def test_df_with_many_columns_is_downsampled_preferentially_on_columns(
df, max_bytes):
dn = downsample(df, max_bytes=max_bytes)
if max_bytes == 1e5:
assert len(dn.index) == len(
df.index) and len(dn.columns) < len(df.columns)
else:
# aspect ratio is close to 1
assert 0.5 < len(dn.index) / len(dn.columns) < 2
def _datatables_repr_(df=None, tableId=None, **kwargs):
"""Return the HTML/javascript representation of the table"""
# Default options
for option in dir(opt):
if option not in kwargs and not option.startswith("__"):
kwargs[option] = getattr(opt, option)
# These options are used here, not in DataTable
classes = kwargs.pop("classes")
showIndex = kwargs.pop("showIndex")
maxBytes = kwargs.pop("maxBytes", 0)
maxRows = kwargs.pop("maxRows", 0)
maxColumns = kwargs.pop("maxColumns", pd.get_option("display.max_columns") or 0)
if isinstance(df, (np.ndarray, np.generic)):
df = pd.DataFrame(df)
if isinstance(df, pd.Series):
df = df.to_frame()
df = downsample(df, max_rows=maxRows, max_columns=maxColumns, max_bytes=maxBytes)
# Do not show the page menu when the table has fewer rows than min length menu
if "paging" not in kwargs and len(df.index) <= kwargs.get("lengthMenu", [10])[0]:
kwargs["paging"] = False
tableId = tableId or str(uuid.uuid4())
if isinstance(classes, list):
classes = " ".join(classes)
if showIndex == "auto":
showIndex = df.index.name is not None or not isinstance(df.index, pd.RangeIndex)
if not showIndex:
df = df.set_index(pd.RangeIndex(len(df.index)))
# Generate table head using pandas.to_html()
pattern = re.compile(r".*<thead>(.*)</thead>", flags=re.MULTILINE | re.DOTALL)
match = pattern.match(df.head(0).to_html())
thead = match.groups()[0]
if not showIndex:
thead = thead.replace("<th></th>", "", 1)
html_table = (
'<table id="'
+ tableId
+ '" class="'
+ classes
+ '"><thead>'
+ thead
+ "</thead></table>"
)
kwargs["data"] = _formatted_values(df.reset_index() if showIndex else df)
try:
dt_args = json.dumps(kwargs)
return (
"""<div>"""
+ html_table
+ """
<script type="text/javascript">
require(["datatables"], function (datatables) {
$(document).ready(function () {
var dt_args = """
+ dt_args
+ """;
dt_args = eval_functions(dt_args);
var el = $('#"""
+ tableId
+ """')
if ($.fn.dataTable.isDataTable(el)) {
table = el.DataTable();
table.destroy();
}
table = el.DataTable(dt_args);
});
})
</script>
</div>
"""
)
except TypeError as error:
logger.error(str(error))
return ""
def test_max_one_byte(df, max_bytes=1):
dn = downsample(df, max_bytes=max_bytes)
assert len(dn.columns) == len(dn.index) == 1
assert dn.iloc[0, 0] == "..."
def test_max_bytes(df, max_bytes):
dn = downsample(df, max_bytes=max_bytes)
assert dn.values.nbytes <= max_bytes
assert dn.values.nbytes > max_bytes / 2
def test_max_columns(df, max_columns):
dn = downsample(df, max_columns=max_columns)
pd.testing.assert_index_equal(dn.index, df.index)
assert len(dn.columns) == max_columns
def test_max_rows(df, max_rows):
dn = downsample(df, max_rows=max_rows)
assert len(dn.index) == max_rows
pd.testing.assert_index_equal(dn.columns, df.columns)