\u001b[0m:\u001b[94m1\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m1 catalog \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m2 \u001b[0m\u001b[96mdir\u001b[0m(catalog) \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m3 \u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n",
"\u001b[1;91mNameError: \u001b[0mname \u001b[32m'catalog'\u001b[0m is not defined\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"catalog\n",
"dir(catalog)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "40417f25",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"[06/30/23 17:50:49] INFO Loading data from 'xmlreflector' (XMLHousesReflector)... data_catalog.py:345\n",
"\n"
],
"text/plain": [
"\u001b[2;36m[06/30/23 17:50:49]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO \u001b[0m Loading data from \u001b[32m'xmlreflector'\u001b[0m \u001b[1m(\u001b[0mXMLHousesReflector\u001b[1m)\u001b[0m\u001b[33m...\u001b[0m \u001b]8;id=287074;file:///home/gwen/.local/lib/python3.10/site-packages/kedro/io/data_catalog.py\u001b\\\u001b[2mdata_catalog.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=134334;file:///home/gwen/.local/lib/python3.10/site-packages/kedro/io/data_catalog.py#345\u001b\\\u001b[2m345\u001b[0m\u001b]8;;\u001b\\\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮\n",
"│ /home/gwen/.local/lib/python3.10/site-packages/kedro/io/core.py:187 in load │\n",
"│ │\n",
"│ 184 │ │ self._logger.debug(\"Loading %s\", str(self)) │\n",
"│ 185 │ │ │\n",
"│ 186 │ │ try: │\n",
"│ ❱ 187 │ │ │ return self._load() │\n",
"│ 188 │ │ except DataSetError: │\n",
"│ 189 │ │ │ raise │\n",
"│ 190 │ │ except Exception as exc: │\n",
"│ │\n",
"│ /media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/actes-princiers/src/actesdataset │\n",
"│ .py:62 in _load │\n",
"│ │\n",
"│ 59 │ │ self.filepath = filepath │\n",
"│ 60 │ │\n",
"│ 61 │ def _load(self): │\n",
"│ ❱ 62 │ │ raise \"C'est chargé!\" │\n",
"│ 63 │ │\n",
"│ 64 │ def _save(self): │\n",
"│ 65 │ │ raise NotImplementedError(\"Attention : dataset en lecture seule !\") │\n",
"╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\n",
"TypeError: exceptions must derive from BaseException\n",
"\n",
"The above exception was the direct cause of the following exception:\n",
"\n",
"╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮\n",
"│ /tmp/ipykernel_28884/4226322454.py:1 in <module> │\n",
"│ │\n",
"│ [Errno 2] No such file or directory: '/tmp/ipykernel_28884/4226322454.py' │\n",
"│ │\n",
"│ /home/gwen/.local/lib/python3.10/site-packages/kedro/io/data_catalog.py:349 in load │\n",
"│ │\n",
"│ 346 │ │ │ \"Loading data from '%s' (%s)...\", name, type(dataset).__name__ │\n",
"│ 347 │ │ ) │\n",
"│ 348 │ │ │\n",
"│ ❱ 349 │ │ result = dataset.load() │\n",
"│ 350 │ │ │\n",
"│ 351 │ │ return result │\n",
"│ 352 │\n",
"│ │\n",
"│ /home/gwen/.local/lib/python3.10/site-packages/kedro/io/core.py:196 in load │\n",
"│ │\n",
"│ 193 │ │ │ message = ( │\n",
"│ 194 │ │ │ │ f\"Failed while loading data from data set {str(self)}.\\n{str(exc)}\" │\n",
"│ 195 │ │ │ ) │\n",
"│ ❱ 196 │ │ │ raise DataSetError(message) from exc │\n",
"│ 197 │ │\n",
"│ 198 │ def save(self, data: _DI) -> None: │\n",
"│ 199 │ │ \"\"\"Saves data by delegation to the provided save method. │\n",
"╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\n",
"DataSetError: Failed while loading data from data set XMLHousesReflector(name=my own dataset).\n",
"exceptions must derive from BaseException\n",
"\n"
],
"text/plain": [
"\u001b[31m╭─\u001b[0m\u001b[31m────────────────────────────── \u001b[0m\u001b[1;31mTraceback \u001b[0m\u001b[1;2;31m(most recent call last)\u001b[0m\u001b[31m ───────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2;33m/home/gwen/.local/lib/python3.10/site-packages/kedro/io/\u001b[0m\u001b[1;33mcore.py\u001b[0m:\u001b[94m187\u001b[0m in \u001b[92mload\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m184 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[96mself\u001b[0m._logger.debug(\u001b[33m\"\u001b[0m\u001b[33mLoading \u001b[0m\u001b[33m%s\u001b[0m\u001b[33m\"\u001b[0m, \u001b[96mstr\u001b[0m(\u001b[96mself\u001b[0m)) \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m185 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m186 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mtry\u001b[0m: \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m187 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m \u001b[96mself\u001b[0m._load() \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m188 