8020
, skf_cv = skf_cv
, blind_test_df = X_bts
, blind_test_target = y_bts
, add_cm = True
, add_yn = True
, return_formatted_output = True)
mmDD[k] = scores_8020D
# Extracting the dfs from within the dict and concatenating to output as one df
for k, v in mmDD.items():
out_wf_8020 = pd.concat(mmDD, ignore_index = True)
out_wf_8020f = out_wf_8020.sort_values(by = ['resampling', 'source_data', 'MCC'], ascending = [True, True, False], inplace = False)
print('\n######################################################################'
, '\nEnd--> Successfully generated output DF for Multiple classifiers (baseline models)'
, '\nGene:', gene.lower()
, '\nDrug:', drug
, '\noutput file:', outFile_wf
, '\nDim of output:', out_wf_8020f.shape
, '\n######################################################################')
###############################################################################
#====================
# Write output file
#====================
out_wf_8020f.to_csv(outFile_wf, index = False)
print('\nFile successfully written:', outFile_wf)
###############################################################################

242
scripts/ml/run_FS_7030.py Normal file
View file

@ -0,0 +1,242 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue May 24 08:11:05 2022
@author: tanu
"""
#%%
import os, sys
import pandas as pd
import numpy as np
import pprint as pp
from copy import deepcopy
from sklearn import linear_model
from sklearn import datasets
from collections import Counter
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
from sklearn.linear_model import RidgeClassifier, RidgeClassifierCV, SGDClassifier, PassiveAggressiveClassifier
from sklearn.naive_bayes import BernoulliNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, AdaBoostClassifier, GradientBoostingClassifier, BaggingClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.gaussian_process import GaussianProcessClassifier, kernels
from sklearn.gaussian_process.kernels import RBF, DotProduct, Matern, RationalQuadratic, WhiteKernel
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC
from xgboost import XGBClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.compose import make_column_transformer
from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
# added
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score, LeaveOneOut, KFold, RepeatedKFold, cross_val_predict
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
from sklearn.pipeline import Pipeline, make_pipeline
from sklearn.feature_selection import RFE, RFECV
import itertools
import seaborn as sns
import matplotlib.pyplot as plt
from statistics import mean, stdev, median, mode
from imblearn.over_sampling import RandomOverSampler
from imblearn.under_sampling import RandomUnderSampler
from imblearn.over_sampling import SMOTE
from sklearn.datasets import make_classification
from imblearn.combine import SMOTEENN
from imblearn.combine import SMOTETomek
from imblearn.over_sampling import SMOTENC
from imblearn.under_sampling import EditedNearestNeighbours
from imblearn.under_sampling import RepeatedEditedNearestNeighbours
from sklearn.model_selection import GridSearchCV
from sklearn.base import BaseEstimator
from sklearn.impute import KNNImputer as KNN
import json
import argparse
import re
###############################################################################
#gene = 'pncA'
#drug = 'pyrazinamide'
#total_mtblineage_uc = 8
#%% command line args: case sensitive
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('-d', '--drug', help = 'drug name', default = '')
arg_parser.add_argument('-g', '--gene', help = 'gene name', default = '')
args = arg_parser.parse_args()
drug = args.drug
gene = args.gene
###############################################################################
#==================
# other vars
#==================
tts_split = '70_30'
OutFile_suffix = '7030_FS'
###############################################################################
homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml')
###############################################################################
#==================
# Import data
#==================
from ml_data_7030 import *
setvars(gene,drug)
from ml_data_7030 import *
# from YC run_all_ML: run locally
#from UQ_yc_RunAllClfs import run_all_ML
