{ "cells": [ { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Using custom data configuration tappyness1--causion-f0c7d8cb97d796fc\n", "Found cached dataset parquet (C:/Users/neoce/.cache/huggingface/datasets/tappyness1___parquet/tappyness1--causion-f0c7d8cb97d796fc/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)\n", "100%|██████████| 1/1 [00:00<00:00, 144.77it/s]\n" ] } ], "source": [ "from datasets import load_dataset\n", "import pandas as pd\n", "import os\n", "import yaml\n", "import sys\n", "sys.path.append(\"..\")\n", "from src.pred_plot import prep_data_pred_plot, data_split\n", "%load_ext autoreload\n", "%autoreload 2\n", "\n", "token_file = open(\"../token_secret.yaml\")\n", "token_obj = yaml.load(token_file, Loader=yaml.FullLoader)\n", "dataset = load_dataset(\"tappyness1/causion\", use_auth_token=token_obj['TOKEN'])\n", "counts_df = pd.DataFrame(dataset['train'])" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | date | \n", "time | \n", "view | \n", "car | \n", "motorcycle | \n", "large_vehicle | \n", "
---|---|---|---|---|---|---|
0 | \n", "2023-02-14 | \n", "22:36:03 | \n", "View_from_Second_Link_at_Tuas | \n", "0 | \n", "0 | \n", "1 | \n", "
1 | \n", "2023-02-14 | \n", "22:36:03 | \n", "View_from_Tuas_Checkpoint | \n", "2 | \n", "0 | \n", "0 | \n", "
2 | \n", "2023-02-14 | \n", "22:36:03 | \n", "View_from_Woodlands_Causeway_Towards_Johor | \n", "2 | \n", "0 | \n", "0 | \n", "
3 | \n", "2023-02-14 | \n", "22:36:03 | \n", "View_from_Woodlands_Checkpoint_Towards_BKE | \n", "3 | \n", "0 | \n", "1 | \n", "
4 | \n", "2023-02-14 | \n", "23:14:34 | \n", "View_from_Second_Link_at_Tuas | \n", "0 | \n", "0 | \n", "6 | \n", "