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mexcept\u001b[0m DataSetError: \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m189 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m190 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mexcept\u001b[0m \u001b[96mException\u001b[0m \u001b[94mas\u001b[0m exc: \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2;33m/media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/actes-princiers/src/\u001b[0m\u001b[1;33mactesdataset\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[1;33m.py\u001b[0m:\u001b[94m62\u001b[0m in \u001b[92m_load\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m 59 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[96mself\u001b[0m.filepath = filepath \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m 60 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m 61 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mdef\u001b[0m \u001b[92m_load\u001b[0m(\u001b[96mself\u001b[0m): \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 62 \u001b[2m│ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[33m\"\u001b[0m\u001b[33mC\u001b[0m\u001b[33m'\u001b[0m\u001b[33mest chargé!\u001b[0m\u001b[33m\"\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m 63 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m 64 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mdef\u001b[0m \u001b[92m_save\u001b[0m(\u001b[96mself\u001b[0m): \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m 65 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[96mNotImplementedError\u001b[0m(\u001b[33m\"\u001b[0m\u001b[33mAttention : dataset en lecture seule !\u001b[0m\u001b[33m\"\u001b[0m) \u001b[31m│\u001b[0m\n",
"\u001b[31m╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n",
"\u001b[1;91mTypeError: \u001b[0mexceptions must derive from BaseException\n",
"\n",
"\u001b[3mThe above exception was the direct cause of the following exception:\u001b[0m\n",
"\n",
"\u001b[31m╭─\u001b[0m\u001b[31m────────────────────────────── \u001b[0m\u001b[1;31mTraceback \u001b[0m\u001b[1;2;31m(most recent call last)\u001b[0m\u001b[31m ───────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2;33m/tmp/ipykernel_28884/\u001b[0m\u001b[1;33m4226322454.py\u001b[0m:\u001b[94m1\u001b[0m in \u001b[92m\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[3;31m[Errno 2] No such file or directory: '/tmp/ipykernel_28884/4226322454.py'\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2;33m/home/gwen/.local/lib/python3.10/site-packages/kedro/io/\u001b[0m\u001b[1;33mdata_catalog.py\u001b[0m:\u001b[94m349\u001b[0m in \u001b[92mload\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m346 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[33m\"\u001b[0m\u001b[33mLoading data from \u001b[0m\u001b[33m'\u001b[0m\u001b[33m%s\u001b[0m\u001b[33m'\u001b[0m\u001b[33m (\u001b[0m\u001b[33m%s\u001b[0m\u001b[33m)...\u001b[0m\u001b[33m\"\u001b[0m, name, \u001b[96mtype\u001b[0m(dataset).\u001b[91m__name__\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m347 \u001b[0m\u001b[2m│ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m348 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m349 \u001b[2m│ │ \u001b[0mresult = dataset.load() \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m350 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m351 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m result \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m352 \u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2;33m/home/gwen/.local/lib/python3.10/site-packages/kedro/io/\u001b[0m\u001b[1;33mcore.py\u001b[0m:\u001b[94m196\u001b[0m in \u001b[92mload\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m193 \u001b[0m\u001b[2m│ │ │ \u001b[0mmessage = ( \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m194 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[33mf\u001b[0m\u001b[33m\"\u001b[0m\u001b[33mFailed while loading data from data set \u001b[0m\u001b[33m{\u001b[0m\u001b[96mstr\u001b[0m(\u001b[96mself\u001b[0m)\u001b[33m}\u001b[0m\u001b[33m.\u001b[0m\u001b[33m\\n\u001b[0m\u001b[33m{\u001b[0m\u001b[96mstr\u001b[0m(exc)\u001b[33m}\u001b[0m\u001b[33m\"\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m195 \u001b[0m\u001b[2m│ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m196 \u001b[2m│ │ │ \u001b[0m\u001b[94mraise\u001b[0m DataSetError(message) \u001b[94mfrom\u001b[0m \u001b[4;96mexc\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m197 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m198 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mdef\u001b[0m \u001b[92msave\u001b[0m(\u001b[96mself\u001b[0m, data: _DI) -> \u001b[94mNone\u001b[0m: \u001b[31m│\u001b[0m\n",
