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

added cm run for logo_skf for actual data

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-02 16:57:11 +01:00
parent 9071a87056
commit b2d0b827ad
4 changed files with 56 additions and 124 deletions
Download patch file Download diff file Expand all files Collapse all files

77
scripts/ml/combined_model/cm_logo_skf.py
View file

@ -98,13 +98,14 @@ skf_cv = StratifiedKFold(n_splits = 10 , shuffle = True, random_state = 42)
# COMPLETE data: No tts_split
########################################################################
#%%
def CMLogoSkf(combined_df
def CMLogoSkf(cm_input_df
, all_genes = ["embb", "katg", "rpob", "pnca", "gid", "alr"]
, bts_genes = ["embb", "katg", "rpob", "pnca", "gid"]
, cols_to_drop = ['dst', 'dst_mode', 'gene_name']
, target_var = 'dst_mode'
, gene_group = 'gene_name'
, std_gene_omit = []
, file_suffix = ""
):
for bts_gene in bts_genes:
@ -127,17 +128,24 @@ def CMLogoSkf(combined_df
,'\nTraining on genes:', training_genesL
, '\nOmitted genes:', tr_gene_omit
, '\nBlind test gene:', bts_gene)
print('\nDim of data:', cm_input_df.shape)
tts_split_type = "logo_skf_BT_" + bts_gene
outFile = outdir + str(n_tr_genes+1) + "genes_" + tts_split_type + ".csv"
# if len(file_suffix) > 0:
# file_suffix = '_' + file_suffix
# else:
# file_suffix = file_suffix
outFile = outdir + str(n_tr_genes+1) + "genes_" + tts_split_type + '_' + file_suffix + ".csv"
print(outFile)
#-------
# training
#------
cm_training_df = combined_df[~combined_df['gene_name'].isin(tr_gene_omit)]
cm_training_df = cm_input_df[~cm_input_df['gene_name'].isin(tr_gene_omit)]
cm_X = cm_training_df.drop(cols_to_drop, axis=1, inplace=False)
#cm_y = cm_training_df.loc[:,'dst_mode']
@ -156,7 +164,7 @@ def CMLogoSkf(combined_df
#---------------
# BTS: genes
#---------------
cm_test_df = combined_df[combined_df['gene_name'].isin([bts_gene])]
cm_test_df = cm_input_df[cm_input_df['gene_name'].isin([bts_gene])]
cm_bts_X = cm_test_df.drop(cols_to_drop, axis = 1, inplace = False)
#cm_bts_y = cm_test_df.loc[:, 'dst_mode']
@ -165,31 +173,40 @@ def CMLogoSkf(combined_df
print('\nTEST data dim:', cm_bts_X.shape
, '\nTEST Target dim:', cm_bts_y.shape)
print("Running Multiple models on LOGO with SKF")
# #%%:Running Multiple models on LOGO with SKF
# cD3_v2 = MultModelsCl_logo_skf(input_df = cm_X
# , target = cm_y
# #, group = 'none'
# , sel_cv = skf_cv
#%%:Running Multiple models on LOGO with SKF
cD3_v2 = MultModelsCl_logo_skf(input_df = cm_X
, target = cm_y
#, group = 'none'
, sel_cv = skf_cv
# , blind_test_df = cm_bts_X
# , blind_test_target = cm_bts_y
# , tts_split_type = tts_split_type
# , resampling_type = 'none' # default
# , add_cm = True
# , add_yn = True
# , var_type = 'mixed'
# , run_blind_test = True
# , return_formatted_output = True
# , random_state = 42
# , n_jobs = os.cpu_count() # the number of jobs should equal the number of CPU cores
# )
, blind_test_df = cm_bts_X
, blind_test_target = cm_bts_y
, tts_split_type = tts_split_type
, resampling_type = 'none' # default
, add_cm = True
, add_yn = True
, var_type = 'mixed'
, run_blind_test = True
, return_formatted_output = True
, random_state = 42
, n_jobs = os.cpu_count() # the number of jobs should equal the number of CPU cores
)
cD3_v2.to_csv(outFile)
# cD3_v2.to_csv(outFile)
#%%
#CMLogoSkf(combined_df)
CMLogoSkf(combined_df, std_gene_omit=['alr'])
#%% RUN
#===============
# Complete Data
#===============
#CMLogoSkf(cm_input_df = combined_df,file_suffix = "complete")
#CMLogoSkf(cm_input_df = combined_df, std_gene_omit=['alr'], file_suffix = "complete")
#===============
# Actual Data
#===============
CMLogoSkf(cm_input_df = combined_df_actual, file_suffix = "actual")
CMLogoSkf(cm_input_df = combined_df_actual, std_gene_omit=['alr'], file_suffix = "actual")