tjh.dev
1diff --git a/src/c++/lib/tools/Roc.cpp b/src/c++/lib/tools/Roc.cpp
2index fabe2be..2c6bb49 100644
3--- a/src/c++/lib/tools/Roc.cpp
4+++ b/src/c++/lib/tools/Roc.cpp
5@@ -34,6 +34,9 @@
6 */
7
8 #include "helpers/Roc.hh"
9+#include <stdexcept>
10+#include <limits>
11+
12
13 #include <algorithm>
14 #include <cmath>
15diff --git a/src/cmake/cxx.cmake b/src/cmake/cxx.cmake
16old mode 100755
17new mode 100644
18diff --git a/src/python/Haplo/happyroc.py b/src/python/Haplo/happyroc.py
19index 152bd18..e439957 100644
20--- a/src/python/Haplo/happyroc.py
21+++ b/src/python/Haplo/happyroc.py
22@@ -97,7 +97,7 @@ def roc(roc_table, output_path,
23 header = l.split("\t")
24 else:
25 rec = {}
26- for k, v in itertools.izip(header, l.split("\t")):
27+ for k, v in zip(header, l.split("\t")):
28 rec[k] = v
29
30 if filter_handling:
31@@ -160,11 +160,11 @@ def roc(roc_table, output_path,
32
33 if "all" not in result:
34 # minimal empty DF
35- minidata = [{"Type": "SNP", "Subtype": "*", "Filter": "ALL", "Genotype": "*", "Subset": "*", "QQ": "*"} for _ in xrange(2)]
36+ minidata = [{"Type": "SNP", "Subtype": "*", "Filter": "ALL", "Genotype": "*", "Subset": "*", "QQ": "*"} for _ in range(2)]
37 minidata[1]["Type"] = "INDEL"
38 result["all"] = pandas.DataFrame(minidata, columns=RESULT_ALLCOLUMNS)
39 for i, c in enumerate(RESULT_ALLCOLUMNS):
40- result["all"][c] = result["all"][c].astype(RESULT_ALLDTYPES[i], raise_on_error=False)
41+ result["all"][c] = result["all"][c].astype(RESULT_ALLDTYPES[i], errors="ignore")
42
43 for k, v in result.items():
44 result[k] = _postprocessRocData(pandas.DataFrame(v, columns=RESULT_ALLCOLUMNS))
45diff --git a/src/python/Haplo/partialcredit.py b/src/python/Haplo/partialcredit.py
46index d9e22bb..0f2b2cf 100644
47--- a/src/python/Haplo/partialcredit.py
48+++ b/src/python/Haplo/partialcredit.py
49@@ -202,7 +202,7 @@ def partialCredit(vcfname,
50 try:
51 res = runParallel(pool,
52 preprocessWrapper,
53- itertools.izip(itertools.repeat(vcfname), locations),
54+ zip(itertools.repeat(vcfname), locations),
55 {"reference": reference,
56 "decompose": decompose,
57 "leftshift": leftshift,
58diff --git a/src/python/Haplo/quantify.py b/src/python/Haplo/quantify.py
59index 042d13e..b1d362e 100755
60--- a/src/python/Haplo/quantify.py
61+++ b/src/python/Haplo/quantify.py
62@@ -152,7 +152,7 @@ def run_quantify(filename,
63 run_str += " -v %s" % pipes.quote(write_vcf)
64
65 if regions:
66- for k, v in regions.iteritems():
67+ for k, v in regions.items():
68 run_str += " -R '%s:%s'" % (k, v)
69
70 if roc_regions:
71diff --git a/src/python/Somatic/Mutect.py b/src/python/Somatic/Mutect.py
72index 7ac923c..81f08b5 100755
73--- a/src/python/Somatic/Mutect.py
74+++ b/src/python/Somatic/Mutect.py
75@@ -148,7 +148,7 @@ def extractMutectSNVFeatures(vcfname, tag, avg_depth=None):
76 n_allele_alt_count = 0
77 else:
78 n_allele_alt_count = 0
79- for a in xrange(0, len(alleles_alt)):
80+ for a in range(0, len(alleles_alt)):
81 n_allele_alt_count += float(rec[n_sample + "AD"][a + 1])
82
83 if n_allele_alt_count + n_allele_ref_count == 0:
84@@ -163,7 +163,7 @@ def extractMutectSNVFeatures(vcfname, tag, avg_depth=None):
85 t_allele_alt_count = 0
86 else:
87 t_allele_alt_count = 0
