{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "We want to build a CPU dataset.\n", "There is pointer on https://github.com/felixsteinke/cpu-spec-dataset\n", "\n", "## AMD Dataset\n", "\n", "Manually Export Data as CSV/Excel from https://www.amd.com/en/products/specifications/processors\n", "Website Screenshot\n", "\n", "blob:https://www.amd.com/fc70f2d3-27d4-4bf1-a466-9912927167de\n", "\n", "## Ampere Dataset\n", "\n", "Extracted from https://amperecomputing.com/briefs/ampere-altra-family-product-brief with the responsible Web Scraper.\n", "\n", "cd ampere-web-scraper\n", "java -jar ./target/exectuable.jar\n", "\n", "## Intel Dataset\n", "\n", "Extracted from https://ark.intel.com/content/www/us/en/ark.html with the responsible Web Scraper.\n", "\n", "cd intel-web-scraper\n", "java -jar ./target/exectuable.jar\n", "\n", "## CPU Benchmark Dataset\n", "\n", "Extracted from https://www.cpubenchmark.net/cpu_list.php with the responsible Web Scraper.\n", "\n", "cd benchmark-web-scraper\n", "java -jar ./target/exectuable.jar\n", "\n", "## CPU World Dataset\n", "\n", "Extracted from https://www.cpu-world.com/CPUs/CPU.html with the responsible Web Scraper.\n", "\n", "cd cpuworld-web-scraper\n", "mvn -jar ./target/exectuable.jar" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "test" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Extraction from https://www.intel.com/content/www/us/en/ark/products/series/236644/5th-gen-intel-xeon-scalable-processors.html\n", "```html\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", " \n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " ```" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Prompt**\n", "\n", "How to automate extraction ?" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Response**\n", "\n", "I see you're looking to extract CPU data from Intel's website. Before diving into the automation, I'd like to understand a few things:\n", "\n", "1. Are you comfortable with Python programming? \n", "2. Have you tried web scraping before?\n", "3. Would you prefer using a specific library (like BeautifulSoup, Scrapy, or Selenium)?\n", "\n", "This looks like a dynamic table with sortable columns, so we'll need to consider the best approach based on your experience level and requirements. Let me know your preferences, and I'll help guide you through the process." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Prompt**\n", "\n", "BeautifulSoup" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Response**\n", "\n", "Great choice! BeautifulSoup is perfect for this. Looking at the HTML you shared, we can extract the table data. Would you like me to:\n", "\n", "1. Help you write the code step by step, or\n", "2. Provide a complete solution?\n", "\n", "Also, do you need to:\n", "- Extract just this one page, or\n", "- Navigate through multiple pages?\n", "\n", "Let me know your preference and I'll help accordingly." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Prompt**\n", "\n", "Extract just this one page" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Response**\n", "\n", "I'll help you extract data from this page. Let's break it down into steps:\n", "\n", "1. First, we'll need to set up BeautifulSoup and make the request. Would you like to start by writing the code to import the required libraries and fetch the page?