wehub/fastai--fastai
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity
Files
main
fastai--fastai/dev_nbs/course/lesson4-tabular.ipynb
T
wehub-resource-sync 844360907f chore: import upstream snapshot with attribution
2026-07-13 13:21:43 +08:00

392 lines
10 KiB
Plaintext
Raw Permalink Blame History

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Tabular models"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from fastai.tabular.all import *"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Tabular data should be in a Pandas `DataFrame`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"path = untar_data(URLs.ADULT_SAMPLE)\n",
"df = pd.read_csv(path/'adult.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dep_var = 'salary'\n",
"cat_names = ['workclass', 'education', 'marital-status', 'occupation', 'relationship', 'race']\n",
"cont_names = ['age', 'fnlwgt', 'education-num']\n",
"procs = [Categorify, FillMissing, Normalize]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#test = TabularList.from_df(df.iloc[800:1000].copy(), path=path, cat_names=cat_names, cont_names=cont_names)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"splits = IndexSplitter(list(range(800,1000)))(range_of(df))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#splits = (L(splits[0], use_list=True), L(splits[1], use_list=True))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"to = TabularPandas(df, procs, cat_names, cont_names, y_names=\"salary\", splits=splits)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dls = to.dataloaders(bs=64)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>workclass</th>\n",
" <th>education</th>\n",
" <th>marital-status</th>\n",
" <th>occupation</th>\n",
" <th>relationship</th>\n",
" <th>race</th>\n",
" <th>age_na</th>\n",
" <th>fnlwgt_na</th>\n",
" <th>education-num_na</th>\n",
" <th>age</th>\n",
" <th>fnlwgt</th>\n",
" <th>education-num</th>\n",
" <th>salary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Private</td>\n",
" <td>Bachelors</td>\n",
" <td>Never-married</td>\n",
" <td>Machine-op-inspct</td>\n",
" <td>Not-in-family</td>\n",
" <td>Asian-Pac-Islander</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>27.0</td>\n",
" <td>104457.001298</td>\n",
" <td>13.0</td>\n",
" <td>&lt;50k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Self-emp-not-inc</td>\n",
" <td>HS-grad</td>\n",
" <td>Never-married</td>\n",
" <td>Farming-fishing</td>\n",
" <td>Own-child</td>\n",
" <td>White</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>20.0</td>\n",
" <td>306709.997905</td>\n",
" <td>9.0</td>\n",
" <td>&lt;50k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Private</td>\n",
" <td>Bachelors</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Prof-specialty</td>\n",
" <td>Husband</td>\n",
" <td>White</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>40.0</td>\n",
" <td>209547.000700</td>\n",
" <td>13.0</td>\n",
" <td>&gt;=50k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Private</td>\n",
" <td>Bachelors</td>\n",
" <td>Never-married</td>\n",
" <td>Prof-specialty</td>\n",
" <td>Not-in-family</td>\n",
" <td>White</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>26.0</td>\n",
" <td>184120.000065</td>\n",
" <td>13.0</td>\n",
" <td>&lt;50k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Private</td>\n",
" <td>HS-grad</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Adm-clerical</td>\n",
" <td>Husband</td>\n",
" <td>White</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>38.0</td>\n",
" <td>248886.000709</td>\n",
" <td>9.0</td>\n",
" <td>&lt;50k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Private</td>\n",
" <td>HS-grad</td>\n",
" <td>Never-married</td>\n",
" <td>Machine-op-inspct</td>\n",
" <td>Not-in-family</td>\n",
" <td>Asian-Pac-Islander</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>28.0</td>\n",
" <td>149769.001037</td>\n",
" <td>9.0</td>\n",
" <td>&lt;50k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Private</td>\n",
" <td>Bachelors</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Exec-managerial</td>\n",
" <td>Wife</td>\n",
" <td>White</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>40.0</td>\n",
" <td>225659.999761</td>\n",
" <td>13.0</td>\n",
" <td>&gt;=50k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Private</td>\n",
" <td>Some-college</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Craft-repair</td>\n",
" <td>Husband</td>\n",
" <td>Asian-Pac-Islander</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>27.0</td>\n",
" <td>100668.997583</td>\n",
" <td>10.0</td>\n",
" <td>&gt;=50k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Private</td>\n",
" <td>Masters</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Exec-managerial</td>\n",
" <td>Husband</td>\n",
" <td>White</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>46.0</td>\n",
" <td>55720.003421</td>\n",
" <td>14.0</td>\n",
" <td>&gt;=50k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>?</td>\n",
" <td>Assoc-acdm</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>?</td>\n",
" <td>Wife</td>\n",
" <td>White</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>35.0</td>\n",
" <td>144172.001567</td>\n",
" <td>12.0</td>\n",
" <td>&lt;50k</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"dls.show_batch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"learn = tabular_learner(dls, layers=[200,100], metrics=accuracy)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: left;\">\n",
" <th>epoch</th>\n",
" <th>train_loss</th>\n",
" <th>valid_loss</th>\n",
" <th>accuracy</th>\n",
" <th>time</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>0</td>\n",
" <td>0.372055</td>\n",
" <td>0.369126</td>\n",
" <td>0.840000</td>\n",
" <td>00:10</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"learn.fit(1, 1e-2)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Inference -> To do"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"row = df.iloc[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"learn.predict(row)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"jupytext": {
"split_at_heading": true
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue View Git Blame Copy Permalink