Merge pull request #26 from pombo-lab/v1.1.1-dev

Merge V1.1.1 dev

Author: rbeagrie

.pylintrc

@@ -65,7 +65,7 @@ confidence=
 # --enable=similarities". If you want to run only the classes checker, but have
 # no Warning level messages displayed, use"--disable=all --enable=classes
 # --disable=W"
-disable=import-star-module-level,old-octal-literal,oct-method,print-statement,unpacking-in-except,parameter-unpacking,backtick,old-raise-syntax,old-ne-operator,long-suffix,dict-view-method,dict-iter-method,metaclass-assignment,next-method-called,raising-string,indexing-exception,raw_input-builtin,long-builtin,file-builtin,execfile-builtin,coerce-builtin,cmp-builtin,buffer-builtin,basestring-builtin,apply-builtin,filter-builtin-not-iterating,using-cmp-argument,useless-suppression,range-builtin-not-iterating,suppressed-message,no-absolute-import,old-division,cmp-method,reload-builtin,zip-builtin-not-iterating,intern-builtin,unichr-builtin,reduce-builtin,standarderror-builtin,unicode-builtin,xrange-builtin,coerce-method,delslice-method,getslice-method,setslice-method,input-builtin,round-builtin,hex-method,nonzero-method,map-builtin-not-iterating,no-member,fixme,anomalous-backslash-in-string,too-many-public-methods,no-self-use
+disable=import-star-module-level,old-octal-literal,oct-method,print-statement,unpacking-in-except,parameter-unpacking,backtick,old-raise-syntax,old-ne-operator,long-suffix,dict-view-method,dict-iter-method,metaclass-assignment,next-method-called,raising-string,indexing-exception,raw_input-builtin,long-builtin,file-builtin,execfile-builtin,coerce-builtin,cmp-builtin,buffer-builtin,basestring-builtin,apply-builtin,filter-builtin-not-iterating,using-cmp-argument,useless-suppression,range-builtin-not-iterating,suppressed-message,no-absolute-import,old-division,cmp-method,reload-builtin,zip-builtin-not-iterating,intern-builtin,unichr-builtin,reduce-builtin,standarderror-builtin,unicode-builtin,xrange-builtin,coerce-method,delslice-method,getslice-method,setslice-method,input-builtin,round-builtin,hex-method,nonzero-method,map-builtin-not-iterating,no-member,fixme,anomalous-backslash-in-string,too-many-public-methods,no-self-use,useless-object-inheritance
 
 
 [REPORTS]

.travis.yml

@@ -1,7 +1,6 @@
 language: python
 python:
   - '2.7'
-  - '3.4'
   - '3.5'
   - '3.6'
 install:

CHANGELOG.md

@@ -0,0 +1,55 @@
+# Changelog
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [1.1.1] - 2019-02-08
+### Added
+- Added a CHANGELOG
+
+### Changed
+- Fix problem processing uncompressed fastas
+- Fix bug where pandas converts sample names to numeric types
+
+### Removed
+- Removed command line option for MACS window calling
+- Removed support for Python3.4
+
+## [1.1.0] - 2017-05-06
+### Added
+- Added fixed threshold option to process_nps
+- Added functions for extracting sub-regions of a matrix
+
+### Changed
+- Enable coveralls
+- Enable codeclimate
+
+
+## [1.0.0] - 2017-03-04
+### Added
+- First release of GAMtools package
+- Created a master command line script
+- Added support for gzipped input/output
+- Added a command to calculate enrichments
+- Added a command to convert different matrix formats
+- Added a command for circular permutation
+- Added a command for getting compaction
+- Added a command for getting radial position
+- Added QC scripts and automatic exclusion of bad samples
+- Added documentation
+- Added unit tests
+- Added tutorial
+- Added continuous integration through tox and Travis
+
+### Changed
+- Made code PEP8 compliant
+- Made code python3 compatible
+
+### Removed
+- Old command line scripts
+
+[1.0.0]: https://github.com/pombo-lab/gamtools/compare/nature-2017...v1.0.0
+[1.1.0]: https://github.com/pombo-lab/gamtools/compare/v1.0.0...v1.1.0
+[1.1.1]: https://github.com/pombo-lab/gamtools/compare/v1.1.0...v1.1.1
+

lib/gamtools/call_windows.py

@@ -763,10 +763,6 @@ def threshold_from_args(args):
     Wrapper function to pass arguments to threshold_file from argparse.
     """
 
