[arrow] branch master updated: ARROW-1575: [Python] Add tests for pyarrow.column factory function

[we...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

wesm pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow.git


The following commit(s) were added to refs/heads/master by this push:
     new 9f9dc5b  ARROW-1575: [Python] Add tests for pyarrow.column factory function
9f9dc5b is described below

commit 9f9dc5b7025744458e50713fa460803bf52f5d33
Author: Wes McKinney <we...@twosigma.com>
AuthorDate: Sat Nov 18 16:25:56 2017 -0500

    ARROW-1575: [Python] Add tests for pyarrow.column factory function
    
    Author: Wes McKinney <we...@twosigma.com>
    
    Closes #1329 from wesm/ARROW-1575 and squashes the following commits:
    
    d9f14a12 [Wes McKinney] Add tests for pyarrow.column factory function
---
 python/pyarrow/table.pxi           |  9 +++++
 python/pyarrow/tests/test_table.py | 79 ++++++++++++++++++++++----------------
 2 files changed, 55 insertions(+), 33 deletions(-)

diff --git a/python/pyarrow/table.pxi b/python/pyarrow/table.pxi
index 1a9d23d..591f329 100644
--- a/python/pyarrow/table.pxi
+++ b/python/pyarrow/table.pxi
@@ -166,6 +166,15 @@ def chunked_array(arrays, type=None):
 def column(object field_or_name, arr):
     """
     Create Column object from field/string and array-like data
+
+    Parameters
+    ----------
+    field_or_name : string or Field
+    arr : Array, list of Arrays, or ChunkedArray
+
+    Returns
+    -------
+    column : Column
     """
     cdef:
         Field boxed_field
diff --git a/python/pyarrow/tests/test_table.py b/python/pyarrow/tests/test_table.py
index 4282224..cd05fb8 100644
--- a/python/pyarrow/tests/test_table.py
+++ b/python/pyarrow/tests/test_table.py
@@ -21,42 +21,55 @@ from pandas.util.testing import assert_frame_equal
 import pandas as pd
 import pytest
 
-from pyarrow.compat import unittest
 import pyarrow as pa
 
 
-class TestColumn(unittest.TestCase):
-
-    def test_basics(self):
-        data = [
-            pa.array([-10, -5, 0, 5, 10])
-        ]
-        table = pa.Table.from_arrays(data, names=['a'])
-        column = table.column(0)
-        assert column.name == 'a'
-        assert column.length() == 5
-        assert len(column) == 5
-        assert column.shape == (5,)
-        assert column.to_pylist() == [-10, -5, 0, 5, 10]
-
-    def test_from_array(self):
-        arr = pa.array([0, 1, 2, 3, 4])
-
-        col1 = pa.Column.from_array('foo', arr)
-        col2 = pa.Column.from_array(pa.field('foo', arr.type), arr)
-
-        assert col1.equals(col2)
-
-    def test_pandas(self):
-        data = [
-            pa.array([-10, -5, 0, 5, 10])
-        ]
-        table = pa.Table.from_arrays(data, names=['a'])
-        column = table.column(0)
-        series = column.to_pandas()
-        assert series.name == 'a'
-        assert series.shape == (5,)
-        assert series.iloc[0] == -10
+def test_column_basics():
+    data = [
+        pa.array([-10, -5, 0, 5, 10])
+    ]
+    table = pa.Table.from_arrays(data, names=['a'])
+    column = table.column(0)
+    assert column.name == 'a'
+    assert column.length() == 5
+    assert len(column) == 5
+    assert column.shape == (5,)
+    assert column.to_pylist() == [-10, -5, 0, 5, 10]
+
+
+def test_column_factory_function():
+    # ARROW-1575
+    arr = pa.array([0, 1, 2, 3, 4])
+    arr2 = pa.array([5, 6, 7, 8])
+
+    col1 = pa.Column.from_array('foo', arr)
+    col2 = pa.Column.from_array(pa.field('foo', arr.type), arr)
+
+    assert col1.equals(col2)
+
+    col3 = pa.column('foo', [arr, arr2])
+    chunked_arr = pa.chunked_array([arr, arr2])
+    col4 = pa.column('foo', chunked_arr)
+    assert col3.equals(col4)
+
+    col5 = pa.column('foo', arr.to_pandas())
+    assert col5.equals(pa.column('foo', arr))
+
+    # Type mismatch
+    with pytest.raises(ValueError):
+        pa.Column.from_array(pa.field('foo', pa.string()), arr)
+
+
+def test_column_to_pandas():
+    data = [
+        pa.array([-10, -5, 0, 5, 10])
+    ]
+    table = pa.Table.from_arrays(data, names=['a'])
+    column = table.column(0)
+    series = column.to_pandas()
+    assert series.name == 'a'
+    assert series.shape == (5,)
+    assert series.iloc[0] == -10
 
 
 def test_recordbatch_basics():

-- 
To stop receiving notification emails like this one, please contact
['"commits@arrow.apache.org" <co...@arrow.apache.org>'].