1090 lines
26 KiB
Plaintext
1090 lines
26 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "7f1f5a4a-ae34-4a27-9efa-399edc0e384a",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"## Benchmark: ClickHouse Vs. InfluxDB Vs. Postgresql Vs. Parquet \n",
|
|
"\n",
|
|
"-----\n",
|
|
"\n",
|
|
"#### How to use:\n",
|
|
"* Rename the file \"properties-model.ini\" to \"properties.ini\"\n",
|
|
"* Fill with your own credentials\n",
|
|
"----\n",
|
|
"\n",
|
|
"The proposal of this work is to compare the speed in read/writing a midle level of data ( a dataset with 9 columns and 50.000 lines) to four diferent databases:\n",
|
|
"* ClickHouse\n",
|
|
"* InfluxDB\n",
|
|
"* Postgresql\n",
|
|
"* Parquet (in a S3 Minio Storage) <br>\n",
|
|
"ToDo: <br>\n",
|
|
"* DuckDB with Polars\n",
|
|
"* MongoDB\n",
|
|
"* Kdb+\n",
|
|
"\n",
|
|
" \n",
|
|
"Deve-se relevar:\n",
|
|
"é uma \"cold-storage\" ou \"frezze-storage\"? <br>\n",
|
|
"influxdb: alta leitura e possui a vantagem da indexaçõa para vizualização de dados em gráficos.\n",
|
|
"\n",
|
|
"notas: \n",
|
|
"* comparar tamanho do csv com parquet"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "6bb26ce7-1e84-4665-accd-916bb977f95d",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"### Imports "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ab6c6c81-6ac1-4668-a79b-a9a0341fb35a",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"import configparser\n",
|
|
"import time\n",
|
|
"import timeit\n",
|
|
"from datetime import datetime\n",
|
|
"\n",
|
|
"import duckdb\n",
|
|
"import influxdb_client\n",
|
|
"import pandas as pd\n",
|
|
"\n",
|
|
"# import pymongo\n",
|
|
"from clickhouse_driver import Client\n",
|
|
"from dotenv import load_dotenv\n",
|
|
"from minio import Minio\n",
|
|
"from pymongo import MongoClient\n",
|
|
"from pytz import timezone\n",
|
|
"from sqlalchemy import create_engine\n",
|
|
"\n",
|
|
"load_dotenv()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "55c3cd57-0996-4723-beb5-8f3196c96009",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Variables\n",
|
|
"dbname = \"EURUSDtest\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 42,
|
|
"id": "968403e3-2e5e-4834-b969-be4600e2963a",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"arq = configparser.RawConfigParser()\n",
|
|
"arq.read(\"properties.ini\")\n",
|
|
"ClickHouseUser = arq.get(\"CLICKHOUSE\", \"user\")\n",
|
|
"ClickHouseKey = arq.get(\"CLICKHOUSE\", \"key\")\n",
|
|
"ClickHouseUrl = arq.get(\"CLICKHOUSE\", \"url\")\n",
|
|
"\n",
|
|
"InfluxDBUser = arq.get(\"INFLUXDB\", \"user\")\n",
|
|
"InfluxDBKey = arq.get(\"INFLUXDB\", \"key\")\n",
|
|
"InfluxDBUrl = arq.get(\"INFLUXDB\", \"url\")\n",
|
|
"InfluxDBBucket = arq.get(\"INFLUXDB\", \"bucket\")\n",
|
|
"\n",
|
|
"PostgresqlUser = arq.get(\"POSTGRESQL\", \"user\")\n",
|
|
"PostgresqlKey = arq.get(\"POSTGRESQL\", \"key\")\n",
|
|
"PostgresqlUrl = arq.get(\"POSTGRESQL\", \"url\")\n",
|
|
"PostgresqlDB = arq.get(\"POSTGRESQL\", \"database\")\n",
|
|
"\n",
|
|
"S3MinioUser = arq.get(\"S3MINIO\", \"user\")\n",
|
|
"S3MinioKey = arq.get(\"S3MINIO\", \"key\")\n",
|
|
"S3MinioUrl = arq.get(\"S3MINIO\", \"url\")\n",
|
|
"S3MinioRegion = arq.get(\"S3MINIO\", \"region\")\n",
|
|
"\n",
|
|
"MongoUser = arq.get(\"MONGODB\", \"user\")\n",
|
|
"MongoKey = arq.get(\"MONGODB\", \"key\")\n",
|
|
"MongoUrl = arq.get(\"MONGODB\", \"url\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3634a4ec-04c2-4f1e-8659-5d22eb17a254",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# %%time\n",
|
|
"# Load Dataset\n",
|
|
"df = pd.read_csv(\"out.csv\", index_col=0)\n",
|
|
