You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/docs/extras/integrations/document_loaders/tsv.ipynb

182 lines
4.8 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# TSV\n",
"\n",
">A [tab-separated values (TSV)](https://en.wikipedia.org/wiki/Tab-separated_values) file is a simple, text-based file format for storing tabular data.[3] Records are separated by newlines, and values within a record are separated by tab characters."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `UnstructuredTSVLoader`\n",
"\n",
"You can also load the table using the `UnstructuredTSVLoader`. One advantage of using `UnstructuredTSVLoader` is that if you use it in `\"elements\"` mode, an HTML representation of the table will be available in the metadata."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders.tsv import UnstructuredTSVLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"loader = UnstructuredTSVLoader(\n",
" file_path=\"example_data/mlb_teams_2012.csv\", mode=\"elements\"\n",
")\n",
"docs = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<table border=\"1\" class=\"dataframe\">\n",
" <tbody>\n",
" <tr>\n",
" <td>Nationals, 81.34, 98</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Reds, 82.20, 97</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Yankees, 197.96, 95</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Giants, 117.62, 94</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Braves, 83.31, 94</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Athletics, 55.37, 94</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Rangers, 120.51, 93</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Orioles, 81.43, 93</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Rays, 64.17, 90</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Angels, 154.49, 89</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Tigers, 132.30, 88</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Cardinals, 110.30, 88</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Dodgers, 95.14, 86</td>\n",
" </tr>\n",
" <tr>\n",
" <td>White Sox, 96.92, 85</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Brewers, 97.65, 83</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Phillies, 174.54, 81</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Diamondbacks, 74.28, 81</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Pirates, 63.43, 79</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Padres, 55.24, 76</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Mariners, 81.97, 75</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Mets, 93.35, 74</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Blue Jays, 75.48, 73</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Royals, 60.91, 72</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Marlins, 118.07, 69</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Red Sox, 173.18, 69</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Indians, 78.43, 68</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Twins, 94.08, 66</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Rockies, 78.06, 64</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Cubs, 88.19, 61</td>\n",
" </tr>\n",
" <tr>\n",
" <td>Astros, 60.65, 55</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n"
]
}
],
"source": [
"print(docs[0].metadata[\"text_as_html\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": "3.8.13"
}
},
"nbformat": 4,
"nbformat_minor": 4
}