(In this case, classes are 0, 1, 2 and so on until 9) inputs. We use the sparse variant of the categorical cross entropy loss function so that we can use the index of the correct class for each example sparse_categorical_accuracy: 0.9500 - val_loss: 0.0753 - val_sparse_categorical_accuracy: 0.9789 Epoch 2/15 469/469 [==============================] - 2s 5ms/step - loss: 0.0570 - sparse_categorical_accuracy: val_sparse_categorical_accuracy: 0.9855 Epoch 3/15 469/469 [==============================] - 2s 5ms/step - loss: 0.0412 - sparse_categorical_accuracy: 0.9873 - val_loss: 0.0486 - val_sparse_categorical_accuracy:

denote missing values for more. 1.5.8 By default Categorical.min() now returns the minimum instead of np.nan When Categorical contains np.nan, Categorical.min() no longer return np.nan by default (skipna=True) (skipna=True) (GH25303) pandas 0.25.x In [1]: pd.Categorical([1, 2, np.nan], ordered=True).min() Out[1]: nan pandas 1.0.0 In [47]: pd.Categorical([1, 2, np.nan], ordered=True).min() Out[47]: 1 1.5.9 Default (GH4205) • Categorical.take_nd() and CategoricalIndex.take_nd() are deprecated, use Categorical.take() and CategoricalIndex.take() instead (GH27745) • The parameter numeric_only of Categorical.min() and

Experimental NA scalar to denote missing values . . . . . . . . . . . . . . . . . . . . . . . 547 2.11 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1869 3.5.8 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1874 3 that can store data of different types (including characters, integers, floating point values, categorical data and more) in columns. It is similar to a spreadsheet, a SQL table or the data. frame in R

Experimental NA scalar to denote missing values . . . . . . . . . . . . . . . . . . . . . . . 547 2.11 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1869 3.5.8 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1874 3 that can store data of different types (including characters, integers, floating point values, categorical data and more) in columns. It is similar to a spreadsheet, a SQL table or the data. frame in R

observed parameter which is passed to underlying calls to DataFrame.groupby() to speed up grouping categorical data. (GH24923) • Series.str has gained Series.str.casefold() method to removes all case distinctions powerful Python data analysis toolkit, Release 0.25.1 1.2.6 Categorical dtypes are preserved during groupby Previously, columns that were categorical, but not the groupby key(s) would be converted to object during groupby operations. Pandas now will preserve these dtypes. (GH18502) In [29]: cat = pd.Categorical(["foo", "bar", "bar", "qux"], ordered=True) In [30]: df = pd.DataFrame({'payload': [-1, -2, -1

Numeric . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.1.5.8 Categorical . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.1.5.9 String 7 GroupBy objects now have a pipe method . . . . . . . . . . . . . . . . . . . . . 12 1.2.1.8 Categorical.rename_categories accepts a dict-like . . . . . . . . . . . . 13 1.2.1.9 Other Enhancements . Numeric . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 1.2.7.9 Categorical . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 1.2.7.10 PyPy

observed parameter which is passed to underlying calls to DataFrame.groupby() to speed up grouping categorical data. (GH24923) • Series.str has gained Series.str.casefold() method to removes all case distinctions powerful Python data analysis toolkit, Release 0.25.0 1.2.6 Categorical dtypes are preserved during groupby Previously, columns that were categorical, but not the groupby key(s) would be converted to object during groupby operations. Pandas now will preserve these dtypes. (GH18502) In [29]: cat = pd.Categorical(["foo", "bar", "bar", "qux"], ordered=True) In [30]: df = pd.DataFrame({'payload': [-1, -2, -1

Disallowing Duplicate Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 631 2.12 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2056 3.5.8 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2061 3 that can store data of different types (including characters, integers, floating point values, categorical data and more) in columns. It is similar to a spreadsheet, a SQL table or the data. frame in R

Disallowing Duplicate Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 632 2.12 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2056 3.5.8 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2061 3 that can store data of different types (including characters, integers, floating point values, categorical data and more) in columns. It is similar to a spreadsheet, a SQL table or the data. frame in R

Disallowing Duplicate Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 603 2.12 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1990 3.5.8 Categorical data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1995 3 that can store data of different types (including characters, integers, floating point values, categorical data and more) in columns. It is similar to a spreadsheet, a SQL table or the data. frame in R