added run_7030.py that runs as cmd for all gene targets and sampling methods and outputs a single csv
This commit is contained in:
parent
5b0ccdfec4
commit
bc12dbd7c2
5 changed files with 749 additions and 229 deletions
|
|
@ -52,7 +52,7 @@ sampling_type_name = 'none'
|
|||
feature_gp_nameEV = 'evolutionary'
|
||||
n_featuresEV = len(X_evolFN)
|
||||
|
||||
scores_mmEV = MultModelsCl_dissected(input_df = X[X_evolFN]
|
||||
scores_mmEV = MultModelsCl(input_df = X[X_evolFN]
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
|
|
@ -96,7 +96,7 @@ baseline_EV['n_features'] = n_featuresEV
|
|||
feature_gp_nameGN = 'genomics'
|
||||
n_featuresGN = len(X_genomicFN)
|
||||
|
||||
scores_mmGN = MultModelsCl_dissected(input_df = X[X_genomicFN]
|
||||
scores_mmGN = MultModelsCl(input_df = X[X_genomicFN]
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
|
|
@ -143,7 +143,7 @@ baseline_GN['n_features'] = n_featuresGN
|
|||
feature_gp_nameSTR = 'structural'
|
||||
n_featuresSTR = len(X_structural_FN)
|
||||
|
||||
scores_mmSTR = MultModelsCl_dissected(input_df = X[X_structural_FN]
|
||||
scores_mmSTR = MultModelsCl(input_df = X[X_structural_FN]
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
|
|
@ -187,7 +187,7 @@ baseline_STR['n_features'] = n_featuresSTR
|
|||
feature_gp_nameSTB = 'stability'
|
||||
n_featuresSTB = len(X_stability_FN)
|
||||
|
||||
scores_mmSTB = MultModelsCl_dissected(input_df = X[X_stability_FN]
|
||||
scores_mmSTB = MultModelsCl(input_df = X[X_stability_FN]
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
|
|
@ -231,7 +231,7 @@ baseline_STB['n_features'] = n_featuresSTB
|
|||
feature_gp_nameAFF = 'affinity'
|
||||
n_featuresAFF = len(X_affinityFN)
|
||||
|
||||
scores_mmAFF = MultModelsCl_dissected(input_df = X[X_affinityFN]
|
||||
scores_mmAFF = MultModelsCl(input_df = X[X_affinityFN]
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
|
|
@ -275,7 +275,7 @@ baseline_AFF['n_features'] = n_featuresAFF
|
|||
feature_gp_nameRES = 'residue_prop'
|
||||
n_featuresRES = len(X_resprop_FN)
|
||||
|
||||
scores_mmRES = MultModelsCl_dissected(input_df = X[X_resprop_FN]
|
||||
scores_mmRES = MultModelsCl(input_df = X[X_resprop_FN]
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
|
|
@ -321,7 +321,7 @@ X_respropNOaaFN = list(set(X_resprop_FN) - set(X_aaindex_Fnum))
|
|||
feature_gp_nameRNAA = 'ResPropNoAA'
|
||||
n_featuresRNAA = len(X_respropNOaaFN)
|
||||
|
||||
scores_mmRNAA = MultModelsCl_dissected(input_df = X[X_respropNOaaFN]
|
||||
scores_mmRNAA = MultModelsCl(input_df = X[X_respropNOaaFN]
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
|
|
@ -367,7 +367,7 @@ X_strNOaaFN = list(set(X_structural_FN) - set(X_aaindex_Fnum))
|
|||
feature_gp_nameSNAA = 'StrNoAA'
|
||||
n_featuresSNAA = len(X_strNOaaFN)
|
||||
|
||||
scores_mmSNAA = MultModelsCl_dissected(input_df = X[X_strNOaaFN]
|
||||
scores_mmSNAA = MultModelsCl(input_df = X[X_strNOaaFN]
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
|
|
|
|||
|
|
@ -34,6 +34,8 @@ def setvars(gene,drug):
|
|||
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
|
||||
|
||||
from sklearn.pipeline import Pipeline, make_pipeline
|
||||
import argparse
|
||||
import re
|
||||
#%% GLOBALS
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
|
|
@ -422,118 +424,31 @@ def setvars(gene,drug):
|
|||
#==========================
|
||||
my_df_ml = my_df.copy()
|
||||
|
||||
#%% Build X: input for ML
|
||||
common_cols_stabiltyN = ['ligand_distance'
|
||||
, 'ligand_affinity_change'
|
||||
, 'duet_stability_change'
|
||||
, 'ddg_foldx'
|
||||
, 'deepddg'
|
||||
, 'ddg_dynamut2'
|
||||
, 'mmcsm_lig'
|
||||
, 'contacts']
|
||||
|
||||
# Build stability columns ~ gene
|
||||
# Build column names to mask for affinity chanhes
|
||||
if gene.lower() in geneL_basic:
|
||||
X_stabilityN = common_cols_stabiltyN
|
||||
#X_stabilityN = common_cols_stabiltyN
|
||||
gene_affinity_colnames = []# not needed as its the common ones
|
||||
cols_to_mask = ['ligand_affinity_change']
|
||||
|
||||
if gene.lower() in geneL_ppi2:
|
||||
# X_stabilityN = common_cols_stabiltyN + ['mcsm_ppi2_affinity' , 'interface_dist']
|
||||
geneL_ppi2_st_cols = ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
X_stabilityN = common_cols_stabiltyN + geneL_ppi2_st_cols
|
||||
gene_affinity_colnames = ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
#X_stabilityN = common_cols_stabiltyN + geneL_ppi2_st_cols
|
||||
cols_to_mask = ['ligand_affinity_change', 'mcsm_ppi2_affinity']
|
||||
|
||||
if gene.lower() in geneL_na:
|
||||
# X_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity']
|
||||
geneL_na_st_cols = ['mcsm_na_affinity']
|
||||
X_stabilityN = common_cols_stabiltyN + geneL_na_st_cols
|
||||
gene_affinity_colnames = ['mcsm_na_affinity']
|
||||
#X_stabilityN = common_cols_stabiltyN + geneL_na_st_cols
|
||||
cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity']
|
||||
|
||||
if gene.lower() in geneL_na_ppi2:
|
||||
# X_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
geneL_na_ppi2_st_cols = ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
X_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols
|
||||
gene_affinity_colnames = ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
#X_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols
|
||||
cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity', 'mcsm_ppi2_affinity']
|
||||
|
||||
|
||||
X_foldX_cols = [ 'electro_rr', 'electro_mm', 'electro_sm', 'electro_ss'
|
||||
, 'disulfide_rr', 'disulfide_mm', 'disulfide_sm', 'disulfide_ss'
|
||||
, 'hbonds_rr', 'hbonds_mm', 'hbonds_sm', 'hbonds_ss'
|
||||
, 'partcov_rr', 'partcov_mm', 'partcov_sm', 'partcov_ss'
|
||||
, 'vdwclashes_rr', 'vdwclashes_mm', 'vdwclashes_sm', 'vdwclashes_ss'
|
||||
, 'volumetric_rr', 'volumetric_mm', 'volumetric_ss'
|
||||
]
|
||||
|
||||
X_str = ['rsa'
|
||||
#, 'asa'
|
||||
, 'kd_values'
|
||||
, 'rd_values']
|
||||
|
||||
X_ssFN = X_stabilityN + X_str + X_foldX_cols
|
||||
|
||||
X_evolFN = ['consurf_score'
|
||||
, 'snap2_score'
|
||||
, 'provean_score']
|
||||
|
||||
X_genomic_mafor = ['maf'
|
||||
, 'logorI'
|
||||
# , 'or_rawI'
|
||||
# , 'or_mychisq'
|
||||
# , 'or_logistic'
|
||||
# , 'or_fisher'
|
||||
# , 'pval_fisher'
|
||||
]
|
||||
|
||||
X_genomic_linegae = ['lineage_proportion'
|
||||
, 'dist_lineage_proportion'
|
||||
