Files
compare-timeseries-database/compareDBs.ipynb
T

1243 lines
54 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"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": 18,
"id": "ab6c6c81-6ac1-4668-a79b-a9a0341fb35a",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"False"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import configparser\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": 1,
"id": "55c3cd57-0996-4723-beb5-8f3196c96009",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Variables\n",
"dbname = \"EURUSDtest\""
]
},
{
"cell_type": "code",
"execution_count": 5,
"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)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7e7c46b6-90ee-4ca3-8b5a-553b09ece913",
"metadata": {},
"outputs": [],
"source": [
"# 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": {
"jp-MarkdownHeadingCollapsed": true,
"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": {
"jp-MarkdownHeadingCollapsed": true,
"tags": []
},
"source": [
"### ClickHouse"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9cf86669-7722-4a2c-895c-51f0a5eebefc",
"metadata": {
"tags": []
},
"outputs": [],
"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",
"client = Client(\n",
" host=ClickHouseUrl,\n",
" user=ClickHouseUser,\n",
" password=ClickHouseKey,\n",
" settings={\"use_numpy\": True},\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a0a1f67b-2e63-462e-be66-d322d99837ea",
"metadata": {},
"outputs": [],
"source": [
"# Create Tables in ClickHouse\n",
"# !! ALTERAR TIPOS !!\n",
"# ENGINE: 'Memory' desaparece quando server é reiniciado\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(dbname)\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3a029a09-46f4-43c3-b3df-cfbed33fb0dc",
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"# Write dataframe to db\n",
"client.insert_dataframe(\"INSERT INTO {} VALUES\".format(dbname), df)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "17251288-2442-43ee-98f2-ca680c3c4f13",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"%%time\n",
"client.query_dataframe(\"SELECT * FROM default.{}\".format(dbname)) # LIMIT 10000"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "51497522-bd6c-44a8-aaea-ec5dda30b95b",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# %%time\n",
"# df = pd.DataFrame(client.query_dataframe(\"SELECT * FROM default.{}\".format(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": {
"jp-MarkdownHeadingCollapsed": true,
"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": "e37a93e1-fc0e-4d27-9e16-dca6c8aea324",
"metadata": {},
"outputs": [],
"source": [
"# Read"
]
},
{
"cell_type": "markdown",
"id": "f9e0393d-7d1d-406a-a068-9dbf4968e977",
"metadata": {
"jp-MarkdownHeadingCollapsed": true,
"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": {
"jp-MarkdownHeadingCollapsed": true,
"tags": []
},
"source": [
"### MongoDB"
]
},
{
"cell_type": "code",
"execution_count": 10,
"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": 36,
"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": 37,
"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": 38,
"id": "70674d23-f375-4659-87ec-c745dec96d54",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 19.2 s, sys: 269 ms, total: 19.5 s\n",
"Wall time: 50.1 s\n"
]
},
{
"data": {
"text/plain": [
"<pymongo.results.InsertManyResult at 0x7f8e39c991e0>"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"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": {
"jp-MarkdownHeadingCollapsed": true,
"tags": []
},
"source": [
"### DuckDB"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "bbcdb883-d6dc-46db-88db-4c90b84522ba",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[(42,)]\n"
]
}
],
"source": [
"cursor = duckdb.connect()\n",
"print(cursor.execute(\"SELECT 42\").fetchall())"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "35025a6e-9dc7-46cf-a792-76b3d84f1ac0",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 1.53 s, sys: 63.6 ms, total: 1.59 s\n",
"Wall time: 1.59 s\n"
]
},
{
"data": {
"text/plain": [
"<duckdb.DuckDBPyConnection at 0x7f8e3b2261b0>"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%time\n",
"conn = duckdb.connect()\n",
"data = pd.read_csv(\"out.csv\")\n",
"conn.register(\"EURUSDtest\", data)"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "c6abdaaa-3ac2-425b-9208-d6cb79afe966",