"df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "76199f91-31d6-416b-9f15-5d435b3792c9",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"df[\"from\"] = pd.to_datetime(df[\"from\"], unit=\"s\")\n",
|
|
"df[\"to\"] = pd.to_datetime(df[\"to\"], unit=\"s\")\n",
|
|
"# Optional use when not transoformed yet\n",
|
|
"# Transform Datetime"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "274cc026-2f48-4e38-b80f-b1a9ff982060",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"#### Funçoes\n",
|
|
"\n",
|
|
"-> Class"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "27de1ec8-4de1-440a-b555-b4a46c5ef7ce",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def timestamp2dataHora(x, timezone_=\"America/Sao_Paulo\"):\n",
|
|
" d = datetime.fromtimestamp(x, tz=timezone(timezone_))\n",
|
|
" return d"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "4a8d5703-9bc9-4d38-83ff-457159304d58",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"### ClickHouse"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 44,
|
|
"id": "c3202bbb-2655-45b2-b166-9f45a3ef854c",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Database created'"
|
|
]
|
|
},
|
|
"execution_count": 44,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# !! O client oficial usa um driver http, nesse exemplo vamos usar a biblioteca\n",
|
|
"# de terceirtos clickhouse_driver recomendada, por sua vez que usa tcp.\n",
|
|
"def cHouseConnect():\n",
|
|
" client = Client(\n",
|
|
" host=ClickHouseUrl,\n",
|
|
" user=ClickHouseUser,\n",
|
|
" password=ClickHouseKey,\n",
|
|
" settings={\"use_numpy\": True},\n",
|
|
" )\n",
|
|
" return client\n",
|
|
"\n",
|
|
"\n",
|
|
"# Create Tables in ClickHouse\n",
|
|
"# !! ALTERAR TIPOS !!\n",
|
|
"# ENGINE: 'Memory' desaparece quando server é reiniciado\n",
|
|
"def cHouseCreateDb(databasename):\n",
|
|
" client = cHouseConnect()\n",
|
|
" client.execute(\n",
|
|
" \"CREATE TABLE IF NOT EXISTS {} (id UInt32,\"\n",
|
|
" \"from DateTime, at UInt64, to DateTime, open Float64,\"\n",
|
|
" \"close Float64, min Float64, max Float64, volume UInt32)\"\n",
|
|
" \"ENGINE MergeTree ORDER BY to\".format(databasename)\n",
|
|
" )\n",
|
|
" client.disconnect()\n",
|
|
" return \"Database created\"\n",
|
|
"\n",
|
|
"\n",
|
|
"# Write dataframe to db\n",
|
|
"def cHouseInsertDf(dbName, dataframe):\n",
|
|
" client = cHouseConnect()\n",
|
|
" client.insert_dataframe(\"INSERT INTO {} VALUES\".format(dbName), dataframe)\n",
|
|
" client.disconnect()\n",
|
|
" return \" dataframe {} inserted in clickhouse database\".format(dataframe)\n",
|
|
"\n",
|
|
"\n",
|
|
"def cHouseQueryDf(databaseName):\n",
|
|
" client = cHouseConnect()\n",
|
|
" dfQuery = client.query_dataframe(\n",
|
|
" \"SELECT * FROM default.{}\".format(databaseName)\n",
|
|
" ) # LIMIT 10000\n",
|
|
" client.disconnect()\n",
|
|
" return dfQuery\n",
|
|
"\n",
|
|
"\n",
|
|
"cHouseCreateDb(dbname)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 47,
|
|
"id": "cc4865b3-a1bc-4a35-9624-15334754b3a1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Insert to db and benchmark time\n",
|
|
"start = timeit.default_timer()\n",
|
|
"cHouseInsertDf(dbname, df)\n",
|
|
"stop = timeit.default_timer()\n",
|
|
"cHouse_write_execution_time = stop - start"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 48,
|
|
"id": "1fac82c1-2d04-44ef-893a-dc13b755e6d8",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# read from db and benchmark time\n",
|
|
"start = timeit.default_timer()\n",
|
|
"dfCh = cHouseQueryDf(dbname)\n",
|
|
"stop = timeit.default_timer()\n",
|
|
"cHouse_read_execution_time = stop - start"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 49,
