Merge pull request #28 from sjanssen2/skbio

flake8 + skbio 0.4.2

.travis.yml

@@ -1,18 +1,20 @@
 # Modified from https://github.com/biocore/biom-format/
 language: python
 env:
-  - PYTHON_VERSION=2.7 NUMPY_VERSION=1.7
+  - PYTHON_VERSION=2.7
 before_install:
-  - wget http://repo.continuum.io/miniconda/Miniconda-2.2.2-Linux-x86_64.sh -O miniconda.sh
-  - chmod +x miniconda.sh
-  - ./miniconda.sh -b
-  - export PATH=/home/travis/anaconda/bin:$PATH
+  - wget https://repo.continuum.io/miniconda/Miniconda2-latest-Linux-x86_64.sh -O miniconda.sh
+  - export MINICONDA_PREFIX="$HOME/miniconda"
+  - bash miniconda.sh -b -p $MINICONDA_PREFIX
+  - export PATH="$MINICONDA_PREFIX/bin:$PATH"
   # Update conda itself
-  - conda update --yes conda
+  - conda config --set always_yes yes
+  - conda update -q conda
+  - conda info -a
 install:
-  - conda create --yes -n env_name python=$PYTHON_VERSION pip numpy=$NUMPY_VERSION scipy matplotlib nose pep8 Sphinx
+  - conda create --yes -n env_name python=$PYTHON_VERSION pip numpy scipy matplotlib nose pep8 Sphinx
   - source activate env_name
-  - pip install future==0.13.1 coveralls natsort pyflakes flake8 python-dateutil scikit-bio click
+  - pip install future coveralls natsort pyflakes flake8 python-dateutil scikit-bio==0.4.2 click
   - pip install -e . --no-deps
 script:
   - if [ ${WITH_DOCTEST} ]; then PYTHONWARNINGS=ignore nosetests --with-doctest --with-coverage -I DONOTIGNOREANYTHING; else PYTHONWARNINGS=ignore nosetests --with-coverage -I DONOTIGNOREANYTHING; fi

INSTALL

@@ -11,4 +11,3 @@ $ python setup.py install --prefix=$HOME
 and tax2tree will be placed into your path. To run, just call:
 
 $ t2t
-

scripts/t2t

@@ -17,8 +17,10 @@ def print_version(ctx, param, value):
     click.echo('Version %s' % t2t.__version__)
     ctx.exit()
 
+CONTEXT_SETTINGS = dict(help_option_names=['-h', '--help'])
 
-@click.group()
+
+@click.group(context_settings=CONTEXT_SETTINGS)
 @click.option('--version', is_flag=True, callback=print_version,
               expose_value=False, is_eager=True)
 @click.pass_context
@@ -32,16 +34,28 @@ def cli(ctx):
 @click.option('--output', '-o', required=True, help='Output basename')
 @click.option('--tree', '-t', required=True, help='Input tree',
               type=click.File('U'))
-def decorate(tree, consensus_map, output):
+@click.option('--no-suffix', '-n',
+              help="Don't append suffixes (e.g. _1, _2) to polyphyletic " +
+                   "groups",
+              is_flag=True, default=False)
+@click.option('--suffix-char', '-s',
+              help="Use a different char (instead of underscore) for " +
+                   "polyphyletic group suffixes",
+              required=False, default="_", type=str)
+
+def decorate(tree, consensus_map, output, no_suffix, suffix_char):
     """Decorate a taxonomy onto a tree"""
     append_rank = False
-    seed_con = consensus_map.readline().strip().split('\t')[1]
 
+    # get desired ranks from first line of consensus map
+    seed_con = consensus_map.readline().strip().split('\t')[1]
     nl.determine_rank_order(seed_con)
+    consensus_map.seek(0)
 
     tipname_map = nl.load_consensus_map(consensus_map, append_rank)
     tree_ = nl.load_tree(tree, tipname_map)
     counts = nl.collect_names_at_ranks_counts(tree_)
+
     nl.decorate_ntips(tree_)
     nl.decorate_name_relative_freqs(tree_, counts, 2)
     nl.set_ranksafe(tree_)
@@ -53,7 +67,9 @@ def decorate(tree, consensus_map, output):
     contree, contree_lookup = nl.make_consensus_tree(tipname_map.values())
     nl.backfill_names_gap(tree_, contree_lookup)
     nl.commonname_promotion(tree_)
-    nl.make_names_unique(tree_)
+
+    if not no_suffix:
+        nl.make_names_unique(tree_, suffix_glue_char=suffix_char)
 
     constrings = nl.pull_consensus_strings(tree_)
 
