scriptname = 'mesa_kpca2'
#List of datasets to test
#dataset_list = ['diabetes', 'sex', 'cac_binomial', 'cac_extremes', 'family_hx_diabetes', 'parent_cvd_65_hx', 'family_hx_cvd', 'bp_treatment', 'diabetes_treatment', 'lipids_treatment', 'mi_stroke_hx', 'plaque']
dataset_list = ['diabetes', 'sex', 'cac_binomial']
for dataset in dataset_list:
print('\n##### Now running dataset %s #####' % dataset)
#Create directory if directory does not exist
filepath = '../../figs/out/%s/%s/%s/' % (scriptname, nowdate, dataset)
if not os.path.exists(filepath):
os.makedirs(filepath)
X = pd.read_csv(
'../../data/mesa/MESA_CPMG_MBINV2_ManuallyBinnedData_BatchCorrected_LogTransformed_1stcol_%s.csv'
% dataset,
sep=',',
header=None,
index_col=0)
#print(X)
X_imp = p2f.filt_imp(X, 0.1)
X_imp_df = pd.DataFrame.from_records(X_imp)
#print(X_imp_df)
X, y = p2f.tsplit(X_imp_df)
#print(y)
X_scaled = scale(X)
# Collect optimal tier1 gammas
opt_t1_gammas = []
#Using first input dataset to generate toy datasets
inp_df = pd.read_csv(
'../../data/mesa/MESA_CPMG_MBINV2_ManuallyBinnedData_BatchCorrected_LogTransformed_1stcol_%s.csv'
% inp_dataset_list[0][1],
sep=',',
header=None,
index_col=0)
print(
'\nUsing %s dataset to generate simulated datasets for the purpose of tuning algorithms and hyperperameters.'
% inp_dataset_list[0][0])
X_imp = p2f.filt_imp(inp_df, 0.1)
X, y = p2f.tsplit(X_imp)
toy_dataset_list, toy_y = p2f.toybox_gen(X)
for toy_label, toy_X in toy_dataset_list:
print('\n##### Now running dataset %s through tier 1 #####' % toy_label)
#Create directory if directory does not exist
filepath = '../../figs/out/%s/%s/%s/' % (scriptname, nowdate, toy_label)
plotpath = '%splotting/' % filepath
if not os.path.exists(filepath):
os.makedirs(filepath)
os.makedirs(plotpath)
toy_X_scaled = scale(toy_X)