Merge pull request #59 from open-contracting/ah-chart-components

Ah chart components

README.md

@@ -48,6 +48,7 @@ To ease maintenance, the notebooks are made up of reusable components. To see wh
 Component name | Open in Colab | Tasks
 -- | -- | --
 [Environment](https://github.com/open-contracting/notebooks-ocds/blob/main/component_environment.ipynb) | [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/open-contracting/notebooks-ocds/blob/main/component_environment.ipynb) | Install requirements, import packages, load extensions and configure the notebook.
+[Charts setup](https://github.com/open-contracting/notebooks-ocds/blob/main/component_charts.ipynb) | [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/open-contracting/notebooks-ocds/blob/main/component_charts.ipynb) | Install charts requirements, import charts packages and define plot functions.
 [Kingfisher Process setup](https://github.com/open-contracting/notebooks-ocds/blob/main/component_setup_kingfisher.ipynb) | [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/open-contracting/notebooks-ocds/blob/main/component_setup_kingfisher.ipynb) | Connect to the database. Choose the collection(s) and schema to work with.
 [Field list setup](https://github.com/open-contracting/notebooks-ocds/blob/main/component_setup_fieldlist.ipynb) | [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/open-contracting/notebooks-ocds/blob/main/component_setup_fieldlist.ipynb) | Load the field list.
 [Data Registry setup](https://github.com/open-contracting/notebooks-ocds/blob/main/component_setup_registry.ipynb) | [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/open-contracting/notebooks-ocds/blob/main/component_setup_registry.ipynb) | Install Cardinal, download the data, and calculate the field list.

component_check_quality.ipynb

@@ -547,14 +547,7 @@
         "id": "yeBOaDsO6uDS"
       },
       "source": [
-        "release_count_chart = sns.catplot(\n",
-        "    x=\"release_count\", y=\"ocid_count\", kind=\"bar\", col=\"collection_id\", hue=\"release_type\", data=release_counts\n",
-        ").set_xticklabels(rotation=90)\n",
-        "\n",
-        "for ax in release_count_chart.axes.flat:\n",
-        "    format_thousands(ax.yaxis)\n",
-        "\n",
-        "plt.show(release_count_chart)"
+        "plot_release_count(release_counts)"
       ],
       "execution_count": null,
       "outputs": []

component_check_usability.ipynb

@@ -788,70 +788,7 @@
     {
       "cell_type": "code",
       "source": [
-        "if lang.value == \"English\":\n",
-        "    alt.Chart(result_final).transform_window(\n",
-        "        nrow=\"row_number(indicator)\", frame=[None, None], sort=[{\"field\": \"calculation\"}], groupby=[\"Use case\"]\n",
-        "    ).mark_circle(size=250, opacity=1).encode(\n",
-        "        x=alt.X(\n",
-        "            \"nrow\", type=\"quantitative\", axis=alt.Axis(title=[\"number of indicators\", \"\"], orient=\"top\", tickCount=5)\n",
-        "        ),\n",
-        "        y=alt.Y(\"Use case\", type=\"nominal\", sort=alt.Sort(field=\"indicator\", op=\"count\", order=\"descending\")),\n",
-        "        color=alt.Color(\n",
-        "            \"calculation\",\n",
-        "            type=\"nominal\",\n",
-        "            scale=alt.Scale(range=[\"#fb6045\", \"#d6e100\"]),\n",
-        "            legend=alt.Legend(title=[\"can we calculate it?\"]),\n",
-        "        ),\n",
-        "        tooltip=[\n",
-        "            alt.Tooltip(\"indicator\", type=\"nominal\"),\n",
-        "            alt.Tooltip(\"Use case\", type=\"nominal\"),\n",
-        "            alt.Tooltip(\"calculation\", type=\"nominal\"),\n",
-        "            alt.Tooltip(\"missing fields\", type=\"nominal\"),\n",
-        "        ],\n",
-        "    ).properties(\n",
-        "        width=600, height=350, padding=50, title=alt.TitleParams(text=\"\", subtitle=[\"\"], fontSize=18)\n",
-        "    ).configure_axis(\n",
-        "        titleFontSize=14, labelFontSize=14, labelPadding=5, ticks=False, domain=False\n",
-        "    ).configure_legend(\n",
-        "        labelFontSize=14, titleFontSize=14\n",
-        "    ).configure_view(\n",
-        "        strokeWidth=0\n",
-        "    ).display()\n",
-        "\n",
-        "else:\n",
-        "    alt.Chart(result_final).transform_window(\n",
-        "        nrow=\"row_number(Indicador)\",\n",
-        "        frame=[None, None],\n",
-        "        sort=[{\"field\": \"¿Se puede calcular?\"}],\n",
-        "        groupby=[\"Caso de Uso\"],\n",
-        "    ).mark_circle(size=250, opacity=1).encode(\n",
-        "        x=alt.X(\n",
-        "            \"nrow\",\n",
-        "            type=\"quantitative\",\n",
-        "            axis=alt.Axis(title=[\"Cantidad de indicadores\", \"\"], orient=\"top\", tickCount=5),\n",
-        "        ),\n",
-        "        y=alt.Y(\"Caso de Uso\", type=\"nominal\", sort=alt.Sort(field=\"Indicador\", op=\"count\", order=\"descending\")),\n",
-        "        color=alt.Color(\n",
-        "            \"¿Se puede calcular?\",\n",
-        "            type=\"nominal\",\n",
-        "            scale=alt.Scale(range=[\"#fb6045\", \"#d6e100\"]),\n",
-        "            legend=alt.Legend(title=[\"¿Se puede calcular?\"]),\n",
-        "        ),\n",
-        "        tooltip=[\n",
-        "            alt.Tooltip(\"Indicador\", type=\"nominal\"),\n",
-        "            alt.Tooltip(\"Caso de uso\", type=\"nominal\"),\n",
-        "            alt.Tooltip(\"¿Se puede calcular?\", type=\"nominal\"),\n",
-        "            alt.Tooltip(\"Campos faltantes\", type=\"nominal\"),\n",
-        "        ],\n",
-        "    ).properties(\n",
-        "        width=600, height=350, padding=50, title=alt.TitleParams(text=\"\", subtitle=[\"\"], fontSize=18)\n",
-        "    ).configure_axis(\n",
-        "        titleFontSize=14, labelFontSize=14, labelPadding=5, ticks=False, domain=False\n",
-        "    ).configure_legend(\n",
-        "        labelFontSize=14, titleFontSize=14\n",
-        "    ).configure_view(\n",
-        "        strokeWidth=0\n",
-        "    ).display()"
+        "plot_usability_indicators(result_final, lang.value)"
       ],
       "metadata": {
         "id": "3tW-Q8-uJC89"

