Merge pull request #1868 from datadryad/3057-analyze-api-updates-need…

…ed-for-data-science-tools added jupyter notebooks examples in documentation
datadryad · Oct 23, 2024 · 0b15fd5 · 0b15fd5
2 parents bea47cb + cce5520
commit 0b15fd5
Show file tree

Hide file tree

Showing 4 changed files with 497 additions and 0 deletions.
diff --git a/.gitignore b/.gitignore
@@ -221,3 +221,6 @@ yarn-debug.log*
 .yarn-integrity
 
 /config/credentials/development.key
+
+# Jupyter notebooks checkpoints
+documentation/apis/Jupyter-Notebooks/.ipynb_checkpoints/
diff --git a/documentation/apis/Jupyter-Notebooks/create_dataset_notebook.ipynb b/documentation/apis/Jupyter-Notebooks/create_dataset_notebook.ipynb
@@ -0,0 +1,274 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cd03e984-7b12-4689-9d22-42a4b495a09e",
+   "metadata": {},
+   "source": [
+    "Import all needed libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e02e99ee-1c49-4197-b452-15ea2478beb6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "import urllib.parse\n",
+    "import urllib.request\n",
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a4388476-7221-4591-b391-269fe2cd02f1",
+   "metadata": {},
+   "source": [
+    "Set host and API credentials\n",
+    "* __host__               - API host\n",
+    "* __API_CLIENT_ID__      - API client ID\n",
+    "* __API_CLIENT_SECRET__  - API client secret\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c265b1b2-d713-4b0b-bcdc-def9ef474e2f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "host = 'https://sandbox.datadryad.org'\n",
+    "API_CLIENT_ID = \"[CLIENT_ID]\"\n",
+    "API_CLIENT_SECRET = \"[CLIENT_SECRET]\"\n",
+    "\n",
+    "headers = {\"Content-Type\": \"application/json\"}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5a9e7dea-9d24-4128-91e0-0dac589da4ea",
+   "metadata": {},
+   "source": [
+    "Authorize API connection and retrieve access token"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6f3bd89a-e475-4cec-8aa9-8254929a4842",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "payload = {'client_id': API_CLIENT_ID, 'client_secret': API_CLIENT_SECRET, 'grant_type': 'client_credentials'}\n",
+    "payload = {\n",
+    "    \"client_id\": API_CLIENT_ID,\n",
+    "    \"client_secret\": API_CLIENT_SECRET, \n",
+    "    \"grant_type\": \"client_credentials\"\n",
+    "}\n",
+    "url = f'{host}/oauth/token'\n",
+    "response = requests.post(url, data=json.dumps(payload), headers=headers)\n",
+    "\n",
+    "if response.status_code != 200:\n",
+    "    raise SystemExit(response.json()['error_description'])\n",
+    "token = response.json()['access_token']\n",
+    "\n",
+    "if not token:\n",
+    "    raise SystemExit('Unable to retrieve access token')\n",
+    "\n",
+    "headers['Authorization'] = f'{response.json()['token_type']} {token}'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a9a42849-70f6-42e7-9a57-086be116325c",
+   "metadata": {},
+   "source": [
+    "Create dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "9072c664-e89c-4286-9f4d-40387bff0e58",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "payload = {\n",
+    "    \"title\": \"Data from: Jupyter Notebook uploaded through API\",\n",
+    "    \"abstract\" : \"This study develops the random phylogenies rate test (RAPRATE), a likelihood method that simulates morphological evolution along randomly generated phylogenies, and uses it to determine whether a considerable difference in morphological diversity between two sister clades of South American fishes should be taken as evidence of differing rates of morphological change or lineage turnover.\",\n",
+    "    \"authors\" : [ \n",
+    "        {\n",
+    "            \"firstName\" : \"Test\",\n",
+    "    \t    \"lastName\" : \"Author\",\n",
+    "    \t    \"email\" : \"test@examples.com\",\n",
+    "    \t    \"orcid\" : \"0009-0000-4404-1689\",\n",
+    "    \t    \"affiliation\" : \"Oregon State University\",\n",
+    "    \t    \"affiliationROR\" : \"https://ror.org/00ysfqy60\"\n",
+    "    \t}\n",
+    "    ]\n",
+    "}\n",
+    "headers['Content-Type'] = 'application/json'\n",
+    "url = f'{host}/api/v2/datasets'\n",
+    "response = requests.post(url, data=json.dumps(payload), headers=headers)\n",
+    "dataset_id = response.json()['id']\n",
+    "dataset_url = f'{host}{response.json()['_links']['self']['href']}'\n",
+    "\n",
+    "if 'error' in response.json():\n",
+    "    raise SystemExit(response.json()['error']); exit\n",