#==========================================
# Import ML functions:
# fsgs_rfecv(): RFECV for Feature selection
#==========================================
from MultClfs import *
#==================
# Specify outdir
#==================
outdir_ml = outdir + 'ml/tts_7030/fs/'
print('\nOutput directory:', outdir_ml)
#OutFileFS = outdir_ml + gene.lower() + '_FS' + OutFile_suffix + '.json'
OutFileFS = outdir_ml + gene.lower() + '_FS_noOR' + OutFile_suffix + '.json'
############################################################################
###############################################################################
#====================
# single model CALL
#====================
# aFS = fsgs(input_df = X
# , target = y
# , param_gridLd = [{'fs__min_features_to_select': [1]}]
# , blind_test_df = X_bts
# , blind_test_target = y_bts
# , estimator = LogisticRegression(**rs)
# , 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
# , var_type = 'mixed'
# )
#############
# Loop
############
#models_fs = [('Decision Tree' , DecisionTreeClassifier(**rs)) ]
models_fs = [('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 ) )
, ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
, n_estimators = 1000
, bootstrap = True
, oob_score = True
, **njobs
, **rs
, max_features = 'auto') )
, ('Ridge Classifier' , RidgeClassifier(**rs) )
, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
## , ('XGBoost' , XGBClassifier(**rs, **njobs, verbosity = 3 , use_label_encoder = False) )
]
print('\n#####################################################################'
, '\nRunning Feature Selection using classfication models_fs (n):', len(models_fs)
, '\nGene:' , gene.lower()
, '\nDrug:' , drug
, '\nSplit:' , tts_split
,'\n####################################################################')
for m in models_fs:
print(m)
print('\n====================================================================\n')
out_fsD = {}
index = 1
for model_name, model_fn in models_fs:
print('\nRunning classifier with FS:', index
, '\nModel_name:' , model_name
, '\nModel func:' , model_fn)
#, '\nList of models_fs:', models_fs)
index = index+1
out_fsD[model_name] = fsgs_rfecv(input_df = X
, target = y
, param_gridLd = [{'fs__min_features_to_select': [1]}]
, blind_test_df = X_bts
, blind_test_target = 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
, var_type = 'mixed'
)
out_fsD
#%% Checking results dict
tot_Ditems = sum(len(v) for v in out_fsD.values())
checkL = []
for k, v in out_fsD.items():
l = [len(out_fsD[k])]
checkL = checkL + l
n_sD = len(checkL) # no. of subDicts
l_sD = list(set(checkL)) # length of each subDict
print('\nTotal no.of subdicts:', n_sD)
if len(l_sD) == 1 and tot_Ditems == n_sD*l_sD[0]:
print('\nPASS: successful run for all Classifiers'
, '\nLength of each subdict:', l_sD)
print('\nSuccessfully ran Feature selection on', len(models_fs), 'classifiers'
, '\nGene:', gene.lower()
, '\nDrug:', drug
, '\nSplit type:', tts_split
, '\nTotal fs models results:', len(out_fsD)
, '\nTotal items in output:', sum(len(v) for v in out_fsD.values()) )
##############################################################################
#%% json output
#========================================
# Write final output file
# https://stackoverflow.com/questions/19201290/how-to-save-a-dictionary-to-a-file
#========================================
# Output final dict as a json
print('\nWriting Final output file (json):', OutFileFS)
with open(OutFileFS, 'w') as f:
f.write(json.dumps(out_fsD
# , cls = NpEncoder
))
# read json
with open(OutFileFS, 'r') as f:data = json.load(f)
#############################################################################

142
scripts/ml/run_cd_7030.py Executable file
View file

@ -0,0 +1,142 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Jun 20 13:05:23 2022
@author: tanu
"""
#%%Imports ####################################################################
import re
import argparse
import os, sys
# gene = 'pncA'
# drug = 'pyrazinamide'
#total_mtblineage_uc = 8
###############################################################################
#%% command line args: case sensitive
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('-d', '--drug', help = 'drug name', default = '')
