mean2 = [20, 15]
#Set up target array
target = np.zeros(100, dtype=int)
target[0:50] = '1'
dataset_list = []
# counter for labelling dataset
counter = 1
# Second component consistent. Generate first to save time.
d2_x, d2_y = multivariate_normal(mean2, cov2, comp_size).T
for i in range(len(cov1)):
d1_x, d1_y = multivariate_normal(mean1[i], cov1[i], comp_size).T
#Put components together
mvn_sim = np.vstack((d1_x, d2_x))
mvn_sim_df = pd.DataFrame.from_records(mvn_sim)
dataset_list.append(('ds00%d' % counter, mvn_sim_df))
counter += 1
return(dataset_list, target)
'''
ds_list, y = p2f.toybox_gen(imp_df)
print('Length of y: %s' % len(y))
print('SHAPE of X: ')
print(ds_list[0][1].shape)
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)
now = datetime.datetime.now()
nowdate = now.strftime("%Y-%m-%d")
nowtime = now.strftime("%H-%M")
# Name of script to trace where images came from
scriptname = 'tbgenplot'
X = pd.read_csv('../../data/mesa/MESA_CPMG_MBINV2_ManuallyBinnedData_BatchCorrected_LogTransformed_1stcol_diabetes.csv', sep=',', header=None, index_col=0)
X_imp = p2f.filt_imp(X, 0.1)
X, y = p2f.tsplit(X_imp)
X_scaled = scale(X)
dataset_list, y = p2f.toybox_gen(X_scaled)
for ds_label, dataset in dataset_list:
print(dataset.shape)
'''
for ds_label, 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)