Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit508deae

Browse files
authored
fix: Improve Anywidget pagination and display for unknown row counts (#2258)
Previously, when the total number of rows (row_count) was unknown (e.g.,due to deferred computation or errors), it would incorrectly default to0. This resulted in confusing UI, such as displaying "Page 1 of 0", andallowed users to navigate to empty pages without automatically returningto valid data.current display strategy for the interactive table widget: * When `row_count` is a positive number (e.g., 50): * Total Rows Display: Shows the exact count, like 50 total rows.* Pagination Display: Shows the page relative to the total rows, likePage 1 of 50.* Navigation: The "Next" button is disabled only on the final page. * When `row_count` is `None` (unknown): * Total Rows Display: Shows Total rows unknown.* Pagination Display: Shows the page relative to an unknown total, likePage 1 of many.* Navigation: The "Next" button is always enabled, allowing you to pageforward until the backend determines there is no more data.Fixes #<428238610> 🦕
1 parent7c062a6 commit508deae

File tree

4 files changed

+310
-72
lines changed

4 files changed

+310
-72
lines changed

‎bigframes/display/anywidget.py‎

Lines changed: 44 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -55,7 +55,11 @@ class TableWidget(WIDGET_BASE):
5555

5656
page=traitlets.Int(0).tag(sync=True)
5757
page_size=traitlets.Int(0).tag(sync=True)
58-
row_count=traitlets.Int(0).tag(sync=True)
58+
row_count=traitlets.Union(
59+
[traitlets.Int(),traitlets.Instance(type(None))],
60+
default_value=None,
61+
allow_none=True,
62+
).tag(sync=True)
5963
table_html=traitlets.Unicode().tag(sync=True)
6064
_initial_load_complete=traitlets.Bool(False).tag(sync=True)
6165
_batches:Optional[blocks.PandasBatches]=None
@@ -94,12 +98,17 @@ def __init__(self, dataframe: bigframes.dataframe.DataFrame):
9498
# SELECT COUNT(*) query. It is a must have however.
9599
# TODO(b/428238610): Start iterating over the result of `to_pandas_batches()`
96100
# before we get here so that the count might already be cached.
97-
# TODO(b/452747934): Allow row_count to be None and check to see if
98-
# there are multiple pages and show "page 1 of many" in this case
99101
self._reset_batches_for_new_page_size()
100-
ifself._batchesisNoneorself._batches.total_rowsisNone:
101-
self._error_message="Could not determine total row count. Data might be unavailable or an error occurred."
102-
self.row_count=0
102+
103+
ifself._batchesisNone:
104+
self._error_message="Could not retrieve data batches. Data might be unavailable or an error occurred."
105+
self.row_count=None
106+
elifself._batches.total_rowsisNone:
107+
# Total rows is unknown, this is an expected state.
108+
# TODO(b/461536343): Cheaply discover if we have exactly 1 page.
109+
# There are cases where total rows is not set, but there are no additional
110+
# pages. We could disable the "next" button in these cases.
111+
self.row_count=None
103112
else:
104113
self.row_count=self._batches.total_rows
105114

@@ -131,11 +140,22 @@ def _validate_page(self, proposal: Dict[str, Any]) -> int:
131140
Returns:
132141
The validated and clamped page number as an integer.
133142
"""
134-
135143
value=proposal["value"]
144+
145+
ifvalue<0:
146+
raiseValueError("Page number cannot be negative.")
147+
148+
# If truly empty or invalid page size, stay on page 0.
149+
# This handles cases where row_count is 0 or page_size is 0, preventing
150+
# division by zero or nonsensical pagination, regardless of row_count being None.
136151
ifself.row_count==0orself.page_size==0:
137152
return0
138153

154+
# If row count is unknown, allow any non-negative page. The previous check
155+
# ensures that invalid page_size (0) is already handled.
156+
ifself.row_countisNone:
157+
returnvalue
158+
139159
# Calculate the zero-indexed maximum page number.
140160
max_page=max(0,math.ceil(self.row_count/self.page_size)-1)
141161

