sandro.labruzzo
/
openaire_beginners_kit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

edited MD comments

This commit is contained in:
Andrea Mannocci 2023-06-06 16:40:31 +02:00
parent 630280d1c6
commit 4fecff9028
1 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
data/beginners_kit.ipynb
View File

@ -34,20 +34,20 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"!rm -rf data\n", "# !rm -rf data\n",
"!mkdir data\n", "# !mkdir data\n",
"\n", "\n",
"import os\n", "# import os\n",
"base_url = \"https://zenodo.org/record/7490192/files/\"\n", "# base_url = \"https://zenodo.org/record/7490192/files/\"\n",
"\n", "\n",
"\n", "\n",
"items =[\"communities_infrastructures.tar\",\"dataset.tar\",\"datasource.tar\",\"organization.tar\",\"otherresearchproduct.tar\",\"project.tar\",\"publication.tar\",\"relation.tar\", \"software.tar\"]\n", "# items =[\"communities_infrastructures.tar\",\"dataset.tar\",\"datasource.tar\",\"organization.tar\",\"otherresearchproduct.tar\",\"project.tar\",\"publication.tar\",\"relation.tar\", \"software.tar\"]\n",
"\n", "\n",
"for item in items: \n", "# for item in items: \n",
" print(f\"Downloading {item}\")\n", "# print(f\"Downloading {item}\")\n",
" os.system(f'wget {base_url}{item}?download=1 -O data/{item}')\n", "# os.system(f'wget {base_url}{item}?download=1 -O data/{item}')\n",
" print(f\"Extracting {item}\")\n", "# print(f\"Extracting {item}\")\n",
" os.system(f'tar -xf data/{item} -C data/; rm data/{item}')" "# os.system(f'tar -xf data/{item} -C data/; rm data/{item}')"
] ]
}, },
{ {
@ -55,7 +55,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Have a look at the input data" "## Load the datasets"
] ]
}, },
{ {
@ -279,7 +279,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"All the exercises follow the following template.\n", "All the exercises follow the template below.\n",
"```python\n", "```python\n",
"query = \"\"\"\n", "query = \"\"\"\n",
"SELECT <columns>\n", "SELECT <columns>\n",
@ -295,7 +295,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### **Task**: Split relations based on their semantics and compute their numbers; sort results in descending order, limit to the first 20. " "### **Task**: Split relations based on their semantics and count them; sort results in descending order, limit to the first 20. "
] ]
}, },
{ {
@ -323,7 +323,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### **Task:** Show the most occurring publication subject term; sort results in descending order; limit to the first 20" "### **Task:** Show the most occurring publication subjects; sort results in descending order; limit to the first 20"
] ]
}, },
{ {
@ -356,7 +356,7 @@
"tags": [] "tags": []
}, },
"source": [ "source": [
"### **Task:** Show the most co-occurring publication subjects from controlled vocabularies (i.e. scheme != 'keyword') avoiding repetition; limit to the first 20" "### **Task:** Show the most co-occurring publication subjects from controlled vocabularies (i.e., scheme != 'keyword') avoiding repetition; limit to the first 20"
] ]
}, },
{ {