Merge commit 'v0.15.1-125-ge463818' into debian

* commit 'v0.15.1-125-ge463818':
  TST: Moved test functions to module level. pandas-dev#8023
  TST: skip on < mpl 1.3.1 (GH8947)
  preserve left frame order in left merge
  BLD: run slow tests on new optional build 2.7_SLOW using current versions of everything BLD: run graphics tests on 2.7_LOCALE using old matplotlib
  BUG: Fixed font size (set it on both x and y axis). pandas-dev#8765
  BUG: Resample across multiple days
  TST: 32-bit construction fix re GH8907
  Categorical: let unique only return used categories
  BUG: fix doctests in pandas.core.common
  BUG: DatetimeIndex with time as key

Author: yarikoptic

.travis.yml

@@ -38,6 +38,13 @@ matrix:
       - BUILD_TYPE=conda
       - JOB_NAME: "27_nslow"
       - DOC_BUILD=true # if rst files were changed, build docs in parallel with tests
+    - python: 2.7
+      env:
+      - NOSE_ARGS="slow and not network and not disabled"
+      - FULL_DEPS=true
+      - JOB_TAG=_SLOW
+      - BUILD_TYPE=conda
+      - JOB_NAME: "27_slow"
     - python: 3.3
       env:
       - NOSE_ARGS="not slow and not disabled"
@@ -76,6 +83,13 @@ matrix:
         - CLIPBOARD_GUI=qt4
         - BUILD_TYPE=pydata
         - JOB_NAME: "32_nslow"
+      - python: 2.7
+        env:
+        - NOSE_ARGS="slow and not network and not disabled"
+        - FULL_DEPS=true
+        - JOB_TAG=_SLOW
+        - BUILD_TYPE=conda
+        - JOB_NAME: "27_slow"
       - python: 2.7
         env:
         - EXPERIMENTAL=true

ci/requirements-2.7_LOCALE.txt

@@ -7,7 +7,7 @@ xlrd=0.9.2
 numpy=1.7.1
 cython=0.19.1
 bottleneck=0.8.0
-matplotlib=1.3.0
+matplotlib=1.2.1
 patsy=0.1.0
 sqlalchemy=0.8.1
 html5lib=1.0b2

ci/requirements-2.7_SLOW.txt

@@ -0,0 +1,25 @@
+dateutil
+pytz
+numpy
+cython
+matplotlib
+scipy
+patsy
+statsmodels
+xlwt
+openpyxl
+xlsxwriter
+xlrd
+numexpr
+pytables
+sqlalchemy
+lxml
+boto
+bottleneck
+psycopg2
+pymysql
+html5lib
+beautiful-soup
+httplib2
+python-gflags
+google-api-python-client

doc/source/whatsnew/v0.15.2.txt

@@ -42,6 +42,9 @@ API changes
 
 - Bug in concat of Series with ``category`` dtype which were coercing to ``object``. (:issue:`8641`)
 
+- Bug in unique of Series with ``category`` dtype, which returned all categories regardless
+  whether they were "used" or not (see :issue:`8559` for the discussion).
+
 - ``Series.all`` and ``Series.any`` now support the ``level`` and ``skipna`` parameters. ``Series.all``, ``Series.any``, ``Index.all``, and ``Index.any`` no longer support the ``out`` and ``keepdims`` parameters, which existed for compatibility with ndarray. Various index types no longer support the ``all`` and ``any`` aggregation functions and will now raise ``TypeError``. (:issue:`8302`):
 
   .. ipython:: python
@@ -97,7 +100,10 @@ Bug Fixes
 - ``sql_schema`` now generates dialect appropriate ``CREATE TABLE`` statements (:issue:`8697`)
 - ``slice`` string method now takes step into account (:issue:`8754`)
 - Bug in ``BlockManager`` where setting values with different type would break block integrity (:issue:`8850`)
+- Bug in ``DatetimeIndex`` when using ``time`` object as key (:issue:`8667`)
+- Bug in ``merge`` where ``how='left'`` and ``sort=False`` would not preserve left frame order (:issue:`7331`)
 - Fix negative step support for label-based slices (:issue:`8753`)
+- Fix: The font size was only set on x axis if vertical or the y axis if horizontal. (:issue:`8765`)
 
   Old behavior:
 
@@ -145,7 +151,8 @@ Bug Fixes
 - BUG: Option context applies on __enter__ (:issue:`8514`)
 
 
-
+- Bug in resample that causes a ValueError when resampling across multiple days
+  and the last offset is not calculated from the start of the range (:issue:`8683`)
 
 
 - Bug in `pd.infer_freq`/`DataFrame.inferred_freq` that prevented proper sub-daily frequency inference

pandas/core/categorical.py

@@ -1326,13 +1326,18 @@ def unique(self):
         """
         Return the unique values.
 
