关于制作基因数据集的代码

import numpy as np
import pandas as pd
import scipy.stats as stats
import ast

P = pd.read_csv(fr'D:数因信科预训练result.csv',                    #CRISPR_gene_dependency  #CCLE_expression
                # skiprows=lambda x: x not in range(0, 1000)
                low_memory=False)
T = pd.read_csv(fr'D:数因信科预训练predata.csv',                #CCLE_expression         Fprint
                # skiprows=lambda x: x not in range(0, 1000)
                low_memory=False)

# P = np.array(P)
T = np.array(T)

# PP = np.transpose(P, (1, 0))
TT = np.transpose(T, (1, 0))
# print(PP[0])
# print(TT[0])
#
result = np.intersect1d(P,T[0])
# # # result1 = np.intersect1d(PP[0],TT[0])
x,y=T.shape
print(x,y)
# print(result.shape)
# record = pd.DataFrame(result)  # predictive   real
# record.to_csv('result.csv', index=False)
# print(PP[0][12321])
# print(T[0].shape)
# print(PP[2].shape)
X = []
Y = []
for i in range(0,y):
    # print(PP[0][i])
    # print(result[i])
    if (T[0][i] == result).any():
        X.append(TT[i])
        # Y.append(P[0][i])
        # print(P[i])
X = np.array(X)
Y = T[0][i]
# Y = np.array(Y)

print(X.shape)
#
record = pd.DataFrame(X)  # predictive   real
record.to_csv('exp123.csv', index=False)
record = pd.DataFrame(Y)  # predictive   real
record.to_csv('exp12223.csv', index=False)
# # #
#     print(result[i])
#     print(P[result[i]])


# x,y = P.shape   #x:1394 y:19178
# z,c = T.shape
# print(x,y)
# print(T[0][3])                           #CCL列表   T[x][0]   #GEN列表[0][y]
# record = pd.DataFrame(P[0])  # predictive
#
# record.to_csv('new3.csv', index=False)