Using Koalas EntitySets (BETA)

Note

Support for Koalas EntitySets is still in Beta. While the key functionality has been implemented, development is ongoing to add the remaining functionality.

All planned improvements to the Featuretools/Koalas integration are documented on Github. If you see an open issue that is important for your application, please let us know by upvoting or commenting on the issue. If you encounter any errors using Koalas dataframes in EntitySets, or find missing functionality that does not yet have an open issue, please create a new issue on Github.

Creating a feature matrix from a very large dataset can be problematic if the underlying pandas dataframes that make up the EntitySet cannot easily fit in memory. To help get around this issue, Featuretools supports creating EntitySet objects from Koalas dataframes. A Koalas EntitySet can then be passed to featuretools.dfs or featuretools.calculate_feature_matrix to create a feature matrix, which will be returned as a Koalas dataframe. In addition to working on larger than memory datasets, this approach also allows users to take advantage of the parallel and distributed processing capabilities offered by Koalas and Spark.

This guide will provide an overview of how to create a Koalas EntitySet and then generate a feature matrix from it. If you are already familiar with creating a feature matrix starting from pandas dataframes, this process will seem quite familiar, as there are no differences in the process. There are, however, some limitations when using Koalas dataframes, and those limitations are reviewed in more detail below.

Creating EntitySets

Koalas EntitySets require Koalas and PySpark. Both can be installed directly with pip install featuretools[koalas]. Java is also required for PySpark and may need to be installed, see the Spark documentation for more details. We will create a very small Koalas dataframe for this example. Koalas dataframes can also be created from pandas dataframes, Spark dataframes, or read in directly from a file.

[2]:
import featuretools as ft
import databricks.koalas as ks
id = [0, 1, 2, 3, 4]
values = [12, -35, 14, 103, -51]
koalas_df = ks.DataFrame({"id": id, "values": values})
koalas_df

[2]:
id values
0 0 12
1 1 -35
2 2 14
3 3 103
4 4 -51

Now that we have our Koalas dataframe, we can start to create the EntitySet. Inferring Woodwork logical types for the columns in a Koalas dataframe can be computationally expensive. To avoid this expense, logical type inference can be skipped by supplying a dictionary of logical types using the logical_types parameter when calling es.add_dataframe(). Logical types can be specified as Woodwork LogicalType classes, or their equivalent string representation. For more information on using Woodwork types refer to the Woodwork Typing in Featuretools guide.

Aside from supplying the logical types, the rest of the process of creating an EntitySet is the same as if we were using pandas DataFrames.

[3]:
from woodwork.logical_types import Double, Integer

es = ft.EntitySet(id="koalas_es")
es = es.add_dataframe(
    dataframe_name="koalas_input_df",
    dataframe=koalas_df,
    index="id",
    logical_types={"id": Integer, "values": Double})

es
[3]:
Entityset: koalas_es
  DataFrames:
    koalas_input_df [Rows: 5, Columns: 2]
  Relationships:
    No relationships

Running DFS

We can pass the EntitySet we created above to featuretools.dfs in order to create a feature matrix. If the EntitySet we pass to dfs is made of Koalas dataframes, the feature matrix we get back will be a Koalas dataframe.

[4]:
feature_matrix, features = ft.dfs(entityset=es,
                                  target_dataframe_name="koalas_input_df",
                                  trans_primitives=["negate"],
                                  max_depth=1)
feature_matrix
21/11/15 22:38:56 WARN WindowExec: No Partition Defined for Window operation! Moving all data to a single partition, this can cause serious performance degradation.
[4]:
values -(values) id
0 14.0 -14.0 2
1 -51.0 51.0 4
2 12.0 -12.0 0
3 -35.0 35.0 1
4 103.0 -103.0 3

This feature matrix can be saved to disk or converted to a pandas dataframe and brought into memory, using the appropriate Koalas dataframe methods.

While this is a simple example to illustrate the process of using Koalas dataframes with Featuretools, this process will also work with an EntitySet containing multiple dataframes, as well as with aggregation primitives.

Limitations

The key functionality of Featuretools is available for use with a Koalas EntitySet, and work is ongoing to add the remaining functionality that is available when using a pandas EntitySet. There are, however, some limitations to be aware of when creating a Koalas Entityset and then using it to generate a feature matrix. The most significant limitations are reviewed in more detail in this section.

Note

If the limitations of using a Koalas EntitySet are problematic for your problem, you may still be able to compute a larger-than-memory feature matrix by partitioning your data as described in Improving Computational Performance.

Supported Primitives

When creating a feature matrix from a Koalas EntitySet, only certain primitives can be used. Primitives that rely on the order of the entire dataframe or require an entire column for computation are currently not supported when using a Koalas EntitySet. Multivariable and time-dependent aggregation primitives also are not currently supported.

To obtain a list of the primitives that can be used with a Koalas EntitySet, you can call featuretools.list_primitives(). This will return a table of all primitives. Any primitive that can be used with a Koalas EntitySet will have a value of True in the koalas_compatible column.