#, 'lineage' # could be included as a category but it has L2;L4 formatting
|
||||
, 'lineage_count_all'
|
||||
, 'lineage_count_unique'
|
||||
]
|
||||
|
||||
X_genomicFN = X_genomic_mafor + X_genomic_linegae
|
||||
|
||||
X_aaindexFN = list(aa_df_cols)
|
||||
|
||||
print('\nTotal no. of features for aaindex:', len(X_aaindexFN))
|
||||
|
||||
# numerical feature names
|
||||
numerical_FN = X_ssFN + X_evolFN + X_genomicFN + X_aaindexFN
|
||||
|
||||
# categorical feature names
|
||||
categorical_FN = ['ss_class'
|
||||
# , 'wt_prop_water'
|
||||
# , 'mut_prop_water'
|
||||
# , 'wt_prop_polarity'
|
||||
# , 'mut_prop_polarity'
|
||||
# , 'wt_calcprop'
|
||||
# , 'mut_calcprop'
|
||||
, 'aa_prop_change'
|
||||
, 'electrostatics_change'
|
||||
, 'polarity_change'
|
||||
, 'water_change'
|
||||
, 'drtype_mode_labels' # beware then you can't use it to predict [USED it for uq_v1, not v2]
|
||||
, 'active_site' #[didn't use it for uq_v1]
|
||||
#, 'gene_name' # will be required for the combined stuff
|
||||
]
|
||||
|
||||
#----------------------------------------------
|
||||
# count numerical and categorical features
|
||||
#----------------------------------------------
|
||||
|
||||
print('\nNo. of numerical features:', len(numerical_FN)
|
||||
, '\nNo. of categorical features:', len(categorical_FN))
|
||||
|
||||
#=======================
|
||||
# Masking columns:
|
||||
# (mCSM-lig, mCSM-NA, mCSM-ppi2) values for lig_dist >10
|
||||
#=======================
|
||||
# my_df_ml['mutationinformation'][my_df['ligand_distance']>10].value_counts()
|
||||
# my_df_ml.groupby('mutationinformation')['ligand_distance'].apply(lambda x: (x>10)).value_counts()
|
||||
|
||||
# my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), 'ligand_affinity_change'] = 0
|
||||
# (my_df_ml['ligand_affinity_change'] == 0).sum()
|
||||
|
||||
my_df_ml['mutationinformation'][my_df_ml['ligand_distance']>10].value_counts()
|
||||
my_df_ml.groupby('mutationinformation')['ligand_distance'].apply(lambda x: (x>10)).value_counts()
|
||||
my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask].value_counts()
|
||||
|
|
@ -544,23 +459,149 @@ def setvars(gene,drug):
|
|||
|
||||
mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask]
|
||||
|
||||
#===================================================
|
||||
# write file for check
|
||||
mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
|
||||
mask_check.to_csv(outdir + 'ml/' + gene.lower() + '_mask_check.csv')
|
||||
#===================================================
|
||||
###############################################################################
|
||||
#%% Feature groups (FG): Build X for Input ML
|
||||
############################################################################
|
||||
#===========================
|
||||
# FG1: Evolutionary features
|
||||
#===========================
|
||||
X_evolFN = ['consurf_score'
|
||||
, 'snap2_score'
|
||||
, 'provean_score']
|
||||
|
||||
#####################################################################
|
||||
###############################################################################
|
||||
#========================
|
||||
# FG2: Stability features
|
||||
#========================
|
||||
#--------
|
||||
# common
|
||||
#--------
|
||||
X_common_stability_Fnum = [
|
||||
'duet_stability_change'
|
||||
, 'ddg_foldx'
|
||||
, 'deepddg'
|
||||
, 'ddg_dynamut2'
|
||||
, 'contacts']
|
||||
#--------
|
||||
# FoldX
|
||||
#--------
|
||||
X_foldX_Fnum = [ 'electro_rr', 'electro_mm', 'electro_sm', 'electro_ss'
|
||||
, 'disulfide_rr', 'disulfide_mm', 'disulfide_sm', 'disulfide_ss'
|
||||
, 'hbonds_rr', 'hbonds_mm', 'hbonds_sm', 'hbonds_ss'
|
||||
, 'partcov_rr', 'partcov_mm', 'partcov_sm', 'partcov_ss'
|
||||
, 'vdwclashes_rr', 'vdwclashes_mm', 'vdwclashes_sm', 'vdwclashes_ss'
|
||||
, 'volumetric_rr', 'volumetric_mm', 'volumetric_ss']
|
||||
|
||||
X_stability_FN = X_common_stability_Fnum + X_foldX_Fnum
|
||||
|
||||
###############################################################################
|
||||
#===================
|
||||
# FG3: Affinity features
|
||||
#===================
|
||||
common_affinity_Fnum = ['ligand_distance'
|
||||
, 'ligand_affinity_change'
|
||||
, 'mmcsm_lig']
|
||||
|
||||
# if gene.lower() in geneL_basic:
|
||||
# X_affinityFN = common_affinity_Fnum
|
||||
# else:
|
||||
# X_affinityFN = common_affinity_Fnum + gene_affinity_colnames
|
||||
|
||||
X_affinityFN = common_affinity_Fnum + gene_affinity_colnames
|
||||
|
||||
###############################################################################
|
||||
#============================
|
||||
# FG4: Residue level features
|
||||
#============================
|
||||
#-----------
|
||||
# AA index
|
||||
#-----------
|
||||
X_aaindex_Fnum = list(aa_df_cols)
|
||||
print('\nTotal no. of features for aaindex:', len(X_aaindex_Fnum))
|
||||
|
||||
#-----------------
|
||||
# surface area
|
||||
# depth
|
||||
# hydrophobicity
|
||||
#-----------------
|
||||
X_str_Fnum = ['rsa'
|
||||
#, 'asa'
|
||||
, 'kd_values'
|
||||
, 'rd_values']
|
||||
|
||||
#---------------------------
|
||||
# Other aa properties
|
||||
# active site indication
|
||||
#---------------------------
|
||||
X_aap_Fcat = ['ss_class'
|
||||
# , 'wt_prop_water'
|
||||
# , 'mut_prop_water'
|
||||
# , 'wt_prop_polarity'
|
||||
# , 'mut_prop_polarity'
|
||||
# , 'wt_calcprop'
|
||||
# , 'mut_calcprop'
|
||||
, 'aa_prop_change'
|
||||
, 'electrostatics_change'
|
||||
, 'polarity_change'
|
||||
, 'water_change'
|
||||
, 'active_site']
|
||||
|
||||
X_resprop_FN = X_aaindex_Fnum + X_str_Fnum + X_aap_Fcat
|
||||
###############################################################################
|
||||
#========================
|
||||
# FG5: Genomic features
|
||||
#========================
|
||||
X_gn_mafor_Fnum = ['maf'
|
||||
, 'logorI'
|
||||
# , 'or_rawI'
|
||||
# , 'or_mychisq'
|
||||
# , 'or_logistic'
|
||||
# , 'or_fisher'
|
||||
# , 'pval_fisher'
|
||||
]
|
||||
|
||||
X_gn_linegae_Fnum = ['lineage_proportion'
|
||||
, 'dist_lineage_proportion'
|
||||
#, 'lineage' # could be included as a category but it has L2;L4 formatting
|
||||
, 'lineage_count_all'
|
||||
, 'lineage_count_unique'
|
||||
]
|
||||
|
||||
X_gn_Fcat = ['drtype_mode_labels' # beware then you can't use it to predict [USED it for uq_v1, not v2]
|
||||
#, 'gene_name' # will be required for the combined stuff