@@ -229,6 +249,23 @@ def _set_table_html(self) -> None:
229249
# Get the data for the current page
230250
page_data=cached_data.iloc[start:end]
231251

252+
# Handle case where user navigated beyond available data with unknown row count
253+
is_unknown_count=self.row_countisNone
254+
is_beyond_data=self._all_data_loadedandlen(page_data)==0andself.page>0
255+
ifis_unknown_countandis_beyond_data:
256+
# Calculate the last valid page (zero-indexed)
257+
total_rows=len(cached_data)
258+
iftotal_rows>0:
259+
last_valid_page=max(0,math.ceil(total_rows/self.page_size)-1)
260+
# Navigate back to the last valid page
261+
self.page=last_valid_page
262+
# Recursively call to display the correct page
263+
returnself._set_table_html()
264+
else:
265+
# If no data at all, stay on page 0 with empty display
266+
self.page=0
267+
returnself._set_table_html()
268+
232269
# Generate HTML table
233270
self.table_html=bigframes.display.html.render_html(
234271
dataframe=page_data,

‎bigframes/display/table_widget.js‎

Lines changed: 15 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -85,14 +85,21 @@ function render({ model, el }) {
8585
constrowCount=model.get(ModelProperty.ROW_COUNT);
8686
constpageSize=model.get(ModelProperty.PAGE_SIZE);
8787
constcurrentPage=model.get(ModelProperty.PAGE);
88-
consttotalPages=Math.ceil(rowCount/pageSize);
89-
90-
rowCountLabel.textContent=`${rowCount.toLocaleString()} total rows`;
91-
paginationLabel.textContent=`Page${(
92-
currentPage+1
93-
).toLocaleString()} of${(totalPages||1).toLocaleString()}`;
94-
prevPage.disabled=currentPage===0;
95-
nextPage.disabled=currentPage>=totalPages-1;
88+
89+
if(rowCount===null){
90+
// Unknown total rows
91+
rowCountLabel.textContent="Total rows unknown";
92+
paginationLabel.textContent=`Page${(currentPage+1).toLocaleString()} of many`;
93+
prevPage.disabled=currentPage===0;
94+
nextPage.disabled=false;// Allow navigation until we hit the end
95+
}else{
96+
// Known total rows
97+
consttotalPages=Math.ceil(rowCount/pageSize);
98+
rowCountLabel.textContent=`${rowCount.toLocaleString()} total rows`;
99+
paginationLabel.textContent=`Page${(currentPage+1).toLocaleString()} of${rowCount.toLocaleString()}`;
100+
prevPage.disabled=currentPage===0;
101+
nextPage.disabled=currentPage>=totalPages-1;
102+
}
96103
pageSizeSelect.value=pageSize;
97104
}
98105