"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>name</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Empty DataFrame\n",
"Columns: [name]\n",
"Index: []"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"display(conn.execute(\"SHOW TABLES\").df())"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "2acce0f3-f0b2-47d0-8e0d-f9e9687efc18",
"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>Unnamed: 0</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>0</td>\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>1</td>\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>2</th>\n",
" <td>2</td>\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",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>7730804</td>\n",
" <td>2023-01-02 15:59:30</td>\n",
" <td>1672675185000000000</td>\n",
" <td>2023-01-02 15:59:45</td>\n",
" <td>1.065980</td>\n",
" <td>1.065985</td>\n",
" <td>1.065885</td>\n",
" <td>1.066045</td>\n",
" <td>64</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>7730805</td>\n",
" <td>2023-01-02 15:59:45</td>\n",
" <td>1672675200000000000</td>\n",
" <td>2023-01-02 16:00:00</td>\n",
" <td>1.065975</td>\n",
" <td>1.066055</td>\n",
" <td>1.065830</td>\n",
" <td>1.066055</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999995</th>\n",
" <td>999995</td>\n",
" <td>7984748</td>\n",
" <td>2023-03-03 18:13:30</td>\n",
" <td>1677867225000000000</td>\n",
" <td>2023-03-03 18:13:45</td>\n",
" <td>1.062695</td>\n",
" <td>1.062635</td>\n",
" <td>1.062630</td>\n",
" <td>1.062700</td>\n",
" <td>64</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999996</th>\n",
" <td>999996</td>\n",
" <td>7984749</td>\n",
" <td>2023-03-03 18:13:45</td>\n",
" <td>1677867240000000000</td>\n",
" <td>2023-03-03 18:14:00</td>\n",
" <td>1.062645</td>\n",
" <td>1.062650</td>\n",
" <td>1.062625</td>\n",
" <td>1.062650</td>\n",
" <td>43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999997</th>\n",
" <td>999997</td>\n",
" <td>7984750</td>\n",
" <td>2023-03-03 18:14:00</td>\n",
" <td>1677867255000000000</td>\n",
" <td>2023-03-03 18:14:15</td>\n",
" <td>1.062640</td>\n",
" <td>1.062625</td>\n",
" <td>1.062620</td>\n",
" <td>1.062665</td>\n",
" <td>47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999998</th>\n",
" <td>999998</td>\n",
" <td>7984751</td>\n",
" <td>2023-03-03 18:14:15</td>\n",
" <td>1677867270000000000</td>\n",
" <td>2023-03-03 18:14:30</td>\n",
" <td>1.062625</td>\n",
" <td>1.062535</td>\n",
" <td>1.062535</td>\n",
" <td>1.062645</td>\n",
" <td>43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999999</th>\n",
" <td>999999</td>\n",
" <td>7984752</td>\n",
" <td>2023-03-03 18:14:30</td>\n",
" <td>1677867285000000000</td>\n",
" <td>2023-03-03 18:14:45</td>\n",
" <td>1.062535</td>\n",
" <td>1.062520</td>\n",
" <td>1.062520</td>\n",
" <td>1.062580</td>\n",
" <td>59</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1000000 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 id from at \n",
"0 0 7730801 2023-01-02 15:58:45 1672675140000000000 \\\n",
"1 1 7730802 2023-01-02 15:59:00 1672675155000000000 \n",
"2 2 7730803 2023-01-02 15:59:15 1672675170000000000 \n",
"3 3 7730804 2023-01-02 15:59:30 1672675185000000000 \n",
"4 4 7730805 2023-01-02 15:59:45 1672675200000000000 \n",
"... ... ... ... ... \n",
"999995 999995 7984748 2023-03-03 18:13:30 1677867225000000000 \n",
"999996 999996 7984749 2023-03-03 18:13:45 1677867240000000000 \n",
"999997 999997 7984750 2023-03-03 18:14:00 1677867255000000000 \n",
"999998 999998 7984751 2023-03-03 18:14:15 1677867270000000000 \n",
"999999 999999 7984752 2023-03-03 18:14:30 1677867285000000000 \n",
"\n",
" to open close min max volume \n",
"0 2023-01-02 15:59:00 1.065995 1.066035 1.065930 1.066070 57 \n",
"1 2023-01-02 15:59:15 1.066055 1.066085 1.066005 1.066115 52 \n",
"2 2023-01-02 15:59:30 1.066080 1.066025 1.066025 1.066110 57 \n",
"3 2023-01-02 15:59:45 1.065980 1.065985 1.065885 1.066045 64 \n",
"4 2023-01-02 16:00:00 1.065975 1.066055 1.065830 1.066055 50 \n",
"... ... ... ... ... ... ... \n",
"999995 2023-03-03 18:13:45 1.062695 1.062635 1.062630 1.062700 64 \n",
"999996 2023-03-03 18:14:00 1.062645 1.062650 1.062625 1.062650 43 \n",
"999997 2023-03-03 18:14:15 1.062640 1.062625 1.062620 1.062665 47 \n",
