from fastai.gen_doc.nbdoc import *
from fastai.tabular.models import *

from fastai.tabular import * 

path = untar_data(URLs.ADULT_SAMPLE)
path

df = pd.read_csv(path/'adult.csv')
df.head()

procs = [FillMissing, Categorify, Normalize]

valid_idx = range(len(df)-2000, len(df))

dep_var = 'salary'
cat_names = ['workclass', 'education', 'marital-status', 'occupation', 'relationship', 'race', 'sex', 'native-country']

data = TabularDataBunch.from_df(path, df, dep_var, valid_idx=valid_idx, procs=procs, cat_names=cat_names)
print(data.train_ds.cont_names)  # `cont_names` defaults to: set(df)-set(cat_names)-{dep_var}

(cat_x,cont_x),y = next(iter(data.train_dl))
for o in (cat_x, cont_x, y): print(to_np(o[:5]))

learn = tabular_learner(data, layers=[200,100], emb_szs={'native-country': 10}, metrics=accuracy)
learn.fit_one_cycle(1, 1e-2)

learn.predict(df.iloc[0])