teras.utils module

clean_reloaded_config_data(x)	Cleans reloaded dictionary/list config data in the from_config method.
compute_cardinalities(x, categorical_idx[, ...])	Compute cardinalities for features in the given dataset/dataframe.
convert_tf_dict_to_array_tensor(dict_tensor)	Converts a batch of data taken from tensorflow dictionary format dataset to array format.
inject_missing_values(x[, miss_rate])	Injects missing (np.nan) values in the given dataframe or ndarray.
generate_fake_gemstone_data([num_samples])	Generate fake gemstone like data of specified num_samples.
get_metadata_for_embedding(dataframe[, ...])	Utility function that create metadata for features in a given dataframe required by the Categorical and Numerical embedding layers in Teras.