arg_parser.add_argument('-g', '--gene', help = 'gene name', default = '')
args = arg_parser.parse_args()
drug = args.drug
gene = args.gene
###############################################################################
homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml')
###############################################################################
#==================
# Import data
#==================
from ml_data_cd_7030 import *
setvars(gene,drug)
from ml_data_cd_7030 import *
# from YC run_all_ML: run locally
#from UQ_yc_RunAllClfs import run_all_ML
#====================
# Import ML functions
#====================
from MultClfs import *
#==================
# other vars
#==================
tts_split_cd_7030 = 'cd_7030'
OutFile_suffix = '_cd_7030'
#==================
# Specify outdir
#==================
outdir_ml = outdir + 'ml/tts_cd_7030/'
print('\nOutput directory:', outdir_ml)
#outFile_wf = outdir_ml + gene.lower() + '_baselineC_' + OutFile_suffix + '.csv'
outFile_wf = outdir_ml + gene.lower() + '_baselineC_noOR' + OutFile_suffix + '.csv'
#%% Running models ############################################################
print('\n#####################################################################\n'
, '\nStarting--> Running ML analysis: Baseline modes (No FS)'
, '\nGene name:', gene
, '\nDrug name:', drug
, '\n#####################################################################\n')
paramD = {
'baseline_paramD': { 'input_df' : X
, 'target' : y
, 'var_type' : 'mixed'
, 'resampling_type': 'none'}
, 'smnc_paramD': { 'input_df' : X_smnc
, 'target' : y_smnc
, 'var_type' : 'mixed'
, 'resampling_type' : 'smnc'}
, 'ros_paramD': { 'input_df' : X_ros
, 'target' : y_ros
, 'var_type' : 'mixed'
, 'resampling_type' : 'ros'}
, 'rus_paramD' : { 'input_df' : X_rus
, 'target' : y_rus
, 'var_type' : 'mixed'
, 'resampling_type' : 'rus'}
, 'rouC_paramD' : { 'input_df' : X_rouC
, 'target' : y_rouC
, 'var_type' : 'mixed'
, 'resampling_type' : 'rouC'}
}
##==============================================================================
## Dict with no CV BT formatted df
## mmD = {}
## for k, v in paramD.items():
## # print(mmD[k])
## scores_cd_7030D = MultModelsCl(**paramD[k]
## , tts_split_type = tts_split_cd_7030
## , skf_cv = skf_cv
## , blind_test_df = X_bts
## , blind_test_target = y_bts
## , add_cm = True
## , add_yn = True
## , return_formatted_output = False)
## mmD[k] = scores_cd_7030D
##==============================================================================
## Initial run to get the dict of dicts for each sampling type containing CV, BT and metadata DFs
mmDD = {}
for k, v in paramD.items():
scores_cd_7030D = MultModelsCl(**paramD[k]
, tts_split_type = tts_split_cd_7030
, skf_cv = skf_cv
, blind_test_df = X_bts
, blind_test_target = y_bts
, add_cm = True
, add_yn = True
, return_formatted_output = True)
mmDD[k] = scores_cd_7030D
# Extracting the dfs from within the dict and concatenating to output as one df
for k, v in mmDD.items():
out_wf_cd_7030 = pd.concat(mmDD, ignore_index = True)
out_wf_cd_7030f = out_wf_cd_7030.sort_values(by = ['resampling', 'source_data', 'MCC'], ascending = [True, True, False], inplace = False)
print('\n######################################################################'
, '\nEnd--> Successfully generated output DF for Multiple classifiers (baseline models)'
, '\nGene:', gene.lower()
, '\nDrug:', drug
, '\noutput file:', outFile_wf
, '\nDim of output:', out_wf_cd_7030f.shape
, '\n######################################################################')
###############################################################################
#====================
# Write output file
#====================
out_wf_cd_7030f.to_csv(outFile_wf, index = False)
print('\nFile successfully written:', outFile_wf)
###############################################################################

141
scripts/ml/run_cd_8020.py Executable file
View file

@ -0,0 +1,141 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Jun 20 13:05:23 2022
@author: tanu
"""
#%%Imports ####################################################################
import re
import argparse
import os, sys
# gene = 'pncA'
# drug = 'pyrazinamide'
#total_mtblineage_uc = 8
###############################################################################
