-
Notifications
You must be signed in to change notification settings - Fork 295
/
readstats.py
executable file
·184 lines (143 loc) · 5.69 KB
/
readstats.py
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
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
#! /usr/bin/env python2
#
# This file is part of khmer, http://github.com/ged-lab/khmer/, and is
# Copyright (C) Michigan State University, 2009-2013. It is licensed under
# the three-clause BSD license; see LICENSE.
# Contact: khmer-project@idyll.org
#
"""
Display summary statistics for one or more FASTA/FASTQ files.
% scripts/readstats.py [ -o output.txt ] <file1> <file2>
Use '-h' for parameter help.
"""
import sys
import csv
import screed
import argparse
import textwrap
def get_parser():
descr = "Display summary statistics for one or more FASTA/FASTQ files."
epilog = ("""
Report number of bases, number of sequences, and average sequence length
for one or more FASTA/FASTQ files; and report aggregate statistics at end.
With :option:`-o`/:options:`--output`, the output will be saved to the
specified file.
Example::
readstats.py tests/test-data/test-abund-read-2.fa
""")
parser = argparse.ArgumentParser(description=descr,
epilog=textwrap.dedent(epilog))
parser.add_argument('filenames', nargs='+')
parser.add_argument('-o', '--output', dest='outfp', metavar="filename",
help="output file for statistics; defaults to stdout.",
type=argparse.FileType('w'), default=sys.stdout)
parser.add_argument('--csv', default=False, action='store_true',
help='Use the CSV format for the statistics, '
'including column headers.')
return parser
class StatisticsOutput(object):
# pylint: disable=too-few-public-methods
"""Output statistics for several data files.
The format of the output is determined by the formatter used.
All statistics are aggregated and a summary is added to the data.
"""
def __init__(self, formatter):
self.formatter = formatter
def __enter__(self):
self.formatter.write_header()
return self
def append(self, basepairs, seqs, filename):
"""Append a new line for the given basepair number, sequences and file.
"""
self.formatter.append(
basepairs, seqs, basepairs / float(seqs), filename)
def __exit__(self, exc_type, exc_value, traceback):
if exc_type is None:
self.formatter.finalize()
class CsvFormatter(object):
"""Format the statistis information as CSV."""
headers = ['bp', 'seqs', 'avg_len', 'filename']
def __init__(self, underlying_file):
self.file = csv.writer(underlying_file)
def write_header(self):
"""Add headers for the csv columns."""
self.file.writerow(self.headers)
def append(self, basepairs, seqs, avg_len, filename):
"""Append the data separated by comma."""
self.file.writerow([basepairs, seqs, "%.1f" % avg_len, filename])
def finalize(self):
"""No statistics since the CSV data is supposed to be processed further.
"""
pass
class StdFormatter(object):
"""Format the statistics in a human readable string."""
def __init__(self, underlying_file):
self.file = underlying_file
self.bp_total = 0
self.seqs_total = 0
def write_header(self):
"""Write a header line."""
self.file.write('---------------\n')
def append(self, basepairs, seqs, avg_len, filename):
"""Append the data human readable."""
self.bp_total += basepairs
self.seqs_total += seqs
self.file.write('%d bp / %d seqs; %.1f average length -- %s\n' %
(basepairs,
seqs,
avg_len,
filename))
def finalize(self):
"""Add a summary with the accumulated data."""
self.file.write('---------------\n')
avg = self.bp_total / float(self.seqs_total)
self.file.write('%d bp / %d seqs; %.1f average length -- total\n' %
(self.bp_total, self.seqs_total, avg))
def analyze_file(filename):
"""Run over the given file and count base pairs and sequences."""
bps = 0
seqs = 0
input_iter = screed.open(filename, parse_description=False)
for record in input_iter:
if seqs % 100000 == 0:
print >>sys.stderr, '...', filename, seqs
bps += len(record.sequence)
seqs += 1
return bps, seqs
def main():
"""Main function - run when executed as a script."""
parser = get_parser()
args = parser.parse_args()
total_bp = 0
total_seqs = 0
statistics = []
for filename in args.filenames:
try:
bps, seqs = analyze_file(filename)
except (IOError, OSError, EOFError) as exc:
print >>sys.stderr, 'ERROR in opening %s:' % filename
print >>sys.stderr, ' ', str(exc)
continue
if seqs:
statistics.append((bps, seqs, filename))
avg = bps / float(seqs)
msg = '%d bps / %d seqs; %.1f average length -- %s' % (bps,
seqs,
avg,
filename)
print >>sys.stderr, '... found', msg
else:
print >>sys.stderr, 'No sequences found in %s' % filename
if statistics:
if args.csv:
formatter = CsvFormatter(args.outfp)
else:
formatter = StdFormatter(args.outfp)
with StatisticsOutput(formatter) as out:
for stat in statistics:
out.append(*stat)
else:
print >>args.outfp, \
'No sequences found in %d files' % len(args.filenames)
if __name__ == '__main__':
main()