Feature/speed up plotting #586
Conversation
- Classifies traces by analyzing y-values: positive, negative, mixed, zero - Sets stackgroup='positive' or stackgroup='negative' for proper separate stacking - Mixed values shown as dashed lines (no fill) - Opaque fills, no line borders, hv line shape Performance: ┌────────────────────────┬───────┐ │ Method │ Time │ ├────────────────────────┼───────┤ │ .plotly.bar() + update │ 0.14s │ ├────────────────────────┼───────┤ │ .plotly.area() + style │ 0.10s │ ├────────────────────────┼───────┤ │ Speedup │ ~1.4x │ └────────────────────────┴───────┘
# Iterate over all traces (main + animation frames)
def _iter_all_traces(fig: go.Figure):
yield from fig.data
for frame in getattr(fig, 'frames', []) or []:
yield from frame.data
# Apply unified hover styling (works with any plot type)
def _apply_unified_hover(fig: go.Figure, unit: str = '', decimals: int = 1):
# Sets: <b>name</b>: value unit
# + hovermode='x unified' + spike lines
Updated Methods
┌───────────────────┬──────────────────────────────────────────────┐
│ Method │ Changes │
├───────────────────┼──────────────────────────────────────────────┤
│ balance() │ + _apply_unified_hover(fig, unit=unit_label) │
├───────────────────┼──────────────────────────────────────────────┤
│ carrier_balance() │ + _apply_unified_hover(fig, unit=unit_label) │
├───────────────────┼──────────────────────────────────────────────┤
│ storage() │ + _apply_unified_hover(fig, unit=unit_label) │
└───────────────────┴──────────────────────────────────────────────┘
Result
- Hover format: <b>Solar</b>: 45.3 kW
- Hovermode: x unified (single tooltip for all traces)
- Spikes: Gray vertical line at cursor
… aggregating sign info across all traces returned by _iter_all_traces(fig), including animation frames. The color_map is still derived from fig.data. The implementation uses a sign_flags dictionary to incrementally update has_pos/has_neg flags for each trace.name, then computes class_map from those aggregated flags. 2. _apply_unified_hover (lines 271-274): Replaced the fig.update_layout(xaxis_showspikes=..., ...) with a single fig.update_xaxes(showspikes=True, spikecolor='gray', spikethickness=1) call so spike settings apply to all x-axes (xaxis, xaxis2, xaxis3, ...) in faceted plots.
|
Caution Review failedThe pull request is closed. 📝 WalkthroughWalkthroughReplaces legacy trace-iteration and area-styling helpers with a centralized Changes
Sequence Diagram(s)(Section intentionally omitted — changes are internal plotting substitutions and do not introduce a new multi-component sequential control flow that requires visualization.) Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
…ting # Conflicts: # flixopt/statistics_accessor.py
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@flixopt/statistics_accessor.py`:
- Around line 1551-1556: The ds.plotly.fast_bar calls are passing an unsupported
parameter line_shape='hv'; remove the line_shape argument from each
ds.plotly.fast_bar invocation (the ones that assign to fig) so the call becomes
fig = ds.plotly.fast_bar(title=..., **color_kwargs, **plotly_kwargs), relying on
plotly_kwargs (e.g., barmode) for stacking/behavior instead.
| fig = ds.plotly.fast_bar( | ||
| title=f'{node} [{unit_label}]' if unit_label else node, | ||
| line_shape='hv', | ||
| **color_kwargs, | ||
| **plotly_kwargs, | ||
| ) |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# First, let's find the fast_bar function definition
find . -type f -name "*.py" | head -20Repository: flixOpt/flixopt
Length of output: 174
🏁 Script executed:
# Search for fast_bar definition in the codebase
rg -n "def fast_bar" --type pyRepository: flixOpt/flixopt
Length of output: 41
🏁 Script executed:
# Check the context of the lines mentioned in the review
sed -n '1545,1560p' flixopt/statistics_accessor.pyRepository: flixOpt/flixopt
Length of output: 596
🏁 Script executed:
# Also check the other locations mentioned
sed -n '1670,1685p' flixopt/statistics_accessor.py
sed -n '2275,2290p' flixopt/statistics_accessor.pyRepository: flixOpt/flixopt
Length of output: 1359
🏁 Script executed:
# Search for previous implementation using area and _style_area_as_bar
rg -n "_style_area_as_bar|\.area\(" flixopt/statistics_accessor.py -B 3 -A 3Repository: flixOpt/flixopt
Length of output: 41
🏁 Script executed:
# Check where fast_bar comes from - look for imports
rg -n "fast_bar|import.*plotly" flixopt/statistics_accessor.py | head -30Repository: flixOpt/flixopt
Length of output: 217
🏁 Script executed:
# Try to find fast_bar in xarray-plotly or plotly packages
rg -n "def fast_bar" . --type py 2>/dev/null | head -20Repository: flixOpt/flixopt
Length of output: 41
🌐 Web query:
xarray-plotly fast_bar function parameters documentation
💡 Result:
I couldn’t find any official function named fast_bar in xarray or Plotly docs. Xarray’s plotting API wraps Matplotlib (DataArray.plot and friends) and Plotly’s bar function is plotly.express.bar (see its full parameter list). If you meant a third‑party helper, there’s an independent xarray_plotly project that wraps plotly.express for xarray (GitHub). Sources:
- xarray plotting documentation (DataArray.plot / plotting guide). [1]
- plotly.express.bar parameter reference. [2]
- xarray_plotly (third‑party accessor on GitHub). [3]
If you want, tell me which behavior/parameters you need and I’ll map those to plotly.express.bar arguments or inspect the xarray_plotly code.