|
||||
]
|
||||
|
||||
X_genomicFN = X_gn_mafor_Fnum + X_gn_linegae_Fnum + X_gn_Fcat
|
||||
###############################################################################
|
||||
#========================
|
||||
# FG6 collapsed: Structural : Atability + Affinity + ResidueProp
|
||||
#========================
|
||||
X_structural_FN = X_stability_FN + X_affinityFN + X_resprop_FN
|
||||
|
||||
###############################################################################
|
||||
#========================
|
||||
# BUILDING all features
|
||||
#========================
|
||||
all_featuresN = X_evolFN + X_structural_FN + X_genomicFN
|
||||
|
||||
###############################################################################
|
||||
#%% Define training and test data
|
||||
#================================================================
|
||||
# Training and BLIND test set: 70/30
|
||||
|
||||
# Throw away previous blind_test_df, and call the 30% data as blind_test
|
||||
# as these were imputed values and initial analysis shows that this
|
||||
# is not very representative
|
||||
# dst with actual values : training set
|
||||
# dst with imputed values : THROW AWAY [unrepresentative]
|
||||
#================================================================
|
||||
my_df_ml[drug].isna().sum()
|
||||
|
||||
# blind_test_df = my_df_ml[my_df_ml[drug].isna()]
|
||||
# blind_test_df.shape
|
||||
|
||||
training_df = my_df_ml[my_df_ml[drug].notna()]
|
||||
training_df = my_df_ml[my_df_ml[drug].notna()]
|
||||
training_df.shape
|
||||
|
||||
# Target 1: dst_mode
|
||||
|
|
@ -568,80 +609,14 @@ def setvars(gene,drug):
|
|||
training_df['dst_mode'].value_counts()
|
||||
|
||||
####################################################################
|
||||
|
||||
###############################################################################
|
||||
###############################################################################
|
||||
# #%% extracting dfs based on numerical, categorical column names
|
||||
# #----------------------------------
|
||||
# # WITHOUT the target var included
|
||||
# #----------------------------------
|
||||
# num_df = training_df[numerical_FN]
|
||||
# num_df.shape
|
||||
|
||||
# cat_df = training_df[categorical_FN]
|
||||
# cat_df.shape
|
||||
|
||||
# all_df = training_df[numerical_FN + categorical_FN]
|
||||
# all_df.shape
|
||||
|
||||
# #------------------------------
|
||||
# # WITH the target var included:
|
||||
# #'wtgt': with target
|
||||
# #------------------------------
|
||||
# # drug and dst_mode should be the same thing
|
||||
# num_df_wtgt = training_df[numerical_FN + ['dst_mode']]
|
||||
# num_df_wtgt.shape
|
||||
|
||||
# cat_df_wtgt = training_df[categorical_FN + ['dst_mode']]
|
||||
# cat_df_wtgt.shape
|
||||
|
||||
# all_df_wtgt = training_df[numerical_FN + categorical_FN + ['dst_mode']]
|
||||
# all_df_wtgt.shape
|
||||
|
||||
#%%########################################################################
|
||||
# #============
|
||||
# # ML data: OLD
|
||||
# #============
|
||||
# #------
|
||||
# # X: Training and Blind test (BTS)
|
||||
# #------
|
||||
# X = all_df_wtgt[numerical_FN + categorical_FN] # training data ALL
|
||||
# X_bts = blind_test_df[numerical_FN + categorical_FN] # blind test data ALL
|
||||
# #X = all_df_wtgt[numerical_FN] # training numerical only
|
||||
# #X_bts = blind_test_df[numerical_FN] # blind test data numerical
|
||||
|
||||
# #------
|
||||
# # y
|
||||
# #------
|
||||
# y = all_df_wtgt['dst_mode'] # training data y
|
||||
# y_bts = blind_test_df['dst_mode'] # blind data test y
|
||||
|
||||
# #X_bts_wt = blind_test_df[numerical_FN + ['dst_mode']]
|
||||
|
||||
# # Quick check
|
||||
# #(X['ligand_affinity_change']==0).sum() == (X['ligand_distance']>10).sum()
|
||||
# for i in range(len(cols_to_mask)):
|
||||
# ind = i+1
|
||||
# print('\nindex:', i, '\nind:', ind)
|
||||
# print('\nMask count check:'
|
||||
# , (my_df_ml[cols_to_mask[i]]==0).sum() == (my_df_ml['ligand_distance']>10).sum()
|
||||
# )
|
||||
|
||||
# print('Original Data\n', Counter(y)
|
||||
# , 'Data dim:', X.shape)
|
||||
|
||||
###############################################################################
|
||||
###############################################################################
|
||||
#====================================
|
||||
# ML data: Train test split: 70/30
|
||||
# with stratification
|
||||
# 70% : training_data for CV
|
||||
# 30% : blind test
|
||||
#=====================================
|
||||
|
||||
# features: all_df or
|
||||
x_features = training_df[numerical_FN + categorical_FN]
|
||||
y_target = training_df['dst_mode']
|
||||
x_features = training_df[all_featuresN]
|
||||
y_target = training_df['dst_mode']
|
||||
|
||||
# sanity check
|
||||
if not 'dst_mode' in x_features.columns:
|
||||
|
|
@ -652,7 +627,9 @@ def setvars(gene,drug):
|
|||
#https://towardsdatascience.com/finally-why-we-use-an-80-20-split-for-training-and-test-data-plus-an-alternative-method-oh-yes-edc77e96295d
|
||||
else:
|
||||
sys.exit('\nFAIL: x_features has target variable included. FIX it and rerun!')
|
||||
|
||||
#-------------------
|
||||
# train-test split
|
||||
#-------------------
|
||||
#x_train, x_test, y_train, y_test # traditional var_names
|
||||
# so my downstream code doesn't need to change
|
||||
X, X_bts, y, y_bts = train_test_split(x_features, y_target
|
||||
|
|
@ -665,15 +642,63 @@ def setvars(gene,drug):
|
|||
yc2 = Counter(y_bts)
|
||||
yc2_ratio = yc2[0]/yc2[1]
|
||||
|
||||
###############################################################################
|
||||
#======================================================
|
||||
# Determine categorical and numerical features
|
||||
#======================================================
|
||||
numerical_cols = X.select_dtypes(include=['int64', 'float64']).columns
|
||||
numerical_cols
|
||||
categorical_cols = X.select_dtypes(include=['object', 'bool']).columns
|
||||
categorical_cols
|
||||
|
||||
################################################################################
|
||||
# IMPORTANT sanity checks
|
||||
if len(X.columns) == len(X_evolFN) + len(X_stability_FN) + len(X_affinityFN) + len(X_resprop_FN) + len(X_genomicFN):
|
||||
print('\nPASS: ML data with input features, training and test generated...'