88- for a in xrange(0, len(alleles_alt)):
89+ for a in range(0, len(alleles_alt)):
90 t_allele_alt_count += float(rec[t_sample + "AD"][a + 1])
91
92 if t_allele_alt_count + t_allele_ref_count == 0:
93@@ -344,7 +344,7 @@ def extractMutectIndelFeatures(vcfname, tag, avg_depth=None):
94 n_allele_alt_count = 0
95 else:
96 n_allele_alt_count = 0
97- for a in xrange(0, len(alleles_alt)):
98+ for a in range(0, len(alleles_alt)):
99 n_allele_alt_count += float(rec[n_sample + "AD"][a + 1])
100
101 if n_allele_alt_count + n_allele_ref_count == 0:
102@@ -359,7 +359,7 @@ def extractMutectIndelFeatures(vcfname, tag, avg_depth=None):
103 t_allele_alt_count = 0
104 else:
105 t_allele_alt_count = 0
106- for a in xrange(0, len(alleles_alt)):
107+ for a in range(0, len(alleles_alt)):
108 t_allele_alt_count += float(rec[t_sample + "AD"][a + 1])
109
110 if t_allele_alt_count + t_allele_ref_count == 0:
111diff --git a/src/python/Tools/bcftools.py b/src/python/Tools/bcftools.py
112index 6146b7a..6d80d14 100755
113--- a/src/python/Tools/bcftools.py
114+++ b/src/python/Tools/bcftools.py
115@@ -128,8 +128,8 @@ def concatenateParts(output, *args):
116 to_delete.append(tf2.name)
117 to_delete.append(tf1.name + ".csi")
118 to_delete.append(tf2.name + ".csi")
119- half1 = [tf1.name] + list(args[:len(args)/2])
120- half2 = [tf2.name] + list(args[len(args)/2:])
121+ half1 = [tf1.name] + list(args[:len(args)//2])
122+ half2 = [tf2.name] + list(args[len(args)//2:])
123 concatenateParts(*half1)
124 runBcftools("index", tf1.name)
125 concatenateParts(*half2)
126diff --git a/src/python/Tools/metric.py b/src/python/Tools/metric.py
127index 71ccc99..372626d 100755
128--- a/src/python/Tools/metric.py
129+++ b/src/python/Tools/metric.py
130@@ -115,7 +115,7 @@ def replaceNaNs(xobject):
131 if type(xobject[k]) is dict or type(xobject[k]) is list or type(xobject[k]) is float:
132 xobject[k] = replaceNaNs(xobject[k])
133 elif type(xobject) is list:
134- for k in xrange(0, len(xobject)):
135+ for k in range(0, len(xobject)):
136 if type(xobject[k]) is dict or type(xobject[k]) is list or type(xobject[k]) is float:
137 xobject[k] = replaceNaNs(xobject[k])
138 elif type(xobject) is float:
139diff --git a/src/python/Tools/parallel.py b/src/python/Tools/parallel.py
140index 9d49760..5fcb37e 100755
141--- a/src/python/Tools/parallel.py
142+++ b/src/python/Tools/parallel.py
143@@ -17,9 +17,9 @@ import logging
144 import traceback
145 import subprocess
146 import multiprocessing
147-import cPickle
148+import pickle
149 import tempfile
150-from itertools import islice, izip, repeat
151+from itertools import islice, repeat
152
153 from . import LoggingWriter
154
155@@ -93,7 +93,7 @@ def runParallel(pool, fun, par, *args, **kwargs):
156
157 """
158 if pool:
159- result = pool.map(parMapper, izip(par, repeat( { "fun": fun, "args": args, "kwargs": kwargs } )))
160+ result = pool.map(parMapper, zip(par, repeat( { "fun": fun, "args": args, "kwargs": kwargs } )))
161 else:
162 result = []
163 for c in par:
164diff --git a/src/python/Tools/sessioninfo.py b/src/python/Tools/sessioninfo.py
165index 75650ec..b49bf59 100644
166--- a/src/python/Tools/sessioninfo.py
167+++ b/src/python/Tools/sessioninfo.py
168@@ -34,7 +34,6 @@ def sessionInfo():
169 'version': version,
