✈️ fix for #270 (#272)

* :plane: fix for #270 * ✨ add `customdata` to hf_data_container * 💪 adding tests * 💨 linting * 🙈 fix futurewarning * 🧹 formatting * 🙈 fix tests * ✈️ ➡️ 🇧🇪 Autosize support (#273) * ✈️ 🇧🇪 fix for #259 * 💨 linting * 💨 adding autosize support * ✨ updating action versions * 🙈 skip dtype test on window * 🙏 skip test --------- Co-authored-by: Jeroen Van Der Donckt <boebievdd@gmail.com>
predict-idlab · Nov 20, 2023 · 741da5d · 741da5d
1 parent 780062c
commit 741da5d
Show file tree

Hide file tree

Showing 7 changed files with 456 additions and 231 deletions.
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -10,18 +10,18 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
       with:
         lfs: true
     - name: Set up Python 3.10
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: '3.10'
     - name: Install Poetry
       uses: snok/install-poetry@v1
     - name: Cache poetry
       id: cached-poetry-dependencies
-      uses: actions/cache@v2
+      uses: actions/cache@v3
       with:
         path: ~/.cache/pypoetry/virtualenvs
         key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}-python-${{ matrix.python-version }}

diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -31,11 +31,11 @@ jobs:
         shell: bash
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
       with:
         lfs: true
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
@@ -50,7 +50,7 @@ jobs:
         version: 1.5.1
     - name: Cache poetry
       id: cached-poetry-dependencies
-      uses: actions/cache@v2
+      uses: actions/cache@v3
       with:
         path: ~/.cache/pypoetry/virtualenvs
         key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}-python-${{ matrix.python-version }}
@@ -70,12 +70,12 @@ jobs:
       run: |
         poetry run pytest --cov=plotly_resampler --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov-report=xml tests
     - name: Upload pytest test results
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: pytest-results-${{ matrix.python-version }}
         path: junit/test-results-${{ matrix.python-version }}.xml
         # Use always() to always run this step to publish test results when there are test failures
       if: ${{ always() }}
 
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v1
+      uses: codecov/codecov-action@v3
diff --git a/examples/basic_example.ipynb b/examples/basic_example.ipynb
diff --git a/plotly_resampler/figure_resampler/figure_resampler.py b/plotly_resampler/figure_resampler/figure_resampler.py
@@ -521,6 +521,8 @@ def show_dash(
         ), f"mode must be one of {available_modes}"
         graph_properties = {} if graph_properties is None else graph_properties
         assert "config" not in graph_properties  # There is a param for config
+        if self["layout"]["autosize"] is True and self["layout"]["height"] is None:
+            graph_properties.setdefault("style", {}).update({"height": "100%"})
 
         # 0. Check if the traces need to be updated when there is a xrange set
         # This will be the case when the users has set a xrange (via the `update_layout`
@@ -569,17 +571,18 @@ def show_dash(
         else:
             # jupyter dash uses a normal Dash app as figure
             app = dash.Dash("local_app", **app_init_kwargs)
-
+        # fmt: off
         div = dash.html.Div(
-            [
-                dash.dcc.Graph(
-                    id="resample-figure", figure=self, config=config, **graph_properties
-                ),
-                TraceUpdater(
-                    id="trace-updater", gdID="resample-figure", sequentialUpdate=False
-                ),
-            ]
+            style={
+                "display": "flex", "flex-flow": "column",
+                "height": "95vh", "width": "100%",
+            },
+            children=[
+                dash.dcc.Graph(id="resample-figure", figure=self, config=config, **graph_properties),
+                TraceUpdater(id="trace-updater", gdID="resample-figure", sequentialUpdate=False),
+            ],
         )
+        # # fmt: on
         if self._create_overview:
             overview_config = config.copy() if config is not None else {}
             overview_config["displayModeBar"] = False

diff --git a/plotly_resampler/figure_resampler/figure_resampler_interface.py b/plotly_resampler/figure_resampler/figure_resampler_interface.py
@@ -34,7 +34,8 @@
 # `_hf_data_container._asdict()` function is used in
 #  `AbstractFigureAggregator._construct_hf_data_dict`.
 _hf_data_container = namedtuple(
-    "DataContainer", ["x", "y", "text", "hovertext", "marker_size", "marker_color"]
+    "DataContainer",
+    ["x", "y", "text", "hovertext", "marker_size", "marker_color", "customdata"],
 )
 