#%% command line args: case sensitive
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('-d', '--drug', help = 'drug name', default = '')
arg_parser.add_argument('-g', '--gene', help = 'gene name', default = '')
args = arg_parser.parse_args()
drug = args.drug
gene = args.gene
###############################################################################
homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml')
###############################################################################
#==================
# Import data
#==================
from ml_data_cd_8020 import *
setvars(gene,drug)
from ml_data_cd_8020 import *
# from YC run_all_ML: run locally
#from UQ_yc_RunAllClfs import run_all_ML
#====================
# Import ML functions
#====================
from MultClfs import *
#==================
# other vars
#==================
tts_split_cd_8020 = 'cd_80_20'
OutFile_suffix = '_cd_8020'
#==================
# Specify outdir
#==================
outdir_ml = outdir + 'ml/tts_cd_8020/'
print('\nOutput directory:', outdir_ml)
#outFile_wf = outdir_ml + gene.lower() + '_baselineC_' + OutFile_suffix + '.csv'
outFile_wf = outdir_ml + gene.lower() + '_baselineC_noOR' + OutFile_suffix + '.csv'
#%% Running models ############################################################
print('\n#####################################################################\n'
, '\nStarting--> Running ML analysis: Baseline modes (No FS)'
, '\nGene name:', gene
, '\nDrug name:', drug
, '\n#####################################################################\n')
paramD = {
'baseline_paramD': { 'input_df' : X
, 'target' : y
, 'var_type' : 'mixed'
, 'resampling_type': 'none'}
, 'smnc_paramD': { 'input_df' : X_smnc
, 'target' : y_smnc
, 'var_type' : 'mixed'
, 'resampling_type' : 'smnc'}
, 'ros_paramD': { 'input_df' : X_ros
, 'target' : y_ros
, 'var_type' : 'mixed'
, 'resampling_type' : 'ros'}
, 'rus_paramD' : { 'input_df' : X_rus
, 'target' : y_rus
, 'var_type' : 'mixed'
, 'resampling_type' : 'rus'}
, 'rouC_paramD' : { 'input_df' : X_rouC
, 'target' : y_rouC
, 'var_type' : 'mixed'
, 'resampling_type' : 'rouC'}
}
##==============================================================================
## Dict with no CV BT formatted df
## mmD = {}
## for k, v in paramD.items():
## # print(mmD[k])
## scores_cd_8020D = MultModelsCl(**paramD[k]
## , tts_split_type = tts_split_cd_8020
## , skf_cv = skf_cv
## , blind_test_df = X_bts
## , blind_test_target = y_bts
## , add_cm = True
## , add_yn = True
## , return_formatted_output = False)
## mmD[k] = scores_cd_8020D
##==============================================================================
## Initial run to get the dict of dicts for each sampling type containing CV, BT and metadata DFs
mmDD = {}
for k, v in paramD.items():
scores_cd_8020D = MultModelsCl(**paramD[k]
, tts_split_type = tts_split_cd_8020
, skf_cv = skf_cv
, blind_test_df = X_bts
, blind_test_target = y_bts
, add_cm = True
, add_yn = True
, return_formatted_output = True)
mmDD[k] = scores_cd_8020D
# Extracting the dfs from within the dict and concatenating to output as one df
for k, v in mmDD.items():
out_wf_cd_8020 = pd.concat(mmDD, ignore_index = True)
out_wf_cd_8020f = out_wf_cd_8020.sort_values(by = ['resampling', 'source_data', 'MCC'], ascending = [True, True, False], inplace = False)
print('\n######################################################################'
, '\nEnd--> Successfully generated output DF for Multiple classifiers (baseline models)'
, '\nGene:', gene.lower()
, '\nDrug:', drug
, '\noutput file:', outFile_wf
, '\nDim of output:', out_wf_cd_8020f.shape
, '\n######################################################################')
###############################################################################
#====================
# Write output file
#====================
out_wf_cd_8020f.to_csv(outFile_wf, index = False)
print('\nFile successfully written:', outFile_wf)
###############################################################################

141
scripts/ml/run_cd_sl.py Executable file
View file

@ -0,0 +1,141 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Jun 20 13:05:23 2022
@author: tanu
"""
#%%Imports ####################################################################
