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

show_doc(TabularDataBunch, doc_string=False)

path = untar_data(URLs.ADULT_SAMPLE)
df = pd.read_csv(path/'adult.csv')
valid_idx = range(len(df)-2000, len(df))
df.head()

cat_names = ['workclass', 'education', 'marital-status', 'occupation', 'relationship', 'race', 'sex', 'native-country']
dep_var = '>=50k'

show_doc(TabularDataBunch.from_df, doc_string=False)

procs = [FillMissing, Categorify, Normalize]
data = TabularDataBunch.from_df(path, df, dep_var, valid_idx=valid_idx, procs=procs, cat_names=cat_names)

show_doc(tabular_learner)

show_doc(TabularList)

show_doc(TabularList.from_df)

show_doc(TabularList.get_emb_szs)

show_doc(TabularLine, doc_string=False)

show_doc(TabularLine.show_batch)

show_doc(TabularProcessor)

show_doc(TabularProcessor.process_one)

show_doc(TabularList.new)

show_doc(TabularList.get)

show_doc(TabularProcessor.process)