|
|
"id": "597ae7bd-2eea-44d7-b379-f0eb7e745c15",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>id</th>\n",
|
|
" <th>from</th>\n",
|
|
" <th>at</th>\n",
|
|
" <th>to</th>\n",
|
|
" <th>open</th>\n",
|
|
" <th>close</th>\n",
|
|
" <th>min</th>\n",
|
|
" <th>max</th>\n",
|
|
" <th>volume</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>7730801</td>\n",
|
|
" <td>2023-01-02 15:58:45</td>\n",
|
|
" <td>1672675140000000000</td>\n",
|
|
" <td>2023-01-02 15:59:00</td>\n",
|
|
" <td>1.065995</td>\n",
|
|
" <td>1.066035</td>\n",
|
|
" <td>1.065930</td>\n",
|
|
" <td>1.066070</td>\n",
|
|
" <td>57</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>7730801</td>\n",
|
|
" <td>2023-01-02 15:58:45</td>\n",
|
|
" <td>1672675140000000000</td>\n",
|
|
" <td>2023-01-02 15:59:00</td>\n",
|
|
" <td>1.065995</td>\n",
|
|
" <td>1.066035</td>\n",
|
|
" <td>1.065930</td>\n",
|
|
" <td>1.066070</td>\n",
|
|
" <td>57</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>7730802</td>\n",
|
|
" <td>2023-01-02 15:59:00</td>\n",
|
|
" <td>1672675155000000000</td>\n",
|
|
" <td>2023-01-02 15:59:15</td>\n",
|
|
" <td>1.066055</td>\n",
|
|
" <td>1.066085</td>\n",
|
|
" <td>1.066005</td>\n",
|
|
" <td>1.066115</td>\n",
|
|
" <td>52</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>7730802</td>\n",
|
|
" <td>2023-01-02 15:59:00</td>\n",
|
|
" <td>1672675155000000000</td>\n",
|
|
" <td>2023-01-02 15:59:15</td>\n",
|
|
" <td>1.066055</td>\n",
|
|
" <td>1.066085</td>\n",
|
|
" <td>1.066005</td>\n",
|
|
" <td>1.066115</td>\n",
|
|
" <td>52</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>7730803</td>\n",
|
|
" <td>2023-01-02 15:59:15</td>\n",
|
|
" <td>1672675170000000000</td>\n",
|
|
" <td>2023-01-02 15:59:30</td>\n",
|
|
" <td>1.066080</td>\n",
|
|
" <td>1.066025</td>\n",
|
|
" <td>1.066025</td>\n",
|
|
" <td>1.066110</td>\n",
|
|
" <td>57</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" id from at to \\\n",
|
|
"0 7730801 2023-01-02 15:58:45 1672675140000000000 2023-01-02 15:59:00 \n",
|
|
"1 7730801 2023-01-02 15:58:45 1672675140000000000 2023-01-02 15:59:00 \n",
|
|
"2 7730802 2023-01-02 15:59:00 1672675155000000000 2023-01-02 15:59:15 \n",
|
|
"3 7730802 2023-01-02 15:59:00 1672675155000000000 2023-01-02 15:59:15 \n",
|
|
"4 7730803 2023-01-02 15:59:15 1672675170000000000 2023-01-02 15:59:30 \n",
|
|
"\n",
|
|
" open close min max volume \n",
|
|
"0 1.065995 1.066035 1.065930 1.066070 57 \n",
|
|
"1 1.065995 1.066035 1.065930 1.066070 57 \n",
|
|
"2 1.066055 1.066085 1.066005 1.066115 52 \n",
|
|
"3 1.066055 1.066085 1.066005 1.066115 52 \n",
|
|
"4 1.066080 1.066025 1.066025 1.066110 57 "
|
|
]
|
|
},
|
|
"execution_count": 49,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"dfCh.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 50,
|
|
"id": "86794e47-611f-4ca8-a7e8-07e71afafe67",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"5.175396532999002\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print(cHouse_read_execution_time)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 51,
|
|
"id": "e7926062-8e84-4d3f-90a9-32807ce4f3d4",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"6.163630739996734\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print(cHouse_write_execution_time)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "8faa5683-a204-461d-80c3-67644aa714ce",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"dfCh = cHouseQueryDf(dbname)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "1d389546-911f-43f7-aad1-49f7bcc83503",
|
|
"metadata": {
|
|
"jp-MarkdownHeadingCollapsed": true,
