Python2andpython3

.gitignore

@@ -5,6 +5,7 @@ dist
 .idea*
 .idea/*
 *DS_store
+.cache
 
 virtualenv
 
@@ -14,5 +15,9 @@ virtualenv
 .ipynb_checkpoints
 _build
 
+# data
+data
 # Shalek and Satija data
-nature12172-s1
+#nature12172-s1
+__*
+examples/__*

.travis.yml

@@ -1,6 +1,7 @@
 language: python
 python:
 - '2.7'
+- '3.5'
 sudo: false
 before_install:
 - if [ ${TRAVIS_PYTHON_VERSION:0:1} == "2" ]; then wget http://repo.continuum.io/miniconda/Miniconda-latest-Linux-x86_64.sh
@@ -34,7 +35,7 @@ script:
   - MASTER=master
   - if [[ $TRAVIS_BRANCH == v*.*.* ]] ; then export DEPLOY_HTML_DIR=docs ; fi
   - if [[ $TRAVIS_BRANCH == "$MASTER" ]] ; then export DEPLOY_HTML_DIR=docs-dev ; fi
-  - if [[ $TRAVIS_BRANCH == v*.*.* ]] || [[ $TRAVIS_BRANCH == "$MASTER" ]] ; then sudo apt-get install pandoc; conda install --yes --file doc/conda_requirements.txt ; conda install --yes ipython-notebook=2; pip install -r doc/requirements.txt; pip install . ; cd doc ; make setup_gh_pages ; make generate ; make deploy ; fi
+  - if [[ $TRAVIS_BRANCH == v*.*.* ]] || [[ $TRAVIS_BRANCH == "$MASTER" ]] ; then sudo apt-get install pandoc; conda install --yes --file doc/conda_requirements.txt ; pip install -r doc/requirements.txt; pip install . ; cd doc ; make setup_gh_pages ; make generate ; make deploy ; fi
 after_script:
 - coveralls
 notifications:

README.md

@@ -1,5 +1,11 @@
 [![Stories in Ready](https://badge.waffle.io/yeolab/flotilla.png?label=ready&title=Ready)](https://waffle.io/yeolab/flotilla)
-[![Build Status](https://travis-ci.org/YeoLab/flotilla.svg?branch=master)](https://travis-ci.org/YeoLab/flotilla)[![Coverage Status](https://img.shields.io/coveralls/YeoLab/flotilla.svg?style=flat)](https://coveralls.io/r/YeoLab/flotilla?branch=master)[![License](https://img.shields.io/pypi/l/flotilla.svg?style=flat)](https://pypi.python.org/pypi/flotilla/)[![Downloads](https://img.shields.io/pypi/dm/flotilla.svg?style=flat)](https://pypi.python.org/pypi/flotilla/)[![Latest Version](https://img.shields.io/pypi/v/flotilla.svg?style=flat)](https://pypi.python.org/pypi/flotilla/)[![DOI](https://img.shields.io/badge/DOI-10.5281%20%2F%20zenodo.12230-blue.svg)](http://dx.doi.org/10.5281/zenodo.12230)
+[![Build Status](https://travis-ci.org/YeoLab/flotilla.svg?branch=master)](https://travis-ci.org/YeoLab/flotilla)
+[![Coverage Status](https://img.shields.io/coveralls/YeoLab/flotilla.svg?style=flat)](https://coveralls.io/r/YeoLab/flotilla?branch=master)
+[![License](https://img.shields.io/pypi/l/flotilla.svg?style=flat)](https://pypi.python.org/pypi/flotilla/)
+[![Downloads](https://img.shields.io/pypi/dm/flotilla.svg?style=flat)](https://pypi.python.org/pypi/flotilla/)
+[![Latest Version](https://img.shields.io/pypi/v/flotilla.svg?style=flat)](https://pypi.python.org/pypi/flotilla/)
+[![DOI](https://img.shields.io/badge/DOI-10.5281%20%2F%20zenodo.12230-blue.svg)](http://dx.doi.org/10.5281/zenodo.12230)
+[![Binder](http://mybinder.org/badge.svg)](http://mybinder.org/repo/YeoLab/flotilla)
 
 flotilla
 ========
@@ -151,7 +157,11 @@ Problems? Questions?
 
 We invite your input! Please leave any feedback on our [issues page](https://github.com/YeoLab/flotilla/issues).
 