\n", "\n", "The libraries we'll need are:\n", "- `beautifulsoup4`\n", "- `requests`\n", "\n", "Would you like to try writing this first part, or would you like me to show you how?" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Prompt**\n", "\n", "give me the code" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Response**\n", "\n", "Here's the code to get started:\n", "\n", "```python\n", "import requests\n", "from bs4 import BeautifulSoup\n", "\n", "url = \"https://www.intel.com/content/www/us/en/ark/products/series/236644/5th-gen-intel-xeon-scalable-processors.html\"\n", "response = requests.get(url)\n", "soup = BeautifulSoup(response.text, 'html.parser')\n", "```\n", "\n", "Try running this code. Let me know if it works, and then we'll move on to extracting the table data. \n", "\n", "(Note: If you get any errors about missing libraries, you'll need to install them first using `pip install requests beautifulsoup4`)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import requests\n", "from bs4 import BeautifulSoup\n", "\n", "url = \"https://www.intel.com/content/www/us/en/ark/products/series/236644/5th-gen-intel-xeon-scalable-processors.html\"\n", "response = requests.get(url)\n", "soup = BeautifulSoup(response.text, \"html.parser\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Prompt**\n", "\n", "fine, give me the code to extract the data ?" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**AI Response**\n", "\n", "Here's the code to extract the table data:\n", "\n", "```python\n", "# Find the table\n", "table = soup.find('table', id='product-table')\n", "\n", "# Extract headers\n", "headers = []\n", "for th in table.find_all('th'):\n", " header_text = th.find('div', class_='header-text-space').text.strip()\n", " headers.append(header_text)\n", "\n", "# Extract rows\n", "data = []\n", "for row in table.find('tbody').find_all('tr'):\n", " row_data = {}\n", " cells = row.find_all('td')\n", " for i, cell in enumerate(cells):\n", " row_data[headers[i]] = cell.text.strip()\n", " data.append(row_data)\n", "\n", "# Convert to pandas DataFrame for easy viewing/export\n", "import pandas as pd\n", "df = pd.DataFrame(data)\n", "print(df)\n", "```\n", "\n", "Would you like me to explain how this code works, or would you prefer to see how to modify it for specific needs?" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Product Name Launch Date ... Cache TDP\n", "0 Intel® Xeon® Bronze 3508U Processor Q4'23 ... 22.5 MB 125 W\n", "1 Intel® Xeon® Gold 5512U Processor Q4'23 ... 52.5 MB 185 W\n", "2 Intel® Xeon® Gold 5515+ Processor Q4'23 ... 22.5 MB 165 W\n", "3 Intel® Xeon® Gold 5520+ Processor Q4'23 ... 52.5 MB 205 W\n", "4 Intel® Xeon® Gold 6526Y Processor Q4'23 ... 37.5 MB 195 W\n", "5 Intel® Xeon® Gold 6530 Processor Q4'23 ... 160 MB 270 W\n", "6 Intel® Xeon® Gold 6534 Processor Q4'23 ... 22.5 MB 195 W\n", "7 Intel® Xeon® Gold 6538N Processor Q4'23 ... 60 MB 205 W\n", "8 Intel® Xeon® Gold 6538Y+ Processor Q4'23 ... 60 MB 225 W\n", "9 Intel® Xeon® Gold 6542Y Processor Q4'23 ... 60 MB 250 W\n", "10 Intel® Xeon® Gold 6544Y Processor Q4'23 ... 45 MB 270 W\n", "11 Intel® Xeon® Gold 6548N Processor Q4'23 ... 60 MB 250 W\n", "12 Intel® Xeon® Gold 6548Y+ Processor Q4'23 ... 60 MB 250 W\n", "13 Intel® Xeon® Gold 6554S Processor Q4'23 ... 180 MB 270 W\n", "14 Intel® Xeon® Gold 6558Q Processor Q4'23 ... 