170 'runInfo': [{"key": "commandline", "value": " ".join(sys.argv)}],
171 'uname': " / ".join(platform.uname()),
172- 'dist': " / ".join(platform.dist()),
173 'mac_ver': " / ".join([platform.mac_ver()[0], platform.mac_ver()[2]]),
174 'python_implementation': platform.python_implementation(),
175 'python_version': platform.python_version(),
176diff --git a/src/python/Tools/vcfcallerinfo.py b/src/python/Tools/vcfcallerinfo.py
177index eb7e86e..947f2c4 100755
178--- a/src/python/Tools/vcfcallerinfo.py
179+++ b/src/python/Tools/vcfcallerinfo.py
180@@ -33,8 +33,8 @@ class CallerInfo(object):
181
182 def asDict(self):
183 kvd = ["name", "version", "parameters"]
184- return {"aligners": [dict(y for y in itertools.izip(kvd, x)) for x in self.aligners],
185- "callers": [dict(y for y in itertools.izip(kvd, x)) for x in self.callers]}
186+ return {"aligners": [dict(y for y in zip(kvd, x)) for x in self.aligners],
187+ "callers": [dict(y for y in zip(kvd, x)) for x in self.callers]}
188
189 def addVCF(self, vcfname):
190 """ Add caller versions from a VCF
191diff --git a/src/python/hap.py b/src/python/hap.py
192index 8045936..93279a4 100755
193--- a/src/python/hap.py
194+++ b/src/python/hap.py
195@@ -188,7 +188,7 @@ def main():
196 parser.print_help()
197 exit(1)
198
199- print "Hap.py %s" % Tools.version
200+ print("Hap.py %s" % Tools.version)
201 if args.version:
202 exit(0)
203
204diff --git a/src/python/ovc.py b/src/python/ovc.py
205index 2837255..20b4442 100755
206--- a/src/python/ovc.py
207+++ b/src/python/ovc.py
208@@ -34,7 +34,7 @@ lines = 1
209 for line in f:
210 l = line.split("\t")
211 if len(l) > 3 and (last-1) > int(l[1]):
212- print "Overlap at %s:%i (line %i)" % (l[0], int(l[1]), lines)
213+ print(Overlap at %s:%i (line %i)) % (l[0], int(l[1]), lines)
214 exit(1)
215 elif len(l) > 3:
216 last = int(l[2])
217diff --git a/src/python/pre.py b/src/python/pre.py
218index 5ca1644..a37a4b2 100755
219--- a/src/python/pre.py
220+++ b/src/python/pre.py
221@@ -47,8 +47,8 @@ import Haplo.partialcredit
222 def hasChrPrefix(chrlist):
223 """ returns if list of chr names has a chr prefix or not """
224
225- noprefix = map(str, range(23)) + ["X", "Y", "MT"]
226- withprefix = ["chr" + x for x in map(str, range(23)) + ["X", "Y", "M"]]
227+ noprefix = [str(x) for x in range(23)] + ["X", "Y", "MT"]
228+ withprefix = ["chr" + str(x) for x in range(23)] + ["X", "Y", "M"]
229
230 count_noprefix = len(list(set(noprefix) & set(chrlist)))
231 count_prefix = len(list(set(withprefix) & set(chrlist)))
232@@ -126,7 +126,7 @@ def preprocess(vcf_input,
233
234 if gender == "auto":
235 logging.info(mf)
236- if "female" in mf:
237+ if b"female" in mf:
238 gender = "female"
239 else:
240 gender = "male"
241@@ -392,7 +392,7 @@ def main():
242 exit(0)
243
244 if args.version:
245- print "pre.py %s" % Tools.version # noqa:E999
246+ print(pre.py %s) % Tools.version # noqa:E999
247 exit(0)
248
249 args.input = args.input[0]
250diff --git a/src/python/qfy.py b/src/python/qfy.py
251index 4f247ee..59ed68a 100755
252--- a/src/python/qfy.py
253+++ b/src/python/qfy.py
254@@ -203,8 +203,8 @@ def quantify(args):
255
256 # in default mode, print result summary to stdout
257 if not args.quiet and not args.verbose:
258- print "Benchmarking Summary:"