‎notebooks/dataframes/anywidget_mode.ipynb‎

Lines changed: 97 additions & 38 deletions
Original file line numberDiff line numberDiff line change
@@ -35,16 +35,7 @@
3535
"execution_count":2,
3636
"id":"ca22f059",
3737
"metadata": {},
38-
"outputs": [
39-
{
40-
"name":"stderr",
41-
"output_type":"stream",
42-
"text": [
43-
"/usr/local/google/home/shuowei/src/python-bigquery-dataframes/venv/lib/python3.10/site-packages/google/api_core/_python_version_support.py:266: FutureWarning: You are using a Python version (3.10.15) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.\n",
44-
" warnings.warn(message, FutureWarning)\n"
45-
]
46-
}
47-
],
38+
"outputs": [],
4839
"source": [
4940
"import bigframes.pandas as bpd"
5041
]
@@ -151,7 +142,7 @@
151142
{
152143
"data": {
153144
"application/vnd.jupyter.widget-view+json": {
154-
"model_id":"47795eaa10f149aeb99574232c0936eb",
145+
"model_id":"8fcad7b7e408422cae71d519cd2d4980",
155146
"version_major":2,
156147
"version_minor":1
157148
},
@@ -175,7 +166,7 @@
175166
}
176167
],
177168
"source": [
178-
"df"
169+
"df.set_index(\"name\")"
179170
]
180171
},
181172
{
@@ -214,7 +205,7 @@
214205
{
215206
"data": {
216207
"application/vnd.jupyter.widget-view+json": {
217-
"model_id":"8354ce0f82d3495a9b630dfc362f73ee",
208+
"model_id":"06cb98c577514d5c9654a7792d93f8e6",
218209
"version_major":2,
219210
"version_minor":1
220211
},
@@ -293,27 +284,8 @@
293284
{
294285
"data": {
295286
"text/html": [
296-
"\n",
297-
" Query started with request ID bigframes-dev:US.c45952fb-01b4-409c-9da4-f7c5bfc0d47d.<details><summary>SQL</summary><pre>SELECT\n",
298-
"`state` AS `state`,\n",
299-
"`gender` AS `gender`,\n",
300-
"`year` AS `year`,\n",
301-
"`name` AS `name`,\n",
302-
"`number` AS `number`\n",
303-
"FROM\n",
304-
"(SELECT\n",
305-
" *\n",
306-
"FROM (\n",
307-
" SELECT\n",
308-
" `state`,\n",
309-
" `gender`,\n",
310-
" `year`,\n",
311-
" `name`,\n",
312-
" `number`\n",
313-
" FROM `bigquery-public-data.usa_names.usa_1910_2013` FOR SYSTEM_TIME AS OF TIMESTAMP(&#x27;2025-10-30T21:48:48.979701+00:00&#x27;)\n",
314-
") AS `t0`)\n",
315-
"ORDER BY `name` ASC NULLS LAST ,`year` ASC NULLS LAST ,`state` ASC NULLS LAST\n",
316-
"LIMIT 5</pre></details>\n",
287+
"✅ Completed.\n",
288+
" Query processed 171.4 MB in a moment of slot time.\n",
317289
""
318290
],
319291
"text/plain": [
@@ -333,7 +305,7 @@
333305
{
334306
"data": {
335307
"application/vnd.jupyter.widget-view+json": {
336-
"model_id":"59461286a17d4a42b6be6d9d9c7bf7e3",
308+
"model_id":"1672f826f7a347e38539dbb5fb72cd43",
337309
"version_major":2,
338310
"version_minor":1
339311
},
@@ -373,7 +345,7 @@
373345
"data": {
374346
"text/html": [
375347
"✅ Completed.\n",
376-
" Query processed 85.9 kB in14 seconds of slot time.\n",
348+
" Query processed 85.9 kB in12 seconds of slot time.\n",
377349
""
378350
],
379351
"text/plain": [
@@ -387,7 +359,7 @@
387359
"name":"stderr",
388360
"output_type":"stream",
389361
"text": [
390-
"/usr/local/google/home/shuowei/src/python-bigquery-dataframes/bigframes/dtypes.py:969: JSONDtypeWarning: JSON columns will be represented as pandas.ArrowDtype(pyarrow.json_())\n",
362+
"/usr/local/google/home/shuowei/src/python-bigquery-dataframes/bigframes/dtypes.py:987: JSONDtypeWarning: JSON columns will be represented as pandas.ArrowDtype(pyarrow.json_())\n",
391363
"instead of using `db_dtypes` in the future when available in pandas\n",
392364
"(https://github.com/pandas-dev/pandas/issues/60958) and pyarrow.\n",