"\u001b[31m│\u001b[0m \u001b[2m199 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[33m\"\"\"Saves data by delegation to the provided save method.\u001b[0m \u001b[31m│\u001b[0m\n",
"\u001b[31m╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n",
"\u001b[1;91mDataSetError: \u001b[0mFailed while loading data from data set \u001b[1;35mXMLHousesReflector\u001b[0m\u001b[1m(\u001b[0m\u001b[33mname\u001b[0m=\u001b[35mmy\u001b[0m own dataset\u001b[1m)\u001b[0m.\n",
"exceptions must derive from BaseException\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"catalog.load(\"xmlreflector\")"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "dc290e93",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"[06/16/23 15:56:44] INFO Loading data from 'actors' (CSVDataSet)... data_catalog.py:345\n",
"\n"
],
"text/plain": [
"\u001b[2;36m[06/16/23 15:56:44]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO \u001b[0m Loading data from \u001b[32m'actors'\u001b[0m \u001b[1m(\u001b[0mCSVDataSet\u001b[1m)\u001b[0m\u001b[33m...\u001b[0m \u001b]8;id=858812;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py\u001b\\\u001b[2mdata_catalog.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=44255;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py#345\u001b\\\u001b[2m345\u001b[0m\u001b]8;;\u001b\\\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" NAME | \n",
" ROLE | \n",
" HOUSE | \n",
" DATE1 | \n",
" DATE2 | \n",
" DATE3 | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" Charles Ier de Bourbon | \n",
" prince | \n",
" Bourbon | \n",
" 1400 | \n",
" 1434.0 | \n",
" 1456.0 | \n",
"
\n",
" \n",
" | 1 | \n",
" Gort, Étienne | \n",
" secret | \n",
" Bourbon | \n",
" 1425 | \n",
" 1440.0 | \n",
" NaN | \n",
"
\n",
" \n",
" | 2 | \n",
" Erart | \n",
" secret | \n",
" Berry | \n",
" 1404 | \n",
" 1405.0 | \n",
" NaN | \n",
"
\n",
" \n",
" | 3 | \n",
" Jean de Berry | \n",
" prince | \n",
" Berry | \n",
" 1337 | \n",
" 1360.0 | \n",
" 1416.0 | \n",
"
\n",
" \n",
" | 4 | \n",
" Agnès de Bourgogne | \n",
" prince | \n",
" Bourbon | \n",
" 1407 | \n",
" 1434.0 | \n",
" 1476.0 | \n",
"
\n",
" \n",
"
\n",
"
[06/16/23 14:58:30] INFO Loading data from 'actors' (CSVDataSet)... data_catalog.py:345\n",
"\n"
],
"text/plain": [
"\u001b[2;36m[06/16/23 14:58:30]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO \u001b[0m Loading data from \u001b[32m'actors'\u001b[0m \u001b[1m(\u001b[0mCSVDataSet\u001b[1m)\u001b[0m\u001b[33m...\u001b[0m \u001b]8;id=659228;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py\u001b\\\u001b[2mdata_catalog.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=160900;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py#345\u001b\\\u001b[2m345\u001b[0m\u001b]8;;\u001b\\\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"['NAME', 'ROLE', 'HOUSE', 'DATE1', 'DATE2', 'DATE3']"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"actors = catalog.load(\"actors\")\n",
"actors.columns.tolist()"
]
},
{
"cell_type": "markdown",
"id": "902dd387",
"metadata": {},
"source": [
"## Nettoyage des valeurs non renseignées\n",
"\n",
"Ligne d'origine (ligne 9) : \n",
"`\"René d'Anjou\";\"prince\";\"Anjou\";\"XXXX\";\"XXXX\";\"XXXX\"`\n"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "24fc62ce",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"NAME Bernard d'Armagnac\n",
"ROLE prince\n",
"HOUSE Armagnac\n",
"DATE1 NaN\n",
"DATE2 NaN\n",
"DATE3 NaN\n",
"Name: 9, dtype: object"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#actors.values\n",
"import numpy as np\n",
"cleaned_actors = actors.replace(\"XXXX\", np.NaN)\n",
"actors.head()\n",
"#actors.values\n",
"cleaned_actors.iloc[9]"
]
},
{
"cell_type": "markdown",
"id": "ee287f62",
"metadata": {},
"source": [
"## Autres catalogues"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "053ed17c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['actors',\n",
" 'corpus-agnes-bourgogne',\n",
" 'corpus-charles-i',\n",
" 'dataset_test',\n",
" 'preprocessed_dataset_test',\n",
" 'load_xml',\n",
" 'preprocess_html',\n",
" 'load_full_xml_catalog',\n",
" 'preprocess_full_catalog_html',\n",
" 'preprocessed_actors',\n",
" 'parameters',\n",
