Merge remote-tracking branch 'upstream/master' into index-values

Author: TomAugspurger

doc/source/whatsnew/v0.23.0.txt

@@ -717,6 +717,7 @@ I/O
 ^^^
 
 - :func:`read_html` now rewinds seekable IO objects after parse failure, before attempting to parse with a new parser. If a parser errors and the object is non-seekable, an informative error is raised suggesting the use of a different parser (:issue:`17975`)
+- :meth:`DataFrame.to_html` now has an option to add an id to the leading `<table>` tag (:issue:`8496`)
 - Bug in :func:`read_msgpack` with a non existent file is passed in Python 2 (:issue:`15296`)
 - Bug in :func:`read_csv` where a ``MultiIndex`` with duplicate columns was not being mangled appropriately (:issue:`18062`)
 - Bug in :func:`read_csv` where missing values were not being handled properly when ``keep_default_na=False`` with dictionary ``na_values`` (:issue:`19227`)

pandas/core/frame.py

@@ -1727,7 +1727,7 @@ def to_html(self, buf=None, columns=None, col_space=None, header=True,
                 sparsify=None, index_names=True, justify=None, bold_rows=True,
                 classes=None, escape=True, max_rows=None, max_cols=None,
                 show_dimensions=False, notebook=False, decimal='.',
-                border=None):
+                border=None, table_id=None):
         """
         Render a DataFrame as an HTML table.
 
@@ -1755,6 +1755,12 @@ def to_html(self, buf=None, columns=None, col_space=None, header=True,
             `<table>` tag. Default ``pd.options.html.border``.
 
             .. versionadded:: 0.19.0
+
+        table_id : str, optional
+            A css id is included in the opening `<table>` tag if specified.
+
+            .. versionadded:: 0.23.0
+
         """
 
         if (justify is not None and
@@ -1772,7 +1778,7 @@ def to_html(self, buf=None, columns=None, col_space=None, header=True,
                                            max_rows=max_rows,
                                            max_cols=max_cols,
                                            show_dimensions=show_dimensions,
-                                           decimal=decimal)
+                                           decimal=decimal, table_id=table_id)
         # TODO: a generic formatter wld b in DataFrameFormatter
         formatter.to_html(classes=classes, notebook=notebook, border=border)
 

pandas/core/indexes/base.py

@@ -615,12 +615,13 @@ def _values(self):
         CategoricalIndex  | Categorical     | Categorical | codes           |
         DatetimeIndex[tz] | ndarray[M8ns]   | DTI[tz]     | ndarray[M8ns]   |
 
-        In the near-future, we'll implement two more.
+        For the following, the ``._values`` is currently ``ndarray[object]``,
+        but will soon be an ``ExtensionArray``
 
-        index             | values          | _values     | _ndarray_values |
-        ----------------- | --------------- | ----------- | --------------- |
-        PeriodIndex       | ndarray[object] | PeriodArray | ndarray[int]    |
-        IntervalIndex     | ndarray[object] | PeriodArray | ndarray[object] |
+        index             | values          | _values      | _ndarray_values |
+        ----------------- | --------------- | ------------ | --------------- |
+        PeriodIndex       | ndarray[object] | ndarray[obj] | ndarray[int]    |
+        IntervalIndex     | ndarray[object] | ndarray[obj] | ndarray[object] |
 
         See Also
         --------
@@ -2377,7 +2378,7 @@ def intersection(self, other):
             indexer = Index(rvals).get_indexer(lvals)
             indexer = indexer.take((indexer != -1).nonzero()[0])
         except Exception:
-            # duplicateters
+            # duplicates
             indexer = algos.unique1d(
                 Index(rvals).get_indexer_non_unique(lvals)[0])
             indexer = indexer[indexer != -1]

pandas/io/formats/format.py

@@ -77,7 +77,11 @@
     index_names : bool, optional
         Prints the names of the indexes, default True
     line_width : int, optional
-        Width to wrap a line in characters, default no wrap"""
+        Width to wrap a line in characters, default no wrap
+    table_id : str, optional
+        id for the <table> element create by to_html
+
+        .. versionadded:: 0.23.0"""
 