-![NumFOCUS logo](http://numfocus.org/theme/img/numfocus_logo.png)
+![NumFOCUS logo](https://www.continuum.io/sites/default/files/numfocus_logo.png)
 
 Proudly sponsored by a NumFOCUS John Hunter Technical Fellowship to Olga
 Botvinnik.
+
+
+
+

TODO.md

@@ -35,3 +35,6 @@ Frigate
 
 
 
+
+
+python3 unicode compatibility in flotilla/test/data_model/test_data_model_gene_ontology.py

doc/conda_requirements.txt

@@ -1,4 +1,5 @@
 runipy
 numpydoc
 sphinx
-fabric
+fabric
+jupyter

doc/releases/v0.2.7.txt

@@ -8,4 +8,3 @@ Miscellaneous
 ~~~~~~~~~~~~~
 
 - Fixed tutorial building on the documentation page
-

doc/releases/v0.3.1.txt

@@ -0,0 +1,9 @@
+v0.3.1 (May 17th, 2016)
+-----------------------
+
+This is a patch release, with non-breaking changes from v0.3.0.
+
+Miscellaneous
+~~~~~~~~~~~~~
+
+- Refactored for compatibility with both py2.7 and 3.5

doc/whatsnew.rst

@@ -7,7 +7,8 @@ What's new in the package
 
 A catalog of new features, improvements, and bug-fixes in each release.
 
-.. include:: releases/v0.2.8.txt
+.. include:: releases/v0.3.1.txt
+.. include:: releases/v0.3.0.txt
 .. include:: releases/v0.2.7.txt
 .. include:: releases/v0.2.6.txt
 .. include:: releases/v0.2.5.txt

environment.yml

@@ -0,0 +1,12 @@
+name: flotilla
+dependencies:
+- jupyter
+- pymongo
+- scikit-learn
+- seaborn
+- semantic_version
+- statsmodels
+- xlrd
+- pip:
+  - brewer2mpl
+  - husl

flotilla/__init__.py

@@ -1,28 +1,38 @@
+
+from __future__ import absolute_import, division, print_function
+from __future__ import unicode_literals
+
 import os
 
-from .data_model import ExpressionData, SplicingData, MetaData, \
-    MappingStatsData, GeneOntologyData
+from .data_model import (ExpressionData, SplicingData, MetaData,
+                         MappingStatsData, GeneOntologyData)
 from .compute.predict import PredictorConfigManager, PredictorDataSetManager
 from .datapackage import make_study_datapackage, FLOTILLA_DOWNLOAD_DIR
 from .study import Study
 
 
-__all__ = ['Study', 'PredictorConfigManager', 'PredictorDataSetManager',
+__all__ = ['Study',
+           'PredictorConfigManager', 'PredictorDataSetManager',
            'make_study_datapackage', 'FLOTILLA_DOWNLOAD_DIR',
-           'compute', 'data_model', 'visualize', 'Study', 'ExpressionData',
-           'SplicingData', 'MetaData', 'MappingStatsData',
-           'datapackage', 'GeneOntologyData', 'go', 'util']
+           'compute', 'data_model', 'visualize',
+           'Study',
+           'ExpressionData', 'SplicingData', 'MetaData', 'MappingStatsData',
+           'GeneOntologyData',
+           'datapackage', 'go', 'util']
+
 
-__version__ = 'v0.3.0'
+__version__ = 'v0.3.1'
 
-# 18 cells, multiindex on the splicing data features, features already renamed
-# in the matrices
+
+# 18 cells, multiindex on the splicing data features,
+# features already renamed in the matrices
 _shalek2013 = 'https://raw.githubusercontent.com/YeoLab/shalek2013/master/' \
               'datapackage.json'
 
 # 250 cells, ensembl and miso ids on index, need renaming, lots of celltypes
 _test_data = 'https://raw.githubusercontent.com/YeoLab/flotilla_test_data/' \
              'master/datapackage.json'
+
 _brainspan = 'https://s3-us-west-2.amazonaws.com/flotilla/' \
              'brainspan_batch_corrected_for_amazon_s3/datapackage.json'
 

flotilla/compute/__init__.py

@@ -1 +1,5 @@
+"""
+compute tools
+"""
+
 __author__ = 'olga'

flotilla/compute/decomposition.py

@@ -2,6 +2,9 @@
 Perform various dimensionality reduction algorithms on data
 """
 
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import sys
 
 from sklearn import decomposition
@@ -95,7 +98,7 @@ def fit(self, X):
         return self
 
     def transform(self, X):
-        """Transform a matrix into the compoment space
+        """Transform a matrix into the component space
 
         Parameters
         ----------
@@ -146,7 +149,8 @@ def fit_transform(self, X):
 
 
 class DataFramePCA(DataFrameReducerBase, decomposition.PCA):
-    """Perform Principal Components Analaysis on a DataFrame"""
+    """Perform Principal Components Analaysis on a DataFrame
+    """
     pass
 
 

flotilla/compute/expression.py

@@ -1,4 +1,11 @@
-from __future__ import division
+"""
+compute / expression
+"""
+
+# from __future__ import division
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import itertools
 import math
 import sys

flotilla/compute/generic.py

@@ -1,3 +1,10 @@
+"""
+generic
+"""
+
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import sys
 
 import numpy as np

flotilla/compute/infotheory.py

@@ -2,6 +2,9 @@
 Information-theoretic calculations
 """
 
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import numpy as np
 import pandas as pd