60 MB 350 W\n", "15 Intel® Xeon® Platinum 8558 Processor Q4'23 ... 260 MB 330 W\n", "16 Intel® Xeon® Platinum 8558P Processor Q4'23 ... 260 MB 350 W\n", "17 Intel® Xeon® Platinum 8558U Processor Q4'23 ... 260 MB 300 W\n", "18 Intel® Xeon® Platinum 8562Y+ Processor Q4'23 ... 60 MB 300 W\n", "19 Intel® Xeon® Platinum 8568Y+ Processor Q4'23 ... 300 MB 350 W\n", "20 Intel® Xeon® Platinum 8570 Processor Q4'23 ... 300 MB 350 W\n", "21 Intel® Xeon® Platinum 8571N Processor Q4'23 ... 300 MB 300 W\n", "22 Intel® Xeon® Platinum 8580 Processor Q4'23 ... 300 MB 350 W\n", "23 Intel® Xeon® Platinum 8581V Processor Q4'23 ... 300 MB 270 W\n", "24 Intel® Xeon® Platinum 8592+ Processor Q4'23 ... 320 MB 350 W\n", "25 Intel® Xeon® Platinum 8592V Processor Q4'23 ... 320 MB 330 W\n", "26 Intel® Xeon® Platinum 8593Q Processor Q4'23 ... 320 MB 385 W\n", "27 Intel® Xeon® Silver 4509Y Processor Q4'23 ... 22.5 MB 125 W\n", "28 Intel® Xeon® Silver 4510 Processor Q4'23 ... 30 MB 150 W\n", "29 Intel® Xeon® Silver 4510T Processor Q4'23 ... 30 MB 115 W\n", "30 Intel® Xeon® Silver 4514Y Processor Q4'23 ... 30 MB 150 W\n", "31 Intel® Xeon® Silver 4516Y+ Processor Q4'23 ... 45 MB 185 W\n", "\n", "[32 rows x 7 columns]\n" ] } ], "source": [ "# Find the table\n", "table = soup.find(\"table\", id=\"product-table\")\n", "\n", "# Extract headers\n", "headers = []\n", "for th in table.find_all(\"th\"):\n", " header_text = th.find(\"div\", class_=\"header-text-space\").text.strip()\n", " headers.append(header_text)\n", "\n", "# Extract rows\n", "data = []\n", "for row in table.find(\"tbody\").find_all(\"tr\"):\n", " row_data = {}\n", " cells = row.find_all(\"td\")\n", " for i, cell in enumerate(cells):\n", " row_data[headers[i]] = cell.text.strip()\n", " data.append(row_data)\n", "\n", "# Convert to pandas DataFrame for easy viewing/export\n", "import pandas as pd\n", "\n", "df = pd.DataFrame(data)\n", "print(df)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 125 W\n", "1 185 W\n", "2 165 W\n", "3 205 W\n", "4 195 W\n", "5 270 W\n", "6 195 W\n", "7 205 W\n", "8 225 W\n", "9 250 W\n", "10 270 W\n", "11 250 W\n", "12 250 W\n", "13 270 W\n", "14 350 W\n", "15 330 W\n", "16 350 W\n", "17 300 W\n", "18 300 W\n", "19 350 W\n", "20 350 W\n", "21 300 W\n", "22 350 W\n", "23 270 W\n", "24 350 W\n", "25 330 W\n", "26 385 W\n", "27 125 W\n", "28 150 W\n", "29 115 W\n", "30 150 W\n", "31 185 W\n", "Name: TDP, dtype: object" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[\"TDP\"].replace(\"W\", \"\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## AMD" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Average TDP per core from AMD dataset: 4.73 W\n" ] } ], "source": [ "import pandas as pd\n", "\n", "# Path to your manually exported AMD CPU dataset.\n", "# (Adjust the file path as needed.)\n", "amd_csv_path = \"./AMD_CPU_desktop_laptop.csv\"\n", "\n", "try:\n", " amd_df = pd.read_csv(amd_csv_path)\n", " amd_df = amd_df[amd_df[\"Launch Date\"].str.contains(\"2024|2025\", na=False)]\n", " amd_df = amd_df[amd_df[\"Form Factor\"].str.contains(\"Desktops\", na=False)]\n", "\n", " # Convert columns to numeric, forcing errors to NaN\n", " # amd_df['Default TDP'] = amd_df['Default TDP'].str.replace('W', '').astype(float)\n", " amd_df[\"TDP\"] = pd.to_numeric(\n", " amd_df[\"Default TDP\"].str.replace(\"W\", \"\"), errors=\"coerce\"\n", " )\n", " amd_df[\"# of Threads\"] = pd.to_numeric(amd_df[\"# of Threads\"], errors=\"coerce\")\n", "\n", " # It is assumed the CSV contains columns named 'TDP' (in Watts) and 'Total Cores'\n", " # Adjust the column names if they differ.