import re
import argparse
import os, sys
# gene = 'pncA'
# drug = 'pyrazinamide'
#total_mtblineage_uc = 8
###############################################################################
#%% command line args: case sensitive
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('-d', '--drug', help = 'drug name', default = '')
arg_parser.add_argument('-g', '--gene', help = 'gene name', default = '')
args = arg_parser.parse_args()
drug = args.drug
gene = args.gene
###############################################################################
homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml')
###############################################################################
#==================
# Import data
#==================
from ml_data_cd_sl import *
setvars(gene,drug)
from ml_data_cd_sl import *
# from YC run_all_ML: run locally
#from UQ_yc_RunAllClfs import run_all_ML
#====================
# Import ML functions
#====================
from MultClfs import *
#==================
# other vars
#==================
tts_split_cd_sl = 'cd_sl'
OutFile_suffix = '_cd_sl'
#==================
# Specify outdir
#==================
outdir_ml = outdir + 'ml/tts_cd_sl/'
print('\nOutput directory:', outdir_ml)
#outFile_wf = outdir_ml + gene.lower() + '_baselineC_' + OutFile_suffix + '.csv'
outFile_wf = outdir_ml + gene.lower() + '_baselineC_noOR' + OutFile_suffix + '.csv'
#%% Running models ############################################################
print('\n#####################################################################\n'
, '\nStarting--> Running ML analysis: Baseline modes (No FS)'
, '\nGene name:', gene
, '\nDrug name:', drug
, '\n#####################################################################\n')
paramD = {
'baseline_paramD': { 'input_df' : X
, 'target' : y
, 'var_type' : 'mixed'
, 'resampling_type': 'none'}
, 'smnc_paramD': { 'input_df' : X_smnc
, 'target' : y_smnc
, 'var_type' : 'mixed'
, 'resampling_type' : 'smnc'}
, 'ros_paramD': { 'input_df' : X_ros
, 'target' : y_ros
, 'var_type' : 'mixed'
, 'resampling_type' : 'ros'}
, 'rus_paramD' : { 'input_df' : X_rus
, 'target' : y_rus
, 'var_type' : 'mixed'
, 'resampling_type' : 'rus'}
, 'rouC_paramD' : { 'input_df' : X_rouC
, 'target' : y_rouC
, 'var_type' : 'mixed'
, 'resampling_type' : 'rouC'}
}
##==============================================================================
## Dict with no CV BT formatted df
## mmD = {}
## for k, v in paramD.items():
## # print(mmD[k])
## scores_cd_slD = MultModelsCl(**paramD[k]
## , tts_split_type = tts_split_cd_sl
## , skf_cv = skf_cv
## , blind_test_df = X_bts
## , blind_test_target = y_bts
## , add_cm = True
## , add_yn = True
## , return_formatted_output = False)
## mmD[k] = scores_cd_slD
##==============================================================================
## Initial run to get the dict of dicts for each sampling type containing CV, BT and metadata DFs
mmDD = {}
for k, v in paramD.items():
scores_cd_slD = MultModelsCl(**paramD[k]
, tts_split_type = tts_split_cd_sl
, skf_cv = skf_cv
, blind_test_df = X_bts
, blind_test_target = y_bts
, add_cm = True
, add_yn = True
, return_formatted_output = True)
mmDD[k] = scores_cd_slD
# Extracting the dfs from within the dict and concatenating to output as one df
for k, v in mmDD.items():
out_wf_cd_sl = pd.concat(mmDD, ignore_index = True)
out_wf_cd_slf = out_wf_cd_sl.sort_values(by = ['resampling', 'source_data', 'MCC'], ascending = [True, True, False], inplace = False)
print('\n######################################################################'
, '\nEnd--> Successfully generated output DF for Multiple classifiers (baseline models)'
, '\nGene:', gene.lower()
, '\nDrug:', drug
, '\noutput file:', outFile_wf
, '\nDim of output:', out_wf_cd_slf.shape
, '\n######################################################################')
###############################################################################
#====================
# Write output file
#====================
out_wf_cd_slf.to_csv(outFile_wf, index = False)
print('\nFile successfully written:', outFile_wf)
###############################################################################

141
scripts/ml/run_sl.py Executable file
View file

@ -0,0 +1,141 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Jun 20 13:05:23 2022