|
||||
, '\n\nTotal no. of input features:' , len(X.columns)
|
||||
, '\n--------No. of numerical features:' , len(numerical_cols)
|
||||
, '\n--------No. of categorical features:' , len(categorical_cols)
|
||||
|
||||
, '\n\nTotal no. of evolutionary features:' , len(X_evolFN)
|
||||
|
||||
, '\n\nTotal no. of stability features:' , len(X_stability_FN)
|
||||
, '\n--------Common stabilty cols:' , len(X_common_stability_Fnum)
|
||||
, '\n--------Foldx cols:' , len(X_foldX_Fnum)
|
||||
|
||||
, '\n\nTotal no. of affinity features:' , len(X_affinityFN)
|
||||
, '\n--------Common affinity cols:' , len(common_affinity_Fnum)
|
||||
, '\n--------Gene specific affinity cols:' , len(gene_affinity_colnames)
|
||||
|
||||
, '\n\nTotal no. of residue level features:', len(X_resprop_FN)
|
||||
, '\n--------AA index cols:' , len(X_aaindex_Fnum)
|
||||
, '\n--------Residue Prop cols:' , len(X_str_Fnum)
|
||||
, '\n--------AA change Prop cols:' , len(X_aap_Fcat)
|
||||
|
||||
, '\n\nTotal no. of genomic features:' , len(X_genomicFN)
|
||||
, '\n--------MAF+OR cols:' , len(X_gn_mafor_Fnum)
|
||||
, '\n--------Lineage cols:' , len(X_gn_linegae_Fnum)
|
||||
, '\n--------Other cols:' , len(X_gn_Fcat)
|
||||
)
|
||||
else:
|
||||
print('\nFAIL: numbers mismatch'
|
||||
, '\nExpected:',len(X_evolFN) + len(X_stability_FN) + len(X_affinityFN) + len(X_resprop_FN) + len(X_genomicFN)
|
||||
, '\nGot:', len(X.columns))
|
||||
sys.exit()
|
||||
###############################################################################
|
||||
print('\n-------------------------------------------------------------'
|
||||
, '\nSuccessfully split data with stratification: 70/30'
|
||||
, '\nInput features data size:', x_features.shape
|
||||
, '\nTrain data size:', X.shape
|
||||
, '\nTest data size:', X_bts.shape
|
||||
, '\nSuccessfully split data: ALL features'
|
||||
, '\nactual values: training set'
|
||||
, '\nimputed values: blind test set'
|
||||
|
||||
, '\n\nTotal data size:', len(X) + len(X_bts)
|
||||
|
||||
, '\n\nTrain data size:', X.shape
|
||||
, '\ny_train numbers:', yc1
|
||||
, '\ny_train ratio:',yc1_ratio
|
||||
, '\n'
|
||||
|
||||
, '\n\nTest data size:', X_bts.shape
|
||||
, '\ny_test_numbers:', yc2
|
||||
|
||||
, '\n\ny_train ratio:',yc1_ratio
|
||||
, '\ny_test ratio:', yc2_ratio
|
||||
, '\n-------------------------------------------------------------'
|
||||
)
|
||||
|
|
@ -700,7 +725,7 @@ def setvars(gene,drug):
|
|||
#------------------------------
|
||||
oversample = RandomOverSampler(sampling_strategy='minority')
|
||||
X_ros, y_ros = oversample.fit_resample(X, y)
|
||||
print('\nSimple Random OverSampling\n', Counter(y_ros))
|
||||
print('Simple Random OverSampling\n', Counter(y_ros))
|
||||
print(X_ros.shape)
|
||||
|
||||
#------------------------------
|
||||
|
|
@ -709,7 +734,7 @@ def setvars(gene,drug):
|
|||
#------------------------------
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
X_rus, y_rus = undersample.fit_resample(X, y)
|
||||
print('\nSimple Random UnderSampling\n', Counter(y_rus))
|
||||
print('Simple Random UnderSampling\n', Counter(y_rus))
|
||||
print(X_rus.shape)
|
||||
|
||||
#------------------------------
|
||||
|
|
@ -720,7 +745,7 @@ def setvars(gene,drug):
|
|||
X_ros, y_ros = oversample.fit_resample(X, y)
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
X_rouC, y_rouC = undersample.fit_resample(X_ros, y_ros)
|
||||
print('\nSimple Combined Over and UnderSampling\n', Counter(y_rouC))
|
||||
print('Simple Combined Over and UnderSampling\n', Counter(y_rouC))
|
||||
print(X_rouC.shape)
|
||||
|
||||
#------------------------------
|
||||
|
|
@ -740,7 +765,7 @@ def setvars(gene,drug):
|
|||
categorical_colind = X.columns.get_indexer(list(categorical_ix))
|
||||
categorical_colind
|
||||
|
||||
k_sm = 5 # 5 is default
|
||||
k_sm = 5 # 5 is deafult
|
||||
sm_nc = SMOTENC(categorical_features=categorical_colind, k_neighbors = k_sm, **rs, **njobs)
|
||||
X_smnc, y_smnc = sm_nc.fit_resample(X, y)
|
||||
print('\nSMOTE_NC OverSampling\n', Counter(y_smnc))
|
||||
|
|
|
|||
|
|
@ -61,7 +61,6 @@ def setvars(gene,drug):
|
|||
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
|
||||
|
||||
#%% FOR LATER: Combine ED logo data
|
||||
#%% DONE: active aa site annotations **DONE on 15/05/2022 as part of generating merged_dfs
|
||||
###########################################################################
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
|
|
@ -419,7 +418,7 @@ def setvars(gene,drug):
|
|||
#---------------------------------------
|
||||
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
|
||||
|
||||
#%% Data for ML
|
||||
#%%########################################################################
|
||||
#==========================
|
||||
# Data for ML
|
||||
#==========================
|
||||
|
|
@ -552,7 +551,6 @@ def setvars(gene,drug):
|
|||
, 'water_change'
|
||||
, 'active_site']
|
||||
|
||||
|
||||
X_resprop_FN = X_aaindex_Fnum + X_str_Fnum + X_aap_Fcat
|
||||
###############################################################################
|
||||
#========================
|
||||
|
|
@ -594,8 +592,7 @@ def setvars(gene,drug):
|
|||
###############################################################################
|
||||
#%% Define training and test data
|
||||
#======================================================
|
||||
# Training and BLIND test set [UQ]: actual vs imputed
|
||||
# No aa index but active_site included
|
||||
# Training and BLIND test set: actual vs imputed
|
||||
# dst with actual values : training set
|
||||
# dst with imputed values : blind test
|
||||
#======================================================
|
||||
|
|
@ -612,9 +609,9 @@ def setvars(gene,drug):
|
|||
training_df['dst_mode'].value_counts()
|
||||
|
||||
####################################################################
|
||||
#============
|
||||
# ML data
|
||||
#============
|
||||
#=====================================
|
||||
# ML data: actual vs imputed
|
||||
#=====================================
|
||||
#------
|
||||
# X: Training and Blind test (BTS)
|
||||
#------
|
||||
|
|
@ -627,18 +624,6 @@ def setvars(gene,drug):
|
|||
y = training_df['dst_mode']
|
||||
y_bts = blind_test_df['dst_mode']
|
||||
|
||||
# Quick check
|
||||
#(X['ligand_affinity_change']==0).sum() == (X['ligand_distance']>10).sum()
|
||||
for i in range(len(cols_to_mask)):
|
||||
ind = i+1
|
||||
print('\nindex:', i, '\nind:', ind)
|
||||