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"### InfluxDB\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c3e7ebfd-76f1-4ac4-9833-312eb1a531af",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"client = influxdb_client.InfluxDBClient(\n",
|
|
" url=InfluxDBUrl, token=InfluxDBKey, org=InfluxDBUser\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "cbf61f12-830b-4c57-804a-2257d8b3599a",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Read data from CSV without index and parse 'TimeStamp' as date.\n",
|
|
"df = pd.read_csv(\"out.csv\", sep=\",\", index_col=False, parse_dates=[\"from\"])\n",
|
|
"# Set 'TimeStamp' field as index of dataframe # test another indexs\n",
|
|
"df.set_index(\"from\", inplace=True)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "54342a28-ba2b-4ade-a692-00566b53a639",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f861fab2-f1b1-49dd-b758-12d10aef3462",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"# gravando... demorou... mas deu certo\n",
|
|
"with client.write_api() as writer:\n",
|
|
" writer.write(\n",
|
|
" bucket=InfluxDBBucket,\n",
|
|
" record=df,\n",
|
|
" data_frame_measurement_name=\"id\",\n",
|
|
" data_frame_tag_columns=[\"volume\"],\n",
|
|
" )"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0bb2563d-68e2-4ff4-8842-70ac730dc6b1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# data\n",
|
|
"# |> pivot(\n",
|
|
"# rowKey:[\"_time\"],\n",
|
|
"# columnKey: [\"_field\"],\n",
|
|
"# valueColumn: \"_value\"\n",
|
|
"# )"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "bb1596f9-4cee-4642-803a-ee61c9dddf64",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Read"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "b9ddfdc6-c899-4f6c-9b4e-8ec6ab6d7e05",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"### Postgresql"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "16cd8eb7-333d-43fd-88e0-ee983645d3fd",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Connect / Create Tables\n",
|
|
"engine = create_engine(\n",
|
|
" \"postgresql+psycopg2://{}:{}@{}:5432/{}\".format(\n",
|
|
" PostgresqlUser, PostgresqlKey, PostgresqlUrl, PostgresqlDB\n",
|
|
" )\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "be31f3a0-b7ed-48e6-9b65-dc16319fb8d1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Drop old table and create new empty table\n",
|
|
"df.head(0).to_sql(\"comparedbs\", engine, if_exists=\"replace\", index=False)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a7883c4d-4609-4380-8a45-246b7ca2f9c5",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"# Write\n",
|
|
"conn = engine.raw_connection()\n",
|
|
"cur = conn.cursor()\n",
|
|
"output = io.StringIO()\n",
|
|
"df.to_csv(output, sep=\"\\t\", header=False, index=False)\n",
|
|
"output.seek(0)\n",
|
|
"contents = output.getvalue()\n",
|
|
"\n",
|
|
"cur.copy_from(output, \"comparedbs\") # , null=\"\") # null values become ''\n",
|
|
"conn.commit()\n",
|
|
"cur.close()\n",
|
|
"conn.close()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "73de4294-1284-49b0-b31e-45db6e835877",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e37a93e1-fc0e-4d27-9e16-dca6c8aea324",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"start = time.time()\n",
|
|
"# %%time\n",
|
|
"# Read\n",
|
|
"df = pd.read_sql_query('select * from \"comparedbs\"', con=engine)\n",
|
|
"end = time.time()\n",
|
|