🏁 Script executed:
# Check if there's a plotly accessor module in the repo
find . -type f -name "*plotly*" | grep -v __pycache__Repository: flixOpt/flixopt
Length of output: 95
🏁 Script executed:
# Look for the plotly accessor and its methods
fd -e py "plotly" | head -20Repository: flixOpt/flixopt
Length of output: 41
🏁 Script executed:
# Search for xarray accessor registration or plotly accessor definition
rg -n "@.*accessor|register_.*accessor" . --type pyRepository: flixOpt/flixopt
Length of output: 129
🏁 Script executed:
# Look for plotly accessor import or definition
rg -n "plotly" flixopt/*.py | grep -i "import\|from\|accessor"Repository: flixOpt/flixopt
Length of output: 8584
🏁 Script executed:
# Check requirements files for xarray_plotly dependency
find . -type f \( -name "requirements*.txt" -o -name "setup.py" -o -name "setup.cfg" -o -name "pyproject.toml" \) -exec grep -l "xarray" {} \;Repository: flixOpt/flixopt
Length of output: 75
🏁 Script executed:
# Check if there's a local plotly accessor module or definition
find . -type f -name "*.py" -exec grep -l "plotly.*accessor\|fast_bar" {} \;Repository: flixOpt/flixopt
Length of output: 91
🏁 Script executed:
# Look for the specific accessor setup or where plotly methods might be defined
rg -n "class.*Plotly|def fast_bar" . --type pyRepository: flixOpt/flixopt
Length of output: 41
🏁 Script executed:
# Check pyproject.toml for xarray_plotly version
cat pyproject.toml | grep -A 5 -B 5 "xarray_plotly"Repository: flixOpt/flixopt
Length of output: 339
🌐 Web query:
xarray_plotly fast_bar function source code github
💡 Result:
I couldn't find a public GitHub function named fast_bar in an xarray_plotly repository. Do you have a link, package name, or example (repo owner) I should search for?
🌐 Web query:
xarray-plotly fast_bar barmode line_shape parameter
💡 Result:
Short answer: xarray's Plotly-based bar plotting ultimately calls Plotly Express' bar routine, so you can pass barmode (e.g. "group", "overlay", "relative"/"stack") via kwargs to control stacking/grouping. The line_shape parameter is for line plots (px.line / line-type traces) — it does not apply to bar/fast_bar.
Sources:
- px.bar docs (barmode parameter). [1]
- px.line / line_shape docs (line_shape applies to lines, not bars). [2]
- Plotly Express overview (PX is the backend used by high-level calls and accepts xarray inputs). [3]
References:
[1] plotly.express.bar documentation.
[2] plotly.express.line / line_shape documentation.
[3] Plotly Express overview (PX accepts xarray/numpy/pandas inputs).
🌐 Web query:
xarray_plotly pypi package repository github
💡 Result:
- PyPI / package: xarray-plotly (install via pip as xarray-plotly). [1]
- Source / repository: GitHub — FBumann/xarray_plotly. [2]
Sources:
[1] piwheels / xarray-plotly (package listing).
[2] Plotly community post linking the GitHub repo (FBumann/xarray_plotly).
🌐 Web query:
plotly express bar line_shape parameter invalid
💡 Result:
Cause: px.bar creates Bar traces (no line_shape) and Plotly Express may auto-create Scatter/Scattergl traces when drawing lines; the line_shape option applies to Scatter (plotly.graph_objects.Scatter) and only 'scatter' (SVG) supports 'spline' — Scattergl does not. See the px/Scatter docs and community discussion. [1][2]
Fixes:
- If you want a curved/step line, add a separate Scatter trace (go.Scatter) and set its line.shape (or mode/line dict) instead of passing line_shape to px.bar. Example: add_traces(go.Scatter(x=..., y=..., mode='lines', line=dict(shape='spline'))). [1]
- If using px.line or px.scatter and you need 'spline' with many points, force SVG rendering so spline is allowed: set render_mode='svg' (default may switch to 'scattergl' for performance). [1][2]
- For a horizontal/constant line on a bar chart, simpler: fig.add_hline(y=...) or fig.add_shape(...). [3]
Sources:
- Plotly Express / Scatter doc (line_shape options). [1]
- Plotly community thread explaining Scattergl lacks 'spline' and render_mode='svg' workaround. [2]
- StackOverflow examples for adding lines to bar charts (add_hline / go.Scatter). [3]
🏁 Script executed:
# Check if xarray_plotly is vendored or can be searched in pip
python3 << 'EOF'
import subprocess
result = subprocess.run(['pip', 'show', 'xarray_plotly'], capture_output=True, text=True)
print(result.stdout)
print(result.stderr)
EOFRepository: flixOpt/flixopt
Length of output: 145
🌐 Web query:
"xarray_plotly" "fast_bar" documentation api
💡 Result:
Do you want the xarray_plotly fast_bar docs/usage (link + examples) or the API reference (function signature and parameters)? Which one should I fetch?