-    if args.macs:
-        raise NotImplementedError('Thresholding using macs is not supported')
-
-    else:
-        threshold_file(args.coverage_file, args.output_file,
-                       args.fitting_folder, args.details_file,
-                       args.fitting_function)
+    threshold_file(args.coverage_file, args.output_file,
+                   args.fitting_folder, args.details_file,
+                   args.fitting_function)

lib/gamtools/cosegregation.py

@@ -45,7 +45,6 @@ class InvalidDataError(Exception):
     """
     Exception raised if segregation data contains anything other than 0s and 1s.
     """
-    pass
 
 
 def regions_are_valid(regions):

lib/gamtools/data/scripts/mapping_stats.sh

@@ -5,9 +5,11 @@ echo -e "Sample\tReads_sequenced\tReads_mapped\tUnique_reads_mapped\tPercent_map
 for fq in $*; 
  do 
     if [ ${fq: -10} == '.rmdup.bam' ]; then continue; fi;
+    cat_cmd=cat;
+    if [ ${fq##*.} '==' 'gz' ]; then cat_cmd=zcat; fi;
     sample=$(basename $fq);
     name_no_ext=$(echo -n $fq | tr "." "\n" | sed '/^gz$/ d' | sed '$ d' | perl -pe 'chomp if eof' | tr "\n" ".");
-    nlines=$(zcat ${fq} | wc -l);
+    nlines=$(${cat_cmd} ${fq} | wc -l);
     nreads=$(echo "${nlines} / 4" | bc);
     nmap=$(samtools view -c ${name_no_ext}.bam);
     if [ -z $nmap ]; then $nmap=0; fi;

lib/gamtools/qc/fastqc.py

@@ -156,8 +156,7 @@ def process_file(filename):
     # Get start and end position of all modules:
     mod_start = []
     mod_end = []
-    for i in range(0, len(fq_lines)):
-        line = fq_lines[i]
+    for i, line in enumerate(fq_lines):
 
         if line == '>>END_MODULE':
             mod_end.append(i)

lib/gamtools/qc/merge.py

@@ -26,7 +26,30 @@ def merge_stats(input_stats_files, output_merged_file):
         stats_file = pd.read_csv(stats_file_path, delim_whitespace=True, index_col=0)
         base = pd.merge(base, stats_file, left_index=True, right_index=True)
 
-    base.to_csv(output_merged_file, sep='\t')
+    final_df = check_index_column(input_stats_files, base)
+    final_df.to_csv(output_merged_file, sep='\t')
+
+def check_index_column(input_stats_files, merged_df):
+    """
+    After merging several stats files together, check that the index column
+    (i.e. the sample name) has not been converted to an integer or a float.
+
+    :param list input_stats_files: String paths to input dataframes.
+    :param merged_df: Pandas dataframe of merged statistics files.
+
+    :returns: Pandas dataframe with corrected index column.
+    """
+
+    try:
+        first_col = pd.read_csv(input_stats_files[0], delim_whitespace=True, dtype=str).iloc[:, 0]
+    except pd.io.common.EmptyDataError:
+        input_stats_files[0].seek(0)
+        first_col = pd.read_csv(input_stats_files[0], delim_whitespace=True, dtype=str).iloc[:, 0]
+
+    if not all(merged_df.index.get_level_values(0) == first_col):
+        merged_df.index = first_col
+
+    return merged_df
 
 def merge_stats_from_doit(dependencies, targets):
     """

lib/gamtools/qc/pass_qc.py

@@ -96,8 +96,6 @@ class QcParamError(Exception):
     Exception to be raised if the QC Parameters file is malformed.
     """
 
-    pass
-
 
 def do_comparison(left_str, operator, right_str, stats_df):
     """

lib/gamtools/segregation.py

@@ -66,7 +66,6 @@
 
 class InvalidChromError(Exception):
     """Exception to be raised when an invalid chromosome is specified"""
-    pass
 
 
 def open_segregation(path_or_buffer):
@@ -100,7 +99,7 @@ def index_from_interval(segregation_table, interval):
             'Interval start {0} larger than interval end {1}'.format(
                 *interval))
 
-    window_in_region = np.logical_and(
+    window_in_region = np.logical_and( #pylint: disable=assignment-from-no-return
         np.logical_and(
             segregation_table.index.get_level_values('stop') > start,
             segregation_table.index.get_level_values('start') < stop),