"postgresql_read_time = exec_time(start, end)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "6d1b7480-5bc7-4f08-8cf3-b9590802d8f7",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"print(postgresql_read_time)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "6acb2959-3255-43bd-aea5-9ef70acc8902",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "f9e0393d-7d1d-406a-a068-9dbf4968e977",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"### S3 Parquet"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "60a990e2-4607-4654-84ec-17d4985adae2",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# fazer sem funçao para ver se melhora\n",
|
|
"# verifique se esta no ssd os arquivos da pasta git\n",
|
|
"def main():\n",
|
|
" client = Minio(\n",
|
|
" S3MinioUrl,\n",
|
|
" secure=False,\n",
|
|
" region=S3MinioRegion,\n",
|
|
" access_key=\"MatMPA7NyHltz7DQ\",\n",
|
|
" secret_key=\"SO1IG5iBPSjNPZanYUaHCLcoSbjphLCP\",\n",
|
|
" )\n",
|
|
"\n",
|
|
" # Make bucket if not exist.\n",
|
|
" found = client.bucket_exists(\"data\")\n",
|
|
" if not found:\n",
|
|
" client.make_bucket(\"data\")\n",
|
|
" else:\n",
|
|
" print(\"Bucket 'data' already exists\")\n",
|
|
"\n",
|
|
" # Upload\n",
|
|
" client.fput_object(\n",
|
|
" \"data\",\n",
|
|
" \"data.parquet\",\n",
|
|
" \"data/data.parquet\",\n",
|
|
" )\n",
|
|
" # print(\n",
|
|
" # \"'data/data.parquet' is successfully uploaded as \"\n",
|
|
" # \"object 'data.parquet' to bucket 'data'.\"\n",
|
|
" # )"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "390918c8-c88f-404a-96c4-685d578fdad0",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"df.to_parquet(\"data/data.parquet\")\n",
|
|
"if __name__ == \"__main__\":\n",
|
|
" try:\n",
|
|
" main()\n",
|
|
" except S3Error as exc:\n",
|
|
" print(\"error occurred.\", exc)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a9e07143-8c11-4b68-a869-c3922cda9092",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"pq = pd.read_parquet(\"data/data.parquet\", engine=\"pyarrow\")\n",
|
|
"pq.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "50d1fc58-89a7-4507-aff0-6e943656cfe0",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"### MongoDB"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "d104d9af-fa34-4261-8478-329a28ee4f2e",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Load csv dataset\n",
|
|
"data = pd.read_csv(\"out.csv\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0af8f72c-5b58-4dfc-af36-c5b4bc79f127",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Connect to MongoDB\n",
|
|
"client = MongoClient(\n",
|
|
" # \"mongodb://192.168.1.133:27017\"\n",
|
|
" \"mongodb://{}:{}@{}/EURUSDtest?retryWrites=true&w=majority\".format(\n",
|
|
" MongoUser, MongoKey, MongoUrl\n",
|
|
" ),\n",
|
|
" authSource=\"admin\",\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f1b20d15-f5af-463c-813f-ffae61119de1",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"db = client[\"EUROUSDtest\"]\n",
|
|
"collection = db[\"finance\"]\n",
|
|
"# data.reset_index(inplace=True)\n",
|
|
"data_dict = data.to_dict(\"records\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "70674d23-f375-4659-87ec-c745dec96d54",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"# Insert collection\n",
|
|
"collection.insert_many(data_dict)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "81a4a33d-5914-45d8-af4e-2b0aabd2ac38",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# read"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "97405e42-61dc-42c7-8220-237a312c0ec7",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"### DuckDB"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "bbcdb883-d6dc-46db-88db-4c90b84522ba",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"cursor = duckdb.connect()\n",
|
|