🌐 Web query:
site:github.com FBumann xarray_plotly fast_bar
💡 Result:
I found the GitHub repository "FBumann/xarray_plotly" (interactive Plotly Express plotting for xarray) — latest release v0.0.10 (Jan 22, 2026) and docs. [1][2]
I did not find any public GitHub results for "fast_bar" in that repo or tied to FBumann.
Sources:
- FBumann/xarray_plotly GitHub repo. [1]
- Plotly community post announcing the package. [2]
🌐 Web query:
xarray_plotly fast_bar method signature parameters source
💡 Result:
Do you mean the fast_bar method in the xarray-plotly package (the xarray_plotly accessor)? I can fetch the exact method signature and source — confirm and I’ll look it up.
🌐 Web query:
FBumann xarray_plotly figures.py fast_bar source code
💡 Result:
Do you want me to (a) fetch and show the contents of figures.py (fast_bar) from FBumann/xarray_plotly, or (b) provide the repository link and instructions to view it yourself?
🌐 Web query:
xarray_plotly plotly accessor bar method line_shape
💡 Result:
Short answer: plotly.express.bar (and the underlying Bar trace) does not accept a line_shape argument. line_shape is a parameter for line/area/line-like Plotly Express functions (px.line, px.area, etc.) and accepts 'linear', 'spline', 'hv', 'vh', 'hvh', or 'vhv'. See the px.bar signature (no line_shape) and the px docs describing line_shape. [1][2]
Sources:
- px.bar signature (no line_shape). [1]
- px docs showing line_shape and allowed values for line/area-like functions. [2]
🏁 Script executed:
# Try to check the xarray_plotly package directly via pip
python3 << 'EOF'
try:
import xarray_plotly
import inspect
# Try to find fast_bar
if hasattr(xarray_plotly, 'fast_bar'):
print("Found fast_bar in xarray_plotly")
print(inspect.signature(xarray_plotly.fast_bar))
else:
print("fast_bar not found in xarray_plotly module directly")
print("Available attributes:", dir(xarray_plotly))
except Exception as e:
print(f"Error: {e}")
print("Trying to import and check xarray_plotly.figures...")
try:
from xarray_plotly import figures
print("xarray_plotly.figures available")
print("Available in figures:", [x for x in dir(figures) if not x.startswith('_')])
except Exception as e2:
print(f"Error with figures: {e2}")
EOFRepository: flixOpt/flixopt
Length of output: 201
🌐 Web query:
xarray_plotly wraps plotly.express bar function documentation
💡 Result:
Yes — the xarray_plotly package provides a plotting accessor that wraps most plotly.express functions (including px.bar). See the package announcement on the Plotly community and the Plotly Express px.bar reference for the underlying API it wraps. [1][2]
Sources:
- Package announcement / GitHub link (xarray_plotly). [1]
- plotly.express.bar documentation. [2]
Remove line_shape='hv' from fast_bar calls — not supported for bar charts.
The fast_bar method wraps plotly.express.bar, which does not accept the line_shape parameter. This parameter is only valid for line and area plots. Passing it to a bar chart will be silently ignored or cause an error.
Stacking behavior for mixed positive/negative values via barmode='relative' is already supported and will work correctly through **plotly_kwargs.
Remove line_shape='hv' from all three locations: 1551–1556, 1675–1680, and 2279–2283.
🤖 Prompt for AI Agents
In `@flixopt/statistics_accessor.py` around lines 1551 - 1556, The
ds.plotly.fast_bar calls are passing an unsupported parameter line_shape='hv';
remove the line_shape argument from each ds.plotly.fast_bar invocation (the ones
that assign to fig) so the call becomes fig = ds.plotly.fast_bar(title=...,
**color_kwargs, **plotly_kwargs), relying on plotly_kwargs (e.g., barmode) for
stacking/behavior instead.
Description
Brief description of the changes in this PR.
Type of Change
Related Issues
Closes #(issue number)
Testing
Checklist
Summary by CodeRabbit
New Features
Performance
Chores
✏️ Tip: You can customize this high-level summary in your review settings.