Delete columns of matrix of CSR format in Python
If you have a very large number of columns then generating the full set of column indices can become rather costly. One slightly faster alternative would be to temporarily convert to COO format:
import numpy as np
from scipy import sparse
def dropcols_fancy(M, idx_to_drop):
idx_to_drop = np.unique(idx_to_drop)
keep = ~np.in1d(np.arange(M.shape[1]), idx_to_drop, assume_unique=True)
return M[:, np.where(keep)[0]]
def dropcols_coo(M, idx_to_drop):
idx_to_drop = np.unique(idx_to_drop)
C = M.tocoo()
keep = ~np.in1d(C.col, idx_to_drop)
C.data, C.row, C.col = C.data[keep], C.row[keep], C.col[keep]
C.col -= idx_to_drop.searchsorted(C.col) # decrement column indices
C._shape = (C.shape[0], C.shape[1] - len(idx_to_drop))
return C.tocsr()
Check equivalence:
m, n, d = 1000, 2000, 20
M = sparse.rand(m, n, format='csr')
idx_to_drop = np.random.randint(0, n, d)
M_drop1 = dropcols_fancy(M, idx_to_drop)
M_drop2 = dropcols_coo(M, idx_to_drop)
print(np.all(M_drop1.A == M_drop2.A))
# True
Benchmark:
In [1]: m, n = 1000, 1000000
In [2]: %%timeit M = sparse.rand(m, n, format='csr')
...: dropcols_fancy(M, idx_to_drop)
...:
1 loops, best of 3: 1.11 s per loop
In [3]: %%timeit M = sparse.rand(m, n, format='csr')
...: dropcols_coo(M, idx_to_drop)
...:
1 loops, best of 3: 365 ms per loop
You can use fancy indexing to obtain a new csr_matrix
with the columns that you have in your list:
all_cols = np.arange(old_m.shape[1])
cols_to_keep = np.where(np.logical_not(np.in1d(all_cols, cols_to_delete)))[0]
m = old_m[:, cols_to_keep]