\n", " amd_df[\"TDP_per_core\"] = amd_df[\"TDP\"] / amd_df[\"# of Threads\"]\n", "\n", " average_tdp_per_core = amd_df[\"TDP_per_core\"].mean()\n", " print(\n", " \"Average TDP per core from AMD dataset: {:.2f} W\".format(average_tdp_per_core)\n", " )\n", "except Exception as e:\n", " print(\"Error loading or processing AMD dataset:\", e)" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Average TDP per core from AMD dataset: 3.61 W\n" ] } ], "source": [ "# https://www.amd.com/en/products/specifications/server-processor.html\n", "import pandas as pd\n", "\n", "# Path to your manually exported AMD CPU dataset.\n", "# (Adjust the file path as needed.)\n", "amd_csv_path = \"./AMD_Server_Processor_Specifications.csv\"\n", "\n", "try:\n", " amd_df = pd.read_csv(amd_csv_path)\n", " amd_df = amd_df[amd_df[\"Launch Date\"].str.contains(\"2024|2025\", na=False)]\n", "\n", " # Convert columns to numeric, forcing errors to NaN\n", " # amd_df['Default TDP'] = amd_df['Default TDP'].str.replace('W', '').astype(float)\n", " amd_df[\"TDP\"] = pd.to_numeric(\n", " amd_df[\"Default TDP\"].str.replace(\"W\", \"\"), errors=\"coerce\"\n", " )\n", " amd_df[\"# of Threads\"] = pd.to_numeric(amd_df[\"# of Threads\"], errors=\"coerce\")\n", "\n", " # It is assumed the CSV contains columns named 'TDP' (in Watts) and 'Total Cores'\n", " # Adjust the column names if they differ.\n", " amd_df[\"TDP_per_core\"] = amd_df[\"TDP\"] / amd_df[\"# of Threads\"]\n", "\n", " average_tdp_per_core = amd_df[\"TDP_per_core\"].mean()\n", " print(\n", " \"Average TDP per core from AMD dataset: {:.2f} W\".format(average_tdp_per_core)\n", " )\n", "except Exception as e:\n", " print(\"Error loading or processing AMD dataset:\", e)" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['Name', 'Family', 'Series', 'Form Factor', '# of CPU Cores',\n", " '# of Threads', 'Max. Boost Clock', 'Base Clock', 'L2 Cache',\n", " 'L3 Cache', 'Default TDP', 'L1 Cache', 'AMD Configurable TDP (cTDP)',\n", " 'Processor Technology for CPU Cores', 'Unlocked for Overclocking',\n", " 'CPU Socket', 'Thermal Solution (PIB)', 'Recommended Cooler',\n", " 'Thermal Solution (MPK)', 'Max. Operating Temperature (Tjmax)',\n", " 'Launch Date', '*OS Support', 'PCI Express® Version',\n", " 'System Memory Type', 'Memory Channels', 'System Memory Specification',\n", " 'Graphics Model', 'Graphics Core Count', 'Graphics Frequency',\n", " 'AMD Ryzen™ AI', 'Product ID Boxed', 'Product ID Tray',\n", " 'Product ID MPK', 'Supported Technologies', 'TDP_per_core'],\n", " dtype='object')" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "amd_df.columns" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "
\n", "
\n", "
\n", " Product Name\n", "
\n", "
\n", "
\n", "
\n", "
\n", " Launch Date\n", "
\n", "
\n", "
\n", "
\n", "
\n", " Total Cores\n", "
\n", "
\n", "
\n", "
\n", "
\n", " Max Turbo Frequency\n", "
\n", "
\n", "
\n", "
\n", "
\n", " Processor Base Frequency\n", "
\n", "
\n", "
\n", "
\n", "
\n", " Cache\n", "
\n", "
\n", "
\n", "
\n", "
\n", " TDP\n", "
\n", "
\n", "
\n", "
\n", " \n", " Intel® Xeon® Bronze 3508U Processor\n", "
