File: biosql_performance_read.py

package info (click to toggle)
python-biopython 1.68%2Bdfsg-3~bpo8%2B1
  • links: PTS, VCS
  • area: main
  • in suites: jessie-backports
  • size: 46,856 kB
  • sloc: python: 160,306; xml: 93,216; ansic: 9,118; sql: 1,208; makefile: 155; sh: 63
file content (50 lines) | stat: -rw-r--r-- 1,457 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
#!/usr/bin/env python
"""Small script to test timing of getting records from a BioSQL database.
"""
from __future__ import print_function

import time
# set up the connection
from BioSQL import BioSeqDatabase

__docformat__ = "restructuredtext en"

server = BioSeqDatabase.open_database(host="192.168.0.192", user="root",
                                      passwd="", db="test_biosql")
db = server["embl_rod"]

# -- do the fasta-only timing part
start_time = time.time()
num_records = 0
for junk_id, record in db.items():
    num_records += 1
    sequence = record.seq.data
    d = record.description
    i = record.id
    n = record.name

end_time = time.time()
elapsed_time = end_time - start_time
print("Fasta")
print("\tDid %s records in %s seconds for\n\t%f records per second" %
      (num_records, elapsed_time, float(num_records) / float(elapsed_time)))

# -- do the "EMBL" timing part
start_time = time.time()
num_records = 0
for junk_id, record in db.items():
    num_records += 1
    sequence = record.seq.data
    d = record.description
    i = record.id
    n = record.name
    features = record.features
    anns = record.annotations
    dates = record.dates
    species = record.species
    keywords = record.keywords
end_time = time.time()
elapsed_time = end_time - start_time
print("EMBL")
print("\tDid %s records in %s seconds for\n\t%f records per second" %
      (num_records, elapsed_time, float(num_records) / float(elapsed_time)))