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

added different scaling options

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-05 22:47:13 +01:00
parent ebef0c7967
commit 8d831f3613
3 changed files with 99 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

54
scripts/ml/ml_functions/test_func_singlegene.py
View file

@ -14,7 +14,8 @@ sys.path
# import
from GetMLData import *
from SplitTTS import *
from MultClfs_fi import *
#from MultClfs_fi import *
from MultClfs import *
#%%
# X,y = load_boston(return_X_y=True)
@ -33,7 +34,7 @@ from MultClfs_fi import *
#%%
sel_cv = StratifiedKFold(n_splits = 10
skf_cv = StratifiedKFold(n_splits = 10
, shuffle = True,**rs)
#sel_cv = logo
# sel_cv = RepeatedStratifiedKFold(n_splits = 5
@ -48,10 +49,21 @@ gene_model_paramD = {'data_combined_model' : False
#df = getmldata(gene, drug, **gene_model_paramD)
df = getmldata('pncA', 'pyrazinamide', **gene_model_paramD)
df = getmldata('embB', 'ethambutol' , **gene_model_paramD)
df = getmldata('katG', 'isoniazid' , **gene_model_paramD)
df = getmldata('rpoB', 'rifampicin' , **gene_model_paramD)
df = getmldata('gid' , 'streptomycin' , **gene_model_paramD)
#df = getmldata('alr' , 'cycloserine' , **combined_model_paramD)
all(df.columns.isin(['gene_name'])) # should be False
spl_type = '70_30'
spl_type = '80_20'
spl_type = 'sl'
df2 = split_tts(df
, data_type = 'actual'
, split_type = '70_30'
, split_type = spl_type
, oversampling = False
, dst_colname = 'dst'
, target_colname = 'dst_mode'
@ -61,19 +73,43 @@ df2 = split_tts(df
all(df2['X'].columns.isin(['gene_name'])) # should be False
fooD = MultClfs_fi (input_df = df2['X']
fooD = MultModelsCl(input_df = df2['X']
, target = df2['y']
, sel_cv = sel_cv
, sel_cv = skf_cv
, run_blind_test = True
, blind_test_df = df2['X_bts']
, blind_test_target = df2['y_bts']
, tts_split_type = '70_30'
, var_type = 'mixed'
, tts_split_type = spl_type
, resampling_type = 'none' # default
)
, var_type = ['mixed']
, scale_numeric = ['min_max_neg']
, return_formatted_output = False
)
for k, v in fooD.items():
print('\nModel:', k
, '\nTRAIN MCC:', fooD[k]['test_mcc']
, '\nBTS MCC:' , fooD[k]['bts_mcc']
, '\nDIFF:',fooD[k]['bts_mcc'] - fooD[k]['test_mcc'] )
, '\nDIFF:',fooD[k]['bts_mcc'] - fooD[k]['test_mcc'] )
#%% CHECK SCALING
embb_df = getmldata('embB', 'ethambutol' , **combined_model_paramD)
all(embb_df.columns.isin(['gene_name'])) # should be False
scaler = MinMaxScaler(feature_range=(-1, 1))
bar = embb_df[['vdwclashes_rr', 'electro_rr']]
bar_df1 = scaler.fit_transform(bar)
bar_df1 = pd.DataFrame(bar_df1)
bar_df1.rename(columns = {0:'vdw_scaled', 1: 'ele_scaled'}, inplace = True)
bar2 = pd.concat([bar, bar_df1], axis = 1)
scaler2 = StandardScaler()
baz = embb_df[['vdwclashes_rr', 'electro_rr']]
baz_df1 = scaler2.fit_transform(baz)
baz_df1 = pd.DataFrame(baz_df1)
baz_df1.rename(columns = {0:'vdw_scaled', 1: 'ele_scaled'}, inplace = True)
baz2 = pd.concat([baz, baz_df1], axis = 1)
a = pd.concat([bar2, baz2], axis = 1)