Merge branch 'master' of github.com:pydata/pandas into fix-index-dict-assign

cpcloud · cpcloud · commit 216f051e6c42 · 2015-04-14T09:17:01.000-04:00
diff --git a/doc/source/whatsnew/v0.16.1.txt b/doc/source/whatsnew/v0.16.1.txt
@@ -95,6 +95,7 @@ Bug Fixes
 - Fixed bug (:issue:`9542`) where labels did not appear properly in legend of ``DataFrame.plot()``. Passing ``label=`` args also now works, and series indices are no longer mutated.
 - Bug in json serialization when frame has length zero.(:issue:`9805`)
 - Bug in `read_csv` where missing trailing delimiters would cause segfault. (:issue:`5664`)
+- Bug in retaining index name on appending (:issue:`9862`)
 
 
 - Bug in ``scatter_matrix`` draws unexpected axis ticklabels (:issue:`5662`)
@@ -106,6 +107,8 @@ Bug Fixes
 
 - Bug in ``equals`` causing false negatives when block order differed (:issue:`9330`)
 
+- Bug in ``read_sql_table`` error when reading postgres table with timezone (:issue:`7139`)
+
 - Bug in ``DataFrame`` slicing may not retain metadata (:issue:`9776`)
 - Bug where ``TimdeltaIndex`` were not properly serialized in fixed ``HDFStore`` (:issue:`9635`)
 
@@ -134,3 +137,5 @@ Bug Fixes
 - Bug in unequal comparisons between categorical data and a scalar, which was not in the categories (e.g. ``Series(Categorical(list("abc"), ordered=True)) > "d"``. This returned ``False`` for all elements, but now raises a ``TypeError``. Equality comparisons also now return ``False`` for ``==`` and ``True`` for ``!=``. (:issue:`9848`)
 
 - Bug in DataFrame ``__setitem__`` when right hand side is a dictionary (:issue:`9874`)
+
+- Bug in ``MultiIndex.sortlevel()`` results in unicode level name breaks (:issue:`9875`)
diff --git a/pandas/core/index.py b/pandas/core/index.py
@@ -976,7 +976,9 @@ def append(self, other):
             to_concat.append(other)
 
         for obj in to_concat:
-            if isinstance(obj, Index) and obj.name != name:
+            if (isinstance(obj, Index) and
+                obj.name != name and
+                obj.name is not None):
                 name = None
                 break
 
@@ -4023,7 +4025,7 @@ def sortlevel(self, level=0, ascending=True, sort_remaining=True):
         labels = list(self.labels)
         shape = list(self.levshape)
 
-        if isinstance(level, (str, int)):
+        if isinstance(level, (compat.string_types, int)):
             level = [level]
         level = [self._get_level_number(lev) for lev in level]
 
diff --git a/pandas/io/sql.py b/pandas/io/sql.py
@@ -83,14 +83,14 @@ def _handle_date_column(col, format=None):
         return to_datetime(col, **format)
     else:
         if format in ['D', 's', 'ms', 'us', 'ns']:
-            return to_datetime(col, coerce=True, unit=format)
+            return to_datetime(col, coerce=True, unit=format, utc=True)
         elif (issubclass(col.dtype.type, np.floating)
                 or issubclass(col.dtype.type, np.integer)):
             # parse dates as timestamp
             format = 's' if format is None else format
-            return to_datetime(col, coerce=True, unit=format)
+            return to_datetime(col, coerce=True, unit=format, utc=True)
         else:
-            return to_datetime(col, coerce=True, format=format)
+            return to_datetime(col, coerce=True, format=format, utc=True)
 
 
 def _parse_date_columns(data_frame, parse_dates):
@@ -318,6 +318,10 @@ def read_sql_table(table_name, con, schema=None, index_col=None,
     -------
     DataFrame
 
+    Notes
+    -----
+    Any datetime values with time zone information will be converted to UTC
+
     See also
     --------
     read_sql_query : Read SQL query into a DataFrame.
@@ -390,6 +394,11 @@ def read_sql_query(sql, con, index_col=None, coerce_float=True, params=None,
     -------
     DataFrame
 
+    Notes
+    -----
+    Any datetime values with time zone information parsed via the `parse_dates`
+    parameter will be converted to UTC
+
     See also
     --------
     read_sql_table : Read SQL database table into a DataFrame
@@ -451,7 +460,8 @@ def read_sql(sql, con, index_col=None, coerce_float=True, params=None,
     This function is a convenience wrapper around ``read_sql_table`` and
     ``read_sql_query`` (and for backward compatibility) and will delegate
     to the specific function depending on the provided input (database
-    table name or sql query).
+    table name or sql query).  The delegated function might have more specific
+    notes about their functionality not listed here.
 
