remove data from datastore (#79)

Author: JaGeo

example_workflows/arithmetic/jobflow.ipynb

@@ -38,16 +38,26 @@
    "cell_type": "code",
    "source": "from jobflow import job, Flow",
    "metadata": {
-    "trusted": true
+    "trusted": true,
+    "ExecuteTime": {
+     "end_time": "2025-04-24T10:30:16.328511Z",
+     "start_time": "2025-04-24T10:30:16.309562Z"
+    }
    },
    "outputs": [
     {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": "/srv/conda/envs/notebook/lib/python3.12/site-packages/paramiko/pkey.py:82: CryptographyDeprecationWarning: TripleDES has been moved to cryptography.hazmat.decrepit.ciphers.algorithms.TripleDES and will be removed from cryptography.hazmat.primitives.ciphers.algorithms in 48.0.0.\n  \"cipher\": algorithms.TripleDES,\n/srv/conda/envs/notebook/lib/python3.12/site-packages/paramiko/transport.py:253: CryptographyDeprecationWarning: TripleDES has been moved to cryptography.hazmat.decrepit.ciphers.algorithms.TripleDES and will be removed from cryptography.hazmat.primitives.ciphers.algorithms in 48.0.0.\n  \"class\": algorithms.TripleDES,\n"
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'jobflow'",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[31m---------------------------------------------------------------------------\u001B[39m",
+      "\u001B[31mModuleNotFoundError\u001B[39m                       Traceback (most recent call last)",
+      "\u001B[36mCell\u001B[39m\u001B[36m \u001B[39m\u001B[32mIn[4]\u001B[39m\u001B[32m, line 1\u001B[39m\n\u001B[32m----> \u001B[39m\u001B[32m1\u001B[39m \u001B[38;5;28;01mfrom\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34;01mjobflow\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[38;5;28;01mimport\u001B[39;00m job, Flow\n",
+      "\u001B[31mModuleNotFoundError\u001B[39m: No module named 'jobflow'"
+     ]
     }
    ],
-   "execution_count": 1
+   "execution_count": 4
   },
   {
    "id": "06c2bd9e-b2ac-4b88-9158-fa37331c3418",
@@ -60,35 +70,66 @@
    "execution_count": 2
   },
   {
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T10:30:04.618439Z",
+     "start_time": "2025-04-24T10:30:04.598701Z"
+    }
+   },
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": [
     "from workflow import (\n",
     "    get_sum as _get_sum,\n",
     "    get_prod_and_div as _get_prod_and_div,\n",
     ")"
    ],
-   "id": "f9217ce7b093b5fc"
+   "id": "f9217ce7b093b5fc",
+   "outputs": [],
+   "execution_count": 1
   },
   {
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T10:30:04.751088Z",
+     "start_time": "2025-04-24T10:30:04.748941Z"
+    }
+   },
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": "workflow_json_filename = \"jobflow_simple.json\"",
-   "id": "1feba0898ee4e361"
+   "id": "1feba0898ee4e361",
+   "outputs": [],
+   "execution_count": 2
   },
   {
    "id": "07598344-0f75-433b-8902-bea21a42088c",
    "cell_type": "code",
-   "source": "get_sum = job(_get_sum)\nget_prod_and_div = job(_get_prod_and_div, data=[\"prod\", \"div\"])",
+   "source": [
+    "get_sum = job(_get_sum)\n",
+    "# Note: one could also transfer the outputs to the datastore as well: get_prod_and_div = job(_get_prod_and_div, data=[\"prod\", \"div\"])\n",
+    "# On the way from the general definition to the jobflow definition, we do this automatically to avoid overflow databases.\n",
+    "get_prod_and_div = job(_get_prod_and_div)"
+   ],
    "metadata": {
-    "trusted": true
+    "trusted": true,
+    "ExecuteTime": {
+     "end_time": "2025-04-24T10:30:05.169761Z",
+     "start_time": "2025-04-24T10:30:05.043635Z"
+    }
    },
-   "outputs": [],
-   "execution_count": 5
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'job' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[31m---------------------------------------------------------------------------\u001B[39m",
+      "\u001B[31mNameError\u001B[39m                                 Traceback (most recent call last)",
+      "\u001B[36mCell\u001B[39m\u001B[36m \u001B[39m\u001B[32mIn[3]\u001B[39m\u001B[32m, line 1\u001B[39m\n\u001B[32m----> \u001B[39m\u001B[32m1\u001B[39m get_sum = \u001B[43mjob\u001B[49m(_get_sum)\n\u001B[32m      2\u001B[39m get_prod_and_div = job(_get_prod_and_div, data=[\u001B[33m\"\u001B[39m\u001B[33mprod\u001B[39m\u001B[33m\"\u001B[39m, \u001B[33m\"\u001B[39m\u001B[33mdiv\u001B[39m\u001B[33m\"\u001B[39m])\n",
+      "\u001B[31mNameError\u001B[39m: name 'job' is not defined"
+     ]
+    }
+   ],
+   "execution_count": 3
   },
   {
    "id": "ecef1ed5-a8d3-48c3-9e01-4a40e55c1153",

example_workflows/nfdi/jobflow.ipynb

@@ -79,8 +79,8 @@
    "execution_count": null,
    "source": [
     "generate_mesh = job(_generate_mesh)\n",
-    "convert_to_xdmf = job(_convert_to_xdmf, data=[\"xdmf_file\", \"h5_file\"])\n",
-    "poisson = job(_poisson, data=[\"numdofs\", \"pvd_file\", \"vtu_file\"])\n",
+    "convert_to_xdmf = job(_convert_to_xdmf)\n",
+    "poisson = job(_poisson)\n",
     "plot_over_line = job(_plot_over_line)\n",
     "substitute_macros = job(_substitute_macros)\n",
     "compile_paper = job(_compile_paper)"

example_workflows/quantum_espresso/jobflow.ipynb

@@ -87,7 +87,12 @@
   },
   {
    "cell_type": "code",
-   "source": "calculate_qe = job(_calculate_qe, data=[\"energy\", \"volume\", \"structure\"])\ngenerate_structures = job(_generate_structures, data=[f\"s_{i}\" for i in range(100)])\nplot_energy_volume_curve = job(_plot_energy_volume_curve)\nget_bulk_structure = job(_get_bulk_structure)",
+   "source": [
+    "calculate_qe = job(_calculate_qe)\n",
+    "generate_structures = job(_generate_structures)\n",
+    "plot_energy_volume_curve = job(_plot_energy_volume_curve)\n",
+    "get_bulk_structure = job(_get_bulk_structure)"
+   ],
    "metadata": {
     "trusted": true
    },