@author: tanu
"""
#%%Imports ####################################################################
import re
import argparse
import os, sys
# gene = 'pncA'
# drug = 'pyrazinamide'
#total_mtblineage_uc = 8
###############################################################################
#%% command line args: case sensitive
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('-d', '--drug', help = 'drug name', default = '')
arg_parser.add_argument('-g', '--gene', help = 'gene name', default = '')
args = arg_parser.parse_args()
drug = args.drug
gene = args.gene
###############################################################################
homedir = os.path.expanduser("~")
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml')
###############################################################################
#==================
# Import data
#==================
from ml_data_sl import *
setvars(gene,drug)
from ml_data_sl import *
# from YC run_all_ML: run locally
#from UQ_yc_RunAllClfs import run_all_ML
#====================
# Import ML functions
#====================
from MultClfs import *
#==================
# other vars
#==================
tts_split_sl = 'sl'
OutFile_suffix = 'sl'
#==================
# Specify outdir
#==================
outdir_ml = outdir + 'ml/tts_sl/'
print('\nOutput directory:', outdir_ml)
#outFile_wf = outdir_ml + gene.lower() + '_baselineC_' + OutFile_suffix + '.csv'
outFile_wf = outdir_ml + gene.lower() + '_baselineC_noOR' + OutFile_suffix + '.csv'
#%% Running models ############################################################
print('\n#####################################################################\n'
, '\nStarting--> Running ML analysis: Baseline modes (No FS)'
, '\nGene name:', gene
, '\nDrug name:', drug
, '\n#####################################################################\n')
paramD = {
'baseline_paramD': { 'input_df' : X
, 'target' : y
, 'var_type' : 'mixed'
, 'resampling_type': 'none'}
, 'smnc_paramD': { 'input_df' : X_smnc
, 'target' : y_smnc
, 'var_type' : 'mixed'
, 'resampling_type' : 'smnc'}
, 'ros_paramD': { 'input_df' : X_ros
, 'target' : y_ros
, 'var_type' : 'mixed'
, 'resampling_type' : 'ros'}
, 'rus_paramD' : { 'input_df' : X_rus
, 'target' : y_rus
, 'var_type' : 'mixed'
, 'resampling_type' : 'rus'}
, 'rouC_paramD' : { 'input_df' : X_rouC
, 'target' : y_rouC
, 'var_type' : 'mixed'
, 'resampling_type' : 'rouC'}
}
##==============================================================================
## Dict with no CV BT formatted df
## mmD = {}
## for k, v in paramD.items():
## # print(mmD[k])
## scores_slD = MultModelsCl(**paramD[k]
## , tts_split_type = tts_split_sl
## , skf_cv = skf_cv
## , blind_test_df = X_bts
## , blind_test_target = y_bts
## , add_cm = True
## , add_yn = True
## , return_formatted_output = False)
## mmD[k] = scores_slD
##==============================================================================
## Initial run to get the dict of dicts for each sampling type containing CV, BT and metadata DFs
mmDD = {}
for k, v in paramD.items():
scores_slD = MultModelsCl(**paramD[k]
, tts_split_type = tts_split_sl
, skf_cv = skf_cv
, blind_test_df = X_bts
, blind_test_target = y_bts
, add_cm = True
, add_yn = True
, return_formatted_output = True)
mmDD[k] = scores_slD
# Extracting the dfs from within the dict and concatenating to output as one df
for k, v in mmDD.items():
out_wf_sl = pd.concat(mmDD, ignore_index = True)
out_wf_slf = out_wf_sl.sort_values(by = ['resampling', 'source_data', 'MCC'], ascending = [True, True, False], inplace = False)
print('\n######################################################################'
, '\nEnd--> Successfully generated output DF for Multiple classifiers (baseline models)'
, '\nGene:', gene.lower()
, '\nDrug:', drug
, '\noutput file:', outFile_wf
, '\nDim of output:', out_wf_slf.shape
, '\n######################################################################')
###############################################################################
#====================
# Write output file
#====================
out_wf_slf.to_csv(outFile_wf, index = False)
print('\nFile successfully written:', outFile_wf)
###############################################################################