def test_insertOneTime(self):
print(self._testMethodName)
kSize = 31
_kmer, rand_count = self.params.generate_singleKmer()
kf = kp.kDataFrameMQF(kSize)
self.assertTrue(kf.empty())
kf.insert(_kmer, rand_count)
self.assertFalse(kf.empty())
self.assertEqual(kf.getCount(_kmer), rand_count)
import kProcessor as kp
import sys
fasta_file = sys.argv[1]
names_file = sys.argv[2]
kf = kp.kDataFrameMQF(21, 29, 1)
# Mode 1 activates the kmers mode
ckf = kp.index(kf, {"mode": 1}, fasta_file, 10000, names_file)
print("Serializing the index ...")
ckf.save("index/idx_gencode.v32.transcripts")
import kProcessor as kp
from glob import glob
import os
import sys
if len(sys.argv) < 3:
sys.exit(
"run: python genomes_kmerCounting.py <genomes_dir> <kDataframes_output_dir>"
)
genomes_dir = sys.argv[1]
output_directory = sys.argv[2]
kSize = 21
chunk_size = 10000
hashing_mode = 1 # Integer hashing
genomes = glob(f"{genomes_dir}/*")
for genome_fasta in genomes:
print(f"counting {genome_fasta} kmers ...")
kf = kp.kDataFrameMQF(kSize)
kp.countKmersFromFile(kf, {"mode": hashing_mode}, genome_fasta, chunk_size)
print(f"finished and counted {kf.size()} kmers...")
print(f"saving ...")
output_prefix = os.path.join(output_directory,
"idx_" + os.path.basename(genome_fasta))
kf.save(output_prefix)
import os
import sys
import kProcessor as kp
fasta_file = str()
namesFile = str()
if len(sys.argv) < 4:
sys.exit("run: python genes_indexing.py <fasta> <namesFiles> <kSize>")
else:
fasta_file = sys.argv[1]
namesFile = sys.argv[2]
kSize = int(sys.argv[3])
idx_suffix = os.path.basename(fasta_file).replace(".fa.names", "")
print(f"Indexing {idx_suffix} ...", file=sys.stderr)
kmers_mode = 1
hashing_mode = 1
chunk_size = 10000
#kf_PHMAP = kp.kDataFramePHMAP(kSize, hashing_mode)
kf_PHMAP = kp.kDataFrameMQF(kSize, 29, hashing_mode)
ckf = kp.index(kf_PHMAP, {"mode": kmers_mode}, fasta_file, chunk_size,
namesFile)
ckf.save(f"idx_{idx_suffix}")