Skip to main content

Competition-oriented framework for interactive feature engineering and building pipelines

Project description

# Kaggle Tool Set

kts is a working title, highly likely it will be changed to avoid legal consequences.

## Getting started

To install the package, just clone the repo to a directory included in `PYTHONPATH`.

## What works by now

- Base of feature engineering submodule

## How it works

First of all, you need to import the module:

``` python
import kts
from kts import *
```

Then you should define a function to make new features based on your input dataframe:

``` python
def make_new_features(df):
...
```

To test it out, use `@test` decorator from `kts` or `kts.feature`:

``` python
@test
def make_new_features(df):
...
```

When you're sure that your function works fine, `@register` it:

``` python
@register
def make_new_features(df):
...
```

Since registering source of the function is stored in `storage/features` and calls are cached unless `no_cache=True` is used.

The function will also be contained in `kts.storage.feature_constructors`. If you want to separate feature engineering from other steps of your pipeline, you can easily define all registered functions in a new notebook via
``` python
kts.storage.feature_constructors.define_in_scope(globals())
```

To learn more, read source and example notebook.


Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kts-0.0.29.tar.gz (16.9 kB view hashes)

Uploaded Source

Built Distribution

kts-0.0.29-py3-none-any.whl (26.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page