"999998 2023-03-03 18:14:30 1.062625 1.062535 1.062535 1.062645 43 \n",
"999999 2023-03-03 18:14:45 1.062535 1.062520 1.062520 1.062580 59 \n",
"\n",
"[1000000 rows x 10 columns]"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%time\n",
"df = conn.execute(\"SELECT * FROM EURUSDtest\").df()\n",
"df"
]
},
{
"cell_type": "markdown",
"id": "4409cc89-ed14-4313-ac89-65b826038533",
"metadata": {},
"source": [
"### Kdb+"
]
},
{
"cell_type": "code",
"execution_count": 66,
"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": 49,
"id": "8ff6c090-7e02-435a-a179-f2aab81da972",
"metadata": {},
"outputs": [],
"source": [
"# read csv\n",
"data = pd.read_csv(\"out.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 50,
"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": 51,
"id": "97cb6b5b-65a5-46a0-a4ee-e5c535a716ab",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 837 ms, sys: 40 ms, total: 877 ms\n",
"Wall time: 1.16 s\n"
]
}
],
"source": [
"# send df to kd+ in memory bank\n",
"%%time\n",
"q.sendSync(\"{t::x}\", data)"
]
},
{
"cell_type": "code",
"execution_count": 52,
"id": "c2ed2d51-bc8e-4207-892a-35fc55d43570",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"b':/home/sandman/q/tab1'"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# write to on disk table\n",
"q.sendSync(\"`:/home/sandman/q/tab1 set t\")"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "9c055a95-f73f-43a3-8fbd-61e42235117e",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 1.78 ms, sys: 2 µs, total: 1.79 ms\n",
"Wall time: 329 ms\n"
]
}
],
"source": [
"%%time\n",
"# read from on disk table\n",
"df2 = q.sendSync(\"tab2: get `:/home/sandman/q/tab1\")"
]
},
{
"cell_type": "code",
"execution_count": 54,
"id": "9760de38-9f04-4322-bfff-c7ee12d5dee5",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# print(df2)"
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "c06c9222-c69d-4872-9d21-052281a013e2",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 957 ms, sys: 87.9 ms, total: 1.05 s\n",
"Wall time: 1.13 s\n"
]
}
],
"source": [
"%%time\n",
"# load to variable df2\n",
"df2 = q.sendSync(\"tab2\")"
]
},
{
"cell_type": "code",
"execution_count": 58,
"id": "8815f01c-fd0a-4f94-ab7f-f8ede84ba4e7",
"metadata": {
"tags": []
},
"outputs": [
{
"ename": "TypeError",
"evalue": "'QTable' object is not callable",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[58], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdf2\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mtype\u001b[39;49m\u001b[43m)\u001b[49m\n",
"\u001b[0;31mTypeError\u001b[0m: 'QTable' object is not callable"
]
}
],
"source": [
"# df2(type)"
]
},
{
"cell_type": "code",
"execution_count": 67,
"id": "e6ed3927-4395-45cd-9a28-88c5db01f2e5",
"metadata": {
"tags": []
},
"outputs": [
{
"ename": "AttributeError",
"evalue": "'bool' object has no attribute 'to_numpy'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"File \u001b[0;32m<timed exec>:2\u001b[0m\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/qconnection.py:385\u001b[0m, in \u001b[0;36mQConnection.__call__\u001b[0;34m(self, *parameters, **options)\u001b[0m\n\u001b[1;32m 384\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39mparameters, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions):\n\u001b[0;32m--> 385\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msendSync\u001b[49m\u001b[43m(\u001b[49m\u001b[43mparameters\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mparameters\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/qconnection.py:303\u001b[0m, in \u001b[0;36mQConnection.sendSync\u001b[0;34m(self, query, *parameters, **options)\u001b[0m\n\u001b[1;32m 249\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m'''Performs a synchronous query against a q service and returns parsed \u001b[39;00m\n\u001b[1;32m 250\u001b[0m \u001b[38;5;124;03mdata.\u001b[39;00m\n\u001b[1;32m 251\u001b[0m \u001b[38;5;124;03m\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 300\u001b[0m \u001b[38;5;124;03m :class:`.QReaderException`\u001b[39;00m\n\u001b[1;32m 301\u001b[0m \u001b[38;5;124;03m'''\u001b[39;00m\n\u001b[1;32m 302\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mquery(MessageType\u001b[38;5;241m.