178 lines
3.7 KiB
Plaintext
178 lines
3.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "d8185790-0793-4881-99e8-6730f95a8006",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"import json\n",
|
|
"import pathlib\n",
|
|
"\n",
|
|
"import pandas as pd"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ea2b3e33-d58e-4e30-a0cc-8218a1f252c9",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"pd_options = {\n",
|
|
" \"display.max_rows\": None,\n",
|
|
"}\n",
|
|
"\n",
|
|
"[pd.set_option(option, value) for option, value in pd_options.items()]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "36149580-91d9-431d-99c3-51feee829e79",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"data_directory = (\n",
|
|
" pathlib.Path(\".\").resolve().parents[1] / \"data\" / \"scrapy\" / \"raw_country_data\"\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "d03be94e-8642-4916-8a43-1711e0c21b36",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"countries_file = data_directory / \"countries.json\"\n",
|
|
"countries = json.loads(countries_file.read_text())\n",
|
|
"# countries"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "29cca9ea-16d3-4534-8c9e-49fde37f8cdd",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"df = pd.read_json(countries_file)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ef8bc3ce-08dd-4260-807c-2616b2e1c1ba",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"country_url = df[\"country_url\"]\n",
|
|
"print(country_url.shape)\n",
|
|
"print(country_url.isnull().unique())\n",
|
|
"print(country_url.isna().unique())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "48db8f93-659b-45a4-8477-a7cec139bebc",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"short_country_name = df[\"short_country_name\"]\n",
|
|
"print(short_country_name.shape)\n",
|
|
"print(short_country_name.isnull().unique())\n",
|
|
"print(short_country_name.isna().unique())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a52f6aa2-5bbd-46e4-9b2f-cdbd7269cb6e",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"flag_description = df[\"flag_description\"]\n",
|
|
"print(flag_description.shape)\n",
|
|
"print(flag_description.isnull().unique())\n",
|
|
"print(flag_description.isna().unique())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "643e6512-1e5b-4eb2-9f0a-6b680ada787b",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"no_anthem = [item for item in [df[\"files\"]][0] if len(item) == 1]\n",
|
|
"print(len(no_anthem))\n",
|
|
"no_anthem"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "227b0c76-9e45-4849-849e-36355976cba9",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"df[\"short_country_name\"]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f7712d7d-9074-4fc5-89f2-6e5f47c57d20",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"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": "3.8.12"
|
|
},
|
|
"toc-autonumbering": true,
|
|
"toc-showcode": false
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|