393365
" warnings.warn(msg, bigframes.exceptions.JSONDtypeWarning)\n"
@@ -408,7 +380,7 @@
408380
{
409381
"data": {
410382
"application/vnd.jupyter.widget-view+json": {
411-
"model_id":"d1794b42579542a8980bd158e521bd3e",
383+
"model_id":"127a2e356b834c18b6f07c58ee2c4228",
412384
"version_major":2,
413385
"version_minor":1
414386
},
@@ -443,6 +415,93 @@
443415
" LIMIT 5;\n",
444416
"\"\"\")"
445417
]
418+
},
419+
{
420+
"cell_type":"markdown",
421+
"id":"multi-index-display-markdown",
422+
"metadata": {},
423+
"source": [
424+
"## Display Multi-Index DataFrame in anywidget mode\n",
425+
"This section demonstrates how BigFrames can display a DataFrame with multiple levels of indexing (a\"multi-index\") when using the `anywidget` display mode."
426+
]
427+
},
428+
{
429+
"cell_type":"code",
430+
"execution_count":11,
431+
"id":"ad7482aa",
432+
"metadata": {},
433+
"outputs": [
434+
{
435+
"data": {
436+
"text/html": [
437+
"✅ Completed.\n",
438+
" Query processed 483.3 GB in 51 minutes of slot time. [<a target=\"_blank\" href=\"https://console.cloud.google.com/bigquery?project=bigframes-dev&j=bq:US:3eace7c0-7776-48d6-925c-965be33d8738&page=queryresults\">Job bigframes-dev:US.3eace7c0-7776-48d6-925c-965be33d8738 details</a>]\n",
439+
""
440+
],
441+
"text/plain": [
442+
"<IPython.core.display.HTML object>"
443+
]
444+
},
445+
"metadata": {},
446+
"output_type":"display_data"
447+
},
448+
{
449+
"data": {
450+
"text/html": [
451+
"✅ Completed.\n",
452+
" Query processed 124.4 MB in 7 seconds of slot time. [<a target=\"_blank\" href=\"https://console.cloud.google.com/bigquery?project=bigframes-dev&j=bq:US:job_UJ5cx4R1jW5cNxq_1H1x-9-ATfqS&page=queryresults\">Job bigframes-dev:US.job_UJ5cx4R1jW5cNxq_1H1x-9-ATfqS details</a>]\n",
453+
""
454+
],
455+
"text/plain": [
456+
"<IPython.core.display.HTML object>"
457+
]
458+
},
459+
"metadata": {},
460+
"output_type":"display_data"
461+
},
462+
{
463+
"data": {
464+
"application/vnd.jupyter.widget-view+json": {
465+
"model_id":"3f9652b5fdc0441eac2b05ab36d571d0",
466+
"version_major":2,
467+
"version_minor":1
468+
},
469+
"text/plain": [
470+
"TableWidget(page_size=10, row_count=3967869, table_html='<table border=\"1\" class=\"dataframe table table-stripe…"
471+
]
472+
},
473+
"metadata": {},
474+
"output_type":"display_data"
475+
},
476+
{
477+
"data": {
478+
"text/html": [],
479+
"text/plain": [
480+
"Computation deferred. Computation will process 513.5 GB"
481+
]
482+
},
483+
"execution_count":11,
484+
"metadata": {},
485+
"output_type":"execute_result"
486+
}
487+
],
488+
"source": [
489+
"import datetime\n",
490+
"\n",
491+
" # Read the PyPI downloads dataset\n",
492+
"pypi_df = bpd.read_gbq(\"bigquery-public-data.pypi.file_downloads\")\n",
493+
"\n",
494+
"# Filter for the last 7 days to reduce the data size for this example\n",
495+
"seven_days_ago = datetime.datetime.now(datetime.timezone.utc) - datetime.timedelta(days=7)\n",
496+
"pypi_df_recent = pypi_df[pypi_df[\"timestamp\"] > seven_days_ago]\n",
497+
"\n",
498+
"# Create a multi-index by grouping by date and project\n",
499+
"pypi_df_recent['date'] = pypi_df_recent['timestamp'].dt.date\n",
500+
"multi_index_df = pypi_df_recent.groupby([\"date\",\"project\"]).size().to_frame(\"downloads\")\n",
501+
"\n",
502+
"# Display the DataFrame with the multi-index\n",
503+
"multi_index_df"
504+
]
446505
}
447506
],
448507
"metadata": {

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp