import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import random as rd

from sklearn.decomposition import PCA
from sklearn import preprocessing

# Create 'gene' names as the feature variables
genes = ['gene' + str(i) for i in range(1, 101)]

# Create arrays of sample names
wt = ['wt' + str(i) for i in range(1, 6)]
ko = ['ko' + str(i) for i in range(1, 6)]

data = pd.DataFrame(columns=[*wt, *ko], index=genes)