\n", " 		\n", " \n", " \n", " \n", " \n", " \n", " Q4'23\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " 8\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " 2.2 GHz\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " 2.10 GHz\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " 22.5 MB\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " 125 W\n", " \n", " \n", " \n", "
\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NameTDP# of ThreadsTDP_per_coreLaunch Date
34AMD Ryzen™ 9 9950X17032.05.31250008/15/2024
36AMD Ryzen™ 9 9900X12024.05.00000008/15/2024
38AMD Ryzen™ 7 9800X3D12016.07.50000011/07/2024
39AMD Ryzen™ 7 9700X6516.04.06250008/08/2024
40AMD Ryzen™ 5 9600X6512.05.41666708/08/2024
44AMD Ryzen™ 7 PRO 8845HS4516.02.81250004/16/2024
46AMD Ryzen™ 7 PRO 8700GE3516.02.1875004/16/2024
47AMD Ryzen™ 7 PRO 8700G6516.04.0625004/16/2024
51AMD Ryzen™ 5 PRO 8600GE3512.02.9166674/16/2024
52AMD Ryzen™ 5 PRO 8600G6512.05.4166674/16/2024
54AMD Ryzen™ 5 PRO 8500GE3512.02.9166674/16/2024
55AMD Ryzen™ 5 PRO 8500G6512.05.4166674/16/2024
57AMD Ryzen™ 3 PRO 8300GE358.04.3750004/16/2024
58AMD Ryzen™ 3 PRO 8300G658.08.1250004/16/2024
62AMD Ryzen™ 7 8700G6516.04.0625001/31/2024
63AMD Ryzen™ 7 8700F6516.04.06250004/01/2024
67AMD Ryzen™ 5 8600G6512.05.4166671/31/2024
69AMD Ryzen™ 5 8500GE3512.02.9166674/16/2024
70AMD Ryzen™ 5 8500G6512.05.4166671/31/2024
72AMD Ryzen™ 3 8300GE358.04.3750004/16/2024
73AMD Ryzen™ 5 8400F6512.05.41666704/01/2024
74AMD Ryzen™ 3 8300G658.08.1250001/31/2024
105AMD Ryzen™ 9 7940HX5532.01.7187501/17/2024
111AMD Ryzen™ 7 7840HX5524.02.2916671/17/2024
124AMD Ryzen™ 5 7600X3D6512.05.4166679/5/2024
138AMD Ryzen™ 5 7400F6512.05.4166671/9/2025
178AMD Ryzen™ 7 PRO 5755GE3516.02.1875009/5/2024
179AMD Ryzen™ 7 PRO 5755G6516.04.0625009/5/2024
183AMD Ryzen™ 5 PRO 5655GE3512.02.9166675/7/2024
184AMD Ryzen™ 5 PRO 5655G6512.05.4166675/7/2024
191AMD Ryzen™ 3 PRO 5355GE358.04.3750009/5/2024
192AMD Ryzen™ 3 PRO 5355G658.08.1250009/5/2024
198AMD Ryzen™ 9 5900XT10532.03.28125007/31/2024
206AMD Ryzen™ 7 5800XT10516.06.56250007/31/2024
214AMD Ryzen™ 7 5700X3D10516.06.56250001/08/2024
219AMD Ryzen™ 7 57006516.04.06250001/31/2024
229AMD Ryzen™ 5 5600XT6512.05.41666710/31/2024
230AMD Ryzen™ 5 5600T6512.05.41666710/31/2024
231AMD Ryzen™ 5 5600GT6512.05.41666701/08/2024
238AMD Ryzen™ 5 5500GT6512.05.41666701/08/2024
\n", "" ], "text/plain": [ " Name TDP # of Threads TDP_per_core Launch Date\n", "34 AMD Ryzen™ 9 9950X 170 32.0 5.312500 08/15/2024\n", "36 AMD Ryzen™ 9 9900X 120 24.0 5.000000 08/15/2024\n", "38 AMD Ryzen™ 7 9800X3D 120 16.0 7.500000 11/07/2024\n", "39 AMD Ryzen™ 7 9700X 65 16.0 4.062500 08/08/2024\n", "40 AMD Ryzen™ 5 9600X 65 12.0 5.416667 08/08/2024\n", "44 AMD Ryzen™ 7 PRO 8845HS 45 16.0 2.812500 04/16/2024\n", "46 AMD Ryzen™ 7 PRO 8700GE 35 16.0 2.187500 4/16/2024\n", "47 AMD Ryzen™ 7 PRO 8700G 65 16.0 4.062500 4/16/2024\n", "51 AMD Ryzen™ 5 PRO 8600GE 35 12.0 2.916667 4/16/2024\n", "52 AMD Ryzen™ 5 PRO 8600G 65 12.0 5.416667 4/16/2024\n", "54 AMD Ryzen™ 5 PRO 8500GE 35 12.0 2.916667 4/16/2024\n", "55 AMD Ryzen™ 5 PRO 8500G 65 12.0 5.416667 4/16/2024\n", "57 AMD Ryzen™ 3 PRO 8300GE 35 8.0 4.375000 4/16/2024\n", "58 AMD Ryzen™ 3 PRO 8300G 65 8.0 8.125000 4/16/2024\n", "62 AMD Ryzen™ 7 8700G 65 16.0 4.062500 1/31/2024\n", "63 AMD Ryzen™ 7 8700F 65 16.0 4.062500 