Removed the jupyter connector.

This commit is contained in:
Philipp Horstenkamp 2023-01-10 23:58:17 +01:00
parent e949d7467f
commit 3a2b9b1b2a
Signed by: Philipp
GPG Key ID: DD53EAC36AFB61B4
1 changed files with 0 additions and 288 deletions

View File

@ -1,288 +0,0 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "f536eab6-2776-4535-972a-3ece6be99b3a",
"metadata": {},
"outputs": [],
"source": [
"import warnings\n",
"\n",
"warnings.simplefilter(action=\"ignore\", category=FutureWarning)"
]
},
{
"cell_type": "markdown",
"id": "f6597a28-a4fc-46bb-a9b2-3cafbc944ef5",
"metadata": {},
"source": [
"# Start here\n",
"### Install couchbase and pandas with specified versions\n",
"The cell below installs the couchbase python package and pandas."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "0c9dbddc-f5f5-4f58-a2e2-dfff0faf517f",
"metadata": {},
"outputs": [],
"source": [
"!pip install couchbase==4.1.1 -q\n",
"!pip install pandas==1.5.2 -q"
]
},
{
"cell_type": "markdown",
"id": "8f41454c-0bf0-4e53-992b-34fb47bf7dd1",
"metadata": {},
"source": [
"Import the the classes necessary to run the couchbase connector."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "5c4c7d02-c06b-49c3-a6e6-9819e9eae44b",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from couchbase.cluster import Cluster\n",
"from couchbase.auth import PasswordAuthenticator\n",
"\n",
"from couchbase.options import ClusterOptions, QueryOptions"
]
},
{
"cell_type": "markdown",
"id": "2e5173f8-7c64-40f4-8fbe-e3bf28ad96a3",
"metadata": {},
"source": [
"Connect to the cluster select the sample bucket and connect to the default collection."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "66ada60d-8a49-473b-bc38-a40999ba761a",
"metadata": {},
"outputs": [],
"source": [
"cluster = Cluster.connect(\n",
" \"couchbase://couchbase1\",\n",
" ClusterOptions(\n",
" PasswordAuthenticator(\"Administrator\", \"some-pw-that-is-better-than-this!\")\n",
" ),\n",
")\n",
"bucket = cluster.bucket(\"travel-sample\")\n",
"\n",
"# get a reference to the default collection\n",
"cb_coll = bucket.default_collection()"
]
},
{
"cell_type": "markdown",
"id": "3dbc2840-9793-4a92-802b-78d0b333e632",
"metadata": {},
"source": [
"Acces a document by key."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "5e5fd8c8-200f-4857-b63d-1172b842f11c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'id': 10,\n",
" 'type': 'airline',\n",
" 'name': '40-Mile Air',\n",
" 'iata': 'Q5',\n",
" 'icao': 'MLA',\n",
" 'callsign': 'MILE-AIR',\n",
" 'country': 'United States'}"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# get a document by key\n",
"result = cb_coll.get(\"airline_10\")\n",
"result.value"
]
},
{
"cell_type": "markdown",
"id": "e818c095-e2d9-40c7-9234-ceddcb27cddb",
"metadata": {},
"source": [
"The Querry language contains a \n",
"If a hyphen is used please use a pair of \\` to surround the name using a hyphen."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8eb6d0be-9fc0-4c89-ad18-801c0349d5cc",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 1968 entries, 0 to 1967\n",
"Data columns (total 9 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 airportname 1968 non-null object\n",
" 1 city 1968 non-null object\n",
" 2 country 1968 non-null object\n",
" 3 faa 1709 non-null object\n",
