Notebook added for Singlestore Now Raffle (#116)

Co-authored-by: chetan thote <[email protected]>
singlestore-labs · Oct 1, 2024 · c5db129 · c5db129
1 parent 64e60fb
commit c5db129
Show file tree

Hide file tree

Showing 2 changed files with 374 additions and 0 deletions.
diff --git a/notebooks/singlestore-now-2024/meta.toml b/notebooks/singlestore-now-2024/meta.toml
@@ -0,0 +1,11 @@
+[meta]
+authors=["chetan-thote"]
+title = "Singlestore Now 2024 Raffle"
+description = """
+    "Explore the power of SingleStore in this interactive notebook by creating an account, loading data, and running queries for a chance to win the SignleStore Now 2024 Raffle!" """
+icon = "radar"
+difficulty="intermediate"
+tags =  ["mongo", "embeddings", "vector", "genai", "kai", "starter"]
+lesson_areas=["Kai", "AI"]
+destinations = ["spaces"]
+minimum_tier="free-shared"
diff --git a/notebooks/singlestore-now-2024/notebook.ipynb b/notebooks/singlestore-now-2024/notebook.ipynb
@@ -0,0 +1,363 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "1d35bf5a-7a16-4eea-9a45-797273ac5491",
+      "metadata": {},
+      "source": [
+        "<div id=\"singlestore-header\" style=\"display: flex; background-color: rgba(255, 182, 176, 0.25); padding: 5px;\">\n",
+        "    <div id=\"icon-image\" style=\"width: 90px; height: 90px;\">\n",
+        "        <img width=\"100%\" height=\"100%\" src=\"https://raw.githubusercontent.com/singlestore-labs/spaces-notebooks/master/common/images/header-icons/radar.png\" />\n",
+        "    </div>\n",
+        "    <div id=\"text\" style=\"padding: 5px; margin-left: 10px;\">\n",
+        "        <div id=\"badge\" style=\"display: inline-block; background-color: rgba(0, 0, 0, 0.15); border-radius: 4px; padding: 4px 8px; align-items: center; margin-top: 6px; margin-bottom: -2px; font-size: 80%\">SingleStore Notebooks</div>\n",
+        "        <h1 style=\"font-weight: 500; margin: 8px 0 0 4px;\">Singlestore Now 2024 Raffle</h1>\n",
+        "    </div>\n",
+        "</div>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "5fc3a6d9-e064-40dd-8cd0-636a567d5af0",
+      "metadata": {},
+      "source": [
+        "<div class=\"alert alert-block alert-warning\">\n",
+        "    <b class=\"fa fa-solid fa-exclamation-circle\"></b>\n",
+        "    <div>\n",
+        "        <p><b>Note</b></p>\n",
+        "        <p>This notebook can be run on a Free Starter Workspace. To create a Free Starter Workspace navigate to <tt>Start</tt> using the left nav. You can also use your existing Standard or Premium workspace with this Notebook.</p>\n",
+        "    </div>\n",
+        "</div>"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "id": "dfc73c1e-9918-4d0a-ab22-4187a9c47678",
+      "metadata": {},
+      "source": [
+        "<img src=https://raw.githubusercontent.com/singlestore-labs/spaces-notebooks/master/notebooks/atlas-and-kai/images/mongo-db-singlestoredb.png width=\"100%\">"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "id": "1c7f4c37-2c1d-4507-9564-de2bea190005",
+      "metadata": {},
+      "source": [
+        "## Install libraries and import modules"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "fb64cdc7-3ff1-4809-a9f1-9f0e770874b3",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "!pip install pymongo pandas ipywidgets --quiet"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "784ccd70-014c-429a-8325-91407fbf0e96",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "shared_tier_check = %sql show variables like 'is_shared_tier'\n",
+        "\n",
+        "if shared_tier_check and shared_tier_check[0][1] == 'ON':\n",
+        "    current_database = %sql SELECT DATABASE() as CurrentDatabase\n",
+        "    database_to_use = current_database[0][0]\n",
+        "else:\n",
+        "    database_to_use = \"new_transactions\"\n",
+        "    %sql CREATE DATABASE {{database_to_use}}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "id": "3f1f2731-e117-4ead-871a-5711eb1cb391",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import time\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "import pymongo\n",
+        "from pymongo import MongoClient"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "id": "ca323068-a897-478f-839a-244f4bbc1719",
