From bb2a708ec35d17b977549a541aebab5c91f14512 Mon Sep 17 00:00:00 2001 From: zin Date: Wed, 6 May 2026 17:42:02 +0000 Subject: [PATCH] Download DEAM --- src/download_DEAM.ipynb | 140 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 140 insertions(+) create mode 100644 src/download_DEAM.ipynb diff --git a/src/download_DEAM.ipynb b/src/download_DEAM.ipynb new file mode 100644 index 0000000..cc08585 --- /dev/null +++ b/src/download_DEAM.ipynb @@ -0,0 +1,140 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Загрузка датасета DEAM\n", + "\n", + "Этот ноутбук предназначен для автоматизации процесса скачивания и подготовки музыкального датасета **DEAM** (Database for Emotional Analysis in Music).\n", + "Данные будут помещены в папку `dataset/DEAM`." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting kagglehub\n", + " Downloading kagglehub-1.0.1-py3-none-any.whl.metadata (40 kB)\n", + "Collecting kagglesdk<1.0,>=0.1.22 (from kagglehub)\n", + " Downloading kagglesdk-0.1.23-py3-none-any.whl.metadata (13 kB)\n", + "Requirement already satisfied: packaging in /home/zin/projects/Thesis/.venv/lib/python3.11/site-packages (from kagglehub) (25.0)\n", + "Requirement already satisfied: pyyaml in /home/zin/projects/Thesis/.venv/lib/python3.11/site-packages (from kagglehub) (6.0.3)\n", + "Requirement already satisfied: requests in /home/zin/projects/Thesis/.venv/lib/python3.11/site-packages (from kagglehub) (2.32.5)\n", + "Requirement already satisfied: tqdm in /home/zin/projects/Thesis/.venv/lib/python3.11/site-packages (from kagglehub) (4.67.1)\n", + "Requirement already satisfied: protobuf in /home/zin/projects/Thesis/.venv/lib/python3.11/site-packages (from kagglesdk<1.0,>=0.1.22->kagglehub) (6.33.4)\n", + "Requirement already satisfied: charset_normalizer<4,>=2 in /home/zin/projects/Thesis/.venv/lib/python3.11/site-packages (from requests->kagglehub) (3.4.4)\n", + "Requirement already satisfied: idna<4,>=2.5 in /home/zin/projects/Thesis/.venv/lib/python3.11/site-packages (from requests->kagglehub) (3.11)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /home/zin/projects/Thesis/.venv/lib/python3.11/site-packages (from requests->kagglehub) (2.6.3)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /home/zin/projects/Thesis/.venv/lib/python3.11/site-packages (from requests->kagglehub) (2026.1.4)\n", + "Downloading kagglehub-1.0.1-py3-none-any.whl (70 kB)\n", + "Downloading kagglesdk-0.1.23-py3-none-any.whl (217 kB)\n", + "Installing collected packages: kagglesdk, kagglehub\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2/2\u001b[0m [kagglehub]\n", + "\u001b[1A\u001b[2KSuccessfully installed kagglehub-1.0.1 kagglesdk-0.1.23\n", + "\n", + "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m25.3\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m26.1.1\u001b[0m\n", + "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n" + ] + } + ], + "source": [ + "!pip install kagglehub" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Скачиваем датасет DEAM...\n", + "Downloading to /home/zin/.cache/kagglehub/datasets/imsparsh/deam-mediaeval-dataset-emotional-analysis-in-music/1.archive...\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1.83G/1.83G [01:09<00:00, 28.2MB/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Extracting files...\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Датасет скачан во временную директорию: /home/zin/.cache/kagglehub/datasets/imsparsh/deam-mediaeval-dataset-emotional-analysis-in-music/versions/1\n", + "Переносим файлы в ../dataset/DEAM...\n", + "\n", + "[УСПЕХ] Датасет DEAM готов к работе!\n" + ] + } + ], + "source": [ + "import os\n", + "import shutil\n", + "import kagglehub\n", + "from pathlib import Path\n", + "\n", + "# 1. Настройка путей\n", + "DATASET_ROOT = Path(\"../dataset\")\n", + "DEAM_ROOT = DATASET_ROOT / \"DEAM\"\n", + "DEAM_ROOT.mkdir(parents=True, exist_ok=True)\n", + "\n", + "# 2. Загрузка через kagglehub\n", + "print(\"Скачиваем датасет DEAM...\")\n", + "kaggle_cache_path = kagglehub.dataset_download(\"imsparsh/deam-mediaeval-dataset-emotional-analysis-in-music\")\n", + "print(f\"Датасет скачан во временную директорию: {kaggle_cache_path}\")\n", + "\n", + "# 3. Перемещение файлов в проект\n", + "print(f\"Переносим файлы в {DEAM_ROOT}...\")\n", + "shutil.copytree(kaggle_cache_path, DEAM_ROOT, dirs_exist_ok=True)\n", + "\n", + "print(\"\\n[УСПЕХ] Датасет DEAM готов к работе!\")\n" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python (my-python-project)", + "language": "python", + "name": "my-python-project" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.7" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}