From 52ae257714fb3d96bc0c6dc6164ce0bde7d35bbe Mon Sep 17 00:00:00 2001 From: vaishnavipalyam Date: Sat, 2 Aug 2025 18:41:19 +0530 Subject: [PATCH] Add Vaishnavi's Day 1 dashboard summarization (cleared outputs) --- .../Dashboard summarization.ipynb | 256 ++++++++++++++++++ 1 file changed, 256 insertions(+) create mode 100644 week1/community-contributions/Dashboard summarization.ipynb diff --git a/week1/community-contributions/Dashboard summarization.ipynb b/week1/community-contributions/Dashboard summarization.ipynb new file mode 100644 index 0000000..99c18f9 --- /dev/null +++ b/week1/community-contributions/Dashboard summarization.ipynb @@ -0,0 +1,256 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 3, + "id": "e0ab4a60-bc68-446d-ae13-6bd90d54ae44", + "metadata": {}, + "outputs": [], + "source": [ + "# imports\n", + "import os\n", + "from dotenv import load_dotenv\n", + "import requests\n", + "from bs4 import BeautifulSoup\n", + "from IPython.display import Markdown, display\n", + "from openai import OpenAI" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "749afaa0-a82e-4783-91fc-f69756075606", + "metadata": {}, + "outputs": [], + "source": [ + "# A class to represent a Webpage\n", + "\n", + "# Some websites need you to use proper headers when fetching them:\n", + "headers = {\n", + " \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n", + "}\n", + "\n", + "class Website:\n", + "\n", + " def __init__(self, url):\n", + " \"\"\"\n", + " Create this Website object from the given url using the BeautifulSoup library\n", + " \"\"\"\n", + " self.url = url\n", + " response = requests.get(url, headers=headers)\n", + " soup = BeautifulSoup(response.content, 'html.parser')\n", + " self.title = soup.title.string if soup.title else \"No title found\"\n", + " for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", + " irrelevant.decompose()\n", + " self.text = soup.body.get_text(separator=\"\\n\", strip=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "7e760d9c-d899-49e5-8b8f-c202794486cc", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "API key found and looks good so far!\n" + ] + } + ], + "source": [ + "# Load environment variables in a file called .env\n", + "\n", + "load_dotenv(override=True)\n", + "api_key = os.getenv('OPENAI_API_KEY')\n", + "\n", + "# Check the key\n", + "\n", + "if not api_key:\n", + " print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n", + "elif not api_key.startswith(\"sk-proj-\"):\n", + " print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\n", + "elif api_key.strip() != api_key:\n", + " print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n", + "else:\n", + " print(\"API key found and looks good so far!\")" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "8efb8bb3-9be9-404b-aff5-306db64a75e7", + "metadata": {}, + "outputs": [], + "source": [ + "openai = OpenAI()" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "cf677c78-012c-4b86-a76c-be47ed3cb987", + "metadata": {}, + "outputs": [], + "source": [ + "# Define our system prompt - you can experiment with this later, changing the last sentence to 'Respond in markdown in Spanish.\"\n", + "\n", + "system_prompt = \"You are an assistant that analyzes the \\\n", + "the dashboard in a website and provides a short executive summary, ignoring text that might be navigation related. \\\n", + "Respond in markdown.\"" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "970a493a-880a-4206-9609-eee0651aa91f", + "metadata": {}, + "outputs": [], + "source": [ + "# A function that writes a User Prompt that asks for summaries of websites:\n", + "\n", + "def user_prompt_for(website):\n", + " user_prompt = f\"You are looking at a website titled {website.title}\"\n", + " user_prompt += \"\\nPlease provide a detailed summary of the report for the year in markdown for its user (CFO); \\\n", + "The summary should be in a suitable form which could be sent through a mail for the exective.\\n\\n\"\n", + " user_prompt += website.text\n", + " return user_prompt" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "2520cdd1-4755-4c87-854f-430e81dbc3fc", + "metadata": {}, + "outputs": [], + "source": [ + "def messages_for(website):\n", + " return [\n", + " {\"role\": \"system\", \"content\": system_prompt},\n", + " {\"role\": \"user\", \"content\": user_prompt_for(website)}\n", + " ]" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "7452990b-352b-43cc-adc6-4307d6d5c1d5", + "metadata": {}, + "outputs": [], + "source": [ + "def summarize(url):\n", + " website = Website(url)\n", + " response = openai.chat.completions.create(\n", + " model = \"gpt-4o-mini\",\n", + " messages = messages_for(website)\n", + " )\n", + " return response.choices[0].message.content" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "7372da3c-f3c7-455b-825e-f54d3b0cee68", + "metadata": {}, + "outputs": [], + "source": [ + "def display_summary(url):\n", + " summary = summarize(url)\n", + " display(Markdown(summary))" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "be7d57dc-bec1-4771-9d15-d80fd4d3fbb5", + "metadata": {}, + "outputs": [ + { + "data": { + "text/markdown": [ + "# Executive Summary: Revenue & Profitability Dashboard\n", + "\n", + "**To:** [CFO Name] \n", + "**From:** [Your Name] \n", + "**Date:** [Current Date] \n", + "**Subject:** Yearly Analysis of Revenue & Profitability \n", + "\n", + "---\n", + "\n", + "Dear [CFO Name],\n", + "\n", + "I am pleased to present the Year-over-Year analysis derived from the Revenue & Profitability Dashboard. This dashboard has been designed to provide concise insights into our core financial performance metrics, enabling data-driven decision-making at the executive level.\n", + "\n", + "### Key Metrics Overview:\n", + "- **Revenue**: Comprehensive insights into total revenue across various regions and product categories, indicating sustainable growth patterns.\n", + "- **Profit**: Detailed profitability analysis segmented by customer groups, revealing key opportunities for margin improvement and cost optimization.\n", + "- **Unit Sales**: Analysis of unit sales trends that highlight product performance and demand fluctuations.\n", + "\n", + "### Insights by Segment:\n", + "- **Regional Performance**: Comparative analysis of revenue and profitability by region helps identify areas of growth and those requiring strategic intervention.\n", + "- **Product Performance**: A focused review of individual product lines shows which offerings are driving profitability and where we might consider realignment or innovation.\n", + "\n", + "### Dashboard Features:\n", + "- A **clean and focused layout** reduces cognitive load, allowing for quick assimilation and understanding of critical data points.\n", + "- **Contextual metrics** that align with our overarching business strategy, ensuring that our analysis supports our organizational goals.\n", + "- **Clear comparison points** are established to aid executives in making informed and timely decisions.\n", + "- Insightful details are presented at both product and regional levels, facilitating targeted strategies for improvement.\n", + "\n", + "### Conclusion:\n", + "The integration of design and context in our dashboard framework turns our data into strategic tools, empowering us to make faster and more informed decisions that drive real business impact.\n", + "\n", + "Please feel free to reach out for a more detailed discussion or specific metrics that may interest you.\n", + "\n", + "Best regards,\n", + "\n", + "[Your Name] \n", + "[Your Position]\n", + "\n", + "--- \n", + "\n", + "*Note: For additional inquiries or insights, feel free to follow our updates on LinkedIn or contact me directly.*" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display_summary(\"https://community.fabric.microsoft.com/t5/Data-Stories-Gallery/Revenue-amp-Profitability-Dashboard/td-p/4780272\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "1aa33cfd-d497-4ab8-abb5-eb4e6030890b", + "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": "3.11.13" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}