@@ -62,9 +78,7 @@ def decorate(tree, consensus_map, output):
     f.close()
 
     nl.save_bootstraps(tree_)
-    f = open(output, 'w')
-    f.write(tree_.to_newick(with_distances=True))
-    f.close()
+    tree_.write(output)
 
 
 @cli.command()
@@ -79,8 +93,7 @@ def reroot(tree, tips, output):
     tipnames = set([l.strip() for l in tips])
     tree_ = TreeNode.from_newick(tree)
     rerooted = ut.reroot(tree_, tipnames)
-
-    output.write(rerooted.to_newick(with_distances=True))
+    rerooted.write(output)
 
 
 @cli.command()
@@ -110,7 +123,7 @@ def fetch(tree, output):
     """Fetch the taxonomy off the tree"""
     result, error = t2tcli.fetch(tree)
     if error:
-        print '\n'.join(result)
+        click.echo('\n'.join(result))
     else:
         output.write('\n'.join(result))
 
@@ -126,7 +139,8 @@ def validate(taxonomy, limit, flat_errors, hierarchy_errors):
     lines = taxonomy.readlines()
     result, err = t2t.cli.validate(lines, limit, flat_errors, hierarchy_errors)
 
-    print '\n'.join(result)
+    click.echo('\n'.join(result))
+    click.echo('Validation complete.')
 
 @cli.command()
 @click.option('--consensus-map', '-m', required=True,
@@ -135,35 +149,35 @@ def validate(taxonomy, limit, flat_errors, hierarchy_errors):
 @click.option('--tree', '-t', required=True, help='Input tree',
               type=click.File('U'))
 @click.option('--rooted/--unrooted', default=True, help='Treat tree as rooted or unrooted')
-@click.option('--quiet', is_flag=True, default=False, help='Suppress output')
-def consistency(tree, consensus_map, output_file, rooted, quiet):
+@click.option('--verbose', is_flag=True, default=False, help='Provide detailed output')
+def consistency(tree, consensus_map, output_file, rooted, verbose):
     """Consistency of a tree relative to taxonomy"""
-    
-    if not quiet:
-        print 'Determining taxonomic consistency of: '
-        print '  tree = ' + tree.name
-        print '  consensus-map = ' + consensus_map.name
-        print '  rooted = ' + str(rooted)
-        print ''
-        
+
+    if verbose:
+        click.echo('Determining taxonomic consistency of: ')
+        click.echo('  tree = ' + tree.name)
+        click.echo('  consensus-map = ' + consensus_map.name)
+        click.echo('  rooted = ' + str(rooted))
+        click.echo('')
+
     # dynamically determine taxonomic ranks
     seed_con = consensus_map.readline().strip().split('\t')[1]
     nl.determine_rank_order(seed_con)
 
-    tipname_map = nl.load_consensus_map(consensus_map, append_rank = False)    
+    tipname_map = nl.load_consensus_map(consensus_map, append_rank=False)
     tree = nl.load_tree(tree, tipname_map)
-    
+
     counts = nl.collect_names_at_ranks_counts(tree)
     nl.decorate_ntips_rank(tree)
     nl.decorate_name_counts(tree)
-    
+
     # determine taxonomic consistency of tree
     c = con.Consistency(counts, len(nl.RANK_ORDER))
     consistency_index = c.calculate(tree, rooted)
     c.write(output_file, consistency_index)
-    
-    if not quiet:
-        print 'Consistency written to: ' + output_file
+
+    if verbose:
+        click.echo('Consistency written to: ' + output_file)
 
 
 if __name__ == '__main__':