-        This includes all categories, even if one or more is unused.
+        Unused categories are NOT returned.
 
         Returns
         -------
         unique values : array
         """
-        return np.asarray(self.categories)
+        unique_codes = np.unique(self.codes)
+        # for compatibility with normal unique, which has nan last
+        if unique_codes[0] == -1:
+            unique_codes[0:-1] = unique_codes[1:]
+            unique_codes[-1] = -1
+        return take_1d(self.categories.values, unique_codes)
 
     def equals(self, other):
         """

pandas/core/common.py

@@ -404,9 +404,13 @@ def array_equivalent(left, right, strict_nan=False):
 
     Examples
     --------
-    >>> array_equivalent(np.array([1, 2, nan]), np.array([1, 2, nan]))
+    >>> array_equivalent(
+    ...     np.array([1, 2, np.nan]),
+    ...     np.array([1, 2, np.nan]))
     True
-    >>> array_equivalent(np.array([1, nan, 2]), np.array([1, 2, nan]))
+    >>> array_equivalent(
+    ...     np.array([1, np.nan, 2]),
+    ...     np.array([1, 2, np.nan]))
     False
     """
 
@@ -2171,8 +2175,8 @@ def iterpairs(seq):
 
     Examples
     --------
-    >>> iterpairs([1, 2, 3, 4])
-    [(1, 2), (2, 3), (3, 4)
+    >>> list(iterpairs([1, 2, 3, 4]))
+    [(1, 2), (2, 3), (3, 4)]
     """
     # input may not be sliceable
     seq_it = iter(seq)

pandas/index.pyx

@@ -545,8 +545,14 @@ cdef class DatetimeEngine(Int64Engine):
                 val = _to_i8(val)
                 return self._get_loc_duplicates(val)
             values = self._get_index_values()
-            conv = _to_i8(val)
-            loc = values.searchsorted(conv, side='left')
+
+            try:
+                conv = _to_i8(val)
+                loc = values.searchsorted(conv, side='left')
+            except TypeError:
+                self._date_check_type(val)
+                raise KeyError(val)
+
             if loc == len(values) or util.get_value_at(values, loc) != conv:
                 raise KeyError(val)
             return loc

pandas/tests/test_categorical.py

@@ -769,11 +769,17 @@ def test_min_max(self):
         self.assertEqual(_max, 1)
 
     def test_unique(self):
-        cat = Categorical(["a","b","c","d"])
-        exp = np.asarray(["a","b","c","d"])
+        cat = Categorical(["a","b"])
+        exp = np.asarray(["a","b"])
         res = cat.unique()
         self.assert_numpy_array_equal(res, exp)
-        self.assertEqual(type(res), type(exp))
+        cat = Categorical(["a","b","a","a"], categories=["a","b","c"])
+        res = cat.unique()
+        self.assert_numpy_array_equal(res, exp)
+        cat = Categorical(["a","b","a", np.nan], categories=["a","b","c"])
+        res = cat.unique()
+        exp = np.asarray(["a","b", np.nan], dtype=object)
+        self.assert_numpy_array_equal(res, exp)
 
     def test_mode(self):
         s = Categorical([1,1,2,4,5,5,5], categories=[5,4,3,2,1], ordered=True)

pandas/tests/test_graphics.py

@@ -77,6 +77,9 @@ def setUp(self):
         else:
             self.bp_n_objects = 8
 
+        self.mpl_le_1_2_1 = str(mpl.__version__) <= LooseVersion('1.2.1')
+        self.mpl_ge_1_3_1 = str(mpl.__version__) >= LooseVersion('1.3.1')
+
     def tearDown(self):
         tm.close()
 
@@ -443,7 +446,6 @@ def setUp(self):
         import matplotlib as mpl
         mpl.rcdefaults()
 
-        self.mpl_le_1_2_1 = str(mpl.__version__) <= LooseVersion('1.2.1')
         self.ts = tm.makeTimeSeries()
         self.ts.name = 'ts'
 
@@ -818,12 +820,13 @@ def test_hist_kwargs(self):
         self._check_text_labels(ax.yaxis.get_label(), 'Degree')
         tm.close()
 
-        ax = self.ts.plot(kind='hist', orientation='horizontal')
-        self._check_text_labels(ax.xaxis.get_label(), 'Degree')
-        tm.close()
+        if self.mpl_ge_1_3_1:
+            ax = self.ts.plot(kind='hist', orientation='horizontal')
+            self._check_text_labels(ax.xaxis.get_label(), 'Degree')
+            tm.close()
 
