finished readme and moved terraform fies

README.md

@@ -38,8 +38,74 @@ Additionaly, we found that having a close integration between the data warehouse
 - **Bring Your Own Storage:** We felt that customers should own their data and not be locked into a particular storage engine.
 
 ## Quickstart
-Have 
 
+1. Dependencies:
+   - Make sure that you have [Docker Engine](https://docs.docker.com/engine/install/) installed.
+   - Install [Python](https://www.python.org/downloads/) if you haven't already.
+   - Install a [MySQL client](https://dev.mysql.com/downloads/mysql/) on your system.
+   - An AWS account with S3 access.
+
+2. Clone the repository:
+
+```bash
+git clone https://github.com/buster-so/warehouse.git
+```
+
+3. Run the warehouse:
+
+```bash
+docker compose up -d
+```
+
+4. Populate the `.env` file with AWS credentials provisioned for S3 access. **Note: You can use any S3 compatible storage, you might just need to tweak some of the configs.** Feel free to look at the Starrocks [docs](https://docs.starrocks.com/en-us/main/loading/iceberg/iceberg_external_catalog) or PyIceberg [docs](https://iceberg.apache.org/docs/latest/spark-configuration/) for more information.
+
+5. Connect to the warehouse with any MySQL client.
+
+6. Create the external catalog:
+
+```sql
+CREATE EXTERNAL CATALOG 'public'
+PROPERTIES
+(
+  "type"="iceberg",
+  "iceberg.catalog.type"="rest",
+  "iceberg.catalog.uri"="http://iceberg-rest:8181",
+  "iceberg.catalog.warehouse"="<BUCKET_NAME>",
+  "aws.s3.access_key"="<ACCESS_KEY>",
+  "aws.s3.secret_key"="<SECRET_KEY>",
+  "aws.s3.region" = "<REGION>",
+  "aws.s3.enable_path_style_access"="true",
+  "client.factory"="com.starrocks.connector.iceberg.IcebergAwsClientFactory"
+);
+```
+
+7. Seed the data. If you want to populate a table with 75m records, you can run the notebook found [here](/notebooks/populate_warehouse.ipynb).
+
+8. Set the catalog
+
+```sql
+SET CATALOG 'public';
+```
+
+9. Set the database
+
+```sql
+USE DATABASE 'public';
+```
+
+10. Run a query
+
+```sql
+SELECT COUNT(*) FROM public.nyc_taxi;
+```
+
+### Optimizations
+
+For data that you think will be accessed frequently, you can cache it on disk for faster access with:
+
+```sql
+CACHE SELECT * FROM public.nyc_taxi WHERE tpep_pickup_datetime > '2022-03-01';
+```
 
 ## Roadmap
 

python/populate_warehouse.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 162,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 163,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 164,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -37,7 +37,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 165,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -48,7 +48,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 166,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -57,7 +57,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 167,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -95,7 +95,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 168,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -109,7 +109,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 169,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -123,7 +123,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 170,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -143,14 +143,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 171,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Appending files: 100%|██████████| 26/26 [10:19<00:00, 23.83s/it, Appended yellow_tripdata_2021-09.parquet]\n"
+      "Appending files:   0%|          | 0/26 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Appending files: 100%|██████████| 26/26 [03:56<00:00,  9.10s/it, Appended 2022-12]\n"
      ]
     },
     {
@@ -162,35 +169,35 @@
     }
    ],
    "source": [
-    "import os\n",
     "import requests\n",
     "import io\n",
     "import pyarrow.parquet as pq\n",
     "from tqdm import tqdm\n",
+    "from datetime import datetime, timedelta\n",
     "\n",
-    "# GitHub repository information\n",
+    "# Base URL for the Parquet files\n",
-    "repo_owner = \"buster-so\"\n",
+    "base_url = \"https://pub-f6a668561f5e4bd6ac651efd8c18998d.r2.dev/nyc_taxi/yellow_tripdata_{}.parquet\"\n",
-    "repo_name = \"sample-data\"\n",
-    "folder_path = \"nyc_taxi\"\n",
     "\n",
-    "# GitHub API endpoint to get repository contents\n",
+    "# Generate a list of dates from 2020-11 to 2022-12\n",
-    "api_url = f\"https://api.github.com/repos/{repo_owner}/{repo_name}/contents/{folder_path}\"\n",
+    "start_date = datetime(2020, 11, 1)\n",
+    "end_date = datetime(2022, 12, 1)\n",
+    "date_list = []\n",
     "\n",
-    "# Fetch the list of files in the repository\n",
+    "current_date = start_date\n",
-    "response = requests.get(api_url)\n",
+    "while current_date <= end_date:\n",
-    "if response.status_code != 200:\n",
+    "    date_list.append(current_date.strftime(\"%Y-%m\"))\n",
-    "    raise Exception(f\"Failed to fetch repository contents: {response.status_code}\")\n",
+    "    current_date += timedelta(days=32)\n",
-    "\n",
+    "    current_date = current_date.replace(day=1)\n",
-    "files = [item for item in response.json() if item['name'].endswith('.parquet')]\n",
     "\n",
     "# Create a progress bar\n",
-    "with tqdm(total=len(files), desc=\"Appending files\") as pbar:\n",
+    "with tqdm(total=len(date_list), desc=\"Appending files\") as pbar:\n",
-    "    for file in files:\n",
+    "    for date_str in date_list:\n",
+    "        file_url = base_url.format(date_str)\n",
+    "        \n",
     "        # Download the file content\n",
-    "        file_url = file['download_url']\n",
     "        file_response = requests.get(file_url)\n",
     "        if file_response.status_code != 200:\n",
-    "            print(f\"Failed to download {file['name']}: {file_response.status_code}\")\n",
+    "            print(f\"Failed to download {date_str}: {file_response.status_code}\")\n",
     "            continue\n",
     "        \n",
     "        # Read the Parquet file from the response content\n",
@@ -201,7 +208,7 @@
     "        table.append(df)\n",
     "        \n",
     "        pbar.update(1)\n",
-    "        pbar.set_postfix_str(f\"Appended {file['name']}\")\n",
+    "        pbar.set_postfix_str(f\"Appended {date_str}\")\n",
     "\n",
     "# Print the total number of rows in the table after appending all files\n",
     "print(f\"Total rows in the table: {len(table.scan().to_arrow())}\")"