print('\nMask count check:'
|
||||
, (my_df_ml[cols_to_mask[i]]==0).sum() == (my_df_ml['ligand_distance']>10).sum()
|
||||
)
|
||||
|
||||
print('Original Data\n', Counter(y)
|
||||
, 'Data dim:', X.shape)
|
||||
|
||||
yc1 = Counter(y)
|
||||
yc1_ratio = yc1[0]/yc1[1]
|
||||
|
||||
|
|
@ -705,7 +690,18 @@ def setvars(gene,drug):
|
|||
, '\ny_test ratio:', yc2_ratio
|
||||
, '\n-------------------------------------------------------------'
|
||||
)
|
||||
##########################################################################
|
||||
# Quick check
|
||||
#(X['ligand_affinity_change']==0).sum() == (X['ligand_distance']>10).sum()
|
||||
for i in range(len(cols_to_mask)):
|
||||
ind = i+1
|
||||
print('\nindex:', i, '\nind:', ind)
|
||||
print('\nMask count check:'
|
||||
, (my_df_ml[cols_to_mask[i]]==0).sum() == (my_df_ml['ligand_distance']>10).sum()
|
||||
)
|
||||
|
||||
print('Original Data\n', Counter(y)
|
||||
, 'Data dim:', X.shape)
|
||||
###########################################################################
|
||||
#%%
|
||||
###########################################################################
|
||||
|
|
@ -760,7 +756,7 @@ def setvars(gene,drug):
|
|||
k_sm = 5 # 5 is deafult
|
||||
sm_nc = SMOTENC(categorical_features=categorical_colind, k_neighbors = k_sm, **rs, **njobs)
|
||||
X_smnc, y_smnc = sm_nc.fit_resample(X, y)
|
||||
print('SMOTE_NC OverSampling\n', Counter(y_smnc))
|
||||
print('\nSMOTE_NC OverSampling\n', Counter(y_smnc))
|
||||
print(X_smnc.shape)
|
||||
globals().update(locals()) # TROLOLOLOLOLOLS
|
||||
#print("i did a horrible hack :-)")
|
||||
|
|
@ -774,7 +770,7 @@ def setvars(gene,drug):
|
|||
# sm = SMOTE(sampling_strategy = 'auto', k_neighbors = k_sm, **rs)
|
||||
# X_sm, y_sm = sm.fit_resample(X, y)
|
||||
# print(X_sm.shape)
|
||||
# print('SMOTE OverSampling\n', Counter(y_sm))
|
||||
# print('\nSMOTE OverSampling\n', Counter(y_sm))
|
||||
# y_sm_df = y_sm.to_frame()
|
||||
# y_sm_df.value_counts().plot(kind = 'bar')
|
||||
|
||||
|
|
@ -785,7 +781,7 @@ def setvars(gene,drug):
|
|||
# sm_enn = SMOTEENN(enn=EditedNearestNeighbours(sampling_strategy='all', **rs, **njobs ))
|
||||
# X_enn, y_enn = sm_enn.fit_resample(X, y)
|
||||
# print(X_enn.shape)
|
||||
# print('SMOTE Over+Under Sampling combined\n', Counter(y_enn))
|
||||
# print('\nSMOTE Over+Under Sampling combined\n', Counter(y_enn))
|
||||
|
||||
###############################################################################
|
||||
# TODO: Find over and undersampling JUST for categorical data
|
||||
|
|
|
|||
499
scripts/ml/run_7030.py
Normal file
499
scripts/ml/run_7030.py
Normal file
|
|
@ -0,0 +1,499 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Created on Mon Jun 20 13:05:23 2022
|
||||
|
||||
@author: tanu
|
||||
"""
|
||||
import re
|
||||
import argparse
|
||||
###############################################################################
|
||||
# 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'
|
||||
###############################################################################
|
||||
#==================
|
||||
# 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 function
|
||||
#====================
|
||||
# TT run all ML clfs: baseline model
|
||||
from MultModelsCl import MultModelsCl
|
||||
|
||||
############################################################################
|
||||
print('\n#####################################################################\n'
|
||||
, '\nRunning ML analysis: feature groups '
|
||||
, '\nGene name:', gene
|
||||
, '\nDrug name:', drug)
|
||||
|
||||
#==================
|
||||
# Specify outdir
|
||||
#==================
|
||||
outdir_ml = outdir + 'ml/tts_7030/'
|
||||
print('\nOutput directory:', outdir_ml)
|
||||
outFile = outdir_ml + gene.lower() + '_baselineC_' + OutFile_suffix + '.csv'
|
||||
|
||||
###############################################################################
|
||||
score_type_ordermapD = { 'mcc' : 1
|
||||
, 'fscore' : 2
|
||||
, 'jcc' : 3
|
||||
, 'precision' : 4
|
||||
, 'recall' : 5
|
||||
, 'accuracy' : 6
|
||||
, 'roc_auc' : 7
|
||||
, 'TN' : 8
|
||||
, 'FP' : 9
|
||||
, 'FN' : 10
|
||||
, 'TP' : 11
|
||||
, 'trainingY_neg': 12
|
||||
, 'trainingY_pos': 13
|
||||
, 'blindY_neg' : 14
|
||||
, 'blindY_pos' : 15
|
||||
, 'fit_time' : 16
|
||||
, 'score_time' : 17
|
||||
}
|
||||
|
||||
# data dependent variable
|
||||
bts_size = len(X_bts)
|
||||
###############################################################################
|
||||
#%% TTS: 7030 split
|
||||
# mm_skf_scoresD = MultModelsCl(input_df = X
|
||||
# , target = y
|
||||
# , var_type = 'mixed'
|
||||
# , skf_cv = skf_cv
|
||||
# , blind_test_input_df = X_bts
|
||||
# , blind_test_target = y_bts)
|
||||
|
||||
# baseline_all = pd.DataFrame(mm_skf_scoresD)
|
||||
# baseline_all = baseline_all.T
|
||||
# #baseline_train = baseline_all.filter(like='train_', axis=1)
|
||||
# baseline_CT = baseline_all.filter(like='test_', axis=1)
|
||||
# baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# baseline_BT = baseline_all.filter(like='bts_', axis=1)
|
||||
# baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# # Write csv
|
||||
# baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
|
||||
# baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
|
||||
|
||||
#================
|
||||
# Baseline
|
||||
# No resampling
|
||||
#================
|
||||
# other data dependent variables
|
||||
training_size_ns = len(X)
|
||||
n_features = len(X.columns)
|
||||
|
||||
scores_mmD = MultModelsCl(input_df = X
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
, blind_test_input_df = X_bts
|
||||
, blind_test_target = y_bts
|
||||
, add_cm = True
|
||||
, add_yn = True)
|
||||
|
||||
baseline_all_scores = pd.DataFrame(scores_mmD)
|
||||
|
||||
baseline_all = baseline_all_scores.filter(regex = 'bts_.*|test_.*|.*_time|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
|
||||
baseline_all = baseline_all.reset_index()
|
||||
baseline_all.rename(columns = {'index': 'original_names'}, inplace = True)
|
||||
|
||||
# Indicate whether BT or CT
|
||||
bt_pattern = re.compile(r'bts_.*')
|
||||
baseline_all['data_source'] = baseline_all.apply(lambda row: 'BT' if bt_pattern.search(row.original_names) else 'CV' , axis = 1)
|
||||
|
||||
baseline_all['score_type'] = baseline_all['original_names'].str.replace('bts_|test_', '', regex = True)
|
||||
|
||||
score_type_uniqueN = set(baseline_all['score_type'])
|
||||
cL1 = list(score_type_ordermapD.keys())
