Merge pull request #11416 from SixtyCapital/namedtuple-fields-as-columns

ENH: namedtuple's fields as columns

Author: jreback

doc/source/whatsnew/v0.17.1.txt

@@ -30,6 +30,7 @@ Other Enhancements
 
 - ``pd.read_*`` functions can now also accept :class:`python:pathlib.Path`, or :class:`py:py._path.local.LocalPath`
   objects for the ``filepath_or_buffer`` argument. (:issue:`11033`)
+- ``DataFrame`` now uses the fields of a ``namedtuple`` as columns, if columns are not supplied (:issue:`11181`)
 - Improve the error message displayed in :func:`pandas.io.gbq.to_gbq` when the DataFrame does not match the schema of the destination table (:issue:`11359`)
 
 .. _whatsnew_0171.api:

pandas/core/common.py

@@ -2676,6 +2676,9 @@ def is_list_like(arg):
      return (hasattr(arg, '__iter__') and
             not isinstance(arg, compat.string_and_binary_types))
 
+def is_named_tuple(arg):
+    return isinstance(arg, tuple) and hasattr(arg, '_fields')
+
 def is_null_slice(obj):
     """ we have a null slice """
     return (isinstance(obj, slice) and obj.start is None and

pandas/core/frame.py

@@ -261,6 +261,8 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
                 data = list(data)
             if len(data) > 0:
                 if is_list_like(data[0]) and getattr(data[0], 'ndim', 1) == 1:
+                    if com.is_named_tuple(data[0]) and columns is None:
+                        columns = data[0]._fields
                     arrays, columns = _to_arrays(data, columns, dtype=dtype)
                     columns = _ensure_index(columns)
 

pandas/tests/test_common.py

@@ -538,6 +538,15 @@ def test_is_list_like():
     for f in fails:
         assert not com.is_list_like(f)
 
+def test_is_named_tuple():
+    passes = (collections.namedtuple('Test',list('abc'))(1,2,3),)
+    fails = ((1,2,3), 'a', Series({'pi':3.14}))
+
+    for p in passes:
+        assert com.is_named_tuple(p)
+
+    for f in fails:
+        assert not com.is_named_tuple(f)
 
 def test_is_hashable():
 

pandas/tests/test_frame.py

@@ -16,8 +16,7 @@
 
 from pandas.compat import(
     map, zip, range, long, lrange, lmap, lzip,
-    OrderedDict, u, StringIO, string_types,
-    is_platform_windows
+    OrderedDict, u, StringIO, is_platform_windows
 )
 from pandas import compat
 
@@ -33,8 +32,7 @@
 import pandas.core.datetools as datetools
 from pandas import (DataFrame, Index, Series, Panel, notnull, isnull,
                     MultiIndex, DatetimeIndex, Timestamp, date_range,
-                    read_csv, timedelta_range, Timedelta, CategoricalIndex,
-                    option_context, period_range)
+                    read_csv, timedelta_range, Timedelta, option_context, period_range)
 from pandas.core.dtypes import DatetimeTZDtype
 import pandas as pd
 from pandas.parser import CParserError
@@ -2239,7 +2237,6 @@ class TestDataFrame(tm.TestCase, CheckIndexing,
     _multiprocess_can_split_ = True
 
     def setUp(self):
-        import warnings
 
         self.frame = _frame.copy()
         self.frame2 = _frame2.copy()
@@ -3568,6 +3565,20 @@ def test_constructor_tuples(self):
         expected = DataFrame({'A': Series([(1, 2), (3, 4)])})
         assert_frame_equal(result, expected)
 
+    def test_constructor_namedtuples(self):
+        # GH11181
+        from collections import namedtuple
+        named_tuple = namedtuple("Pandas", list('ab'))
+        tuples = [named_tuple(1, 3), named_tuple(2, 4)]
+        expected = DataFrame({'a': [1, 2], 'b': [3, 4]})
+        result = DataFrame(tuples)
+        assert_frame_equal(result, expected)
+
+        # with columns
+        expected = DataFrame({'y': [1, 2], 'z': [3, 4]})
+        result = DataFrame(tuples, columns=['y', 'z'])
+        assert_frame_equal(result, expected)
+
     def test_constructor_orient(self):
         data_dict = self.mixed_frame.T._series
         recons = DataFrame.from_dict(data_dict, orient='index')
@@ -4418,7 +4429,7 @@ def test_timedeltas(self):
 
     def test_operators_timedelta64(self):
 
-        from datetime import datetime, timedelta
+        from datetime import timedelta
         df = DataFrame(dict(A = date_range('2012-1-1', periods=3, freq='D'),
                             B = date_range('2012-1-2', periods=3, freq='D'),
                             C = Timestamp('20120101')-timedelta(minutes=5,seconds=5)))
@@ -9645,7 +9656,6 @@ def test_replace_mixed(self):
         assert_frame_equal(result,expected)
 
         # test case from
-        from pandas.util.testing import makeCustomDataframe as mkdf
         df = DataFrame({'A' : Series([3,0],dtype='int64'), 'B' : Series([0,3],dtype='int64') })
         result = df.replace(3, df.mean().to_dict())
         expected = df.copy().astype('float64')
@@ -12227,7 +12237,6 @@ def test_sort_index_inplace(self):
         assert_frame_equal(df, expected)
 
     def test_sort_index_different_sortorder(self):
-        import random
         A = np.arange(20).repeat(5)
         B = np.tile(np.arange(5), 20)
 
@@ -13301,7 +13310,6 @@ def test_quantile(self):
 
     def test_quantile_axis_parameter(self):
         # GH 9543/9544
-        from numpy import percentile
 
         df = DataFrame({"A": [1, 2, 3], "B": [2, 3, 4]}, index=[1, 2, 3])
 
@@ -16093,8 +16101,6 @@ def test_query_doesnt_pickup_local(self):
         n = m = 10
         df = DataFrame(np.random.randint(m, size=(n, 3)), columns=list('abc'))
 
-        from numpy import sin
-
         # we don't pick up the local 'sin'
         with tm.assertRaises(UndefinedVariableError):
             df.query('sin > 5', engine=engine, parser=parser)
@@ -16392,7 +16398,6 @@ def setUpClass(cls):
         cls.frame = _frame.copy()
 
     def test_query_builtin(self):
-        from pandas.computation.engines import NumExprClobberingError
         engine, parser = self.engine, self.parser
 
         n = m = 10
@@ -16413,7 +16418,6 @@ def setUpClass(cls):
         cls.frame = _frame.copy()
 
     def test_query_builtin(self):
-        from pandas.computation.engines import NumExprClobberingError
         engine, parser = self.engine, self.parser
 
         n = m = 10