     See also
     --------
diff --git a/pandas/io/tests/test_packers.py b/pandas/io/tests/test_packers.py
@@ -476,6 +476,10 @@ def test_compression_zlib(self):
             assert_frame_equal(self.frame[k], i_rec[k])
 
     def test_compression_blosc(self):
+        try:
+            import blosc
+        except ImportError:
+            raise nose.SkipTest('no blosc')
         i_rec = self.encode_decode(self.frame, compress='blosc')
         for k in self.frame.keys():
             assert_frame_equal(self.frame[k], i_rec[k])
diff --git a/pandas/io/tests/test_sql.py b/pandas/io/tests/test_sql.py
@@ -29,7 +29,7 @@
 from datetime import datetime, date, time
 
 from pandas import DataFrame, Series, Index, MultiIndex, isnull, concat
-from pandas import date_range, to_datetime, to_timedelta
+from pandas import date_range, to_datetime, to_timedelta, Timestamp
 import pandas.compat as compat
 from pandas.compat import StringIO, range, lrange, string_types
 from pandas.core.datetools import format as date_format
@@ -100,6 +100,7 @@
         'postgresql': """CREATE TABLE types_test_data (
                     "TextCol" TEXT,
                     "DateCol" TIMESTAMP,
+                    "DateColWithTz" TIMESTAMP WITH TIME ZONE,
                     "IntDateCol" INTEGER,
                     "FloatCol" DOUBLE PRECISION,
                     "IntCol" INTEGER,
@@ -109,18 +110,36 @@
                 )"""
     },
     'insert_test_types': {
-        'sqlite': """
+        'sqlite': {
+            'query': """
                 INSERT INTO types_test_data
                 VALUES(?, ?, ?, ?, ?, ?, ?, ?)
                 """,
-        'mysql': """
+            'fields': (
+                'TextCol', 'DateCol', 'IntDateCol', 'FloatCol',
+                'IntCol', 'BoolCol', 'IntColWithNull', 'BoolColWithNull'
+            )
+        },
+        'mysql': {
+            'query': """
                 INSERT INTO types_test_data
                 VALUES("%s", %s, %s, %s, %s, %s, %s, %s)
                 """,
-        'postgresql': """
+            'fields': (
+                'TextCol', 'DateCol', 'IntDateCol', 'FloatCol',
+                'IntCol', 'BoolCol', 'IntColWithNull', 'BoolColWithNull'
+            )
+        },
+        'postgresql': {
+            'query': """
                 INSERT INTO types_test_data
-                VALUES(%s, %s, %s, %s, %s, %s, %s, %s)
-                """
+                VALUES(%s, %s, %s, %s, %s, %s, %s, %s, %s)
+                """,
+            'fields': (
+                'TextCol', 'DateCol', 'DateColWithTz', 'IntDateCol', 'FloatCol',
+                'IntCol', 'BoolCol', 'IntColWithNull', 'BoolColWithNull'
+            )
+        },
     },
     'read_parameters': {
         'sqlite': "SELECT * FROM iris WHERE Name=? AND SepalLength=?",
@@ -218,11 +237,36 @@ def _load_raw_sql(self):
         self._get_exec().execute(SQL_STRINGS['create_test_types'][self.flavor])
         ins = SQL_STRINGS['insert_test_types'][self.flavor]
 
-        data = [(
-            'first', '2000-01-03 00:00:00', 535852800, 10.10, 1, False, 1, False),
-            ('first', '2000-01-04 00:00:00', 1356998400, 10.10, 1, False, None, None)]
+        data = [
+            {
+                'TextCol': 'first',
+                'DateCol': '2000-01-03 00:00:00',
+                'DateColWithTz': '2000-01-01 00:00:00-08:00',
+                'IntDateCol': 535852800,
+                'FloatCol': 10.10,
+                'IntCol': 1,
+                'BoolCol': False,
+                'IntColWithNull': 1,
+                'BoolColWithNull': False,
+            },
+            {
+                'TextCol': 'first',
+                'DateCol': '2000-01-04 00:00:00',
+                'DateColWithTz': '2000-06-01 00:00:00-07:00',
+                'IntDateCol': 1356998400,
+                'FloatCol': 10.10,
+                'IntCol': 1,
+                'BoolCol': False,
+                'IntColWithNull': None,
+                'BoolColWithNull': None,
+            },
+        ]
+
         for d in data:
-            self._get_exec().execute(ins, d)
+            self._get_exec().execute(
+                ins['query'],
+                [d[field] for field in ins['fields']]
+            )
 
