CLN: reorganize index.py, test_index.py

Split apart these two very large modules and created a new
`pandas.indexes` subpackage. It would be nice to move all the index
class code from `pandas.tseries` there in a followup patch.

Author: Wes McKinney <[email protected]>

Closes #12124 from wesm/reorg/indexes and squashes the following commits:

a2e6ec6 [Wes McKinney] Fix Python 2 unicode issue
d87eb63 [Wes McKinney] Add TODO about private names
9b10283 [Wes McKinney] Address comments
a1d4d07 [Wes McKinney] Fix Python 2 issues
49da0e4 [Wes McKinney] Fix pickling
f464384 [Wes McKinney] Reorganize pandas/tests/test_index.py
f73c17b [Wes McKinney] Remove float.py
9cca3c5 [Wes McKinney] Split pandas.core.index into a pandas/indexes subpackage

Author: wesm

pandas/core/index.py

@@ -0,0 +1,118 @@
+from pandas.indexes.base import (Index, _new_Index,  # noqa
+                                 _ensure_index, _get_na_value,
+                                 InvalidIndexError)
+from pandas.indexes.category import CategoricalIndex  # noqa
+from pandas.indexes.multi import MultiIndex  # noqa
+from pandas.indexes.numeric import (NumericIndex, Float64Index,  # noqa
+                                    Int64Index)
+from pandas.indexes.range import RangeIndex  # noqa
+
+import pandas.core.common as com
+import pandas.lib as lib
+
+# TODO: there are many places that rely on these private methods existing in
+# pandas.core.index
+__all__ = ['Index', 'MultiIndex', 'NumericIndex', 'Float64Index', 'Int64Index',
+           'CategoricalIndex', 'RangeIndex',
+           'InvalidIndexError',
+           '_new_Index',
+           '_ensure_index', '_get_na_value', '_get_combined_index',
+           '_get_distinct_indexes', '_union_indexes',
+           '_get_consensus_names',
+           '_all_indexes_same']
+
+
+def _get_combined_index(indexes, intersect=False):
+    # TODO: handle index names!
+    indexes = _get_distinct_indexes(indexes)
+    if len(indexes) == 0:
+        return Index([])
+    if len(indexes) == 1:
+        return indexes[0]
+    if intersect:
+        index = indexes[0]
+        for other in indexes[1:]:
+            index = index.intersection(other)
+        return index
+    union = _union_indexes(indexes)
+    return _ensure_index(union)
+
+
+def _get_distinct_indexes(indexes):
+    return list(dict((id(x), x) for x in indexes).values())
+
+
+def _union_indexes(indexes):
+    if len(indexes) == 0:
+        raise AssertionError('Must have at least 1 Index to union')
+    if len(indexes) == 1:
+        result = indexes[0]
+        if isinstance(result, list):
+            result = Index(sorted(result))
+        return result
+
+    indexes, kind = _sanitize_and_check(indexes)
+
+    def _unique_indices(inds):
+        def conv(i):
+            if isinstance(i, Index):
+                i = i.tolist()
+            return i
+
+        return Index(lib.fast_unique_multiple_list([conv(i) for i in inds]))
+
+    if kind == 'special':
+        result = indexes[0]
+
+        if hasattr(result, 'union_many'):
+            return result.union_many(indexes[1:])
+        else:
+            for other in indexes[1:]:
+                result = result.union(other)
+            return result
+    elif kind == 'array':
+        index = indexes[0]
+        for other in indexes[1:]:
+            if not index.equals(other):
+                return _unique_indices(indexes)
+
+        return index
+    else:
+        return _unique_indices(indexes)
+
+
+def _sanitize_and_check(indexes):
+    kinds = list(set([type(index) for index in indexes]))
+
+    if list in kinds:
+        if len(kinds) > 1:
+            indexes = [Index(com._try_sort(x))
+                       if not isinstance(x, Index) else
+                       x for x in indexes]
+            kinds.remove(list)
+        else:
+            return indexes, 'list'
+
+    if len(kinds) > 1 or Index not in kinds:
+        return indexes, 'special'
+    else:
+        return indexes, 'array'
+
+
+def _get_consensus_names(indexes):
+
+    # find the non-none names, need to tupleify to make
+    # the set hashable, then reverse on return
+    consensus_names = set([tuple(i.names) for i in indexes
+                           if all(n is not None for n in i.names)])
+    if len(consensus_names) == 1:
+        return list(list(consensus_names)[0])
+    return [None] * indexes[0].nlevels
+
+
+def _all_indexes_same(indexes):
+    first = indexes[0]
+    for index in indexes[1:]:
+        if not first.equals(index):
+            return False
+    return True