04/01/2024\n", "67 AMD Ryzen™ 5 8600G 65 12.0 5.416667 1/31/2024\n", "69 AMD Ryzen™ 5 8500GE 35 12.0 2.916667 4/16/2024\n", "70 AMD Ryzen™ 5 8500G 65 12.0 5.416667 1/31/2024\n", "72 AMD Ryzen™ 3 8300GE 35 8.0 4.375000 4/16/2024\n", "73 AMD Ryzen™ 5 8400F 65 12.0 5.416667 04/01/2024\n", "74 AMD Ryzen™ 3 8300G 65 8.0 8.125000 1/31/2024\n", "105 AMD Ryzen™ 9 7940HX 55 32.0 1.718750 1/17/2024\n", "111 AMD Ryzen™ 7 7840HX 55 24.0 2.291667 1/17/2024\n", "124 AMD Ryzen™ 5 7600X3D 65 12.0 5.416667 9/5/2024\n", "138 AMD Ryzen™ 5 7400F 65 12.0 5.416667 1/9/2025\n", "178 AMD Ryzen™ 7 PRO 5755GE 35 16.0 2.187500 9/5/2024\n", "179 AMD Ryzen™ 7 PRO 5755G 65 16.0 4.062500 9/5/2024\n", "183 AMD Ryzen™ 5 PRO 5655GE 35 12.0 2.916667 5/7/2024\n", "184 AMD Ryzen™ 5 PRO 5655G 65 12.0 5.416667 5/7/2024\n", "191 AMD Ryzen™ 3 PRO 5355GE 35 8.0 4.375000 9/5/2024\n", "192 AMD Ryzen™ 3 PRO 5355G 65 8.0 8.125000 9/5/2024\n", "198 AMD Ryzen™ 9 5900XT 105 32.0 3.281250 07/31/2024\n", "206 AMD Ryzen™ 7 5800XT 105 16.0 6.562500 07/31/2024\n", "214 AMD Ryzen™ 7 5700X3D 105 16.0 6.562500 01/08/2024\n", "219 AMD Ryzen™ 7 5700 65 16.0 4.062500 01/31/2024\n", "229 AMD Ryzen™ 5 5600XT 65 12.0 5.416667 10/31/2024\n", "230 AMD Ryzen™ 5 5600T 65 12.0 5.416667 10/31/2024\n", "231 AMD Ryzen™ 5 5600GT 65 12.0 5.416667 01/08/2024\n", "238 AMD Ryzen™ 5 5500GT 65 12.0 5.416667 01/08/2024" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "amd_df[[\"Name\", \"TDP\", \"# of Threads\", \"TDP_per_core\", \"Launch Date\"]]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Update the static CodeCarbon database" ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NameTDP
01075T95
1255e45
23260 HE45
3328065
43320 EE25
.........
3923TL-5231
3924TL-6031
3925TL-6435
3926X115017
3927X94045
\n", "

3928 rows × 2 columns

\n", "
" ], "text/plain": [ " Name TDP\n", "0 1075T 95\n", "1 255e 45\n", "2 3260 HE 45\n", "3 3280 65\n", "4 3320 EE 25\n", "... ... ..\n", "3923 TL-52 31\n", "3924 TL-60 31\n", "3925 TL-64 35\n", "3926 X1150 17\n", "3927 X940 45\n", "\n", "[3928 rows x 2 columns]" ] }, "execution_count": 64, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_csv(\"cpu_power.csv\")\n", "df" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NameTDP
0AMD EPYC 9965500.0
1AMD EPYC 9845390.0
2AMD EPYC 9825390.0
\n", "
" ], "text/plain": [ " Name TDP\n", "0 AMD EPYC 9965 500.0\n", "1 AMD EPYC 9845 390.0\n", "2 AMD EPYC 9825 390.0" ] }, "execution_count": 65, "metadata": {}, "output_type": "execute_result" } ], "source": [ "amd_csv_path = \"./AMD_Server_Processor_Specifications.csv\"\n", "amd_df = pd.read_csv(amd_csv_path)\n", "amd_df[\"TDP\"] = pd.to_numeric(\n", " amd_df[\"Default TDP\"].str.replace(\"W\", \"\"), errors=\"coerce\"\n", ")\n", "amd_df[\"Name\"] = amd_df[\"Name\"].str.replace(\"™\", \"\")\n", "amd_server = amd_df[[\"Name\", \"TDP\"]]\n", "amd_server = amd_server.dropna(subset=[\"TDP\"])\n", "amd_server.head(3)" ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/tmp/ipykernel_52381/4222190993.py:6: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " new_cpus['TDP'] = new_cpus['TDP_AMD']\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NameTDPTDP_AMD_merge
505AMD EPYC 4124P6565right_only
506AMD EPYC 4244P6565right_only
507AMD EPYC 4344P6565right_only
508AMD EPYC 4364P105105right_only
509AMD EPYC 4464P6565right_only
...............
