from fastai.vision import *
from fastai.widgets import ClassConfusion

path = untar_data(URLs.PETS)
path_img = path/'images'
fnames = get_image_files(path_img)
pat = r'/([^/]+)_\d+.jpg$'

data = ImageDataBunch.from_name_re(path_img, fnames, pat, ds_tfms=get_transforms(), 
                                   size=224, bs=64).normalize(imagenet_stats)

learn = cnn_learner(data, models.resnet34, metrics=error_rate)

learn.fit_one_cycle(2)

interp = ClassificationInterpretation.from_learner(learn)

classlist = ['Ragdoll', 'Birman', 'Maine_Coon']
ClassConfusion(interp, classlist, is_ordered=False, figsize=(8,8))

classlist = [('Ragdoll', 'Birman'), ('British_Shorthair', 'Russian_Blue')]
ClassConfusion(interp, classlist, is_ordered=True)

from fastai.tabular import *

path = untar_data(URLs.ADULT_SAMPLE)
df = pd.read_csv(path/'adult.csv')

dep_var = 'salary'
cat_names = ['workclass', 'education', 'marital-status', 'occupation', 'relationship', 'race']
cont_names = ['age', 'fnlwgt', 'education-num']
procs = [FillMissing, Categorify, Normalize]

test = TabularList.from_df(df.iloc[800:1000].copy(), path=path, cat_names=cat_names, cont_names=cont_names)

data = (TabularList.from_df(df, path=path, cat_names=cat_names, cont_names=cont_names, procs=procs)
                           .split_by_idx(list(range(800,1000)))
                           .label_from_df(cols=dep_var)
                           .add_test(test)
                           .databunch())

learn = tabular_learner(data, layers=[200,100], metrics=accuracy)

learn.fit(1, 1e-2)

interp = ClassificationInterpretation.from_learner(learn)

interp.plot_confusion_matrix()

ClassConfusion(interp, ['>=50k', '<50k'], figsize=(12,12))

ClassConfusion(interp, ['>=50k', '<50k'], figsize=(12,12))

ClassConfusion(interp, ['>=50k', '<50k'], varlist=['age', 'education', 'relationship'],
               figsize=(12,12))

ClassConfusion(interp, [['>=50k', '>=50k'], ['>=50k', '<50k']], varlist=['age', 'education', 'relationship'],
               is_ordered=True, figsize=(12,12))