Merge pull request #13 from jmenglund/develop

Code and tests for converting to and from "sequence dictionaries"

CHANGELOG.rst

@@ -1,6 +1,21 @@
 Changelog
 =========
 
+
+0.3.0
+-----
+
+* Functions ``from_dict`` renamed ``from_sequence_dict``, and ``to_dict`` 
+  renamed ``to_sequence_dict``.
+* Added tests for the functions ``from_sequence_dict`` and ``to_sequence_dict``.
+* Installation now requires pandas >= 0.21.
+
+Release date: 2019-05-19
+
+`View commits <https://github.com/jmenglund/pandas-charm/compare/v0.2.0...v0.3.0>`_
+
+
+
 0.2.0
 -----
 

README.rst

@@ -12,7 +12,7 @@ Convert between the following objects:
 
 * BioPython MultipleSeqAlignment <-> pandas DataFrame
 * DendroPy CharacterMatrix <-> pandas DataFrame
-* Python dictionary <-> pandas DataFrame
+* "Sequence dictionary" <-> pandas DataFrame
 
 The code has been tested with Python 2.7, 3.5 and 3.6.
 
@@ -214,8 +214,8 @@ pandas DataFrame to BioPython MultipleSeqAlignment
     TG-AA t3
 
 
-Python dictionary to pandas DataFrame
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+"Sequence dictionary" to pandas DataFrame
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. code-block:: pycon
 
@@ -226,7 +226,7 @@ Python dictionary to pandas DataFrame
     ...     't2': 'TGCAA',
     ...     't3': 'TG-AA'
     ... }
-    >>> df = pc.from_dict(d)
+    >>> df = pc.from_sequence_dict(d)
     >>> df
       t1 t2 t3
     0  T  T  T
@@ -236,8 +236,8 @@ Python dictionary to pandas DataFrame
     4  A  A  A
 
 
-pandas DataFrame to Python dictionary 
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+pandas DataFrame to "sequence dictionary"
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. code-block:: pycon
 
@@ -247,7 +247,7 @@ pandas DataFrame to Python dictionary
     ...     't1': ['T', 'C', 'C', 'A', 'A'],
     ...     't2': ['T', 'G', 'C', 'A', 'A'],
     ...     't3': ['T', 'G', '-', 'A', 'A']})
-    >>> pc.to_dict(df)
+    >>> pc.to_sequence_dict(df)
     {'t1': 'TCCAA', 't2': 'TGCAA', 't3': 'TG-AA'}
 
 

pandascharm.py

@@ -6,7 +6,7 @@
 
 __author__ = 'Markus Englund'
 __license__ = 'MIT'
-__version__ = '0.2.0'
+__version__ = '0.3.0'
 
 
 def frame_as_categorical(frame, include_categories=None):
@@ -83,7 +83,16 @@ def from_charmatrix(charmatrix, categorical=True):
     return new_frame
 
 
-def from_dict(d, categorical=True):
+def from_sequence_dict(d, categorical=True):
+    """
+    Convert a dict with sequences as strings to a pandas DataFrame.
+
+    Parameters
+    ----------
+    d : dict
+    categorical : bool (default: True)
+        If True, the result will be returned as a categorical frame.
+    """
     d_seq_list = {k: list(v) for (k, v) in d.items()}
     frame = pandas.DataFrame(d_seq_list)
     if categorical:
@@ -161,5 +170,6 @@ def to_charmatrix(frame, data_type):
     return charmatrix
 
 
-def to_dict(frame, into=dict):
+def to_sequence_dict(frame, into=dict):
+    """Convert a pandas DataFrame to a dict with sequences as strings."""
     return frame.apply(lambda x: ''.join(x)).to_dict(into=into)

requirements.txt

@@ -1,3 +1,3 @@
-pandas>=0.16
+pandas>=0.21
 DendroPy>=4.0
 BioPython

setup.py

@@ -8,15 +8,15 @@
 
 setup(
     name='pandas-charm',
-    version='0.2.0',
+    version='0.3.0',
     description=(
         'A small Python library for getting character matrices '
         '(alignments) into and out of pandas'),
     long_description=open(
         join(dirname(__file__), 'README.rst'), encoding='utf-8').read(),
     packages=find_packages(exclude=['docs', 'tests*']),
     py_modules=['pandascharm'],
-    install_requires=['pandas>=0.16'],
+    install_requires=['pandas>=0.21'],
     extras_require={'testing': [
         'coverage', 'pytest', 'biopython', 'dendropy']},
     author='Markus Englund',

test_pandascharm.py

@@ -27,8 +27,8 @@
     to_charmatrix,
     from_bioalignment,
     to_bioalignment,
-    from_dict,
-    to_dict)
+    from_sequence_dict,
+    to_sequence_dict)
 
 
 class TestAsCategorical():
@@ -198,18 +198,28 @@ def test_invalid_alphabet(self):
             to_bioalignment(self.dna_frame, alphabet='dna')
 
 
-class TestDictConversion():
+class TestSequenceDictConversion():
 
     dna_frame = pandas.DataFrame({
         't1': ['T', 'C', 'C', 'A', 'A'],
         't2': ['T', 'G', 'C', 'A', 'A'],
         't3': ['T', 'G', '-', 'A', 'A']}, dtype='object')
 
+    dna_frame_nan = pandas.DataFrame({
+        't1': ['T', 'C', 'C', 'A', 'A'],
+        't2': ['T', 'G', 'C', 'A', 'A'],
+        't3': ['T', 'G', '-', 'A', numpy.nan]}, dtype='object')
+
     dna_dict = {'t1': 'TCCAA', 't2': 'TGCAA', 't3': 'TG-AA'}
 
-    def test_from_dict(self):
+    def test_from_sequence_dict(self):
         assert_frame_equal(
-            from_dict(self.dna_dict, categorical=False), self.dna_frame)
+            from_sequence_dict(self.dna_dict, categorical=False),
+            self.dna_frame)
+
+    def test_to_sequence_dict(self):
+        assert(to_sequence_dict(self.dna_frame) == self.dna_dict)
 
-    def test_to_dict(self):
-        assert(to_dict(self.dna_frame) == self.dna_dict)
+    def test_do_sequence_dict_nan(self):
+        with pytest.raises(TypeError):
+            to_sequence_dict(self.dna_frame_nan)