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

removed the two functions MultModelsCl.py and ProcessMultModelsCl.py as these have now been combined

Browse source
This commit is contained in:
Tanushree Tunstall 2022-06-24 13:24:04 +01:00
parent ad99efedd7
commit 19da36842b
2 changed files with 63 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

14
scripts/ml/MultModelsCl.py
View file

@ -105,6 +105,10 @@ jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
from ProcessMultModelsCl import * from ProcessMultModelsCl import *
#%% #%%
############################
# MultModelsCl()
# Run Multiple Classifiers
############################
# Multiple Classification - Model Pipeline # Multiple Classification - Model Pipeline
def MultModelsCl(input_df, target, skf_cv def MultModelsCl(input_df, target, skf_cv
, blind_test_df , blind_test_df
@ -340,17 +344,17 @@ def MultModelsCl(input_df, target, skf_cv
mm_skf_scoresD[model_name]['n_training_size'] = len(input_df) mm_skf_scoresD[model_name]['n_training_size'] = len(input_df)
mm_skf_scoresD[model_name]['n_trainingY_ratio'] = round(yc1_ratio, 2) mm_skf_scoresD[model_name]['n_trainingY_ratio'] = round(yc1_ratio, 2)
mm_skf_scoresD[model_name]['n_blind_test_size'] = len(blind_test_df) mm_skf_scoresD[model_name]['n_test_size'] = len(blind_test_df)
mm_skf_scoresD[model_name]['n_testY_ratio'] = round(yc2_ratio,2) mm_skf_scoresD[model_name]['n_testY_ratio'] = round(yc2_ratio,2)
mm_skf_scoresD[model_name]['n_features'] = len(input_df.columns) mm_skf_scoresD[model_name]['n_features'] = len(input_df.columns)
mm_skf_scoresD[model_name]['tts_split'] = tts_split_type mm_skf_scoresD[model_name]['tts_split'] = tts_split_type
#return(mm_skf_scoresD) #return(mm_skf_scoresD)
#============================ #============================
# Process the dict to have WF # Process the dict to have WF
#============================ #============================
if return_formatted_output: if return_formatted_output:
CV_BT_metaDF = ProcessMultModelCl(mm_skf_scoresD) CV_BT_metaDF = ProcessMultModelsCl(mm_skf_scoresD)
return(CV_BT_metaDF) return(CV_BT_metaDF)
else: else:
return(mm_skf_scoresD) return(mm_skf_scoresD)