 _VALID_JUSTIFY_PARAMETERS = ("left", "right", "center", "justify",
                              "justify-all", "start", "end", "inherit",
@@ -387,7 +391,8 @@ def __init__(self, frame, buf=None, columns=None, col_space=None,
                  header=True, index=True, na_rep='NaN', formatters=None,
                  justify=None, float_format=None, sparsify=None,
                  index_names=True, line_width=None, max_rows=None,
-                 max_cols=None, show_dimensions=False, decimal='.', **kwds):
+                 max_cols=None, show_dimensions=False, decimal='.',
+                 table_id=None, **kwds):
         self.frame = frame
         if buf is not None:
             self.buf = _expand_user(_stringify_path(buf))
@@ -413,6 +418,7 @@ def __init__(self, frame, buf=None, columns=None, col_space=None,
         self.max_rows_displayed = min(max_rows or len(self.frame),
                                       len(self.frame))
         self.show_dimensions = show_dimensions
+        self.table_id = table_id
 
         if justify is None:
             self.justify = get_option("display.colheader_justify")
@@ -740,7 +746,8 @@ def to_html(self, classes=None, notebook=False, border=None):
                                       max_rows=self.max_rows,
                                       max_cols=self.max_cols,
                                       notebook=notebook,
-                                      border=border)
+                                      border=border,
+                                      table_id=self.table_id)
         if hasattr(self.buf, 'write'):
             html_renderer.write_result(self.buf)
         elif isinstance(self.buf, compat.string_types):
@@ -1082,7 +1089,7 @@ class HTMLFormatter(TableFormatter):
     indent_delta = 2
 
     def __init__(self, formatter, classes=None, max_rows=None, max_cols=None,
-                 notebook=False, border=None):
+                 notebook=False, border=None, table_id=None):
         self.fmt = formatter
         self.classes = classes
 
@@ -1101,6 +1108,7 @@ def __init__(self, formatter, classes=None, max_rows=None, max_cols=None,
         if border is None:
             border = get_option('display.html.border')
         self.border = border
+        self.table_id = table_id
 
     def write(self, s, indent=0):
         rs = pprint_thing(s)
@@ -1197,6 +1205,7 @@ def write_style(self):
 
     def write_result(self, buf):
         indent = 0
+        id_section = ""
         frame = self.frame
 
         _classes = ['dataframe']  # Default class.
@@ -1220,8 +1229,12 @@ def write_result(self, buf):
             self.write('<div{style}>'.format(style=div_style))
 
         self.write_style()
-        self.write('<table border="{border}" class="{cls}">'
-                   .format(border=self.border, cls=' '.join(_classes)), indent)
+
+        if self.table_id is not None:
+            id_section = ' id="{table_id}"'.format(table_id=self.table_id)
+        self.write('<table border="{border}" class="{cls}"{id_section}>'
+                   .format(border=self.border, cls=' '.join(_classes),
+                           id_section=id_section), indent)
 
         indent += self.indent_delta
         indent = self._write_header(indent)

pandas/io/pickle.py

@@ -1,4 +1,5 @@
 """ pickle compat """
+import warnings
 
 import numpy as np
 from numpy.lib.format import read_array, write_array
@@ -96,7 +97,9 @@ def try_read(path, encoding=None):
         # cpickle
         # GH 6899
         try:
-            return read_wrapper(lambda f: pkl.load(f))
+            with warnings.catch_warnings(record=True):
+                # We want to silencce any warnings about, e.g. moved modules.
+                return read_wrapper(lambda f: pkl.load(f))
         except Exception:
             # reg/patched pickle
             try:

pandas/tests/io/formats/test_format.py

@@ -1492,15 +1492,15 @@ def test_repr_html_float(self):
                             'B': np.arange(41, 41 + h)}).set_index('idx')
             reg_repr = df._repr_html_()
             assert '..' not in reg_repr
-            assert str(40 + h) in reg_repr
+            assert '<td>{val}</td>'.format(val=str(40 + h)) in reg_repr
 
             h = max_rows + 1
             df = DataFrame({'idx': np.linspace(-10, 10, h),
                             'A': np.arange(1, 1 + h),
                             'B': np.arange(41, 41 + h)}).set_index('idx')
             long_repr = df._repr_html_()
             assert '..' in long_repr
-            assert '31' not in long_repr
+            assert '<td>{val}</td>'.format(val='31') not in long_repr
             assert u('{h} rows ').format(h=h) in long_repr
             assert u('2 columns') in long_repr
 

pandas/tests/io/formats/test_to_html.py

@@ -1864,3 +1864,10 @@ def test_to_html_with_index_names_false(self):
                                                         name='myindexname'))
         result = df.to_html(index_names=False)
         assert 'myindexname' not in result
+
+    def test_to_html_with_id(self):
+        # gh-8496
+        df = pd.DataFrame({"A": [1, 2]}, index=pd.Index(['a', 'b'],
+                                                        name='myindexname'))
+        result = df.to_html(index_names=False, table_id="TEST_ID")
+        assert ' id="TEST_ID"' in result