component_environment.ipynb

@@ -36,7 +36,7 @@
       "cell_type": "code",
       "source": [
         "! pip install --upgrade pip > pip.log\n",
-        "! pip install --upgrade 'ocdskingfishercolab<0.4' altair ipywidgets matplotlib plotly psycopg2-binary seaborn >> pip.log"
+        "! pip install --upgrade 'ocdskingfishercolab<0.4' ipywidgets psycopg2-binary >> pip.log"
       ],
       "metadata": {
         "id": "X4nmyvOa_Ls7"
@@ -58,12 +58,8 @@
       "source": [
         "from collections import Counter\n",
         "\n",
-        "import altair as alt\n",
-        "import matplotlib.pyplot as plt\n",
         "import numpy as np\n",
         "import pandas as pd\n",
-        "import plotly.express as px\n",
-        "import seaborn as sns\n",
         "from google.colab.data_table import DataTable\n",
         "from google.colab.files import download\n",
         "from ipywidgets import widgets\n",

component_scope_kingfisher.ipynb

@@ -222,14 +222,7 @@
         "id": "mKo6Q4HimvQZ"
       },
       "source": [
-        "objects_per_stage_chart = sns.catplot(x=\"stage\", y=\"object_count\", kind=\"bar\", data=objects_per_stage).set_xticklabels(\n",
-        "    rotation=90\n",
-        ")\n",
-        "\n",
-        "for ax in objects_per_stage_chart.axes.flat:\n",
-        "    format_thousands(ax.yaxis)\n",
-        "\n",
-        "objects_per_stage"
+        "plot_objects_per_stage(objects_per_stage)"
       ],
       "execution_count": null,
       "outputs": []
@@ -372,13 +365,9 @@
       "source": [
         "# Resample by month\n",
         "release_dates = release_dates.set_index(\"date\")\n",
-        "release_dates = release_dates.groupby([\"collection_id\", \"release_type\"]).resample(\"M\").sum()\n",
-        "\n",
-        "fig, ax = plt.subplots(figsize=[15, 5])\n",
-        "sns.lineplot(data=release_dates, x=\"date\", y=\"release_count\", hue=\"collection_id\", style=\"release_type\")\n",
+        "release_dates = release_dates.groupby([\"collection_id\", \"release_type\"]).resample(\"M\").sum().reset_index()\n",
         "\n",
-        "format_thousands(ax.yaxis)\n",
-        "sns.despine()"
+        "plot_releases_by_month(release_dates)"
       ],
       "execution_count": null,
       "outputs": []

