{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "36cb4bfb-c6e0-4924-a91d-57dfccd63801", "metadata": {}, "outputs": [], "source": [ "#获得lucaone的中心法则相关数据" ] }, { "cell_type": "code", "execution_count": 2, "id": "01c3e3cc-7f70-4f9f-89f4-ed236845e64e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "--2025-02-15 11:56:31-- http://47.93.21.181/lucaone/DownstreamTasksDataset/dataset/CentralDogma/gene_protein/binary_class/train/train.csv\n", "Connecting to 47.93.21.181:80... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 5302028 (5.1M) [application/octet-stream]\n", "Saving to: ‘train.csv’\n", "\n", "train.csv 100%[===================>] 5.06M 12.7MB/s in 0.4s \n", "\n", "2025-02-15 11:56:31 (12.7 MB/s) - ‘train.csv’ saved [5302028/5302028]\n", "\n", "--2025-02-15 11:56:31-- http://47.93.21.181/lucaone/DownstreamTasksDataset/dataset/CentralDogma/gene_protein/binary_class/test/test.csv\n", "Connecting to 47.93.21.181:80... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 33131633 (32M) [application/octet-stream]\n", "Saving to: ‘test.csv’\n", "\n", "test.csv 100%[===================>] 31.60M 9.59MB/s in 3.3s \n", "\n", "2025-02-15 11:56:35 (9.59 MB/s) - ‘test.csv’ saved [33131633/33131633]\n", "\n", "--2025-02-15 11:56:35-- http://47.93.21.181/lucaone/DownstreamTasksDataset/dataset/CentralDogma/gene_protein/binary_class/dev/dev.csv\n", "Connecting to 47.93.21.181:80... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 3982657 (3.8M) [application/octet-stream]\n", "Saving to: ‘dev.csv’\n", "\n", "dev.csv 100%[===================>] 3.80M 8.46MB/s in 0.4s \n", "\n", "2025-02-15 11:56:35 (8.46 MB/s) - ‘dev.csv’ saved [3982657/3982657]\n", "\n" ] } ], "source": [ "!wget http://47.93.21.181/lucaone/DownstreamTasksDataset/dataset/CentralDogma/gene_protein/binary_class/train/train.csv\n", "!wget http://47.93.21.181/lucaone/DownstreamTasksDataset/dataset/CentralDogma/gene_protein/binary_class/test/test.csv\n", "!wget http://47.93.21.181/lucaone/DownstreamTasksDataset/dataset/CentralDogma/gene_protein/binary_class/dev/dev.csv" ] }, { "cell_type": "code", "execution_count": 3, "id": "23d39250-50a6-4557-9cb9-2d637ce52835", "metadata": {}, "outputs": [], "source": [ "#合并文件\n", "# 先复制第一个文件的内容(包括表头)\n", "!cp train.csv central_dogma.csv\n", "\n", "# 然后将后续文件的内容(跳过表头)追加到combined.csv中\n", "!tail -n +2 test.csv >> central_dogma.csv\n", "!tail -n +2 dev.csv >> central_dogma.csv" ] }, { "cell_type": "code", "execution_count": null, "id": "d54081eb-d30c-4b3f-8a6d-0d1b53c37fd7", "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": "3.11.9" } }, "nbformat": 4, "nbformat_minor": 5 }