+    "else:\n",
+    "    print('Resource successfully created')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6c4e2b56-ca10-4c26-a2ec-38cca903928f",
+   "metadata": {},
+   "source": [
+    "Update dataset and set missing information"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "71a45f81-0063-4643-a78a-f39a6144afbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "payload = {\n",
+    "  \"title\": \"A Study of Red-Black Trees with Weight\",\n",
+    "  \"authors\": [\n",
+    "    {\n",
+    "      \"firstName\": \"Matilda\",\n",
+    "      \"lastName\": \"Swinton\",\n",
+    "      \"email\": \"matilda.swinton@example.com\",\n",
+    "      \"affiliation\": \"Example Organization\"\n",
+    "    }\n",
+    "  ],\n",
+    "  \"abstract\": \"<p>Information theorists agree that \\\"fuzzy\\\" models are an interesting new topic in the field of machine learning.</p>\\r\\n\",\n",
+    "  \"funders\": [\n",
+    "    {\n",
+    "      \"organization\": \"Stichting Sem Presser Archief\",\n",
+    "      \"identifierType\": \"ror\",\n",
+    "      \"identifier\": \"https://ror.org/02f5r3008\",\n",
+    "      \"awardNumber\": \"12345\"\n",
+    "    }\n",
+    "  ],\n",
+    "  \"keywords\": [\n",
+    "    \"Cat\",\n",
+    "    \"Host\",\n",
+    "    \"Computer\",\n",
+    "    \"Log\"\n",
+    "  ],\n",
+    "  \"methods\": \"<p><br>\\r\\nMany mathematicians would agree that, had it not been for systems, the emulation of active networks might never have occurred. We view algorithms as following a cycle of four phases: simulation, investigation, observation, and investigation. After years of robust research into Boolean logic, we confirm the evaluation of Smalltalk. to what extent can spreadsheets be evaluated to realize this intent?</p>\\r\\n\",\n",
+    "  \"relatedWorks\": [\n",
+    "    {\n",
+    "      \"relationship\": \"article\",\n",
+    "      \"identifierType\": \"URL\",\n",
+    "      \"identifier\": \"http://example.org/cats\"\n",
+    "    }\n",
+    "  ],\n",
+    "  \"userId\": 2,\n",
+    "  \"email\": \"some_email@example.com\"\n",
+    "}\n",
+    "\n",
+    "headers['Content-Type'] = 'application/json'\n",
+    "response = requests.put(dataset_url, data=json.dumps(payload), headers=headers)\n",
+    "if response.status_code != 200:\n",
+    "    raise SystemExit(response.json()['error_description'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f6fe81b0-1fe0-43cb-9a00-b9a5a6bdeea8",
+   "metadata": {},
+   "source": [
+    "Embed a file on the dataset using file "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "eef23b0f-8dff-421e-8585-37ef6b8e3c43",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embed_url = f'{dataset_url}/urls'\n",
+    "payload = {\n",
+    "    \"url\": \"https://github.com/datadryad/dryad-app/blob/e927b514efe97fc08c7fc30d99389a5ec6d8a493/documentation/apis/sample_dataset.json\",\n",
+    "    \"digest\": \"aca3032d20c829a6060f1b90afda6d14\",\n",
+    "    \"digestType\": \"md5\",\n",
+    "    \"description\": \"This is the best file ever!\",\n",
+    "    \"size\": 1234,\n",
+    "    \"path\": \"api_submission.md\",\n",
+    "    \"mimeType\": \"text/plain\",\n",
+    "    \"skipValidation\": True\n",
+    "}\n",
+    "\n",
+    "headers['Content-Type'] = 'application/json'\n",
+    "response = requests.post(embed_url, data=json.dumps(payload), headers=headers)\n",
+    "if 'error' in response.json():\n",
+    "    raise SystemExit(response.json()['error']); exit\n",
+    "else:\n",
+    "    print('File successfuly embeded')\n",
+    "    \n",
+    "response.json()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8ce4c50a-5c38-4d0a-866b-95307b87dd13",
+   "metadata": {},
+   "source": [
+    "Submit dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "c1e18f98-e8bd-489e-9d88-9aea1191be5e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "payload = {\n",
+    "    \"op\": \"replace\",\n",
+    "    \"path\": \"/versionStatus\",\n",
+    "    \"value\": \"submitted\"\n",
+    "}\n",
+    "\n",
+    "headers['Content-Type'] = 'application/json-patch+json'\n",
+    "response = requests.patch(dataset_url, data=json.dumps(payload), headers=headers)\n",
+    "\n",
+    "errors = [obj['error'] for obj in response.json()]\n",
+    "\n",
+    "if len(errors) > 0:\n",
+    "    print('Errors: ')\n",
+    "    print(', '.join(errors))\n",
+    "else:\n",
+    "    print('Status successfully updated')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}