[5]:
primitives_df = ft.list_primitives()
koalas_compatible_df = primitives_df[primitives_df["koalas_compatible"] == True]
koalas_compatible_df.head()
[5]:
name type dask_compatible koalas_compatible description valid_inputs return_type
1 max aggregation True True Calculates the highest value, ignoring `NaN` v... <ColumnSchema (Semantic Tags = ['numeric'])> None
4 count aggregation True True Determines the total number of values, excludi... <ColumnSchema (Semantic Tags = ['index'])> None
13 num_unique aggregation True True Determines the number of distinct values, igno... <ColumnSchema (Semantic Tags = ['category'])> None
14 min aggregation True True Calculates the smallest value, ignoring `NaN` ... <ColumnSchema (Semantic Tags = ['numeric'])> None
15 std aggregation True True Computes the dispersion relative to the mean v... <ColumnSchema (Semantic Tags = ['numeric'])> None
[6]:
koalas_compatible_df.tail()
[6]:
name type dask_compatible koalas_compatible description valid_inputs return_type
82 add_numeric transform True True Element-wise addition of two lists. <ColumnSchema (Semantic Tags = ['numeric'])> None
83 num_characters transform True True Calculates the number of characters in a string. <ColumnSchema (Logical Type = NaturalLanguage)> None
84 equal_scalar transform True True Determines if values in a list are equal to a ... <ColumnSchema> None
85 and transform True True Element-wise logical AND of two lists. <ColumnSchema (Logical Type = Boolean)>, <Colu... None
86 is_weekend transform True True Determines if a date falls on a weekend. <ColumnSchema (Logical Type = Datetime)> None

Primitive Limitations

At this time, custom primitives created with featuretools.primitives.make_trans_primitive() or featuretools.primitives.make_agg_primitive() cannot be used for running deep feature synthesis on a Koalas EntitySet. While it is possible to create custom primitives for use with a Koalas EntitySet by extending the proper primitive class, there are several potential problems in doing so, and those issues are beyond the scope of this guide.

DataFrame Limitations

Featuretools stores the DataFrames that make up an EntitySet as Woodwork DataFrames, which include additional typing information about the columns that are in the DataFrame. When adding a DataFrame to an EntitySet, Woodwork will attempt to infer the logical types for any columns that do not have a logical type defined. This inference process can be quite expensive for Koalas DataFrames. In order to skip type inference and speed up the process of adding a Koalas DataFrame to an EntitySet, users can specify the logical type to use for each column in the DataFrame. A list of available logical types can be obtained by running featuretools.list_logical_types(). To learn more about the limitations of a Koalas dataframe with Woodwork typing, see the Woodwork guide on Koalas dataframes.

By default, Woodwork checks that pandas dataframes have unique index values. Because performing this same check with Koalas could be computationally expensive, this check is not performed when adding a Koalas dataframe to an EntitySet. When using Koalas dataframes, users must ensure that the supplied index values are unique.

When using a pandas DataFrames, the ordering of the underlying DataFrame rows is maintained by Featuretools. For a Koalas DataFrame, the ordering of the DataFrame rows is not guaranteed, and Featuretools does not attempt to maintain row order in a Koalas DataFrame. If ordering is important, close attention must be paid to any output to avoid issues.

EntitySet Limitations

When creating a Featuretools EntitySet that will be made of Koalas dataframes, all of the dataframes used to create the EntitySet must be of the same type, either all Koalas dataframe, all Dask dataframes, or all pandas dataframes. Featuretools does not support creating an EntitySet containing a mix of Koalas, Dask, and pandas dataframes.

Additionally, EntitySet.add_interesting_values() cannot be used in Koalas EntitySets to find interesting values; however, it can be used set a column’s interesting values with the values parameter.

[7]:
values_dict = {'values': [12, 103]}
es.add_interesting_values(dataframe_name='koalas_input_df', values=values_dict)

es['koalas_input_df'].ww.columns['values'].metadata
[7]:
{'dataframe_name': 'koalas_input_df',
 'entityset_id': 'koalas_es',
 'interesting_values': [12, 103]}

DFS Limitations

There are a few key limitations when generating a feature matrix from a Koalas EntitySet.

If a cutoff_time parameter is passed to featuretools.dfs() it should be a single cutoff time value, or a pandas dataframe. The current implementation will still work if a Koalas dataframe is supplied for cutoff times, but a .to_pandas() call will be made on the dataframe to convert it into a pandas dataframe. This conversion will result in a warning, and the process could take a considerable amount of time to complete depending on the size of the supplied dataframe.

Additionally, Featuretools does not currently support the use of the approximate or training_window parameters when working with Koalas EntitySets, but should in future releases.

Finally, if the output feature matrix contains a boolean column with NaN values included, the column type may have a different datatype than the same feature matrix generated from a pandas EntitySet. If feature matrix column data types are critical, the feature matrix should be inspected to make sure the types are of the proper types, and recast as necessary.

Other Limitations

Currently featuretools.encode_features() does not work with a Koalas dataframe as input. This will hopefully be resolved in a future release of Featuretools.

The utility function featuretools.make_temporal_cutoffs() will not work properly with Koalas inputs for instance_ids or cutoffs. However, as noted above, if a cutoff_time dataframe is supplied to dfs, the supplied dataframe should be a pandas dataframe, and this can be generated by supplying pandas inputs to make_temporal_cutoffs().

The use of featuretools.remove_low_information_features() cannot currently be used with a Koalas feature matrix.

When manually defining a Feature, the use_previous parameter cannot be used if this feature will be applied to calculate a feature matrix from a Koalas EntitySet.