-        ax = self.ts.plot(kind='hist', align='left', stacked=True)
-        tm.close()
+            ax = self.ts.plot(kind='hist', align='left', stacked=True)
+            tm.close()
 
     @slow
     def test_hist_kde_color(self):
@@ -961,9 +964,6 @@ def setUp(self):
         import matplotlib as mpl
         mpl.rcdefaults()
 
-        self.mpl_le_1_2_1 = str(mpl.__version__) <= LooseVersion('1.2.1')
-        self.mpl_ge_1_3_1 = str(mpl.__version__) >= LooseVersion('1.3.1')
-
         self.tdf = tm.makeTimeDataFrame()
         self.hexbin_df = DataFrame({"A": np.random.uniform(size=20),
                                "B": np.random.uniform(size=20),
@@ -2141,31 +2141,33 @@ def test_hist_df_coord(self):
             self._check_box_coord(axes[2].patches, expected_y=np.array([0, 0, 0, 0, 0]),
                                   expected_h=np.array([6, 7, 8, 9, 10]))
 
-            # horizontal
-            ax = df.plot(kind='hist', bins=5, orientation='horizontal')
-            self._check_box_coord(ax.patches[:5], expected_x=np.array([0, 0, 0, 0, 0]),
-                                  expected_w=np.array([10, 9, 8, 7, 6]))
-            self._check_box_coord(ax.patches[5:10], expected_x=np.array([0, 0, 0, 0, 0]),
-                                  expected_w=np.array([8, 8, 8, 8, 8]))
-            self._check_box_coord(ax.patches[10:], expected_x=np.array([0, 0, 0, 0, 0]),
-                                  expected_w=np.array([6, 7, 8, 9, 10]))
-
-            ax = df.plot(kind='hist', bins=5, stacked=True, orientation='horizontal')
-            self._check_box_coord(ax.patches[:5], expected_x=np.array([0, 0, 0, 0, 0]),
-                                  expected_w=np.array([10, 9, 8, 7, 6]))
-            self._check_box_coord(ax.patches[5:10], expected_x=np.array([10, 9, 8, 7, 6]),
-                                  expected_w=np.array([8, 8, 8, 8, 8]))
-            self._check_box_coord(ax.patches[10:], expected_x=np.array([18, 17, 16, 15, 14]),
-                                  expected_w=np.array([6, 7, 8, 9, 10]))
-
-            axes = df.plot(kind='hist', bins=5, stacked=True,
-                           subplots=True, orientation='horizontal')
-            self._check_box_coord(axes[0].patches, expected_x=np.array([0, 0, 0, 0, 0]),
-                                  expected_w=np.array([10, 9, 8, 7, 6]))
-            self._check_box_coord(axes[1].patches, expected_x=np.array([0, 0, 0, 0, 0]),
-                                  expected_w=np.array([8, 8, 8, 8, 8]))
-            self._check_box_coord(axes[2].patches, expected_x=np.array([0, 0, 0, 0, 0]),
-                                  expected_w=np.array([6, 7, 8, 9, 10]))
+            if self.mpl_ge_1_3_1:
+
+                # horizontal
+                ax = df.plot(kind='hist', bins=5, orientation='horizontal')
+                self._check_box_coord(ax.patches[:5], expected_x=np.array([0, 0, 0, 0, 0]),
+                                      expected_w=np.array([10, 9, 8, 7, 6]))
+                self._check_box_coord(ax.patches[5:10], expected_x=np.array([0, 0, 0, 0, 0]),
+                                      expected_w=np.array([8, 8, 8, 8, 8]))
+                self._check_box_coord(ax.patches[10:], expected_x=np.array([0, 0, 0, 0, 0]),
+                                      expected_w=np.array([6, 7, 8, 9, 10]))
+
+                ax = df.plot(kind='hist', bins=5, stacked=True, orientation='horizontal')
+                self._check_box_coord(ax.patches[:5], expected_x=np.array([0, 0, 0, 0, 0]),
+                                      expected_w=np.array([10, 9, 8, 7, 6]))
+                self._check_box_coord(ax.patches[5:10], expected_x=np.array([10, 9, 8, 7, 6]),
+                                      expected_w=np.array([8, 8, 8, 8, 8]))
+                self._check_box_coord(ax.patches[10:], expected_x=np.array([18, 17, 16, 15, 14]),
+                                      expected_w=np.array([6, 7, 8, 9, 10]))
+
+                axes = df.plot(kind='hist', bins=5, stacked=True,
+                               subplots=True, orientation='horizontal')
+                self._check_box_coord(axes[0].patches, expected_x=np.array([0, 0, 0, 0, 0]),
+                                      expected_w=np.array([10, 9, 8, 7, 6]))
+                self._check_box_coord(axes[1].patches, expected_x=np.array([0, 0, 0, 0, 0]),
+                                      expected_w=np.array([8, 8, 8, 8, 8]))
+                self._check_box_coord(axes[2].patches, expected_x=np.array([0, 0, 0, 0, 0]),
+                                      expected_w=np.array([6, 7, 8, 9, 10]))
 