setup.py

@@ -40,7 +40,7 @@
 if on_rtd:
     install_requires = []
 else:
-    install_requires = ['numpy >= 1.7', 'future==0.13.1', 'scikit-bio',
+    install_requires = ['numpy >= 1.7', 'future', 'scikit-bio',
                         'Click']
 
 setup(name='tax2tree',

t2t/consensus.py

@@ -7,7 +7,7 @@
 etc...
 """
 from nlevel import RANK_ORDER
-from numpy import zeros, where, logical_or
+from numpy import zeros, where, logical_or, long
 
 
 def taxa_score(master, reps):
@@ -111,8 +111,9 @@ def get_consensus_stats(consensus_map):
     rank_names = [c[0] for c in cons[0]]
     for idx, rank in enumerate(rank_names):
         # collect all cons that are classified (ie more info than k__)
-        klassed = [c[idx].lower() for c in cons if c[idx]
-                   and c[idx][0] == rank]
+        klassed = [c[idx].lower()
+                   for c
+                   in cons if c[idx] and c[idx][0] == rank]
 
         n_classified = len(klassed)
 
@@ -126,7 +127,7 @@ def get_consensus_stats(consensus_map):
 
 def pretty_print_consensus_stats(stats):
     seqs, names = stats
-    print '\t'.join(['rank', 'num_classified', 'num_unclassified',
-                     'num_names'])
+    print('\t'.join(['rank', 'num_classified', 'num_unclassified',
+                     'num_names']))
     for k in RANK_ORDER:
-        print '\t'.join(map(str, [k, seqs[k][0], seqs[k][1], len(names[k])]))
+        print('\t'.join(map(str, [k, seqs[k][0], seqs[k][1], len(names[k])])))

t2t/consistency.py

@@ -1,5 +1,9 @@
 #!/usr/bin/env python
 
+from collections import defaultdict
+
+from numpy import mean
+
 __author__ = "Donovan Park"
 __copyright__ = "Copyright 2014, The tax2tree project"
 __credits__ = ["Donovan Park"]
@@ -9,10 +13,6 @@
 __email__ = "donovan.parks@gmail.com"
 __status__ = "Development"
 
-from collections import defaultdict
-
-from numpy import mean
-
 
 class Consistency(object):
     """Calculates the consistency of taxonomic groups within a reference tree.
@@ -50,13 +50,13 @@ def calculate(self, tree, rooted):
         # determine total number of informative tips in tree for each rank
         total_informative_tips = defaultdict(int)
         for n in tree.tips():
-            for rank in xrange(self.n_ranks):
+            for rank in range(self.n_ranks):
                 total_informative_tips[rank] += n.NumTipsRank[rank]
 
         # determine highest consistency node for each taxa
-        consistency_index = {i: defaultdict(int) for i in xrange(self.n_ranks)}
+        consistency_index = {i: defaultdict(int) for i in range(self.n_ranks)}
         for n in tree.traverse(include_self=True):
-            for rank in xrange(self.n_ranks):
+            for rank in range(self.n_ranks):
                 for name, total_taxa_cnt in self.taxa_counts[rank].iteritems():
                     node_taxa_count = n.TaxaCount[rank].get(name, 0)
                     incongruent_taxa = n.NumTipsRank[rank] - node_taxa_count
@@ -92,7 +92,7 @@ def write_taxon_consistency(self, output_file, consistency_index):
 
         fout = open(output_file, 'w')
         fout.write('Taxon\tCount\tConsistency\n')
-        for rank in xrange(self.n_ranks):
+        for rank in range(self.n_ranks):
             for name, consistency in consistency_index[rank].iteritems():
                 fout.write('%s\t%d\t%.3f\n' % (name,
                                                self.taxa_counts[rank][name],
@@ -114,7 +114,7 @@ def write_rank_consistency(self, output_file, consistency_index, min_taxa,
 
         fout = open(output_file, 'w')
         fout.write('Rank #\tRank prefix\t# taxon\tAverage consistency\n')
-        for rank in xrange(self.n_ranks):
+        for rank in range(self.n_ranks):
             val = []
             for name, consistency in consistency_index[rank].iteritems():
                 if self.taxa_counts[rank][name] >= min_taxa: