BUG: to_html misses truncation indicators (...) when index=False (#22786)

Author: simonjayhawkins

doc/source/whatsnew/v0.24.0.rst

@@ -1361,6 +1361,7 @@ Notice how we now instead output ``np.nan`` itself instead of a stringified form
 - :func:`read_sas()` will correctly parse sas7bdat files with many columns (:issue:`22628`)
 - :func:`read_sas()` will correctly parse sas7bdat files with data page types having also bit 7 set (so page type is 128 + 256 = 384) (:issue:`16615`)
 - Bug in :meth:`detect_client_encoding` where potential ``IOError`` goes unhandled when importing in a mod_wsgi process due to restricted access to stdout. (:issue:`21552`)
+- Bug in :func:`to_html()` with ``index=False`` misses truncation indicators (...) on truncated DataFrame (:issue:`15019`, :issue:`22783`)
 - Bug in :func:`DataFrame.to_string()` that broke column alignment when ``index=False`` and width of first column's values is greater than the width of first column's header (:issue:`16839`, :issue:`13032`)
 - Bug in :func:`DataFrame.to_string()` that caused representations of :class:`DataFrame` to not take up the whole window (:issue:`22984`)
 - Bug in :func:`DataFrame.to_csv` where a single level MultiIndex incorrectly wrote a tuple. Now just the value of the index is written (:issue:`19589`).

pandas/io/formats/html.py

@@ -305,6 +305,8 @@ def _column_header():
  align = self.fmt.justify
 
  if truncate_h:
+ if not self.fmt.index:
+ row_levels = 0
  ins_col = row_levels + self.fmt.tr_col_num
  col_row.insert(ins_col, '...')
 
@@ -336,15 +338,10 @@ def _write_body(self, indent):
  fmt_values[i] = self.fmt._format_col(i)
 
  # write values
- if self.fmt.index:
- if isinstance(self.frame.index, ABCMultiIndex):
- self._write_hierarchical_rows(fmt_values, indent)
- else:
- self._write_regular_rows(fmt_values, indent)
+ if self.fmt.index and isinstance(self.frame.index, ABCMultiIndex):
+ self._write_hierarchical_rows(fmt_values, indent)
  else:
- for i in range(min(len(self.frame), self.max_rows)):
- row = [fmt_values[j][i] for j in range(len(self.columns))]
- self.write_tr(row, indent, self.indent_delta, tags=None)
+ self._write_regular_rows(fmt_values, indent)
 
  indent -= self.indent_delta
  self.write('</tbody>', indent)
@@ -358,29 +355,35 @@ def _write_regular_rows(self, fmt_values, indent):
 
  ncols = len(self.fmt.tr_frame.columns)
  nrows = len(self.fmt.tr_frame)
- fmt = self.fmt._get_formatter('__index__')
- if fmt is not None:
- index_values = self.fmt.tr_frame.index.map(fmt)
+
+ if self.fmt.index:
+ fmt = self.fmt._get_formatter('__index__')
+ if fmt is not None:
+ index_values = self.fmt.tr_frame.index.map(fmt)
+ else:
+ index_values = self.fmt.tr_frame.index.format()
+ row_levels = 1
  else:
- index_values = self.fmt.tr_frame.index.format()
+ row_levels = 0
 
  row = []
  for i in range(nrows):
 
  if truncate_v and i == (self.fmt.tr_row_num):
  str_sep_row = ['...'] * len(row)
  self.write_tr(str_sep_row, indent, self.indent_delta,
- tags=None, nindex_levels=1)
+ tags=None, nindex_levels=row_levels)
 
  row = []
- row.append(index_values[i])
+ if self.fmt.index:
+ row.append(index_values[i])
  row.extend(fmt_values[j][i] for j in range(ncols))
 
  if truncate_h:
- dot_col_ix = self.fmt.tr_col_num + 1
+ dot_col_ix = self.fmt.tr_col_num + row_levels
  row.insert(dot_col_ix, '...')
  self.write_tr(row, indent, self.indent_delta, tags=None,
- nindex_levels=1)
+ nindex_levels=row_levels)
 
  def _write_hierarchical_rows(self, fmt_values, indent):
  template = 'rowspan="{span}" valign="top"'

pandas/tests/io/formats/data/gh15019_expected_output.html

@@ -0,0 +1,30 @@
+<table border="1" class="dataframe">
+ <thead>
+ <tr style="text-align: right;">
+ <th>0</th>
+ <th>1</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <td>1.764052</td>
+ <td>0.400157</td>
+ </tr>
+ <tr>
+ <td>0.978738</td>
+ <td>2.240893</td>
+ </tr>
+ <tr>
+ <td>...</td>
+ <td>...</td>
+ </tr>
+ <tr>
+ <td>0.950088</td>
+ <td>-0.151357</td>
+ </tr>
+ <tr>
+ <td>-0.103219</td>
+ <td>0.410599</td>
+ </tr>
+ </tbody>
+</table>

pandas/tests/io/formats/data/gh22783_expected_output.html

@@ -0,0 +1,27 @@
+<table border="1" class="dataframe">
+ <thead>
+ <tr style="text-align: right;">
+ <th>0</th>
+ <th>1</th>
+ <th>...</th>
+ <th>3</th>
+ <th>4</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <td>1.764052</td>
+ <td>0.400157</td>
+ <td>...</td>
+ <td>2.240893</td>
+ <td>1.867558</td>
+ </tr>
+ <tr>
+ <td>-0.977278</td>
+ <td>0.950088</td>
+ <td>...</td>
+ <td>-0.103219</td>
+ <td>0.410599</td>
+ </tr>
+ </tbody>
+</table>

pandas/tests/io/formats/test_to_html.py

@@ -22,6 +22,28 @@
  pass
 
 
+def expected_html(datapath, name):
+ """
+ Read HTML file from formats data directory.
+
+ Parameters
+ ----------
+ datapath : pytest fixture
+ The datapath fixture injected into a test by pytest.
+ name : str
+ The name of the HTML file without the suffix.
+
+ Returns
+ -------
+ str : contents of HTML file.
+ """
+ filename = '.'.join([name, 'html'])
+ filepath = datapath('io', 'formats', 'data', filename)
+ with open(filepath) as f:
+ html = f.read()
+ return html.rstrip()
+
+
 class TestToHTML(object):
 
  def test_to_html_with_col_space(self):
@@ -1881,6 +1903,29 @@ def test_to_html_multiindex_max_cols(self):
  </table>""")
  assert result == expected
 
+ @pytest.mark.parametrize('index', [False, 0])
+ def test_to_html_truncation_index_false_max_rows(self, datapath, index):
+ # GH 15019
+ data = [[1.764052, 0.400157],
+ [0.978738, 2.240893],
+ [1.867558, -0.977278],
+ [0.950088, -0.151357],
+ [-0.103219, 0.410599]]
+ df = pd.DataFrame(data)
+ result = df.to_html(max_rows=4, index=index)
+ expected = expected_html(datapath, 'gh15019_expected_output')
+ assert result == expected
+
+ @pytest.mark.parametrize('index', [False, 0])
+ def test_to_html_truncation_index_false_max_cols(self, datapath, index):
+ # GH 22783
+ data = [[1.764052, 0.400157, 0.978738, 2.240893, 1.867558],
+ [-0.977278, 0.950088, -0.151357, -0.103219, 0.410599]]
+ df = pd.DataFrame(data)
+ result = df.to_html(max_cols=4, index=index)
+ expected = expected_html(datapath, 'gh22783_expected_output')
+ assert result == expected
+
  def test_to_html_notebook_has_style(self):
  df = pd.DataFrame({"A": [1, 2, 3]})
  result = df.to_html(notebook=True)