\u001b[39mSYNC, query, \u001b[38;5;241m*\u001b[39mparameters, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions)\n\u001b[0;32m--> 303\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreceive\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata_only\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 305\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m response\u001b[38;5;241m.\u001b[39mtype \u001b[38;5;241m==\u001b[39m MessageType\u001b[38;5;241m.\u001b[39mRESPONSE:\n\u001b[1;32m 306\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\u001b[38;5;241m.\u001b[39mdata\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/qconnection.py:380\u001b[0m, in \u001b[0;36mQConnection.receive\u001b[0;34m(self, data_only, **options)\u001b[0m\n\u001b[1;32m 341\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mreceive\u001b[39m(\u001b[38;5;28mself\u001b[39m, data_only \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions):\n\u001b[1;32m 342\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m'''Reads and (optionally) parses the response from a q service.\u001b[39;00m\n\u001b[1;32m 343\u001b[0m \u001b[38;5;124;03m \u001b[39;00m\n\u001b[1;32m 344\u001b[0m \u001b[38;5;124;03m Retrieves query result along with meta-information:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 378\u001b[0m \u001b[38;5;124;03m :raises: :class:`.QReaderException`\u001b[39;00m\n\u001b[1;32m 379\u001b[0m \u001b[38;5;124;03m '''\u001b[39;00m\n\u001b[0;32m--> 380\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_reader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_options\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43munion_dict\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 381\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\u001b[38;5;241m.\u001b[39mdata \u001b[38;5;28;01mif\u001b[39;00m data_only \u001b[38;5;28;01melse\u001b[39;00m result\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/qreader.py:139\u001b[0m, in \u001b[0;36mQReader.read\u001b[0;34m(self, source, **options)\u001b[0m\n\u001b[1;32m 120\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m'''\u001b[39;00m\n\u001b[1;32m 121\u001b[0m \u001b[38;5;124;03mReads and optionally parses a single message.\u001b[39;00m\n\u001b[1;32m 122\u001b[0m \u001b[38;5;124;03m\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 136\u001b[0m \u001b[38;5;124;03m with meta information\u001b[39;00m\n\u001b[1;32m 137\u001b[0m \u001b[38;5;124;03m'''\u001b[39;00m\n\u001b[1;32m 138\u001b[0m message \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mread_header(source)\n\u001b[0;32m--> 139\u001b[0m message\u001b[38;5;241m.\u001b[39mdata \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmessage\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msize\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessage\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mis_compressed\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 141\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m message\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/qreader.py:216\u001b[0m, in \u001b[0;36mQReader.read_data\u001b[0;34m(self, message_size, is_compressed, **options)\u001b[0m\n\u001b[1;32m 213\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_stream \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_options\u001b[38;5;241m.\u001b[39mraw:\n\u001b[1;32m 214\u001b[0m raw_data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_buffer\u001b[38;5;241m.\u001b[39mraw(message_size \u001b[38;5;241m-\u001b[39m \u001b[38;5;241m8\u001b[39m)\n\u001b[0;32m--> 216\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m raw_data \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_options\u001b[38;5;241m.\u001b[39mraw \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_read_object\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/qreader.py:225\u001b[0m, in \u001b[0;36mQReader._read_object\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 222\u001b[0m reader \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_reader(qtype)\n\u001b[1;32m 224\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m reader:\n\u001b[0;32m--> 225\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mreader\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mqtype\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 226\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m qtype \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m QBOOL_LIST \u001b[38;5;129;01mand\u001b[39;00m qtype \u001b[38;5;241m<\u001b[39m\u001b[38;5;241m=\u001b[39m QTIME_LIST:\n\u001b[1;32m 227\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_read_list(qtype)\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/_pandas.py:76\u001b[0m, in \u001b[0;36mPandasQReader._read_table\u001b[0;34m(self, qtype)\u001b[0m\n\u001b[1;32m 74\u001b[0m columns \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_read_object()\n\u001b[1;32m 75\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_buffer\u001b[38;5;241m.