|
||||
cL2 = list(score_type_uniqueN)
|
||||
|
||||
if set(cL1).issubset(cL2):
|
||||
print('\nPASS: sorting df by score that is mapped onto the order I want')
|
||||
baseline_all['score_order'] = baseline_all['score_type'].map(score_type_ordermapD)
|
||||
baseline_all.sort_values(by = ['data_source', 'score_order'], ascending = [True, True], inplace = True)
|
||||
else:
|
||||
sys.exit('\nFAIL: could not sort df as score mapping for ordering failed')
|
||||
|
||||
# add cols: specific
|
||||
baseline_all['resampling'] = 'none'
|
||||
baseline_all['training_size'] = training_size_ns
|
||||
|
||||
# add cols: common
|
||||
baseline_all['n_features'] = n_features
|
||||
#baseline_all['test_size'] = bts_size
|
||||
#baseline_all['tts_split'] = tts_split
|
||||
|
||||
###############################################################################
|
||||
#%% SMOTE NC: Oversampling [Numerical + categorical]
|
||||
# mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
|
||||
# , target = y_smnc
|
||||
# , var_type = 'mixed'
|
||||
# , skf_cv = skf_cv
|
||||
# , blind_test_input_df = X_bts
|
||||
# , blind_test_target = y_bts)
|
||||
# smnc_all = pd.DataFrame(mm_skf_scoresD7)
|
||||
# smnc_all = smnc_all.T
|
||||
|
||||
# smnc_CT = smnc_all.filter(like='test_', axis=1)
|
||||
# smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# smnc_BT = smnc_all.filter(like='bts_', axis=1)
|
||||
# smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# # Write csv
|
||||
# smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
|
||||
# smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
|
||||
|
||||
#================
|
||||
# Baselone
|
||||
# SMOTE NC
|
||||
#================
|
||||
# other data dependent variables
|
||||
training_size_smnc = len(X_smnc)
|
||||
n_features = len(X_smnc.columns)
|
||||
|
||||
smnc_scores_mmD = MultModelsCl(input_df = X_smnc
|
||||
, target = y_smnc
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
, blind_test_input_df = X_bts
|
||||
, blind_test_target = y_bts
|
||||
, add_cm = True
|
||||
, add_yn = True)
|
||||
|
||||
smnc_all_scores = pd.DataFrame(smnc_scores_mmD)
|
||||
|
||||
smnc_all = smnc_all_scores.filter(regex = 'bts_.*|test_.*|.*_time|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
|
||||
smnc_all = smnc_all.reset_index()
|
||||
smnc_all.rename(columns = {'index': 'original_names'}, inplace = True)
|
||||
|
||||
# Indicate whether BT or CT
|
||||
bt_pattern = re.compile(r'bts_.*')
|
||||
smnc_all['data_source'] = smnc_all.apply(lambda row: 'BT' if bt_pattern.search(row.original_names) else 'CV' , axis = 1)
|
||||
|
||||
smnc_all['score_type'] = smnc_all['original_names'].str.replace('bts_|test_', '', regex = True)
|
||||
|
||||
score_type_uniqueN = set(smnc_all['score_type'])
|
||||
cL1 = list(score_type_ordermapD.keys())
|
||||
cL2 = list(score_type_uniqueN)
|
||||
|
||||
if set(cL1).issubset(cL2):
|
||||
print('\nPASS: sorting df by score that is mapped onto the order I want')
|
||||
smnc_all['score_order'] = smnc_all['score_type'].map(score_type_ordermapD)
|
||||
smnc_all.sort_values(by = ['data_source', 'score_order'], ascending = [True, True], inplace = True)
|
||||
else:
|
||||
sys.exit('\nFAIL: could not sort df as score mapping for ordering failed')
|
||||
|
||||
# add cols: specific
|
||||
smnc_all['resampling'] = 'smnc'
|
||||
smnc_all['training_size'] = training_size_smnc
|
||||
|
||||
# add cols: common
|
||||
smnc_all['n_features'] = n_features
|
||||
#smnc_all['test_size'] = bts_size
|
||||
#smnc_all['tts_split'] = tts_split
|
||||
###############################################################################
|
||||
#%% ROS: Numerical + categorical
|
||||
# mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
|
||||
# , target = y_ros
|
||||
# , var_type = 'mixed'
|
||||
# , skf_cv = skf_cv
|
||||
# , blind_test_input_df = X_bts
|
||||
# , blind_test_target = y_bts)
|
||||
# ros_all = pd.DataFrame(mm_skf_scoresD3)
|
||||
# ros_all = ros_all.T
|
||||
|
||||
# ros_CT = ros_all.filter(like='test_', axis=1)
|
||||
# ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# ros_BT = ros_all.filter(like='bts_', axis=1)
|
||||
# ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# # Write csv
|
||||
# ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
|
||||
# ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
|
||||
#================
|
||||
# Baseline
|
||||
# ROS
|
||||
#================
|
||||
# other data dependent variables
|
||||
training_size_ros = len(X_ros)
|
||||
n_features = len(X_ros.columns)
|
||||
|
||||
ros_scores_mmD = MultModelsCl(input_df = X_ros
|
||||
, target = y_ros
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
, blind_test_input_df = X_bts
|
||||
, blind_test_target = y_bts
|
||||
, add_cm = True
|
||||
, add_yn = True)
|
||||
|
||||
ros_all_scores = pd.DataFrame(ros_scores_mmD)
|
||||
|
||||
ros_all = ros_all_scores.filter(regex = 'bts_.*|test_.*|.*_time|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
|
||||
ros_all = ros_all.reset_index()
|
||||
ros_all.rename(columns = {'index': 'original_names'}, inplace = True)
|
||||
|
||||
# Indicate whether BT or CT
|
||||
bt_pattern = re.compile(r'bts_.*')
|
||||
ros_all['data_source'] = ros_all.apply(lambda row: 'BT' if bt_pattern.search(row.original_names) else 'CV' , axis = 1)
|
||||
|
||||
ros_all['score_type'] = ros_all['original_names'].str.replace('bts_|test_', '', regex = True)
|
||||
|
||||
score_type_uniqueN = set(ros_all['score_type'])
|
||||
cL1 = list(score_type_ordermapD.keys())
|
||||
cL2 = list(score_type_uniqueN)
|
||||
|
||||
if set(cL1).issubset(cL2):
|
||||
print('\nPASS: sorting df by score that is mapped onto the order I want')
|
||||
ros_all['score_order'] = ros_all['score_type'].map(score_type_ordermapD)
|
||||
ros_all.sort_values(by = ['data_source', 'score_order'], ascending = [True, True], inplace = True)
|
||||
else:
|
||||
sys.exit('\nFAIL: could not sort df as score mapping for ordering failed')
|
||||
|
||||
# add cols: specific
|
||||
ros_all['resampling'] = 'ros'
|
||||
ros_all['training_size'] = training_size_ros
|
||||
|
||||
# add cols: common
|
||||
ros_all['n_features'] = n_features
|
||||
#ros_all['test_size'] = bts_size
|
||||
#ros_all['tts_split'] = tts_split
|
||||
###############################################################################
|
||||
#%% RUS: Numerical + categorical
|
||||
# mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
|
||||