259- print essential_numbers.to_string(index=False)
260+ print("Benchmarking Summary:")
261+ print(essential_numbers.to_string(index=False))
262
263 # keep this for verbose output
264 if not args.verbose:
265@@ -213,12 +213,12 @@ def quantify(args):
266 except:
267 pass
268
269- for t in res.iterkeys():
270+ for t in res.keys():
271 metrics_output["metrics"].append(dataframeToMetricsTable("roc." + t, res[t]))
272
273 # gzip JSON output
274 if args.write_json:
275 with gzip.open(args.reports_prefix + ".metrics.json.gz", "w") as fp:
276- json.dump(metrics_output, fp)
277+ fp.write(json.dumps(metrics_output, default=np_encoder).encode('ascii'))
278
279
280@@ -362,7 +363,7 @@ def main():
281 exit(0)
282
283 if args.version:
284- print "qfy.py %s" % Tools.version
285+ print(qfy.py %s) % Tools.version
286 exit(0)
287
288 if args.fp_bedfile and args.preprocessing_truth_confregions:
289diff --git a/src/python/som.py b/src/python/som.py
290index e942351..c01d522 100755
291--- a/src/python/som.py
292+++ b/src/python/som.py
293@@ -640,7 +640,7 @@ def main():
294 "overlap):\n" + ambie.to_string(index=False))
295 # in default mode, print result summary to stdout
296 if not args.quiet and not args.verbose:
297- print "FP/ambiguity classes with info (multiple classes can " \
298+ print(FP/ambiguity classes with info (multiple classes can ) \
299 "overlap):\n" + ambie.to_string(index=False)
300 ambie.to_csv(args.output + ".ambiclasses.csv")
301 metrics_output["metrics"].append(dataframeToMetricsTable("ambiclasses", ambie))
302@@ -659,7 +659,7 @@ def main():
303 formatters={'reason': '{{:<{}s}}'.format(ambie['reason'].str.len().max()).format}, index=False))
304 # in default mode, print result summary to stdout
305 if not args.quiet and not args.verbose:
306- print "Reasons for defining as ambiguous (multiple reasons can overlap):\n" + ambie.to_string(
307+ print(Reasons for defining as ambiguous (multiple reasons can overlap):\n) + ambie.to_string(
308 formatters={'reason': '{{:<{}s}}'.format(ambie['reason'].str.len().max()).format}, index=False)
309 ambie.to_csv(args.output + ".ambireasons.csv")
310 metrics_output["metrics"].append(dataframeToMetricsTable("ambireasons", ambie))
311@@ -936,7 +936,7 @@ def main():
312 logging.info("\n" + res.to_string())
313 # in default mode, print result summary to stdout
314 if not args.quiet and not args.verbose:
315- print "\n" + res.to_string()
316+ print(\n) + res.to_string()
317
318 res["sompyversion"] = vstring
319
320diff --git a/src/python/qfy.py b/src/python/qfy.py
321index 59ed68a..be8d7e1 100755
322--- a/src/python/qfy.py
323+++ b/src/python/qfy.py
324@@ -33,6 +33,7 @@ import pandas
325 import json
326 import tempfile
327 import gzip
328+import numpy as np
329
330 scriptDir = os.path.abspath(os.path.dirname(os.path.realpath(__file__)))
331 sys.path.append(os.path.abspath(os.path.join(scriptDir, '..', 'lib', 'python27')))
332@@ -45,6 +46,10 @@ import Haplo.happyroc
333 import Haplo.gvcf2bed
334 from Tools import fastasize
335
336+# Cannot convert data to json without a custom enconder
337+def np_encoder(object):
338+ if isinstance(object, np.generic):
339+ return object.item()
340
341 def quantify(args):
342 """ Run quantify and write tables """