hiveplotlib 0.21__tar.gz → 0.23.0__tar.gz

{hiveplotlib-0.21 → hiveplotlib-0.23.0}/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2020 - 2022, Geometric Data Analytics, Inc.
+Copyright (c) 2020 - 2023, Geometric Data Analytics, Inc.
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without modification,

{hiveplotlib-0.21/src/hiveplotlib.egg-info → hiveplotlib-0.23.0}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.1
 Name: hiveplotlib
-Version: 0.21
+Version: 0.23.0
 Summary: Visualize Network Data with Hive Plots
 Author-email: Gary Koplik <gary.koplik@geomdata.com>
-License: Copyright (c) 2020 - 2022, Geometric Data Analytics, Inc.
+License: Copyright (c) 2020 - 2023, Geometric Data Analytics, Inc.
         All rights reserved.
         
         Redistribution and use in source and binary forms, with or without modification,
@@ -34,13 +34,40 @@ License: Copyright (c) 2020 - 2022, Geometric Data Analytics, Inc.
 Project-URL: Documentation, https://geomdata.gitlab.io/hiveplotlib/
 Project-URL: Source, https://gitlab.com/geomdata/hiveplotlib
 Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: matplotlib
+Requires-Dist: numpy
+Requires-Dist: pandas
 Provides-Extra: bokeh
+Requires-Dist: bokeh; extra == "bokeh"
 Provides-Extra: datashader
+Requires-Dist: datashader; extra == "datashader"
+Requires-Dist: seaborn; extra == "datashader"
 Provides-Extra: dev
+Requires-Dist: bokeh; extra == "dev"
+Requires-Dist: datashader; extra == "dev"
+Requires-Dist: jupyter; extra == "dev"
+Requires-Dist: networkx; extra == "dev"
+Requires-Dist: seaborn; extra == "dev"
+Requires-Dist: tqdm; extra == "dev"
 Provides-Extra: docs
+Requires-Dist: nbsphinx; extra == "docs"
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: sphinx-rtd-theme; extra == "docs"
+Requires-Dist: toml; extra == "docs"
 Provides-Extra: networkx
+Requires-Dist: networkx; extra == "networkx"
+Provides-Extra: plotly
+Requires-Dist: plotly; extra == "plotly"
 Provides-Extra: testing
-License-File: LICENSE
+Requires-Dist: black[jupyter]; extra == "testing"
+Requires-Dist: flake8-docstrings; extra == "testing"
+Requires-Dist: Flake8-pyproject; extra == "testing"
+Requires-Dist: pytest; extra == "testing"
+Requires-Dist: pytest-cov; extra == "testing"
+Requires-Dist: pytest-html; extra == "testing"
+Requires-Dist: pytest-timeout; extra == "testing"
+Requires-Dist: pytest-xdist; extra == "testing"
 
 ![](https://geomdata.gitlab.io/hiveplotlib/_static/hiveplotlib.svg)
 

{hiveplotlib-0.21 → hiveplotlib-0.23.0}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hiveplotlib"
-version = "0.21"
+version = "0.23.0"
 authors = [
     {name="Gary Koplik", email="gary.koplik@geomdata.com"}
 ]
@@ -54,7 +54,12 @@ networkx = [
     "networkx"
 ]
 
+plotly = [
+    "plotly"
+]
+
 testing = [
+    "black[jupyter]",
     "flake8-docstrings",
     "Flake8-pyproject",
     "pytest",
@@ -68,6 +73,11 @@ testing = [
 where = ["src"]
 include = ["hiveplotlib*"]
 
+[tool.black]
+line-length = 88
+target-version = ["py311"]
+include = '\.pyi?$|examples\/.*\.ipynb?$'
+
 [tool.flake8]
 exclude = [
     "*_test.py",
@@ -76,10 +86,12 @@ exclude = [
     "sandbox",
     "setup.py",
 ]
-ignore = [
+extend_ignore = [
     "D200",  # 1-line docstrings will be tolerated
-    "E501"  # can't check line-length and have long hyperlinks in the docs
+    "E203",  # https://black.readthedocs.io/en/stable/faq.html#why-are-flake8-s-e203-and-w503-violated
+    "W503"  # docs literally say this should not be a thing https://www.flake8rules.com/rules/W504.html
 ]
-color = "always"
+# keeping a longer-allowed line-length on flake8 side for existing docs
+max-line-length = 120
 show-source = true
 count = true

{hiveplotlib-0.21 → hiveplotlib-0.23.0}/src/hiveplotlib/axis.py

@@ -49,8 +49,14 @@ class Axis:
             axis2 = Axis(axis_id="a2", start=1, end=5, angle=240, long_name="Axis 2")
     """
 
-    def __init__(self, axis_id: Hashable, start: float = 1, end: float = 5,
-                 angle: float = 0, long_name: Optional[Hashable] = None):
+    def __init__(
+        self,
+        axis_id: Hashable,
+        start: float = 1,
+        end: float = 5,
+        angle: float = 0,
+        long_name: Optional[Hashable] = None,
+    ):
         """
         Initialize ``Axis`` object with start and end positions and angle. Default to axis normalized on [0, 1].
 