     def _count_rows(self, table_name):
         result = self._get_exec().execute(
@@ -1512,6 +1556,19 @@ def test_schema_support(self):
         res2 = pdsql.read_table('test_schema_other2')
         tm.assert_frame_equal(res1, res2)
 
+    def test_datetime_with_time_zone(self):
+        # Test to see if we read the date column with timezones that
+        # the timezone information is converted to utc and into a
+        # np.datetime64 (GH #7139)
+        df = sql.read_sql_table("types_test_data", self.conn)
+        self.assertTrue(issubclass(df.DateColWithTz.dtype.type, np.datetime64),
+                        "DateColWithTz loaded with incorrect type")
+
+        # "2000-01-01 00:00:00-08:00" should convert to "2000-01-01 08:00:00"
+        self.assertEqual(df.DateColWithTz[0], Timestamp('2000-01-01 08:00:00'))
+
+        # "2000-06-01 00:00:00-07:00" should convert to "2000-06-01 07:00:00"
+        self.assertEqual(df.DateColWithTz[1], Timestamp('2000-06-01 07:00:00'))
 
 #------------------------------------------------------------------------------
 #--- Test Sqlite / MySQL fallback
diff --git a/pandas/tests/test_frame.py b/pandas/tests/test_frame.py
@@ -16,7 +16,7 @@
 
 from pandas.compat import(
     map, zip, range, long, lrange, lmap, lzip,
-    OrderedDict, u, StringIO
+    OrderedDict, u, StringIO, string_types
 )
 from pandas import compat
 
@@ -12428,6 +12428,30 @@ def test_unstack_bool(self):
                                                        ['c', 'l']]))
         assert_frame_equal(rs, xp)
 
+    def test_unstack_level_binding(self):
+        # GH9856
+        mi = pd.MultiIndex(
+                levels=[[u'foo', u'bar'], [u'one', u'two'], [u'a', u'b']],
+                labels=[[0, 0, 1, 1], [0, 1, 0, 1], [1, 0, 1, 0]],
+                names=[u'first', u'second', u'third'])
+        s = pd.Series(0, index=mi)
+        result = s.unstack([1, 2]).stack(0)
+
+        expected_mi = pd.MultiIndex(
+                        levels=[['foo', 'bar'], ['one', 'two']],
+                        labels=[[0, 0, 1, 1], [0, 1, 0, 1]],
+                        names=['first', 'second'])
+
+        expected = pd.DataFrame(np.array([[np.nan, 0],
+                                          [0, np.nan],
+                                          [np.nan, 0],
+                                          [0, np.nan]],
+                                         dtype=np.float64),
+                                index=expected_mi,
+                                columns=pd.Index(['a', 'b'], name='third'))
+
+        self.assert_frame_equal(result, expected)
+
     def test_unstack_to_series(self):
         # check reversibility
         data = self.frame.unstack()
diff --git a/pandas/tests/test_index.py b/pandas/tests/test_index.py
@@ -4075,6 +4075,19 @@ def test_groupby(self):
         exp = dict((key, [key]) for key in self.index)
         tm.assert_dict_equal(groups, exp)
 
+    def test_index_name_retained(self):
+        # GH9857
+        result = pd.DataFrame({'x': [1, 2, 6],
+                               'y': [2, 2, 8],
+                               'z': [-5, 0, 5]})
+        result = result.set_index('z')
+        result.loc[10] = [9, 10]
+        df_expected = pd.DataFrame({'x': [1, 2, 6, 9],
+                                    'y': [2, 2, 8, 10],
+                                    'z': [-5, 0, 5, 10]})
+        df_expected = df_expected.set_index('z')
+        tm.assert_frame_equal(result, df_expected)
+
 
 def test_get_combined_index():
     from pandas.core.index import _get_combined_index