\u001b[39mskip() \u001b[38;5;66;03m# ignore generic list type indicator\u001b[39;00m\n\u001b[0;32m---> 76\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[43mQReader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_read_general_list\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mqtype\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 78\u001b[0m odict \u001b[38;5;241m=\u001b[39m OrderedDict()\n\u001b[1;32m 79\u001b[0m meta \u001b[38;5;241m=\u001b[39m MetaData(qtype \u001b[38;5;241m=\u001b[39m QTABLE)\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/qreader.py:338\u001b[0m, in \u001b[0;36mQReader._read_general_list\u001b[0;34m(self, qtype)\u001b[0m\n\u001b[1;32m 335\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_buffer\u001b[38;5;241m.\u001b[39mskip() \u001b[38;5;66;03m# ignore attributes\u001b[39;00m\n\u001b[1;32m 336\u001b[0m length \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_buffer\u001b[38;5;241m.\u001b[39mget_int()\n\u001b[0;32m--> 338\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m [\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_read_object() \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(length)]\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/qreader.py:338\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 335\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_buffer\u001b[38;5;241m.\u001b[39mskip() \u001b[38;5;66;03m# ignore attributes\u001b[39;00m\n\u001b[1;32m 336\u001b[0m length \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_buffer\u001b[38;5;241m.\u001b[39mget_int()\n\u001b[0;32m--> 338\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m [\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_read_object\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(length)]\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/qreader.py:227\u001b[0m, in \u001b[0;36mQReader._read_object\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 225\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m reader(\u001b[38;5;28mself\u001b[39m, qtype)\n\u001b[1;32m 226\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m qtype \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m QBOOL_LIST \u001b[38;5;129;01mand\u001b[39;00m qtype \u001b[38;5;241m<\u001b[39m\u001b[38;5;241m=\u001b[39m QTIME_LIST:\n\u001b[0;32m--> 227\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_read_list\u001b[49m\u001b[43m(\u001b[49m\u001b[43mqtype\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 228\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m qtype \u001b[38;5;241m<\u001b[39m\u001b[38;5;241m=\u001b[39m QBOOL \u001b[38;5;129;01mand\u001b[39;00m qtype \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m QTIME:\n\u001b[1;32m 229\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_read_atom(qtype)\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/qpython/_pandas.py:116\u001b[0m, in \u001b[0;36mPandasQReader._read_list\u001b[0;34m(self, qtype)\u001b[0m\n\u001b[1;32m 114\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;241m-\u001b[39m\u001b[38;5;28mabs\u001b[39m(qtype) \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m [QMONTH, QDATE, QDATETIME, QMINUTE, QSECOND, QTIME, QTIMESTAMP, QTIMESPAN, QSYMBOL]:\n\u001b[1;32m 115\u001b[0m null \u001b[38;5;241m=\u001b[39m QNULLMAP[\u001b[38;5;241m-\u001b[39m\u001b[38;5;28mabs\u001b[39m(qtype)][\u001b[38;5;241m1\u001b[39m]\n\u001b[0;32m--> 116\u001b[0m ps \u001b[38;5;241m=\u001b[39m \u001b[43mpandas\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mSeries\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mqlist\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreplace\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnull\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnumpy\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mNaN\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 117\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 118\u001b[0m ps \u001b[38;5;241m=\u001b[39m pandas\u001b[38;5;241m.