@@ -83,7 +89,7 @@ class Axis:
         self.node_placement_label = None
 
         # hold all the cartesian coordinates, polar rho, and corresponding labels in a pandas dataframe
-        self.node_placements = pd.DataFrame(columns=['x', 'y', 'unique_id', 'rho'])
+        self.node_placements = pd.DataFrame(columns=["x", "y", "unique_id", "rho"])
 
     def __repr__(self) -> str:
         """
@@ -91,7 +97,9 @@ class Axis:
         """
         return f"hiveplotlib.Axis {self.axis_id}"
 
-    def _set_node_placements(self, x: List[float], y: List[float], node_ids: List[Hashable], rho: List[float]):
+    def _set_node_placements(
+        self, x: List[float], y: List[float], node_ids: List[Hashable], rho: List[float]
+    ):
         """
         Set ``Axis.node_placements`` to a ``pandas.DataFrame``.
 
@@ -108,10 +116,16 @@ class Axis:
         :param rho: ``list-like`` of polar coordinate distance values corresponding to x, y, and unique ID values.
         :return: ``None``.
         """
-        assert np.array(x).shape[0] == np.array(y).shape[0] == np.array(node_ids).shape[0] == np.array(rho).shape[0], \
-            "Must provide the same number of x values, y values, and node IDs"
-
-        self.node_placements = pd.DataFrame.from_dict({'x': x, 'y': y, 'unique_id': node_ids, 'rho': rho})
+        assert (
+            np.array(x).shape[0]
+            == np.array(y).shape[0]
+            == np.array(node_ids).shape[0]
+            == np.array(rho).shape[0]
+        ), "Must provide the same number of x values, y values, and node IDs"
+
+        self.node_placements = pd.DataFrame.from_dict(
+            {"x": x, "y": y, "unique_id": node_ids, "rho": rho}
+        )
 
         return None
 

{hiveplotlib-0.21 → hiveplotlib-0.23.0}/src/hiveplotlib/datasets/__init__.py

@@ -18,13 +18,15 @@ For Polar Parallel Coordinates Plots (P2CPs), many datasets are available throug
 
 import json
 import numpy as np
+from hiveplotlib import hive_plot_n_axes, HivePlot, Node
 import pandas as pd
 from pathlib import Path
 from typing import Dict, Optional, Tuple, Union
 
 
-def international_trade_data(year: int = 2019, hs92_code: int = 8112,
-                             path: Optional[Union[str, Path]] = None) -> Tuple[pd.DataFrame, Dict]:
+def international_trade_data(
+    year: int = 2019, hs92_code: int = 8112, path: Optional[Union[str, Path]] = None
+) -> Tuple[pd.DataFrame, Dict]:
     """
     Read in international trade data network from the Harvard Growth Lab.
 
@@ -61,29 +63,37 @@ def international_trade_data(year: int = 2019, hs92_code: int = 8112,
         path = Path(path)
 
     # grab the shipped year, hs92 values to present what's available on failure
-    csv_files = [i.stem for i in sorted(internal_path.glob("international_exports*.csv"))]
+    csv_files = [
+        i.stem for i in sorted(internal_path.glob("international_exports*.csv"))
+    ]
     csv_years = [i.split("_")[2] for i in csv_files]
     csv_hs92 = [i.split("_")[-1] for i in csv_files]
-    hiveplotlib_supported_values = pd.DataFrame(np.c_[csv_years, csv_hs92], columns=["Year", "Trade Code"])
+    hiveplotlib_supported_values = pd.DataFrame(
+        np.c_[csv_years, csv_hs92], columns=["Year", "Trade Code"]
+    )
 
     # check that our implied data and metadata files exist
     data_path = path.joinpath(f"international_exports_{year}_{hs92_code}.csv")
-    metadata_path = path.joinpath(f"international_exports_metadata_{year}_{hs92_code}.json")
-    assert data_path.exists() and metadata_path.exists(), \
-        f"Could not find data and / or metadata under specified `path`. If you specified your own path, double check " \
-        f"that the path is correct. Your file names should be " \
-        f"If you are using `hiveplotlib` supported data, note that only the following `year`, " \
+    metadata_path = path.joinpath(
+        f"international_exports_metadata_{year}_{hs92_code}.json"
+    )
+    assert data_path.exists() and metadata_path.exists(), (
+        f"Could not find data and / or metadata under specified `path`. If you specified your own path, double check "
+        f"that the path is correct. Your file names should be "
+        f"If you are using `hiveplotlib` supported data, note that only the following `year`, "
         f"`hs29_code` values are supported:\n{hiveplotlib_supported_values}"
+    )
 
     data = pd.read_csv(data_path)
-    with open(metadata_path, 'r') as openfile:
+    with open(metadata_path, "r") as openfile:
         metadata = json.load(openfile)
 
     return data, metadata
 
 
-def four_gaussian_blobs_3d(num_points: int = 50, noise: float = 0.5,
-                           random_seed: int = 0) -> pd.DataFrame:
+def four_gaussian_blobs_3d(
+    num_points: int = 50, noise: float = 0.5, random_seed: int = 0
+) -> pd.DataFrame:
     """
     Generate a ``pandas`` dataframe of four Gaussian blobs in 3d.
 