     @slow
     def test_hist_df_legacy(self):

pandas/tests/test_index.py

@@ -1886,6 +1886,27 @@ def test_reindex_preserves_tz_if_target_is_empty_list_or_array(self):
         self.assertEqual(str(index.reindex([])[0].tz), 'US/Eastern')
         self.assertEqual(str(index.reindex(np.array([]))[0].tz), 'US/Eastern')
 
+    def test_time_loc(self):  # GH8667
+        from datetime import time
+        from pandas.index import _SIZE_CUTOFF
+
+        ns = _SIZE_CUTOFF + np.array([-100, 100],dtype=np.int64)
+        key = time(15, 11, 30)
+        start = key.hour * 3600 + key.minute * 60 + key.second
+        step = 24 * 3600
+
+        for n in ns:
+            idx = pd.date_range('2014-11-26', periods=n, freq='S')
+            ts = pd.Series(np.random.randn(n), index=idx)
+            i = np.arange(start, n, step)
+
+            tm.assert_array_equal(ts.index.get_loc(key), i)
+            tm.assert_series_equal(ts[key], ts.iloc[i])
+
+            left, right = ts.copy(), ts.copy()
+            left[key] *= -10
+            right.iloc[i] *= -10
+            tm.assert_series_equal(left, right)
 
 class TestPeriodIndex(Base, tm.TestCase):
     _holder = PeriodIndex

pandas/tools/merge.py

@@ -479,8 +479,10 @@ def _get_join_indexers(left_keys, right_keys, sort=False, how='inner'):
         left_group_key, right_group_key, max_groups = \
             _factorize_keys(left_group_key, right_group_key, sort=sort)
 
+    # preserve left frame order if how == 'left' and sort == False
+    kwargs = {'sort':sort} if how == 'left' else {}
     join_func = _join_functions[how]
-    return join_func(left_group_key, right_group_key, max_groups)
+    return join_func(left_group_key, right_group_key, max_groups, **kwargs)
 
 
 class _OrderedMerge(_MergeOperation):

pandas/tools/plotting.py

@@ -1051,13 +1051,15 @@ def _adorn_subplots(self):
                     xticklabels = [labels.get(x, '') for x in ax.get_xticks()]
                     ax.set_xticklabels(xticklabels)
                 self._apply_axis_properties(ax.xaxis, rot=self.rot,
-                                           fontsize=self.fontsize)
+                                            fontsize=self.fontsize)
+                self._apply_axis_properties(ax.yaxis, fontsize=self.fontsize)
             elif self.orientation == 'horizontal':
                 if self._need_to_set_index:
                     yticklabels = [labels.get(y, '') for y in ax.get_yticks()]
                     ax.set_yticklabels(yticklabels)
                 self._apply_axis_properties(ax.yaxis, rot=self.rot,
-                                           fontsize=self.fontsize)
+                                            fontsize=self.fontsize)
+                self._apply_axis_properties(ax.xaxis, fontsize=self.fontsize)
 
     def _apply_axis_properties(self, axis, rot=None, fontsize=None):
         labels = axis.get_majorticklabels() + axis.get_minorticklabels()

pandas/tools/tests/test_merge.py

@@ -1022,6 +1022,13 @@ def test_left_join_index_multi_match_multiindex(self):
 
         tm.assert_frame_equal(result, expected)
 
+        # GH7331 - maintain left frame order in left merge
+        right.reset_index(inplace=True)
+        right.columns = left.columns[:3].tolist() + right.columns[-1:].tolist()
+        result = merge(left, right, how='left', on=left.columns[:-1].tolist())
+        expected.index = np.arange(len(expected))
+        tm.assert_frame_equal(result, expected)
+
     def test_left_join_index_multi_match(self):
         left = DataFrame([
             ['c', 0],
@@ -1059,6 +1066,11 @@ def test_left_join_index_multi_match(self):
 
         tm.assert_frame_equal(result, expected)
 
+        # GH7331 - maintain left frame order in left merge
+        result = merge(left, right.reset_index(), how='left', on='tag')
+        expected.index = np.arange(len(expected))
+        tm.assert_frame_equal(result, expected)
+
     def test_join_multi_dtypes(self):
 
         # test with multi dtypes in the join index