752AMD Opteron 6328115115right_only
753AMD Opteron 6338P9999right_only
754AMD Opteron 6344115115right_only
757AMD Opteron 6370P9999right_only
807AMD Opteron X2170 APU2525right_only
\n", "

113 rows × 4 columns

\n", "
" ], "text/plain": [ " Name TDP TDP_AMD _merge\n", "505 AMD EPYC 4124P 65 65 right_only\n", "506 AMD EPYC 4244P 65 65 right_only\n", "507 AMD EPYC 4344P 65 65 right_only\n", "508 AMD EPYC 4364P 105 105 right_only\n", "509 AMD EPYC 4464P 65 65 right_only\n", ".. ... ... ... ...\n", "752 AMD Opteron 6328 115 115 right_only\n", "753 AMD Opteron 6338P 99 99 right_only\n", "754 AMD Opteron 6344 115 115 right_only\n", "757 AMD Opteron 6370P 99 99 right_only\n", "807 AMD Opteron X2170 APU 25 25 right_only\n", "\n", "[113 rows x 4 columns]" ] }, "execution_count": 66, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Merge df with amd_server, avoiding duplicates\n", "amd_server[\"TDP\"] = amd_server[\"TDP\"].astype(int).astype(str)\n", "merged_df = df.merge(\n", " amd_server, on=\"Name\", how=\"outer\", suffixes=(\"\", \"_AMD\"), indicator=True\n", ")\n", "# Filter for new entries that are only in amd_server\n", "new_cpus = merged_df[merged_df[\"_merge\"] == \"right_only\"]\n", "new_cpus[\"TDP\"] = new_cpus[\"TDP_AMD\"]\n", "new_cpus" ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NameTDP
505AMD EPYC 4124P65
506AMD EPYC 4244P65
507AMD EPYC 4344P65
508AMD EPYC 4364P105
509AMD EPYC 4464P65
.........
752AMD Opteron 6328115
753AMD Opteron 6338P99
754AMD Opteron 6344115
757AMD Opteron 6370P99
807AMD Opteron X2170 APU25
\n", "

113 rows × 2 columns

\n", "
" ], "text/plain": [ " Name TDP\n", "505 AMD EPYC 4124P 65\n", "506 AMD EPYC 4244P 65\n", "507 AMD EPYC 4344P 65\n", "508 AMD EPYC 4364P 105\n", "509 AMD EPYC 4464P 65\n", ".. ... ...\n", "752 AMD Opteron 6328 115\n", "753 AMD Opteron 6338P 99\n", "754 AMD Opteron 6344 115\n", "757 AMD Opteron 6370P 99\n", "807 AMD Opteron X2170 APU 25\n", "\n", "[113 rows x 2 columns]" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# merged_df.query('Name.str.contains(\"EPYC\")')\n", "new_cpus_to_add = new_cpus.drop(columns=[\"_merge\"]).loc[:, df.columns]\n", "new_cpus_to_add" ] }, { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NameTDP
3928AMD EPYC 4124P65
\n", "
" ], "text/plain": [ " Name TDP\n", "3928 AMD EPYC 4124P 65" ] }, "execution_count": 68, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Option 2: Append the new CPUs to the original df\n", "df = pd.concat([df, new_cpus_to_add], ignore_index=True)\n", "df.sort_values(\"Name\", ascending=True, inplace=True)\n", "df.query('Name.str.contains(\"AMD EPYC 4124P\")')" ] }, { "cell_type": "code", "execution_count": 69, "metadata": {}, "outputs": [], "source": [ "df.to_csv(\"cpu_power.csv\", index=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Remove with..." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "# Load the existing dataset\n", "df = pd.read_csv(\"../cpu_power.csv\")\n", "# Replace with re.sub(r\" with.*\", \"\", name)\n", "def clean_cpu_name(name):\n", " import re\n", " # Remove \"with\" and everything after it\n", " name = re.sub(r\" with.*\", \"\", name)\n", " # Remove \"™\" symbol\n", " name = name.replace(\"™\", \"\")\n", " return name.strip()\n", "df[\"Name\"] = df[\"Name\"].apply(clean_cpu_name)\n", "# Save the cleaned dataset\n", "df.to_csv(\"../cpu_power.csv\", index=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] } ], "metadata": { "kernelspec": { "display_name": "3.10.5", "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": "3.10.5" } }, "nbformat": 4, "nbformat_minor": 4 }