Pacman1984

[FEATURE] Categorical Feature Embedding via MLP

1

Using an Embeddinglayer of a deep neural network to encode categorical variables is a common practice also known as "[entity embedding](https://arxiv.org/abs/1604.06737)". One problem is, that you have to install a...

[FEATURE] Categorical Variable Concatenation

6

## Expected Behavior Concatenating categorical variables is a powerful feature engineering technique, often used in competitions. You could watch the 9 minuts of this video for understanding the topic (i...

[FEATURE] Categorical Variable Concatenation

1

## Expected Behavior Also posted in [scikit-lego issue](https://github.com/koaning/scikit-lego/issues/502), but maybe its better implemented here. Concatenating categorical variables is a powerful feature engineering technique, often used in competitions. You could watch...

``` Error: InvalidArgumentError: 2 root error(s) found. (0) Invalid argument: indices[0,0] = 3 is not in [0, 3) [[node functional_1/embedding_4/embedding_lookup (defined at *\lib\site-packages\categorical_embedder\__init__.py:175) ]] (1) Invalid argument: indices[0,0] = 3...