+      "metadata": {},
+      "source": [
+        "## Connect to Atlas and SingleStore Kai endpoints\n",
+        "We are using a shared tier on the backend for Atlas"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "5bf785b4-79c6-440f-9bb1-34a033c9f4db",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# No need to edit anything\n",
+        "myclientmongodb = pymongo.MongoClient(\"mongodb+srv://mongo_sample_reader:[email protected]/?retryWrites=true&w=majority\")\n",
+        "mydbmongodb = myclientmongodb[\"new_transactions\"]\n",
+        "mongoitems = mydbmongodb[\"items\"]\n",
+        "mongocusts = mydbmongodb[\"custs\"]\n",
+        "mongotxs = mydbmongodb[\"txs\"]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "id": "20e25f4a-a6ce-4e3a-80c5-c56002945c7e",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "s2clientmongodb = pymongo.MongoClient(connection_url_kai)\n",
+        "s2dbmongodb = s2clientmongodb[database_to_use]\n",
+        "s2mongoitems = s2dbmongodb[\"items\"]\n",
+        "s2mongocusts = s2dbmongodb[\"custs\"]\n",
+        "s2mongotxs = s2dbmongodb[\"txs\"]"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "id": "36c6162c-e0a2-404b-8d9f-9af8df8b8cea",
+      "metadata": {},
+      "source": [
+        "## Copy Atlas collections into SingleStore Kai"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "ebbefa07-2fbf-468c-bf65-00e12dcc606f",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "mongocollections = [mongoitems, mongocusts, mongotxs]\n",
+        "\n",
+        "for mongo_collection in mongocollections:\n",
+        "    df = pd.DataFrame(list(mongo_collection.find())).reset_index(drop=True)\n",
+        "    data_dict = df.to_dict(orient='records')\n",
+        "    s2mongo_collection = s2dbmongodb[mongo_collection.name]\n",
+        "    s2mongo_collection.insert_many(data_dict)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "id": "ca4dbc9b-f96a-46c1-a4ac-aa761e0d19ec",
+      "metadata": {},
+      "source": [
+        "## Total quantity of products sold across all products"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "2d3e0782-198f-4539-92cd-91e1758db721",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "num_iterations = 10\n",
+        "mongo_times = []\n",
+        "\n",
+        "# Updated pipeline for total quantity of products sold across all products\n",
+        "pipeline = [\n",
+        "    {\"$group\": {\"_id\": None, \"totalQuantity\": {\"$sum\": \"$item.quantity\"}}}\n",
+        "]\n",
+        "\n",
+        "# Simulating same for s2mongoitems\n",
+        "s2_times = []\n",
+        "for i in range(num_iterations):\n",
+        "    s2_start_time = time.time()\n",
+        "    s2_result = s2mongoitems.aggregate(pipeline)\n",
+        "    s2_stop_time = time.time()\n",
+        "    s2_times.append(s2_stop_time - s2_start_time)\n",
+        "\n",
+        "# Retrieving total quantity from the result\n",
+        "total_quantity = next(s2_result)[\"totalQuantity\"] if s2_result else 0\n",
+        "\n",
+        "# Returning the numeric values of total quantity sold\n",
+        "print(\"Total Product Quantity Sold is\",total_quantity)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "id": "58f643e0-0205-4cf7-97de-dcd93bef0a64",
+      "metadata": {},
+      "source": [
+        "## Top selling Product"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "a31e6d36-9eb3-43d3-a8c9-50a740d8d36c",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Updated pipeline to return the #1 selling product based on total quantity sold\n",
+        "pipeline = [\n",
+        "    {\"$group\": {\n",
+        "        \"_id\": \"$item.name\",  # Group by product name\n",
+        "        \"total_quantity_sold\": {\"$sum\": \"$item.quantity\"}  # Sum of quantities sold\n",
+        "    }},\n",
+        "    {\"$sort\": {\"total_quantity_sold\": -1}},  # Sort by total quantity sold in descending order\n",
+        "    {\"$limit\": 1}  # Limit to the top product\n",
+        "]\n",
+        "\n",
+        "s2_result = s2mongoitems.aggregate(pipeline)\n",
+        "\n",
+        "# Retrieve the name of the #1 selling product\n",
+        "top_product = next(s2_result, None)\n",
+        "if top_product:\n",