@@ -113,8 +123,9 @@ def four_gaussian_blobs_3d(num_points: int = 50, noise: float = 0.5,
     for i in [0, 5]:
         for j in [0, 5]:
             for k in [0, 5]:
-                b = rng.normal(scale=noise,
-                               size=num_points * dim).reshape(num_points, dim)
+                b = rng.normal(scale=noise, size=num_points * dim).reshape(
+                    num_points, dim
+                )
                 b[:, 0] += i
                 b[:, 1] += j
                 b[:, 2] += k
@@ -123,8 +134,9 @@ def four_gaussian_blobs_3d(num_points: int = 50, noise: float = 0.5,
                 coords.append((i, j, k))
 
     # put our 4 blobs of interest into a single dataframe
-    df = pd.DataFrame(np.row_stack([b_list[i] for i in corners_to_keep]),
-                      columns=feature_names)
+    df = pd.DataFrame(
+        np.row_stack([b_list[i] for i in corners_to_keep]), columns=feature_names
+    )
 
     # make the labels ints
     df.Label = df.Label.astype(int)
@@ -132,3 +144,76 @@ def four_gaussian_blobs_3d(num_points: int = 50, noise: float = 0.5,
     df.Label.values[df.Label.values == 4] = 3
 
     return df
+
+
+def example_hive_plot(
+    num_nodes: int = 15,
+    num_edges: int = 30,
+    seed: int = 0,
+    **hive_plot_n_axes_kwargs,
+) -> HivePlot:
+    """
+    Generate example hive plot with ``"Low"``, ``"Medium"``, and ``"High"`` axes (plus repeat axes).
+
+    Nodes and edges will be generated and placed randomly.
+
+    :param num_nodes: number of nodes to generate.
+    :param num_edges: number of edges to generate.
+    :param seed: random seed to use when generating nodes and edges.
+    :param hive_plot_n_axes_kwargs: additional keyword arguments for the underlying
+        :py:func:`hiveplotlib.hive_plot.hive_plot_n_axes()` call.
+    :return: resulting ``HivePlot`` instance.
+    """
+    color_dict = {
+        "Low": {"Low_repeat": "#006BA4", "High_repeat": "#FF800E"},
+        "High": {"Medium_repeat": "#ABABAB", "High_repeat": "#595959"},
+        "Medium": {"Medium_repeat": "#5F9ED1", "Low_repeat": "#C85200"},
+        "Low_repeat": {"Low": "#006BA4", "Medium": "#C85200"},
+        "Medium_repeat": {"Medium": "#5F9ED1", "High": "#ABABAB"},
+        "High_repeat": {"High": "#595959", "Low": "#FF800E"},
+    }
+
+    rng = np.random.default_rng(seed)
+    data = pd.DataFrame(
+        np.c_[
+            rng.uniform(low=0, high=10, size=num_nodes),
+            rng.uniform(low=10, high=20, size=num_nodes),
+            rng.uniform(low=20, high=30, size=num_nodes),
+        ],
+        columns=["low", "med", "high"],
+    )
+
+    # convert into dict for later use
+    node_data = data.to_dict(orient="records")
+
+    # use the dataframe's index as unique id
+    node_ids = data.index.values
+
+    nodes = [
+        Node(unique_id=node_id, data=node_data[i]) for i, node_id in enumerate(node_ids)
+    ]
+
+    edges = rng.choice(node_ids, size=num_edges * 2).reshape(-1, 2)
+
+    hp = hive_plot_n_axes(
+        node_list=nodes,
+        edges=edges,
+        axes_assignments=[
+            np.arange(num_nodes)[: num_nodes // 3],
+            np.arange(num_nodes)[num_nodes // 3 : 2 * num_nodes // 3],
+            np.arange(num_nodes)[2 * num_nodes // 3 :],
+        ],
+        sorting_variables=["low", "med", "high"],
+        repeat_axes=[True, True, True],
+        axes_names=["Low", "Medium", "High"],
+        orient_angle=-30,
+        **hive_plot_n_axes_kwargs,
+    )
+
+    # set colors according to above-defined color dictionary
+    #  (so we can replicate more easily in other viz later)
+    for e1 in color_dict:
+        for e2 in color_dict[e1]:
+            hp.add_edge_kwargs(axis_id_1=e1, axis_id_2=e2, color=color_dict[e1][e2])
+
+    return hp