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

trying diff cv thresholds for single gene

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-28 15:19:13 +01:00
parent 8d8a61675f
commit b87f8d0295
2 changed files with 54 additions and 461 deletions
Download patch file Download diff file Expand all files Collapse all files

62
scripts/ml/ml_functions/test_func_singlegene.py
View file

@ -15,8 +15,7 @@ sys.path
from GetMLData import *
from SplitTTS import *
from MultClfs import *
from MultClfs_noBTS import *
from MultClfs_CVs import *
#%%
rs = {'random_state': 42}
@ -27,6 +26,7 @@ skf_cv = StratifiedKFold(n_splits = 10
# , n_repeats = 3
# , **rs)
# param dict for getmldata()
#%% READ data
gene_model_paramD = {'data_combined_model' : False
, 'use_or' : False
, 'omit_all_genomic_features': False
@ -40,7 +40,7 @@ df = getmldata('embB', 'ethambutol' , **gene_model_paramD)
#df = getmldata('rpoB', 'rifampicin' , **gene_model_paramD)
#df = getmldata('gid' , 'streptomycin' , **gene_model_paramD)
#df = getmldata('alr' , 'cycloserine' , **gene_model_paramD)
#%% SPLIT, Data and Resampling types
all(df.columns.isin(['gene_name'])) # should be False
spl_type = '70_30'
#spl_type = '80_20'
@ -143,11 +143,13 @@ from sklearn.utils import all_estimators
all_clfs = all_estimators(type_filter="classifier")
df = pd.DataFrame (all_clfs, columns = ['classifier_name', 'classifier_fn'])
df.to_csv("Model_names_ALL.csv")
################################################################
#%% TEST different CV Thresholds for split_type = NONE
################################################################
Counter(df2['y'])
Counter(df2['y_bts'])
# READ Data
spl_type = 'none'
data_type = "complete"
@ -160,13 +162,13 @@ df2 = split_tts(df
, include_gene_name = True
, random_state = 42 # default
)
fooD = MultModelsCl_noBTS(input_df = df2['X']
#%% Trying different CV thresholds for resampling 'none' ONLY
fooD = MultModelsCl_CVs(input_df = df2['X']
, target = df2['y']
, skf_cv_threshold = 10 # IMP to change
, tts_split_type = spl_type
, resampling_type = 'XXXX' # default
, resampling_type = 'NONE' # default
, add_cm = True # adds confusion matrix based on cross_val_predict
, add_yn = True # adds target var class numbers
@ -185,7 +187,7 @@ for k, v in fooD.items():
)
# formatted df
foo_df3 = MultModelsCl_noBTS(input_df = df2['X']
foo_df3 = MultModelsCl_CVs(input_df = df2['X']
, target = df2['y']
, skf_cv_threshold = 5 # IMP to change
@ -203,6 +205,7 @@ foo_df3 = MultModelsCl_noBTS(input_df = df2['X']
)
dfs_combine_wf = [foo_df, foo_df2, foo_df3]
common_cols_wf = list(set.intersection(*(set(df.columns) for df in dfs_combine_wf)))
@ -246,3 +249,46 @@ if len(common_cols_wf) == dfs_ncols_wf :
, '\nGot:', len(combined_baseline_wf.columns))
sys.exit('\nFIRST IF FAILS')
#%% TRY with dict containing different Resampling types
paramD = {
'baseline_paramD': { 'input_df' : df2['X']
, 'target' : df2['y']
, 'var_type' : 'mixed'
, 'resampling_type': 'none'}
, 'smnc_paramD' : { 'input_df' : df2['X_smnc']
, 'target' : df2['y_smnc']
, 'var_type' : 'mixed'
, 'resampling_type' : 'smnc'}
}
mmDD = {}
for k, v in paramD.items():
print(k)
all_scoresDF = pd.DataFrame()
for skf_cv_threshold in [3,5]:
print('\nRunning CV threhhold:', skf_cv_threshold)
current_scoreDF = MultModelsCl_CVs(**paramD[k]
, skf_cv_threshold = skf_cv_threshold # IMP to change
, tts_split_type = spl_type
#, resampling_type = 'XXXX' # default
, add_cm = True # adds confusion matrix based on cross_val_predict
, add_yn = True # adds target var class numbers
#, var_type = ['mixed']
, scale_numeric = ['min_max']
, random_state = 42
, n_jobs = os.cpu_count()
, return_formatted_output = True
)
all_scoresDF = pd.concat([all_scoresDF, current_scoreDF])
mmDD[k] = all_scoresDF
for k, v in mmDD.items():
print(k, v)
out_wf= pd.concat(mmDD, ignore_index = True)
out_wf2= pd.concat(mmDD)