{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "0",
      "metadata": {},
      "source": [
        "# Validation\n",
        "\n",
        "There are multiple ways to check if a file or dataframe are compliant with the BDF recommendations using the `validate()` function. The validate function take as an argument:\n",
        "\n",
        "- a filepath\n",
        "- a URL\n",
        "- a dataframe\n",
        "\n",
        "It compares the content of the object with the BDF and returns a report. "
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "1",
      "metadata": {},
      "outputs": [],
      "source": [
        "# Import the package\n",
        "import bdf"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "2",
      "metadata": {},
      "outputs": [],
      "source": [
        "# Read from a local file path and convert to bdf\n",
        "filepath = \"../../data/SINTEF__LiGrR2032__2024-04-30__25degC__Landt.csv\"\n",
        "df, meta = bdf.read(filepath)\n",
        "df = df.to_pandas()\n",
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "3",
      "metadata": {},
      "outputs": [],
      "source": [
        "# Validate the dataframe and print the report\n",
        "report = bdf.validate(df, report=True)\n",
        "print(report)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "4",
      "metadata": {},
      "outputs": [],
      "source": [
        "# Validate the file prior to bdf conversion\n",
        "report = bdf.validate(filepath, report=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "5",
      "metadata": {},
      "outputs": [],
      "source": [
        "# Validate all reference BDF files in examples/reference\n",
        "from pathlib import Path\n",
        "\n",
        "candidates = [Path('examples/reference'), Path('reference'), Path('../examples/reference')]\n",
        "reference_dir = next((p.resolve() for p in candidates if p.exists()), candidates[0].resolve())\n",
        "files = sorted(reference_dir.glob('*.csv'))\n",
        "print(f'Found {len(files)} reference files in {reference_dir}')\n",
        "\n",
        "results = []\n",
        "for path in files:\n",
        "    report = bdf.validate(path, report=False, raise_on_error=False)\n",
        "    results.append((path.name, bool(report['ok']), report.get('missing', []), report.get('extras', [])))\n",
        "\n",
        "for name, ok, missing, extras in results:\n",
        "    status = 'PASS' if ok else 'FAIL'\n",
        "    print(f'{status} | {name} | missing={len(missing)} | extras={len(extras)}')\n",
        "\n",
        "n_pass = sum(1 for _, ok, _, _ in results if ok)\n",
        "print(f'\\nSummary: {n_pass}/{len(results)} passed')\n",
        "if n_pass != len(results):\n",
        "    failed = [name for name, ok, _, _ in results if not ok]\n",
        "    print('Failed files:', failed)\n"
      ]
    }
  ],
  "metadata": {
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.10.10"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}