\u001b[39mSeries(data \u001b[38;5;241m=\u001b[39m qlist)\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/pandas/core/series.py:5219\u001b[0m, in \u001b[0;36mSeries.replace\u001b[0;34m(self, to_replace, value, inplace, limit, regex, method)\u001b[0m\n\u001b[1;32m 5203\u001b[0m \u001b[38;5;129m@doc\u001b[39m(\n\u001b[1;32m 5204\u001b[0m NDFrame\u001b[38;5;241m.\u001b[39mreplace,\n\u001b[1;32m 5205\u001b[0m klass\u001b[38;5;241m=\u001b[39m_shared_doc_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mklass\u001b[39m\u001b[38;5;124m\"\u001b[39m],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 5217\u001b[0m method: Literal[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpad\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mffill\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbfill\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m|\u001b[39m lib\u001b[38;5;241m.\u001b[39mNoDefault \u001b[38;5;241m=\u001b[39m lib\u001b[38;5;241m.\u001b[39mno_default,\n\u001b[1;32m 5218\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Series \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 5219\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreplace\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 5220\u001b[0m \u001b[43m \u001b[49m\u001b[43mto_replace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mto_replace\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5221\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5222\u001b[0m \u001b[43m \u001b[49m\u001b[43minplace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minplace\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5223\u001b[0m \u001b[43m \u001b[49m\u001b[43mlimit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlimit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5224\u001b[0m \u001b[43m \u001b[49m\u001b[43mregex\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mregex\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5225\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5226\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/pandas/core/generic.py:7389\u001b[0m, in \u001b[0;36mNDFrame.replace\u001b[0;34m(self, to_replace, value, inplace, limit, regex, method)\u001b[0m\n\u001b[1;32m 7383\u001b[0m new_data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_mgr\u001b[38;5;241m.\u001b[39mreplace_regex(\n\u001b[1;32m 7384\u001b[0m to_replace\u001b[38;5;241m=\u001b[39mto_replace,\n\u001b[1;32m 7385\u001b[0m value\u001b[38;5;241m=\u001b[39mvalue,\n\u001b[1;32m 7386\u001b[0m inplace\u001b[38;5;241m=\u001b[39minplace,\n\u001b[1;32m 7387\u001b[0m )\n\u001b[1;32m 7388\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 7389\u001b[0m new_data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_mgr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreplace\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 7390\u001b[0m \u001b[43m \u001b[49m\u001b[43mto_replace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mto_replace\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minplace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minplace\u001b[49m\n\u001b[1;32m 7391\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 7392\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 7393\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\n\u001b[1;32m 7394\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mInvalid \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mto_replace\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m type: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mrepr\u001b[39m(\u001b[38;5;28mtype\u001b[39m(to_replace)\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m 7395\u001b[0m )\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/pandas/core/internals/managers.py:475\u001b[0m, in \u001b[0;36mBaseBlockManager.replace\u001b[0;34m(self, to_replace, value, inplace)\u001b[0m\n\u001b[1;32m 473\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_list_like(to_replace)\n\u001b[1;32m 