# , target = y_rus
|
||||
# , var_type = 'mixed'
|
||||
# , skf_cv = skf_cv
|
||||
# , blind_test_input_df = X_bts
|
||||
# , blind_test_target = y_bts)
|
||||
# rus_all = pd.DataFrame(mm_skf_scoresD4)
|
||||
# rus_all = rus_all.T
|
||||
|
||||
# rus_CT = rus_all.filter(like='test_', axis=1)
|
||||
# rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# rus_BT = rus_all.filter(like='bts_' , axis=1)
|
||||
# rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# # Write csv
|
||||
# rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
|
||||
# rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
|
||||
|
||||
#================
|
||||
# Baseline
|
||||
# RUS
|
||||
#================
|
||||
# other data dependent variables
|
||||
training_size_rus = len(X_rus)
|
||||
n_features = len(X_rus.columns)
|
||||
|
||||
rus_scores_mmD = MultModelsCl(input_df = X_rus
|
||||
, target = y_rus
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
, blind_test_input_df = X_bts
|
||||
, blind_test_target = y_bts
|
||||
, add_cm = True
|
||||
, add_yn = True)
|
||||
|
||||
rus_all_scores = pd.DataFrame(rus_scores_mmD)
|
||||
|
||||
rus_all = rus_all_scores.filter(regex = 'bts_.*|test_.*|.*_time|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
|
||||
rus_all = rus_all.reset_index()
|
||||
rus_all.rename(columns = {'index': 'original_names'}, inplace = True)
|
||||
|
||||
# Indicate whether BT or CT
|
||||
bt_pattern = re.compile(r'bts_.*')
|
||||
rus_all['data_source'] = rus_all.apply(lambda row: 'BT' if bt_pattern.search(row.original_names) else 'CV' , axis = 1)
|
||||
|
||||
rus_all['score_type'] = rus_all['original_names'].str.replace('bts_|test_', '', regex = True)
|
||||
|
||||
score_type_uniqueN = set(rus_all['score_type'])
|
||||
cL1 = list(score_type_ordermapD.keys())
|
||||
cL2 = list(score_type_uniqueN)
|
||||
|
||||
if set(cL1).issubset(cL2):
|
||||
print('\nPASS: sorting df by score that is mapped onto the order I want')
|
||||
rus_all['score_order'] = rus_all['score_type'].map(score_type_ordermapD)
|
||||
rus_all.sort_values(by = ['data_source', 'score_order'], ascending = [True, True], inplace = True)
|
||||
else:
|
||||
sys.exit('\nFAIL: could not sort df as score mapping for ordering failed')
|
||||
|
||||
# add cols: specific
|
||||
rus_all['resampling'] = 'rus'
|
||||
rus_all['training_size'] = training_size_rus
|
||||
|
||||
# add cols: common
|
||||
rus_all['n_features'] = n_features
|
||||
#rus_all['test_size'] = bts_size
|
||||
#rus_all['tts_split'] = tts_split
|
||||
###############################################################################
|
||||
#%% ROS + RUS Combined: Numerical + categorical
|
||||
# mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
|
||||
# , target = y_rouC
|
||||
# , var_type = 'mixed'
|
||||
# , skf_cv = skf_cv
|
||||
# , blind_test_input_df = X_bts
|
||||
# , blind_test_target = y_bts)
|
||||
# rouC_all = pd.DataFrame(mm_skf_scoresD8)
|
||||
# rouC_all = rouC_all.T
|
||||
|
||||
# rouC_CT = rouC_all.filter(like='test_', axis=1)
|
||||
# rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# rouC_BT = rouC_all.filter(like='bts_', axis=1)
|
||||
# rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# # Write csv
|
||||
# rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
|
||||
# rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')
|
||||
|
||||
#================
|
||||
# Baseline
|
||||
# ROUC
|
||||
#================
|
||||
# other data dependent variables
|
||||
training_size_rouC = len(X_rouC)
|
||||
n_features = len(X_rouC.columns)
|
||||
|
||||
rouC_scores_mmD = MultModelsCl(input_df = X_rouC
|
||||
, target = y_rouC
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
, blind_test_input_df = X_bts
|
||||
, blind_test_target = y_bts
|
||||
, add_cm = True
|
||||
, add_yn = True)
|
||||
|
||||
rouC_all_scores = pd.DataFrame(rouC_scores_mmD)
|
||||
|
||||
rouC_all = rouC_all_scores.filter(regex = 'bts_.*|test_.*|.*_time|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
|
||||
rouC_all = rouC_all.reset_index()
|
||||
rouC_all.rename(columns = {'index': 'original_names'}, inplace = True)
|
||||
|
||||
# Indicate whether BT or CT
|
||||
bt_pattern = re.compile(r'bts_.*')
|
||||
rouC_all['data_source'] = rouC_all.apply(lambda row: 'BT' if bt_pattern.search(row.original_names) else 'CV' , axis = 1)
|
||||
|
||||
rouC_all['score_type'] = rouC_all['original_names'].str.replace('bts_|test_', '', regex = True)
|
||||
|
||||
score_type_uniqueN = set(rouC_all['score_type'])
|
||||
cL1 = list(score_type_ordermapD.keys())
|
||||
cL2 = list(score_type_uniqueN)
|
||||
|
||||
if set(cL1).issubset(cL2):
|
||||
print('\nPASS: sorting df by score that is mapped onto the order I want')
|
||||
rouC_all['score_order'] = rouC_all['score_type'].map(score_type_ordermapD)
|
||||
rouC_all.sort_values(by = ['data_source', 'score_order'], ascending = [True, True], inplace = True)
|
||||
else:
|
||||
sys.exit('\nFAIL: could not sort df as score mapping for ordering failed')
|
||||
|
||||
# add cols: specific
|
||||
rouC_all['resampling'] = 'rouC'
|
||||
rouC_all['training_size'] = training_size_rouC
|
||||
|
||||
# add cols: common
|
||||
rouC_all['n_features'] = n_features
|
||||
#rouC_all['test_size'] = bts_size
|
||||
#rouC_all['tts_split'] = tts_split
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
###############################################################################
|
||||
#%% COMBINING all FG dfs
|
||||
#================
|
||||
# Combine all
|
||||
# https://stackoverflow.com/questions/39862654/pandas-concat-of-multiple-data-frames-using-only-common-columns
|
||||
#================
|
||||
dfs_combine = [baseline_all, smnc_all, ros_all, rus_all, rouC_all ]
|
||||
|
||||
dfs_nrows = []
|
||||
for df in dfs_combine:
|
||||
dfs_nrows = dfs_nrows + [len(df)]
|
||||
dfs_nrows = max(dfs_nrows)
|
||||
|
||||
dfs_ncols = []
|
||||
for df in dfs_combine:
|
||||
dfs_ncols = dfs_ncols + [len(df.columns)]
|
||||
dfs_ncols = max(dfs_ncols)
|
||||
|
||||
# dfs_ncols = []
|
||||
# dfs_ncols2 = mode(dfs_ncols.append(len(df.columns) for df in dfs_combine)
|
||||
# dfs_ncols2
|
||||
|
||||
expected_nrows = len(dfs_combine) * dfs_nrows
|
||||
expected_ncols = dfs_ncols
|
||||
|
||||
common_cols = list(set.intersection(*(set(df.columns) for df in dfs_combine)))
|
||||
|
||||
if len(common_cols) == dfs_ncols :
|
||||
combined_baseline = pd.concat([df[common_cols] for df in dfs_combine], ignore_index=True)
|
||||
