REF: rename factor.py to categorical.py close #1468

Author: wesm

pandas/core/api.py

@@ -6,7 +6,7 @@
 from pandas.core.algorithms import factorize, match, unique, value_counts
 
 from pandas.core.common import isnull, notnull, save, load
-from pandas.core.factor import Categorical, Factor
+from pandas.core.categorical import Categorical, Factor
 from pandas.core.format import (set_printoptions, reset_printoptions,
                                 set_eng_float_format)
 from pandas.core.index import Index, Int64Index, MultiIndex

pandas/core/factor.py renamed to pandas/core/categorical.py

@@ -3,7 +3,7 @@
 import numpy as np
 
 from pandas.core.algorithms import unique
-from pandas.core.factor import Factor
+from pandas.core.categorical import Factor
 from pandas.core.frame import DataFrame
 from pandas.core.generic import NDFrame
 from pandas.core.index import Index, MultiIndex, _ensure_index

pandas/core/groupby.py

@@ -1458,7 +1458,7 @@ def from_arrays(cls, arrays, sortorder=None, names=None):
         -------
         index : MultiIndex
         """
-        from pandas.core.factor import Factor
+        from pandas.core.categorical import Factor
 
         if len(arrays) == 1:
             name = None if names is None else names[0]

pandas/core/index.py

@@ -9,7 +9,7 @@
 
 from pandas.core.common import (PandasError, _mut_exclusive,
                                 _try_sort, _default_index, _infer_dtype)
-from pandas.core.factor import Factor
+from pandas.core.categorical import Factor
 from pandas.core.index import (Index, MultiIndex, _ensure_index,
                                _get_combined_index)
 from pandas.core.indexing import _NDFrameIndexer, _maybe_droplevels

pandas/core/panel.py

@@ -18,7 +18,7 @@
 from pandas.core.common import adjoin
 from pandas.core.algorithms import match, unique
 
-from pandas.core.factor import Factor
+from pandas.core.categorical import Factor
 from pandas.core.common import _asarray_tuplesafe
 from pandas.core.internals import BlockManager, make_block
 from pandas.core.reshape import block2d_to_block3d

pandas/io/pytables.py

@@ -7,7 +7,7 @@
 import numpy as np
 
 from pandas.core.api import value_counts
-from pandas.core.factor import Categorical
+from pandas.core.categorical import Categorical
 from pandas.core.index import Index, Int64Index, MultiIndex
 from pandas.util.testing import assert_almost_equal
 import pandas.core.common as com

pandas/tests/test_factor.py

@@ -7,7 +7,7 @@
 from pandas import bdate_range
 from pandas.core.index import Index, MultiIndex
 from pandas.core.common import rands
-from pandas.core.api import Factor, DataFrame
+from pandas.core.api import Categorical, DataFrame
 from pandas.core.groupby import GroupByError
 from pandas.core.series import Series
 from pandas.util.testing import (assert_panel_equal, assert_frame_equal,
@@ -1900,27 +1900,27 @@ def test_no_dummy_key_names(self):
                                   self.df['B'].values]).sum()
         self.assert_(result.index.names == [None, None])
 
-    def test_groupby_factor(self):
+    def test_groupby_categorical(self):
         levels = ['foo', 'bar', 'baz', 'qux']
         labels = np.random.randint(0, 4, size=100)
 
-        factor = Factor(labels, levels, name='myfactor')
+        cats = Categorical(labels, levels, name='myfactor')
 
         data = DataFrame(np.random.randn(100, 4))
 
-        result = data.groupby(factor).mean()
+        result = data.groupby(cats).mean()
 
-        expected = data.groupby(np.asarray(factor)).mean()
+        expected = data.groupby(np.asarray(cats)).mean()
         expected = expected.reindex(levels)
 
         assert_frame_equal(result, expected)
-        self.assert_(result.index.name == factor.name)
+        self.assert_(result.index.name == cats.name)
 
-        grouped = data.groupby(factor)
+        grouped = data.groupby(cats)
         desc_result = grouped.describe()
 
-        idx = factor.labels.argsort()
-        ord_labels = np.asarray(factor).take(idx)
+        idx = cats.labels.argsort()
+        ord_labels = np.asarray(cats).take(idx)
         ord_data = data.take(idx)
         expected = ord_data.groupby(ord_labels, sort=False).describe()
         assert_frame_equal(desc_result, expected)

pandas/tests/test_groupby.py

@@ -9,7 +9,7 @@
 import numpy as np
 from numpy.testing import assert_array_equal
 
-from pandas.core.factor import Factor
+from pandas.core.categorical import Factor
 from pandas.core.index import Index, Int64Index, MultiIndex
 from pandas.util.testing import assert_almost_equal
 from pandas.util import py3compat

pandas/tests/test_index.py

@@ -4,7 +4,7 @@
 
 import numpy as np
 
-from pandas.core.factor import Factor
+from pandas.core.categorical import Factor
 from pandas.core.frame import DataFrame, _merge_doc
 from pandas.core.generic import NDFrame
 from pandas.core.groupby import get_group_index

pandas/tools/merge.py

@@ -3,7 +3,7 @@
 """
 
 from pandas.core.api import DataFrame, Series
-from pandas.core.factor import Factor
+from pandas.core.categorical import Categorical
 import pandas.core.algorithms as algos
 import pandas.core.common as com
 import pandas.core.nanops as nanops
@@ -181,7 +181,7 @@ def _bins_to_cuts(x, bins, right=True, labels=None, retbins=False,
         if has_nas:
             np.putmask(ids, mask, 0)
 
-        fac = Factor(ids - 1, levels, name=name)
+        fac = Categorical(ids - 1, levels, name=name)
     else:
         fac = ids - 1
         if has_nas: