def extend_samples(samp_hdf_fname, tdict_pkl_fname, reverse_tdict_pkl_fname,
ext_hdf_fname, max_samp=None):
log.info("opening original samples file " + samp_hdf_fname)
samp_hdfile = h5py.File(samp_hdf_fname, "r")
ext_mat = make_extension_matrix(samp_hdfile, tdict_pkl_fname, reverse_tdict_pkl_fname)
log.info("creating extended samples file " + ext_hdf_fname)
ext_hdfile = h5py.File(ext_hdf_fname, "w")
ext_samples = ext_hdfile.create_group("samples")
log.info("copying vocabulary ({0} terms)".format(len(samp_hdfile["vocab"])))
ext_hdfile.create_dataset("vocab", data=samp_hdfile["vocab"])
i = 0
for lemma, lemma_group in samp_hdfile["samples"].iteritems():
for pos, pos_group in lemma_group.iteritems():
log.info(u"{0}: creating extended samples for {1}/{2}".format(i, lemma,pos))
samp_mat = coo_matrix_from_hdf5(pos_group).tocsr()
mat = (samp_mat * ext_mat).tocoo()
group = ext_hdfile.create_group(u"samples/{0}/{1}".format(lemma,pos))
coo_matrix_to_hdf5(mat, group, data_dtype="i1", compression="gzip")
i += 1
if i == max_samp:
log.info("reached maximum number of samples")
break
if i == max_samp:
break
log.info("closing " + samp_hdf_fname)
samp_hdfile.close()
log.info("closing " + ext_hdf_fname)
ext_hdfile.close()
def make_new_samples(sample_hdfile, filtered_hdfile, columns_selector):
org_samples = sample_hdfile["samples"]
filtered_samples = filtered_hdfile.create_group("samples")
for lemma, lemma_group in org_samples.iteritems():
for pos, pos_group in lemma_group.iteritems():
lempos = lemma + u"/" + pos
log.info("adding filtered samples for " + lempos)
sample_mat = coo_matrix_from_hdf5(pos_group)
sample_mat = sample_mat.tocsc()
# select only columns corresponding to filtered vocabulary,
# removing other columns
sample_mat = sample_mat[:, columns_selector]
# get indices of non-empty rows
sample_mat = sample_mat.tolil()
rows_selector = sample_mat.rows.nonzero()[0]
# select only non-empty rows, removing empty rows
sample_mat = sample_mat.tocsr()
sample_mat = sample_mat[rows_selector]
sample_mat = sample_mat.tocoo()
filtered_group = filtered_samples.create_group(lempos)
coo_matrix_to_hdf5(sample_mat, filtered_group, data_dtype="=i1", compression="gzip")