 
@@ -152,8 +153,12 @@ def __init__(
 
         # A list of al xaxis and yaxis string names
         # e.g., "xaxis", "xaxis2", "xaxis3", .... for _xaxis_list
-        self._xaxis_list = self._re_matches(re.compile("xaxis\d*"), self._layout.keys())
-        self._yaxis_list = self._re_matches(re.compile("yaxis\d*"), self._layout.keys())
+        self._xaxis_list = self._re_matches(
+            re.compile(r"xaxis\d*"), self._layout.keys()
+        )
+        self._yaxis_list = self._re_matches(
+            re.compile(r"yaxis\d*"), self._layout.keys()
+        )
         # edge case: an empty `go.Figure()` does not yet contain axes keys
         if not len(self._xaxis_list):
             self._xaxis_list = ["xaxis"]
@@ -382,7 +387,7 @@ def _nest_dict_rec(k: str, v: any, out: dict) -> None:
                 out[k] = v
 
         # Check if (hover)text also needs to be downsampled
-        for k in ["text", "hovertext", "marker_size", "marker_color"]:
+        for k in ["text", "hovertext", "marker_size", "marker_color", "customdata"]:
             k_val = hf_trace_data.get(k)
             if isinstance(k_val, (np.ndarray, pd.Series)):
                 assert isinstance(
@@ -641,6 +646,8 @@ def _parse_get_trace_props(
             else hf_marker_color
         )
 
+        hf_customdata = trace["customdata"] if hasattr(trace, "customdata") else None
+
         if trace["type"].lower() in self._high_frequency_traces:
             if hf_x is None:  # if no data as x or hf_x is passed
                 if hf_y.ndim != 0:  # if hf_y is an array
@@ -742,7 +749,13 @@ def _parse_get_trace_props(
                     trace.marker.color = hf_marker_color
 
         return _hf_data_container(
-            hf_x, hf_y, hf_text, hf_hovertext, hf_marker_size, hf_marker_color
+            hf_x,
+            hf_y,
+            hf_text,
+            hf_hovertext,
+            hf_marker_size,
+            hf_marker_color,
+            hf_customdata,
         )
 
     def _construct_hf_data_dict(

diff --git a/tests/test_figure_resampler.py b/tests/test_figure_resampler.py
@@ -2,10 +2,10 @@
 
 __author__ = "Jonas Van Der Donckt, Jeroen Van Der Donckt, Emiel Deprost"
 
-
 import datetime
 import multiprocessing
 import subprocess
+import sys
 import time
 from datetime import timedelta
 from typing import List
@@ -129,6 +129,10 @@ def test_add_trace_not_resampling_insert_gaps():
 
 
 def test_various_dtypes(float_series):
+    # skip the test on windows
+    if sys.platform.lower().startswith("win"):
+        pytest.skip("Skipping test on windows")
+
     # List of dtypes supported by orjson >= 3.8
     valid_dtype_list = [
         np.bool_,
@@ -1192,6 +1196,9 @@ def test_showdash_not_hanging_when_port_in_use():
 
 
 def test_manual_jupyterdashpersistentinline():
+    if sys.platform.lower().startswith("win"):
+        pytest.skip("This test is currently not supported on windows")
+
     # Manually call the JupyterDashPersistentInline its method
     # This requires some gimmicky stuff to mimmick the behaviour of a jupyter notebook.
 

diff --git a/tests/test_plotly_express.py b/tests/test_plotly_express.py
@@ -0,0 +1,55 @@
+import numpy as np
+import pandas as pd
+import plotly.express as px
+
+from plotly_resampler import register_plotly_resampler, unregister_plotly_resampler
+
+
+def test_px_hoverlabel_figureResampler():
+    labels = list(range(0, 3))
+    N = 60_000
+    x = np.arange(N)
+    y = np.random.normal(size=N)
+    label = np.random.randint(low=labels[0], high=labels[-1] + 1, size=N).astype(str)
+    description = np.random.randint(low=3, high=5, size=N)
+
+    df = pd.DataFrame.from_dict(
+        {"x": x, "y": y, "label": label, "description": description}
+    )
+
+    x_label = "x"
+    y_label = "y"
+    label_label = "label"
+    df = df.sort_values(by=[x_label])
+
+    # Without resampler, shows correct hover data
+    fig = px.scatter(
+        df,
+        x=x_label,
+        y=y_label,
+        color=label_label,
+        title="Without resampler",
+        hover_data=["description"],
+    )
+
+    # With resampler, shows incorrect hover data
+    register_plotly_resampler(mode="auto", default_n_shown_samples=1000)
+    fig2 = px.scatter(
+        df,
+        x=x_label,
+        y=y_label,
+        color=label_label,
+        title="With resampler",
+        hover_data=["description"],
+    )
+
+    # verify whether the selected has the same y and customdata as the original
+    for idx in range(len(fig.data)):
+        trc_orig = fig.data[idx]
+        trc_res = fig2.data[idx]
+
+        agg_indices = np.searchsorted(trc_orig["x"], trc_res["x"]).ravel()
+        for k in ["customdata", "y"]:
+            assert all(trc_orig[k].ravel()[agg_indices] == trc_res[k].ravel())
+
+    unregister_plotly_resampler()