"print(cursor.execute(\"SELECT 42\").fetchall())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "35025a6e-9dc7-46cf-a792-76b3d84f1ac0",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"conn = duckdb.connect()\n",
|
|
"data = pd.read_csv(\"out.csv\")\n",
|
|
"conn.register(\"EURUSDtest\", data)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c6abdaaa-3ac2-425b-9208-d6cb79afe966",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"display(conn.execute(\"SHOW TABLES\").df())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "2acce0f3-f0b2-47d0-8e0d-f9e9687efc18",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"df = conn.execute(\"SELECT * FROM EURUSDtest\").df()\n",
|
|
"df"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "4409cc89-ed14-4313-ac89-65b826038533",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"source": [
|
|
"### Kdb+"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "14f63810-1943-4e28-9bce-2148be6be02d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import numpy as np\n",
|
|
"\n",
|
|
"np.bool = np.bool_\n",
|
|
"from qpython import qconnection"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "8ff6c090-7e02-435a-a179-f2aab81da972",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# read csv\n",
|
|
"data = pd.read_csv(\"out.csv\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b4eb8ab9-81e8-4732-8cf7-51f0981d3d57",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# open connection\n",
|
|
"q = qconnection.QConnection(host=\"localhost\", port=5001)\n",
|
|
"q.open()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "97cb6b5b-65a5-46a0-a4ee-e5c535a716ab",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"# send df to kd+ in memory bank\n",
|
|
"q.sendSync(\"{t::x}\", data)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c2ed2d51-bc8e-4207-892a-35fc55d43570",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# write to on disk table\n",
|
|
"q.sendSync(\"`:/home/sandman/q/tab1 set t\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "9c055a95-f73f-43a3-8fbd-61e42235117e",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"# read from on disk table\n",
|
|
"df2 = q.sendSync(\"tab2: get `:/home/sandman/q/tab1\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "9760de38-9f04-4322-bfff-c7ee12d5dee5",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# print(df2)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c06c9222-c69d-4872-9d21-052281a013e2",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"# load to variable df2\n",
|
|
"df2 = q.sendSync(\"tab2\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "8815f01c-fd0a-4f94-ab7f-f8ede84ba4e7",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# df2(type)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e6ed3927-4395-45cd-9a28-88c5db01f2e5",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"# converto to dataframe\n",
|
|
"df = pd.DataFrame(q(\"t\")) # , pandas=True))\n",
|
|
"df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0fc7f16b-6c39-4ebe-88d2-ff857e30ab62",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%%time\n",
|
|
"# select\n",
|
|
"df3 = q.sendSync(\"select from t\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c88646ca-3d25-4a85-80b5-f9e559f568dd",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"q.close()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "adf9720e-0692-462e-aa99-8b91b454b741",
|
|
"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": "3.10.11"
|
|
},
|
|
"widgets": {
|
|
"application/vnd.jupyter.widget-state+json": {
|
|
"state": {},
|
|
"version_major": 2,
|
|
"version_minor": 0
|
|
}
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|