" 'params:xlststylesheet']"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"catalog.list()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "660b898c",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"[06/20/23 16:44:19] INFO Loading data from 'load_xml' (XMLDataSet)... data_catalog.py:345\n",
"\n"
],
"text/plain": [
"\u001b[2;36m[06/20/23 16:44:19]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO \u001b[0m Loading data from \u001b[32m'load_xml'\u001b[0m \u001b[1m(\u001b[0mXMLDataSet\u001b[1m)\u001b[0m\u001b[33m...\u001b[0m \u001b]8;id=813727;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py\u001b\\\u001b[2mdata_catalog.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=696103;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py#345\u001b\\\u001b[2m345\u001b[0m\u001b]8;;\u001b\\\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
""
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"catalog.load(\"load_xml\")"
]
},
{
"cell_type": "markdown",
"id": "a46ddef9",
"metadata": {},
"source": [
"## PartitionedDataset catalogs"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "96a60999",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"[06/22/23 15:01:39] INFO Loading data from 'load_full_xml_catalog' (PartitionedDataSet)... data_catalog.py:345\n",
"\n"
],
"text/plain": [
"\u001b[2;36m[06/22/23 15:01:39]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO \u001b[0m Loading data from \u001b[32m'load_full_xml_catalog'\u001b[0m \u001b[1m(\u001b[0mPartitionedDataSet\u001b[1m)\u001b[0m\u001b[33m...\u001b[0m \u001b]8;id=663642;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py\u001b\\\u001b[2mdata_catalog.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=709654;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py#345\u001b\\\u001b[2m345\u001b[0m\u001b]8;;\u001b\\\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO Loading data from 'load_full_xml_catalog' (PartitionedDataSet)... data_catalog.py:345\n",
"\n"
],
"text/plain": [
"\u001b[2;36m \u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO \u001b[0m Loading data from \u001b[32m'load_full_xml_catalog'\u001b[0m \u001b[1m(\u001b[0mPartitionedDataSet\u001b[1m)\u001b[0m\u001b[33m...\u001b[0m \u001b]8;id=916916;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py\u001b\\\u001b[2mdata_catalog.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=129179;file:///media/gwen/maxtor/gwen/entrepot/cnrs/nicolas/depot/datascience/.venv/lib/python3.9/site-packages/kedro/io/data_catalog.py#345\u001b\\\u001b[2m345\u001b[0m\u001b]8;;\u001b\\\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"{'anj_is_i_1441_08_05a': >,\n",
" 'anj_lo_i_1360_08a': >,\n",
" 'anj_lo_i_1371_07_08a': >,\n",
" 'anj_lo_ii_1401_04_28a': >,\n",
" 'anj_lo_ii_1402_11_07a': >,\n",
" 'anj_lo_ii_1405_05_02a': >,\n",
" 'anj_lo_ii_1406_01_26a': >,\n",
" 'anj_lo_ii_1406_04_15a': >,\n",
" 'anj_lo_ii_1409_08_07a': >,\n",
" 'anj_lo_ii_1409_12_12a': >,\n",
" 'anj_lo_ii_1413_03_01a': >,\n",
" 'anj_lo_iii_1420_11_04a': >,\n",
" 'anj_lo_iii_1422_02_09a': >,\n",
" 'anj_lo_iii_1424_03_31a': >,\n",
" 'anj_lo_iii_1424_03_31b': >,\n",
" 'anj_lo_iii_1428_06_07a': >,\n",
" 'anj_lo_iii_1428_06_07b': >,\n",
" 'anj_lo_iii_1432_10_27a': >,\n",
" 'anj_ma_i_1370_12_10a': >,\n",
" 'anj_re_i_1437_09_16a': >,\n",
" 'anj_re_i_1439_11_22a': >,\n",
" 'anj_re_i_1440_01_20a': >,\n",
" 'anj_re_i_1445a': >,\n",
" 'anj_re_i_1450_11_07a': >,\n",
" 'anj_re_i_1454_01_14a': >,\n",
" 'anj_re_i_1454_02_09a': >,\n",
" 'anj_re_i_1454_06_17a': >,\n",
" 'anj_re_i_1454_09_01a': >,\n",
" 'anj_re_i_1455_11_13a': >,\n",
" 'anj_re_i_1456_11_29a': >,\n",
" 'anj_re_i_1457_01_04a': >,\n",
" 'anj_re_i_1459_03_17a': >,\n",
" 'anj_re_i_1459_04_16a': >,\n",
" 'anj_re_i_1463_07_21a': >,\n",
" 'anj_re_i_1466_12_16a': >,\n",
" 'anj_re_i_1474_02_01a': >,\n",
" 'anj_re_i_1475_05_26a': >,\n",
" 'anj_yo_i_1418_12_20a': >,\n",
" 'anj_yo_i_1421_06_28a': >,\n",
" 'anj_yo_i_1442_02_24a': >}"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"partitions = catalog.load('load_full_xml_catalog')\n",
"catalog.load('load_full_xml_catalog')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "bdc37079",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
">"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"partitions['anj_is_i_1441_08_05a']"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Kedro (actes_princiers)",
"language": "python",
"name": "kedro_actes_princiers"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}