78
scripts/ml/ProcessMultModelsCl.py
View file

@ -10,7 +10,12 @@ import pandas as pd
import numpy as np import numpy as np
import re import re
############################################################################## ##############################################################################
#%% FUNCTION: Process outout dicr from MultModelsCl #%% FUNCTION: Process output dict from MultModelsCl
############################
# ProcessMultModelsCl()
############################
#Processes the dict from above if use_formatted_output = True
def ProcessMultModelsCl(inputD = {}): def ProcessMultModelsCl(inputD = {}):
scoresDF = pd.DataFrame(inputD) scoresDF = pd.DataFrame(inputD)
@ -25,43 +30,52 @@ def ProcessMultModelsCl(inputD = {}):
if len(set(tts_split_nameL)) == 1: if len(set(tts_split_nameL)) == 1:
tts_split_name = str(list(set(tts_split_nameL))[0]) tts_split_name = str(list(set(tts_split_nameL))[0])
print('\nExtracting tts_split_name:', tts_split_name) print('\nExtracting tts_split_name:', tts_split_name)
#------------------------ #------------------------
# WF: only CV and BTS # WF: only CV and BTS
#----------------------- #-----------------------
scoresDFT = scoresDF.T scoresDFT = scoresDF.T
scoresDF_CV = scoresDFT.filter(regex='test_', axis = 1); scoresDF_CV.columns scoresDF_CV = scoresDFT.filter(regex='^test_.*$', axis = 1); scoresDF_CV.columns
# map colnames for consistency to allow concatenting # map colnames for consistency to allow concatenting
scoresDF_CV.columns = scoresDF_CV.columns.map(scoreCV_mapD); scoresDF_CV.columns scoresDF_CV.columns = scoresDF_CV.columns.map(scoreCV_mapD); scoresDF_CV.columns
scoresDF_CV['Data_source'] = 'CV' scoresDF_CV['source_data'] = 'CV'
scoresDF_BT = scoresDFT.filter(regex='bts_', axis = 1); scoresDF_BT.columns scoresDF_BT = scoresDFT.filter(regex='^bts_.*$', axis = 1); scoresDF_BT.columns
# map colnames for consistency to allow concatenting # map colnames for consistency to allow concatenting
scoresDF_BT.columns = scoresDF_BT.columns.map(scoreBT_mapD); scoresDF_BT.columns scoresDF_BT.columns = scoresDF_BT.columns.map(scoreBT_mapD); scoresDF_BT.columns
scoresDF_BT['Data_source'] = 'BT' scoresDF_BT['source_data'] = 'BT'
# dfs_combine_wf = [baseline_BT, smnc_BT, ros_BT, rus_BT, rouC_BT, # dfs_combine_wf = [baseline_BT, smnc_BT, ros_BT, rus_BT, rouC_BT,
# baseline_CV, smnc_CV, ros_CV, rus_CV, rouC_CV] # baseline_CV, smnc_CV, ros_CV, rus_CV, rouC_CV]
#baseline_all = baseline_all_scores.filter(regex = 'bts_.*|test_.*|.*_time|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0) #baseline_all = baseline_all_scores.filter(regex = 'bts_.*|test_.*|.*_time|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
metaDF = scoresDFT.filter(regex='training_size|blind_test_size|_time|TN|FP|FN|TP|.*_neg|.*_pos|resampling', axis = 1); scoresDF_BT.columns #metaDF = scoresDFT.filter(regex='training_size|blind_test_size|_time|TN|FP|FN|TP|.*_neg|.*_pos|resampling', axis = 1); scoresDF_BT.columns
#metaDF = scoresDFT.filter(regex='n_.*$|_time|TN|FP|FN|TP|.*_neg|.*_pos|resampling|tts.*', axis = 1); metaDF.columns
metaDF = scoresDFT.filter(regex='^(?!test_.*$|bts_.*$|train_.*$).*'); metaDF.columns
print('\nTotal cols in each df:'
, '\nCV df:', len(scoresDF_CV.columns)
, '\nBT_df:', len(scoresDF_BT.columns)
, '\nmetaDF:', len(metaDF.columns))
if len(scoresDF_CV.columns) == len(scoresDF_BT.columns):
print('\nFirst proceeding to rowbind CV and BT dfs:')
expected_ncols_out = len(scoresDF_BT.columns) + len(metaDF.columns)
print('\nFinal output should have:',expected_ncols_out, 'columns' )
#----------------- #-----------------
# Combine WF # Combine WF
#----------------- #-----------------
dfs_combine_wf = [scoresDF_CV, scoresDF_BT] dfs_combine_wf = [scoresDF_CV, scoresDF_BT]
print('\n---------->\n', len(dfs_combine_wf))
print(scoresDF_CV)
print(scoresDF_BT)
print('\nCombinig', len(dfs_combine_wf), 'using pd.concat by row ~ rowbind' print('\nCombinig', len(dfs_combine_wf), 'using pd.concat by row ~ rowbind'