component_scope_usability.ipynb

@@ -155,18 +155,7 @@
     {
       "cell_type": "code",
       "source": [
-        "fig = px.bar(\n",
-        "    stages,\n",
-        "    x=\"stage\",\n",
-        "    y=\"object_count\",\n",
-        "    title=\"Stages covered\",\n",
-        "    template=\"plotly_white\",\n",
-        "    text=\"object_count\",\n",
-        "    labels={\"stage\": \"Stage\", \"object_count\": \"Number of releases\"},\n",
-        ")\n",
-        "fig.update_traces(marker_color=\"#D6E100\")\n",
-        "fig.update_layout(width=400, height=350, bargap=0.5)\n",
-        "fig.show()"
+        "plot_objects_per_stage(stages)"
       ],
       "metadata": {
         "id": "zGNrN_occdW5"
@@ -242,22 +231,7 @@
     {
       "cell_type": "code",
       "source": [
-        "final = pd.melt(dates, id_vars=[\"year\"], value_vars=[\"tenders\", \"awards\"])\n",
-        "fig = px.bar(\n",
-        "    final,\n",
-        "    x=\"year\",\n",
-        "    y=\"value\",\n",
-        "    color=\"variable\",\n",
-        "    barmode=\"group\",\n",
-        "    title=\"Tenders and awards by year\",\n",
-        "    template=\"plotly_white\",\n",
-        "    text=\"value\",\n",
-        "    color_discrete_sequence=[\"#D6E100\", \"#6c75e1\"],\n",
-        "    labels={\"value\": \"Tenders and awards\"},\n",
-        ")\n",
-        "fig.update_layout(width=600, height=350, bargap=0.5)\n",
-        "\n",
-        "fig.show()"
+        "plot_objects_per_year(dates)"
       ],
       "metadata": {
         "id": "ZFUPPW51dF4m"
@@ -371,20 +345,7 @@
     {
       "cell_type": "code",
       "source": [
-        "fig = px.bar(\n",
-        "    buyers.head(10),\n",
-        "    y=\"name\",\n",
-        "    x=\"total_tenders\",\n",
-        "    title=\"Top 10 buyers\",\n",
-        "    template=\"plotly_white\",\n",
-        "    text=\"total_tenders\",\n",
-        "    labels={\"total_tenders\": \"Number of procedures\", \"name\": \"buyer\"},\n",
-        "    color_discrete_sequence=[\"#D6E100\", \"#6c75e1\"],\n",
-        "    orientation=\"h\",\n",
-        ")\n",
-        "# fig.update_traces()\n",
-        "fig.update_layout(width=850, height=450, bargap=0.4, yaxis={\"categoryorder\": \"total ascending\"})\n",
-        "fig.show()"
+        "plot_top_buyers(buyers.head(10))"
       ],
       "metadata": {
         "id": "KmgHVCXaiCeG"

manage.py

@@ -17,19 +17,22 @@
     ],
     "template_publisher_analysis": [
         "component_environment",
+        "component_charts",
         "component_setup_kingfisher",
         "component_errors_kingfisher",
         "component_scope_kingfisher",
     ],
     "template_structure_and_format_feedback": [
         "component_environment",
+        "component_charts",
         "component_setup_kingfisher",
         "component_errors_kingfisher",
         "component_scope_kingfisher",
         "component_check_structure",
     ],
     "template_data_quality_feedback": [
         "component_environment",
+        "component_charts",
         "component_setup_kingfisher",
         "component_errors_kingfisher",
         "component_scope_kingfisher",
@@ -39,17 +42,20 @@
     ],
     "template_usability_checks": [
         "component_environment",
+        "component_charts",
         "component_setup_kingfisher",
         "component_scope_usability",
         "component_check_usability",
     ],
     "template_usability_checks_fieldlist": [
         "component_environment",
+        "component_charts",
         "component_setup_fieldlist",
         "component_check_usability",
     ],
     "template_usability_checks_registry": [
         "component_environment",
+        "component_charts",
         "component_setup_registry",
         "component_check_usability",
     ],

pyproject.toml

@@ -3,10 +3,10 @@ line-length = 119
 
 [tool.ruff]
 line-length = 119
-select = ["ALL"]
+lint.select = ["ALL"]
 target-version = "py310"
 extend-include = ["*.ipynb"]
-ignore = [
+lint.ignore = [
   "ANN", "COM", "CPY", "D", "EM",
   # https://docs.astral.sh/ruff/formatter/#conflicting-lint-rules
   "W191", "E501", "D206", "Q000", "Q001", "Q002", "Q003", "ISC001",
@@ -17,8 +17,8 @@ ignore = [
   "ERA001",  # commented-out code
 ]
 
-[tool.ruff.flake8-builtins]
+[tool.ruff.lint.flake8-builtins]
 builtins-ignorelist = ["copyright"]
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "template_*" = ["E402"]  # import not at top