+        "    product_name = top_product[\"_id\"]\n",
+        "    total_quantity_sold = top_product[\"total_quantity_sold\"]\n",
+        "else:\n",
+        "    product_name = \"No Data\"\n",
+        "    total_quantity_sold = 0\n",
+        "\n",
+        "# Return the #1 selling product and its total quantity sold\n",
+        "print(\"Top-Selling product : \",product_name,\"With total quantity sold \",total_quantity_sold)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e45de51e-f54b-4788-8fb3-2aadc9143533",
+      "metadata": {},
+      "source": [
+        "## Top selling Location"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "id": "923bf8d1-6869-4448-9916-80e4f1b6e3f0",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Updated pipeline to exclude \"Online\" and get top-selling location\n",
+        "pipeline = [\n",
+        "    {\"$lookup\":\n",
+        "         {\n",
+        "          \"from\": \"custs\",\n",
+        "          \"localField\": \"customer.email\",\n",
+        "          \"foreignField\": \"email\",\n",
+        "          \"as\": \"transaction_links\",\n",
+        "         }\n",
+        "    },\n",
+        "    {\"$match\": {\"store_location\": {\"$ne\": \"Online\"}}},  # Exclude Online location\n",
+        "    {\"$limit\": 100},\n",
+        "    {\"$group\":\n",
+        "        {\n",
+        "         \"_id\": {\"location\": \"$store_location\"},\n",
+        "         \"count\": {\"$sum\": 1}\n",
+        "        }\n",
+        "    },\n",
+        "    {\"$sort\": {\"count\": -1}},\n",
+        "    {\"$limit\": 1}\n",
+        "]\n",
+        "\n",
+        "\n",
+        "s2_result = s2mongotxs.aggregate(pipeline)\n",
+        "\n",
+        "\n",
+        "# Retrieve the top-selling location excluding \"Online\"\n",
+        "top_location = next(s2_result, None)\n",
+        "if top_location:\n",
+        "    location_name = top_location[\"_id\"][\"location\"]\n",
+        "    transaction_count = top_location[\"count\"]\n",
+        "else:\n",
+        "    location_name = \"No Data\"\n",
+        "    transaction_count = 0\n",
+        "\n",
+        "# Return the top-selling location and transaction count\n",
+        "\n",
+        "print(\"Top-Selling Location : \",location_name,\"With transaction of Count \",transaction_count)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "93934fde-c22e-4bda-992f-ed01dc83283c",
+      "metadata": {},
+      "source": [
+        "## Clean up"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "599ca6e3-3847-467a-8a33-8f91e52a9cd1",
+      "metadata": {},
+      "source": [
+        "<div class=\"alert alert-block alert-warning\">\n",
+        "    <b class=\"fa fa-solid fa-exclamation-circle\"></b>\n",
+        "    <div>\n",
+        "        <p><b>Action Required</b></p>\n",
+        "        <p> If you created a new database in your Standard or Premium Workspace, you can drop the database by running the cell below. Note: this will not drop your database for Free Starter Workspaces. To drop a Free Starter Workspace, terminate the Workspace using the UI. </p>\n",
+        "    </div>\n",
+        "</div>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "id": "2f4cf3c7-5e1f-442e-8b6e-e4f106ded82b",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "shared_tier_check = %sql show variables like 'is_shared_tier'\n",
+        "if not shared_tier_check or shared_tier_check[0][1] == 'OFF':\n",
+        "    %sql DROP DATABASE IF EXISTS new_transactions;"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "9635adf8-8137-4637-b94d-22835ba8112d",
+      "metadata": {},
+      "source": [
+        "<div id=\"singlestore-footer\" style=\"background-color: rgba(194, 193, 199, 0.25); height:2px; margin-bottom:10px\"></div>\n",
+        "<div><img src=\"https://raw.githubusercontent.com/singlestore-labs/spaces-notebooks/master/common/images/singlestore-logo-grey.png\" style=\"padding: 0px; margin: 0px; height: 24px\"/></div>"
+      ]
+    }
+  ],
+  "metadata": {
+    "jupyterlab": {
+      "notebooks": {
+        "version_major": 6,
+        "version_minor": 4
+      }
+    },
+    "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": "3.11.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}