" 4 geo 1968 non-null object\n",
" 5 icao 1687 non-null object\n",
" 6 id 1968 non-null int64 \n",
" 7 type 1968 non-null object\n",
" 8 tz 1968 non-null object\n",
"dtypes: int64(1), object(8)\n",
"memory usage: 138.5+ KB\n"
]
}
],
"source": [
"result = cluster.query(\n",
" \"\"\"\n",
" SELECT airport.* \n",
" FROM `travel-sample`.inventory.airport airport\n",
" \"\"\",\n",
" QueryOptions(metrics=True),\n",
")\n",
"df = pd.DataFrame(result)\n",
"df.info()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "c1237c23-2ab4-4fa0-9895-0691c20827b6",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\\begin{tabular}{llll}\n",
"\\toprule\n",
"{} & airportname & city & country \\\\\n",
"\\midrule\n",
"\\textbf{4877} & London Heliport & London & United Kingdom \\\\\n",
"\\textbf{4289} & London St Pancras & London & United Kingdom \\\\\n",
"\\textbf{3411} & Stansted & London & United Kingdom \\\\\n",
"\\textbf{6457} & London - Kings Cross & London & United Kingdom \\\\\n",
"\\textbf{8759} & Charles De Gaulle & Paris & France \\\\\n",
"\\bottomrule\n",
"\\end{tabular}\n",
"\n"
]
}
],
"source": [
"result = cluster.query(\n",
" \"\"\"\n",
" SELECT airport.airportname, airport.city, airport.country \n",
" FROM `travel-sample`.inventory.airport airport INNER JOIN `travel-sample`.inventory.landmark landmark on airport.city = landmark.city\n",
" \"\"\",\n",
" QueryOptions(metrics=True),\n",
")\n",
"print(pd.DataFrame(result).sample(5).to_latex(bold_rows=True))"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "a4cc7ef5-511e-4709-9d82-e1c20238f173",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\\begin{tabular}{lllll}\n",
"\\toprule\n",
"{} & airportname & city & country & name \\\\\n",
"\\midrule\n",
"\\textbf{443 } & Edinburgh & Edinburgh & United Kingdom & Murrayfield Ice Rink \\\\\n",
"\\textbf{1487} & Luton & London & United Kingdom & The Phoenix \\\\\n",
"\\textbf{3620} & Paddington Station & London & United Kingdom & Kensal Green Cemetery \\\\\n",
"\\textbf{5629} & London-Corbin Airport-MaGee Field & London & United States & Alexandra Palace \\\\\n",
"\\textbf{8588} & Le Bourget & Paris & France & Aux Merveilleux de Fred \\\\\n",
"\\bottomrule\n",
"\\end{tabular}\n",
"\n"
]
}
],
"source": [
"result = cluster.query(\n",
" \"\"\"\n",
" SELECT airport.airportname, airport.city, airport.country, landmark.name\n",
" FROM `travel-sample`.inventory.airport airport INNER JOIN `travel-sample`.inventory.landmark landmark on airport.city = landmark.city\n",
" \"\"\",\n",
" QueryOptions(metrics=True),\n",
")\n",
"print(pd.DataFrame(result).sample(5).sort_index().to_latex(bold_rows=True))"
]
},
{
"cell_type": "markdown",
"source": [
"# End here\n",
"\n",
"This should not be shownm"
],
"metadata": {
"collapsed": false
},
"outputs": [
{
"ename": "SyntaxError",
"evalue": "invalid syntax (2007221166.py, line 3)",
"output_type": "error",
"traceback": [
"\u001B[1;36m File \u001B[1;32m\"C:\\Users\\phhor\\AppData\\Local\\Temp\\ipykernel_2708\\2007221166.py\"\u001B[1;36m, line \u001B[1;32m3\u001B[0m\n\u001B[1;33m This should not be shownm\u001B[0m\n\u001B[1;37m ^\u001B[0m\n\u001B[1;31mSyntaxError\u001B[0m\u001B[1;31m:\u001B[0m invalid syntax\n"
]
}
],
"execution_count": 1
}
],
"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": "3.10.8"
}
},
"nbformat": 4,
"nbformat_minor": 5
}