resampling_methods = combined_baseline[['resampling', 'training_size']]
|
||||
resampling_methods = resampling_methods.drop_duplicates()
|
||||
print('\nConcatenating dfs with different resampling methods:', tts_split
|
||||
, '\nNo. of dfs combining:', len(dfs_combine)
|
||||
, '\nThe sampling methods are:'
|
||||
, '\n', resampling_methods)
|
||||
if len(combined_baseline) == expected_nrows and len(combined_baseline.columns) == expected_ncols:
|
||||
print('\nPASS:', len(dfs_combine), 'dfs successfully combined'
|
||||
, '\nnrows in combined_df:', len(combined_baseline)
|
||||
, '\nncols in combined_df:', len(combined_baseline.columns))
|
||||
else:
|
||||
print('\nFAIL: concatenating failed'
|
||||
, '\nExpected nrows:', expected_nrows
|
||||
, '\nGot:', len(combined_baseline)
|
||||
, '\nExpected ncols:', expected_ncols
|
||||
, '\nGot:', len(combined_baseline.columns))
|
||||
sys.exit()
|
||||
else:
|
||||
sys.exit('\nConcatenting dfs not possible,check numbers ')
|
||||
|
||||
# Add further column indications
|
||||
combined_baseline['test_size'] = bts_size
|
||||
combined_baseline['tts_split'] = tts_split
|
||||
|
||||
# TODO:
|
||||
# ADD y target ration for all
|
||||
|
||||
# # rpow bind
|
||||
# if all(ll((baseline_all.columns == baseline_GN.columns == baseline_STR.columns)):
|
||||
# print('\nPASS:colnames match, proceeding to rowbind')
|
||||
# comb_df = pd.concat()], axis = 0, ignore_index = True ) combined_baseline
|
||||
###############################################################################
|
||||
#====================
|
||||
# Write output file
|
||||
#====================
|
||||
combined_baseline.to_csv(outFile, index = False)
|
||||
print('\nFile successfully written:', outFile)
|
||||
###############################################################################
|
||||
|
|
@ -30,9 +30,9 @@ os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
|
|||
#==================
|
||||
# Import data
|
||||
#==================
|
||||
from ml_data_dissected import *
|
||||
from ml_data_fg import *
|
||||
setvars(gene,drug)
|
||||
from ml_data_dissected import *
|
||||
from ml_data_fg import *
|
||||
|
||||
# from YC run_all_ML: run locally
|
||||
#from UQ_yc_RunAllClfs import run_all_ML
|
||||
|
|
@ -60,7 +60,7 @@ outFile = outdir_ml + gene.lower() + '_baseline_FG.csv'
|
|||
#==================
|
||||
# other vars
|
||||
#==================
|
||||
tts_split_name = 'original'
|
||||
tts_split = 'original'
|
||||
resampling = 'none'
|
||||
|
||||
###############################################################################
|
||||
|
|
@ -177,7 +177,7 @@ else:
|
|||
|
||||
baseline_EV['feature_group'] = feature_gp_nameEV
|
||||
baseline_EV['resampling'] = resampling
|
||||
baseline_EV['tts_split'] = tts_split_name
|
||||
baseline_EV['tts_split'] = tts_split
|
||||
baseline_EV['n_features'] = n_featuresEV
|
||||
###############################################################################
|
||||
#================
|
||||
|
|
@ -221,7 +221,7 @@ else:
|
|||
|
||||
baseline_GN['feature_group'] = feature_gp_nameGN
|
||||
baseline_GN['resampling'] = resampling
|
||||
baseline_GN['tts_split'] = tts_split_name
|
||||
baseline_GN['tts_split'] = tts_split
|
||||
baseline_GN['n_features'] = n_featuresGN
|
||||
###############################################################################
|
||||
#all_featuresN = X_evolFN + X_structural_FN + X_genomicFN
|
||||
|
|
@ -268,7 +268,7 @@ else:
|
|||
|
||||
baseline_STR['feature_group'] = feature_gp_nameSTR
|
||||
baseline_STR['resampling'] = resampling
|
||||
baseline_STR['tts_split'] = tts_split_name
|
||||
baseline_STR['tts_split'] = tts_split
|
||||
baseline_STR['n_features'] = n_featuresSTR
|
||||
##############################################################################
|
||||
#================
|
||||
|
|
@ -312,7 +312,7 @@ else:
|
|||
|
||||
baseline_STB['feature_group'] = feature_gp_nameSTB
|
||||
baseline_STB['resampling'] = resampling
|
||||
baseline_STB['tts_split'] = tts_split_name
|
||||
baseline_STB['tts_split'] = tts_split
|
||||
baseline_STB['n_features'] = n_featuresSTB
|
||||
###############################################################################
|
||||
#================
|
||||
|
|
@ -356,7 +356,7 @@ else:
|
|||
|
||||
baseline_AFF['feature_group'] = feature_gp_nameAFF
|
||||
baseline_AFF['resampling'] = resampling
|
||||
baseline_AFF['tts_split'] = tts_split_name
|
||||
baseline_AFF['tts_split'] = tts_split
|
||||
baseline_AFF['n_features'] = n_featuresAFF
|
||||
###############################################################################
|
||||
#================
|
||||
|
|
@ -400,7 +400,7 @@ else:
|
|||
|
||||
baseline_RES['feature_group'] = feature_gp_nameRES
|
||||
baseline_RES['resampling'] = resampling
|
||||
baseline_RES['tts_split'] = tts_split_name
|
||||
baseline_RES['tts_split'] = tts_split
|
||||
baseline_RES['n_features'] = n_featuresRES
|
||||
###############################################################################
|
||||
#================
|
||||
|
|
@ -446,7 +446,7 @@ else:
|
|||
|
||||
baseline_RNAA['feature_group'] = feature_gp_nameRNAA
|
||||
baseline_RNAA['resampling'] = resampling
|
||||
baseline_RNAA['tts_split'] = tts_split_name
|
||||
baseline_RNAA['tts_split'] = tts_split
|
||||
baseline_RNAA['n_features'] = n_featuresRNAA
|
||||
###############################################################################
|
||||
#================
|
||||
|
|
@ -492,7 +492,7 @@ else:
|
|||
|
||||
baseline_SNAA['feature_group'] = feature_gp_nameSNAA
|
||||
baseline_SNAA['resampling'] = resampling
|
||||
baseline_SNAA['tts_split'] = tts_split_name
|
||||
baseline_SNAA['tts_split'] = tts_split
|
||||
baseline_SNAA['n_features'] = n_featuresSNAA
|
||||
###############################################################################
|
||||
#%% COMBINING all FG dfs
|
||||
|
|
@ -525,7 +525,7 @@ if len(common_cols) == dfs_ncols :
|
|||
combined_FG_baseline = pd.concat([df[common_cols] for df in dfs_combine], ignore_index=True)
|
||||
fgs = combined_FG_baseline[['feature_group', 'n_features']]
|
||||
fgs = fgs.drop_duplicates()
|
||||
print('\nConcatenating dfs with feature groups after ML analysis (sampling type):'
|
||||
print('\nConcatenating dfs with feature groups after ML analysis:'
|
||||
, '\nNo. of dfs combining:', len(dfs_combine)
|
||||
, '\nSampling type:', resampling
|
||||
, '\nThe feature groups are:'
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue