Merge pull request #4596 from plotly/update-docs-build

Update docs dependencies and Python version

Author: LiamConnors

Diff for: .circleci/config.yml

@@ -448,7 +448,7 @@ jobs:
     docker:
       # specify the version you desire here
       # use `-browsers` prefix for selenium tests, for example, `3.9-browsers`
-      - image: cimg/python:3.9-browsers
+      - image: cimg/python:3.10-browsers
 
     steps:
       - add_ssh_keys:

Diff for: binder/requirements.txt

@@ -2,10 +2,10 @@ jupytext
 plotly==5.22.0
 jupyter
 notebook
-pandas==1.2.0
-statsmodels==0.12.1
+pandas==2.2.2
+statsmodels==0.14.2
 scipy
-patsy==0.5.1
+patsy==0.5.6
 numpy
 plotly-geo
 psutil

Diff for: doc/python/3d-volume.md

@@ -86,7 +86,7 @@ np.random.seed(0)
 l = 30
 X, Y, Z = np.mgrid[:l, :l, :l]
 vol = np.zeros((l, l, l))
-pts = (l * np.random.rand(3, 15)).astype(np.int)
+pts = (l * np.random.rand(3, 15)).astype(int)
 vol[tuple(indices for indices in pts)] = 1
 from scipy import ndimage
 vol = ndimage.gaussian_filter(vol, 4)

Diff for: doc/python/axes.md

@@ -367,7 +367,7 @@ fig.show()
 
 *New in 5.19*
 
-If `tickangle` is not explicitly set, its default value is `auto`, meaning if the label needs to be rotated to avoid labels overlapping, it will rotate by either 30 or 90 degrees. Using `autotickangles`, you can also specify a list of angles for `tickangle` to use. If `tickangle` is `auto` and you provide a list of angles to `autotickangles`, the label angle will be set to the first value in the list that prevents overlap. 
+If `tickangle` is not explicitly set, its default value is `auto`, meaning if the label needs to be rotated to avoid labels overlapping, it will rotate by either 30 or 90 degrees. Using `autotickangles`, you can also specify a list of angles for `tickangle` to use. If `tickangle` is `auto` and you provide a list of angles to `autotickangles`, the label angle will be set to the first value in the list that prevents overlap.
 
 ```python
 import plotly.express as px
@@ -390,14 +390,18 @@ Here is an example.
 import plotly.graph_objects as go
 import pandas as pd
 
-# Load and filter Apple stock data for 2016
 apple_df = pd.read_csv(
-    "https://raw.githubusercontent.com/plotly/datasets/master/finance-charts-apple.csv",
-    parse_dates=["Date"],
-    index_col="Date"
+    "https://raw.githubusercontent.com/plotly/datasets/master/finance-charts-apple.csv"
 )
 
-apple_df_2016 = apple_df["2016"]
+# Convert 'Date' column to datetime format
+apple_df['Date'] = pd.to_datetime(apple_df['Date'])
+
+# Set 'Date' column as index
+apple_df.set_index('Date', inplace=True)
+
+# Filter for 2016
+apple_df_2016 = apple_df.loc['2016']
 
 # Create figure and add line
 fig = go.Figure()
@@ -599,7 +603,7 @@ fig.show()
 
 *New in 5.17*
 
-You can also set just a lower or upper bound manually and have autorange applied to the other bound by setting it to `None`. In the following example, we set a an upper bound of 4.5 on the x axes, while specifying `None` for the lower bound, meaning it will use autorange. On the y axes, we set the lower bound, and use `None` for the upper bound, meaning that uses autorange. 
+You can also set just a lower or upper bound manually and have autorange applied to the other bound by setting it to `None`. In the following example, we set a an upper bound of 4.5 on the x axes, while specifying `None` for the lower bound, meaning it will use autorange. On the y axes, we set the lower bound, and use `None` for the upper bound, meaning that uses autorange.
 
 ```python
 import plotly.express as px
@@ -857,7 +861,7 @@ fig.show()
 
 #### <code>nonnegative</code>, <code>tozero</code>, and <code>normal</code> Rangemode
 
-When you don't specify a range, autorange is used. It's also used for bounds set to `None` when providing a `range`. 
+When you don't specify a range, autorange is used. It's also used for bounds set to `None` when providing a `range`.
 
 The axis auto-range calculation logic can be configured using the `rangemode` axis parameter.
 
@@ -898,7 +902,7 @@ fig.update_xaxes(autorangeoptions=dict(maxallowed=5))
 fig.show()
 ```
 
-##### Clip Minimum and Maximum 
+##### Clip Minimum and Maximum
 
 You can also clip an axis range at a specific maximum or minimum value with `autorangeoptions.clipmax` and `autorangeoptions.clipmin`.
 
@@ -916,7 +920,7 @@ fig.show()
 
 ##### Specify Values to be Included
 
-Use `autorangeoptions.include` to specify a value that should always be included within the calculated autorange. In this example, we specify that for the autorange calculated on the x-axis, 5 should be included. 
+Use `autorangeoptions.include` to specify a value that should always be included within the calculated autorange. In this example, we specify that for the autorange calculated on the x-axis, 5 should be included.
 
 ```python
 import plotly.express as px

Diff for: doc/python/box-plots.md

@@ -458,12 +458,12 @@ x_data = ['Carmelo Anthony', 'Dwyane Wade',
 
 N = 50
 
-y0 = (10 * np.random.randn(N) + 30).astype(np.int)
-y1 = (13 * np.random.randn(N) + 38).astype(np.int)
-y2 = (11 * np.random.randn(N) + 33).astype(np.int)
-y3 = (9 * np.random.randn(N) + 36).astype(np.int)
-y4 = (15 * np.random.randn(N) + 31).astype(np.int)
-y5 = (12 * np.random.randn(N) + 40).astype(np.int)
+y0 = (10 * np.random.randn(N) + 30).astype(int)
+y1 = (13 * np.random.randn(N) + 38).astype(int)
+y2 = (11 * np.random.randn(N) + 33).astype(int)
+y3 = (9 * np.random.randn(N) + 36).astype(int)
+y4 = (15 * np.random.randn(N) + 31).astype(int)
+y5 = (12 * np.random.randn(N) + 40).astype(int)
 
 y_data = [y0, y1, y2, y3, y4, y5]
 

Diff for: doc/python/icicle-charts.md

@@ -305,7 +305,7 @@ def build_hierarchical_dataframe(df, levels, value_column, color_columns=None):
     Levels are given starting from the bottom to the top of the hierarchy,
     ie the last level corresponds to the root.
     """
-    df_all_trees = pd.DataFrame(columns=['id', 'parent', 'value', 'color'])
+    df_list = []
     for i, level in enumerate(levels):
         df_tree = pd.DataFrame(columns=['id', 'parent', 'value', 'color'])
         dfg = df.groupby(levels[i:]).sum()
@@ -317,11 +317,12 @@ def build_hierarchical_dataframe(df, levels, value_column, color_columns=None):
             df_tree['parent'] = 'total'
         df_tree['value'] = dfg[value_column]
         df_tree['color'] = dfg[color_columns[0]] / dfg[color_columns[1]]
-        df_all_trees = df_all_trees.append(df_tree, ignore_index=True)
+        df_list.append(df_tree)
     total = pd.Series(dict(id='total', parent='',
                               value=df[value_column].sum(),
-                              color=df[color_columns[0]].sum() / df[color_columns[1]].sum()))
-    df_all_trees = df_all_trees.append(total, ignore_index=True)
+                              color=df[color_columns[0]].sum() / df[color_columns[1]].sum()), name=0)
+    df_list.append(total)
+    df_all_trees = pd.concat(df_list, ignore_index=True)
     return df_all_trees
 
 

Diff for: doc/python/mixed-subplots.md

@@ -55,8 +55,8 @@ df = pd.read_csv(
 )
 
 # frequency of Country
-freq = df
-freq = freq.Country.value_counts().reset_index().rename(columns={"index": "x"})
+freq = df['Country'].value_counts().reset_index()
+freq.columns = ['x', 'Country']
 
 # read in 3d volcano surface data
 df_v = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/volcano.csv")

Diff for: doc/python/ml-regression.md

@@ -120,7 +120,7 @@ from sklearn.linear_model import LinearRegression
 from sklearn.model_selection import train_test_split
 
 df = px.data.tips()
-X = df.total_bill[:, None]
+X = df.total_bill.to_numpy()[:, None]
 X_train, X_test, y_train, y_test = train_test_split(X, df.tip, random_state=0)
 
 model = LinearRegression()
@@ -129,7 +129,6 @@ model.fit(X_train, y_train)
 x_range = np.linspace(X.min(), X.max(), 100)
 y_range = model.predict(x_range.reshape(-1, 1))
 
-
 fig = go.Figure([
     go.Scatter(x=X_train.squeeze(), y=y_train, name='train', mode='markers'),
     go.Scatter(x=X_test.squeeze(), y=y_test, name='test', mode='markers'),

Diff for: doc/python/sunburst-charts.md

@@ -355,7 +355,7 @@ def build_hierarchical_dataframe(df, levels, value_column, color_columns=None):
     Levels are given starting from the bottom to the top of the hierarchy,
     ie the last level corresponds to the root.
     """
-    df_all_trees = pd.DataFrame(columns=['id', 'parent', 'value', 'color'])
+    df_list = []
     for i, level in enumerate(levels):
         df_tree = pd.DataFrame(columns=['id', 'parent', 'value', 'color'])
         dfg = df.groupby(levels[i:]).sum()
@@ -367,11 +367,12 @@ def build_hierarchical_dataframe(df, levels, value_column, color_columns=None):
             df_tree['parent'] = 'total'
         df_tree['value'] = dfg[value_column]
         df_tree['color'] = dfg[color_columns[0]] / dfg[color_columns[1]]
-        df_all_trees = df_all_trees.append(df_tree, ignore_index=True)
+        df_list.append(df_tree)
     total = pd.Series(dict(id='total', parent='',
                               value=df[value_column].sum(),
-                              color=df[color_columns[0]].sum() / df[color_columns[1]].sum()))
-    df_all_trees = df_all_trees.append(total, ignore_index=True)
+                              color=df[color_columns[0]].sum() / df[color_columns[1]].sum()), name=0)
+    df_list.append(total)
+    df_all_trees = pd.concat(df_list, ignore_index=True)
     return df_all_trees
 
 

Diff for: doc/python/treemaps.md

@@ -90,7 +90,7 @@ When the argument of `color` corresponds to non-numerical data, discrete colors
 ```python
 import plotly.express as px
 df = px.data.tips()
-fig = px.treemap(df, path=[px.Constant("all"), 'sex', 'day', 'time'], 
+fig = px.treemap(df, path=[px.Constant("all"), 'sex', 'day', 'time'],
                  values='total_bill', color='day')
 fig.update_layout(margin = dict(t=50, l=25, r=25, b=25))
 fig.show()
@@ -101,7 +101,7 @@ In the example below the color of Saturday and Sunday sectors is the same as Din
 ```python
 import plotly.express as px
 df = px.data.tips()
-fig = px.treemap(df, path=[px.Constant("all"), 'sex', 'day', 'time'], 
+fig = px.treemap(df, path=[px.Constant("all"), 'sex', 'day', 'time'],
                  values='total_bill', color='time')
 fig.update_layout(margin = dict(t=50, l=25, r=25, b=25))
 fig.show()
@@ -114,7 +114,7 @@ For more information about discrete colors, see the [dedicated page](/python/dis
 ```python
 import plotly.express as px
 df = px.data.tips()
-fig = px.treemap(df, path=[px.Constant("all"), 'sex', 'day', 'time'], 
+fig = px.treemap(df, path=[px.Constant("all"), 'sex', 'day', 'time'],
                  values='total_bill', color='time',
                   color_discrete_map={'(?)':'lightgrey', 'Lunch':'gold', 'Dinner':'darkblue'})
 fig.update_layout(margin = dict(t=50, l=25, r=25, b=25))
@@ -241,7 +241,7 @@ fig = go.Figure(go.Treemap(
     labels = labels,
     values = values,
     parents = parents,
-    marker_colors = ["pink", "royalblue", "lightgray", "purple", 
+    marker_colors = ["pink", "royalblue", "lightgray", "purple",
                      "cyan", "lightgray", "lightblue", "lightgreen"]
 ))
 
@@ -316,7 +316,7 @@ def build_hierarchical_dataframe(df, levels, value_column, color_columns=None):
     Levels are given starting from the bottom to the top of the hierarchy,
     ie the last level corresponds to the root.
     """
-    df_all_trees = pd.DataFrame(columns=['id', 'parent', 'value', 'color'])
+    df_list = []
     for i, level in enumerate(levels):
         df_tree = pd.DataFrame(columns=['id', 'parent', 'value', 'color'])
         dfg = df.groupby(levels[i:]).sum()
@@ -328,11 +328,12 @@ def build_hierarchical_dataframe(df, levels, value_column, color_columns=None):
             df_tree['parent'] = 'total'
         df_tree['value'] = dfg[value_column]
         df_tree['color'] = dfg[color_columns[0]] / dfg[color_columns[1]]
-        df_all_trees = df_all_trees.append(df_tree, ignore_index=True)
+        df_list.append(df_tree)
     total = pd.Series(dict(id='total', parent='',
                               value=df[value_column].sum(),
-                              color=df[color_columns[0]].sum() / df[color_columns[1]].sum()))
-    df_all_trees = df_all_trees.append(total, ignore_index=True)
+                              color=df[color_columns[0]].sum() / df[color_columns[1]].sum()), name=0)
+    df_list.append(total)
+    df_all_trees = pd.concat(df_list, ignore_index=True)
     return df_all_trees
 
 

Diff for: doc/requirements.txt

@@ -4,21 +4,21 @@ ipywidgets==7.7.2
 jupyter-client<7
 jupyter
 notebook
-pandas==1.2.0
-statsmodels==0.12.1
-scipy==1.5.4
-patsy==0.5.1
-numpy==1.19.5
+pandas==2.2.2
+statsmodels==0.14.2
+scipy==1.13.0
+patsy==0.5.6
+numpy==1.26.4
 plotly-geo
 igraph
-geopandas==0.8.1
-pyshp==2.1.2
-shapely==1.7.1
+geopandas==0.14.3
+pyshp==2.3.1
+shapely==2.0.4
 psutil
 requests
-networkx==2.6.3
+networkx==3.3
 squarify
-scikit-image==0.18.1
+scikit-image==0.23.2
 scikit-learn
 sphinx==3.5.4
 sphinxcontrib-applehelp==1.0.2
@@ -31,7 +31,7 @@ sphinx_bootstrap_theme
 recommonmark
 pathlib
 python-frontmatter
-datashader==0.14.4
+datashader==0.16.1
 pyarrow
 cufflinks==0.17.3
 kaleido
@@ -42,7 +42,6 @@ nbconvert==5.6.1
 orjson
 dash-bio
 jinja2<3.1
-parmed<=3.4.4; python_version<"3.8"
-dask==2022.2.0
+dask==2024.4.2
 polars
-geoparse<=2.0.3
+xarray==2022.9.0