python 堆叠稀疏矩阵。

Posted 2021-05-09

import numpy as np
import scipy as sp
import pandas as pd

df1 = pd.DataFrame({"A": [1, 2], "B": [3, 4]})
df2 = pd.DataFrame({"C": [5, 6]})

X1 = sp.sparse.csr_matrix(df1.values)
X1_dense = X1.todense()
# Out[28]:
# matrix([[1, 3],
#         [2, 4]], dtype=int64)

X2 = sp.sparse.csr_matrix(df2.values)
X2_dense = X2.todense()
# Out[29]:
# matrix([[5],
#         [6]], dtype=int64)

X3 = np.hstack(X1, X2)
X3_dense = np.hstack([X1_dense, X2_dense])
# Out[32]:
# matrix([[1, 3, 5],
#         [2, 4, 6]], dtype=int64)

X3 = sp.sparse.hstack([X1, X2])
X3.todense()
# Out[35]:
# matrix([[1, 3, 5],
#         [2, 4, 6]], dtype=int64)