, '\nChecking Dims of df to combine:' , '\nChecking Dims of df to combine:'
, '\nDim of CV:', scoresDF_CV.shape , '\nDim of CV:', scoresDF_CV.shape
, '\nDim of BT:', scoresDF_BT.shape) , '\nDim of BT:', scoresDF_BT.shape)
#print(scoresDF_CV)
#print(scoresDF_BT)
dfs_nrows_wf = [] dfs_nrows_wf = []
for df in dfs_combine_wf: for df in dfs_combine_wf:
dfs_nrows_wf = dfs_nrows_wf + [len(df)] dfs_nrows_wf = dfs_nrows_wf + [len(df)]
@ -77,19 +91,17 @@ def ProcessMultModelsCl(inputD = {}):
expected_ncols_wf = dfs_ncols_wf expected_ncols_wf = dfs_ncols_wf
common_cols_wf = list(set.intersection(*(set(df.columns) for df in dfs_combine_wf))) common_cols_wf = list(set.intersection(*(set(df.columns) for df in dfs_combine_wf)))
print('\nFinding Common cols to ensure row bind is correct:', len(common_cols_wf) print('\nNumber of Common columns:', dfs_ncols_wf
, '\nCOMMON cols are:', common_cols_wf , '\nThese are:', common_cols_wf)
, dfs_ncols_wf)
if len(common_cols_wf) == dfs_ncols_wf : if len(common_cols_wf) == dfs_ncols_wf :
combined_baseline_wf = pd.concat([df[common_cols_wf] for df in dfs_combine_wf], ignore_index=False) combined_baseline_wf = pd.concat([df[common_cols_wf] for df in dfs_combine_wf], ignore_index=False)
#resampling_methods_wf = combined_baseline_wf[['resampling']] print('\nConcatenating dfs with different resampling methods [WF]:'
#resampling_methods_wf = resampling_methods_wf.drop_duplicates() , '\nSplit type:', tts_split_name
print('\nConcatenating dfs with different resampling methods [WF]:', tts_split_name
, '\nNo. of dfs combining:', len(dfs_combine_wf)) , '\nNo. of dfs combining:', len(dfs_combine_wf))
print('\n================================================^^^^^^^^^^^^') #print('\n================================================^^^^^^^^^^^^')
if len(combined_baseline_wf) == expected_nrows_wf and len(combined_baseline_wf.columns) == expected_ncols_wf: if len(combined_baseline_wf) == expected_nrows_wf and len(combined_baseline_wf.columns) == expected_ncols_wf:
print('\n================================================^^^^^^^^^^^^') #print('\n================================================^^^^^^^^^^^^')
print('\nPASS:', len(dfs_combine_wf), 'dfs successfully combined' print('\nPASS:', len(dfs_combine_wf), 'dfs successfully combined'
, '\nnrows in combined_df_wf:', len(combined_baseline_wf) , '\nnrows in combined_df_wf:', len(combined_baseline_wf)
@ -105,12 +117,30 @@ def ProcessMultModelsCl(inputD = {}):
print('\nConcatenting dfs not possible [WF],check numbers ') print('\nConcatenting dfs not possible [WF],check numbers ')
# TODOadd check here #-------------------------------------
combDF = pd.merge(combined_baseline_wf, metaDF, left_index = True, right_index = True) # Combine WF+Metadata: Final output
#-------------------------------------
# checking indices for the dfs to combine:
c1 = list(set(combined_baseline_wf.index))
c2 = list(metaDF.index)
if c1 == c2:
print('\nPASS: proceeding to merge metadata with CV and BT dfs')
combDF = pd.merge(combined_baseline_wf, metaDF, left_index = True, right_index = True)
else:
sys.exit('\nFAIL: Could not merge metadata with CV and BT dfs')
if len(combDF.columns) == expected_ncols_out:
print('\nPASS: Combined df has expected ncols')
else:
sys.exit('\nFAIL: Length mismatch for combined_df')
print('\n========================================================='
, '\nSUCCESS: Ran multiple classifiers'
, '\n=======================================================')
#resampling_methods_wf = combined_baseline_wf[['resampling']] #resampling_methods_wf = combined_baseline_wf[['resampling']]
#resampling_methods_wf = resampling_methods_wf.drop_duplicates() #resampling_methods_wf = resampling_methods_wf.drop_duplicates()
#, '\n', resampling_methods_wf) #, '\n', resampling_methods_wf)
return combDF return combDF
###############################################################################