 from sklearn import cross_validation

flotilla/compute/network.py

@@ -3,6 +3,9 @@
 :py:mod:flotilla.visualize.network
 """
 
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import networkx as nx
 import numpy as np
 import pandas as pd

flotilla/compute/outlier.py

@@ -1,7 +1,9 @@
 """
 Detect outlier samples in data
 """
-import sys
+
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
 
 import sklearn
 import pandas as pd
@@ -37,9 +39,7 @@ def __init__(self, X, method=None, nu=0.1, kernel='rbf', gamma=0.1,
                  random_state=0, **kwargs):
         if method is None:
             method = sklearn.svm.OneClassSVM
-
-        sys.stdout.write('SVM Kernel is: {}\n'.format(kernel))
-
+        print('SVM Kernel is:', kernel)
         kwargs.update(dict(nu=nu, kernel=kernel, gamma=gamma,
                            random_state=random_state))
         self.kwargs = kwargs

flotilla/compute/predict.py

@@ -1,6 +1,10 @@
 """
 Compute predictors on data, e.g. classify or regress on features/samples
 """
+
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import sys
 import warnings
 from collections import defaultdict

flotilla/compute/splicing.py

@@ -2,6 +2,9 @@
 Calculate splicing-specific operations
 """
 
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import numpy as np
 
 

flotilla/data_model/__init__.py

@@ -1,3 +1,7 @@
+"""
+data model
+"""
+
 from .expression import ExpressionData
 from .gene_ontology import GeneOntologyData
 from .metadata import MetaData

flotilla/data_model/base.py

@@ -2,6 +2,11 @@
 Base data class for all data types. All data types in flotilla inherit from
 this, or a child object (like ExpressionData).
 """
+
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+from six import text_type
+
 import sys
 
 import matplotlib.pyplot as plt
@@ -15,11 +20,13 @@
 from ..compute.infotheory import binify, cross_phenotype_jsd, jsd_df_to_2d
 from ..compute.predict import PredictorConfigManager, \
     PredictorDataSetManager, CLASSIFIER
+from ..compute.outlier import OutlierDetection
+
 from ..visualize.decomposition import DecompositionViz
 from ..visualize.generic import violinplot, simple_twoway_scatter
 from ..visualize.network import NetworkerViz
 from ..visualize.predict import ClassifierViz
-from ..compute.outlier import OutlierDetection
+
 
 MINIMUM_FEATURE_SUBSET = 20
 
@@ -1020,8 +1027,9 @@ def _violinplot(self, feature_id, sample_ids=None,
         # feature_id, renamed = feature_id
         # else:
         # renamed = self.feature_renamer(feature_id)
-        title = '{}\n{}'.format(renamed, '\n'.join(
-            feature_id.split('@')))
+        # TODO check switch to unicode
+        # title = b'{}\n{}'.format(renamed, b'\n'.join(feature_id.split(b'@')))
+        title = renamed + u"\n" + u"\n".join(feature_id.split(u'@'))
 
         violinplot(singles, groupby=phenotype_groupby, color_ordered=color,
                    pooled=pooled, order=phenotype_order,
@@ -1129,9 +1137,10 @@ def plot_two_features(self, feature1, feature2, groupby=None,
         """
         feature1s = self.maybe_renamed_to_feature_id(feature1)
         feature2s = self.maybe_renamed_to_feature_id(feature2)
-        if isinstance(feature1s, str):
+
+        if isinstance(feature1s, text_type):
             feature1s = [feature1s]
-        if isinstance(feature2s, str):
+        if isinstance(feature2s, text_type):
             feature2s = [feature2s]
 
         for f1 in feature1s:
@@ -1157,8 +1166,7 @@ def plot_two_features(self, feature1, feature2, groupby=None,
     @staticmethod
     def _figsizer(shape, multiplier=0.25):
         """Scale a heatmap figure based on the dataframe shape"""
-        return tuple(reversed(map(lambda x: min(x * multiplier, 40),
-                                  shape)))
+        return tuple(reversed([min(x * multiplier, 40) for x in shape]))
 
     def plot_clustermap(self, sample_ids=None, feature_ids=None, data=None,
                         feature_colors=None, sample_id_to_color=None,
@@ -1285,7 +1293,7 @@ def subsets_from_metadata(metadata, minimum, subset_type, ignore=None):
                         continue
                     name = '{}: {}'.format(col, group)
                     subsets[name] = grouped.groups[group]
-        for sample_subset in subsets.keys():
+        for sample_subset in subsets.copy().keys():
             name = 'not ({})'.format(sample_subset)
             if 'False' in name or 'True' in name:
                 continue

flotilla/data_model/expression.py

@@ -1,6 +1,10 @@
 """
 Data types related to gene expression, e.g. from RNA-Seq or microarrays.
 """
+
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import sys
 
 import numpy as np