Итак, я следую учебному пособию по классификации классов по нескольким классам и пытаюсь найти способ прогнозирования тегов рецептов в контролируемом методе с помощью файла JSON с рецептами в этом формате:
{
"title": "Turtle Cheesecake",
"summary": "Cheesecake is a staple at the Market, but it’s different nearly every day because we vary the toppings, crusts, and flavorings. Cookie crusts are particularly good with cheesecakes. If you prefer your cheesecake plain, just serve it without the topping",
"ingr": [
"1½ cups graham cracker crumbs",
"½ cup finely chopped pecans (pulse in a food processor several times)",
"6 tablespoons ( ¾ stick) unsalted butter, melted",
"1½ pounds cream cheese, softened",
"¾ cup sugar",
"2 tablespoons all purpose flour",
"3 large eggs",
"1large egg yolk",
"½ cup heavy cream",
"2 teaspoons pure vanilla extract",
"1 cup sugar",
"1 cup heavy cream",
"½ teaspoon pure vanilla extract",
"½ cup coarsely chopped pecans, toasted",
"2 ounces semisweet chocolate, melted"
],
"prep": "To Make the Crust:\n\n\n\n Grease a 9-inch springform pan. Wrap the outside of the pan, including the bottom, with a large square of aluminum foil. Set aside.\n\n\n\..."
"tag": [
"Moderate",
"Casual Dinner Party",
"Family Get-together",
"Formal Dinner Party",
"dessert",
"dinner",
"cake",
"cheesecake",
"dessert"
}
Это код, который я запускаю, потому что ошибка TypeError:
import pandas as pd
df = pd.read_json('tagged-sample.json')
######################### Data Exploration #######################
from io import StringIO
col = ['tag', 'summary']
df = df[col]
df = df[pd.notnull(df['summary'])]
df.columns = ['tag', 'summary']
df['category_id'] = df['tag'].factorize()[0]
Что я могу сделать, чтобы иметь возможность использовать pandas.factorize в категории 'tag' в
JSON. Учебник делает это в CSV-файле, который может иметь значение.
Это ошибка:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-9-d471748e6818> in <module>()
12 df.columns = ['tag', 'summary']
13
---> 14 df['category_id'] = df['tag'].factorize()[0]
15
16 #[['tag', 'category_id']].sort_values('category_id')
~\Anaconda3\lib\site-packages\pandas\core\base.py in factorize(self, sort, na_sentinel)
1155 @Appender(algorithms._shared_docs['factorize'])
1156 def factorize(self, sort=False, na_sentinel=-1):
-> 1157 return algorithms.factorize(self, sort=sort, na_sentinel=na_sentinel)
1158
1159 _shared_docs['searchsorted'] = (
~\Anaconda3\lib\site-packages\pandas\util\_decorators.py in wrapper(*args, **kwargs)
175 else:
176 kwargs[new_arg_name] = new_arg_value
--> 177 return func(*args, **kwargs)
178 return wrapper
179 return _deprecate_kwarg
~\Anaconda3\lib\site-packages\pandas\core\algorithms.py in factorize(values, sort, order, na_sentinel, size_hint)
628 na_sentinel=na_sentinel,
629 size_hint=size_hint,
--> 630 na_value=na_value)
631
632 if sort and len(uniques) > 0:
~\Anaconda3\lib\site-packages\pandas\core\algorithms.py in _factorize_array(values, na_sentinel, size_hint, na_value)
474 uniques = vec_klass()
475 labels = table.get_labels(values, uniques, 0, na_sentinel,
--> 476 na_value=na_value)
477
478 labels = _ensure_platform_int(labels)
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_labels()
TypeError: unhashable type: 'list'