474\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_list_like(value)\n\u001b[0;32m--> 475\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 476\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mreplace\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 477\u001b[0m \u001b[43m \u001b[49m\u001b[43mto_replace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mto_replace\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 478\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 479\u001b[0m \u001b[43m \u001b[49m\u001b[43minplace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minplace\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 480\u001b[0m \u001b[43m \u001b[49m\u001b[43musing_cow\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43musing_copy_on_write\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 481\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/pandas/core/internals/managers.py:352\u001b[0m, in \u001b[0;36mBaseBlockManager.apply\u001b[0;34m(self, f, align_keys, **kwargs)\u001b[0m\n\u001b[1;32m 350\u001b[0m applied \u001b[38;5;241m=\u001b[39m b\u001b[38;5;241m.\u001b[39mapply(f, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 351\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 352\u001b[0m applied \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mb\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 353\u001b[0m result_blocks \u001b[38;5;241m=\u001b[39m extend_blocks(applied, result_blocks)\n\u001b[1;32m 355\u001b[0m out \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mtype\u001b[39m(\u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39mfrom_blocks(result_blocks, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxes)\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/pandas/core/internals/blocks.py:593\u001b[0m, in \u001b[0;36mBlock.replace\u001b[0;34m(self, to_replace, value, inplace, mask, using_cow)\u001b[0m\n\u001b[1;32m 590\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m [\u001b[38;5;28mself\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m inplace \u001b[38;5;28;01melse\u001b[39;00m [\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcopy()]\n\u001b[1;32m 592\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m mask \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 593\u001b[0m mask \u001b[38;5;241m=\u001b[39m \u001b[43mmissing\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmask_missing\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mto_replace\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 594\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m mask\u001b[38;5;241m.\u001b[39many():\n\u001b[1;32m 595\u001b[0m \u001b[38;5;66;03m# Note: we get here with test_replace_extension_other incorrectly\u001b[39;00m\n\u001b[1;32m 596\u001b[0m \u001b[38;5;66;03m# bc _can_hold_element is incorrect.\u001b[39;00m\n\u001b[1;32m 597\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m using_cow:\n",
"File \u001b[0;32m~/dev/pipenv/lib/python3.10/site-packages/pandas/core/missing.py:112\u001b[0m, in \u001b[0;36mmask_missing\u001b[0;34m(arr, values_to_mask)\u001b[0m\n\u001b[1;32m 108\u001b[0m new_mask \u001b[38;5;241m=\u001b[39m arr \u001b[38;5;241m==\u001b[39m x\n\u001b[1;32m 110\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(new_mask, np\u001b[38;5;241m.\u001b[39mndarray):\n\u001b[1;32m 111\u001b[0m \u001b[38;5;66;03m# usually BooleanArray\u001b[39;00m\n\u001b[0;32m--> 112\u001b[0m new_mask \u001b[38;5;241m=\u001b[39m \u001b[43mnew_mask\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_numpy\u001b[49m(dtype\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mbool\u001b[39m, na_value\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m 113\u001b[0m mask \u001b[38;5;241m|\u001b[39m\u001b[38;5;241m=\u001b[39m new_mask\n\u001b[1;32m 115\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m na_mask\u001b[38;5;241m.\u001b[39many():\n",
"\u001b[0;31mAttributeError\u001b[0m: 'bool' object has no attribute 'to_numpy'"
]
}
],
"source": [
"%%time\n",
"# converto to dataframe\n",
"df = pd.DataFrame(q(\"t\", pandas=True))\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"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": {},
"outputs": [],
"source": [
"q.close()"
]
}
],
"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
}