Simulate Omics style data for Machine Learning programs

simulate_data.sh

# Simulate Omics style data for ML

import uuid
import itertools


features = 700
subjects = 40

columns_list = []
for _ in itertools.repeat(1, features):
    columns_list.append(uuid.uuid4().hex.upper()[0:9])

rows_list = []
for _ in itertools.repeat(1, subjects):
    rows_list.append(uuid.uuid4().hex.upper()[0:6])

df = pd.DataFrame(np.random.randint(0,999999,size=(subjects, features)),
                  columns=columns_list)

df['Subject_ID'] = rows_list
df.loc[ : , 'Subject_ID'] = rows_list

df.insert(0,'Subject_ID', df.pop("Subject_ID")) # pop the "rownames" to 1st column

df.head()