grimlock 0.0.1

Simple tool that assists with preprocessing pandas dataframes for Machine Learning.

Grimlock

We all know that when it comes to machine learning, it takes far more time to preprocess your data than it does to actually build a model. Enter, grimlock.

grimlock will fix your missing values, handle data encoding, and feature scaling.

Installation

Provided you already have NumPy, SciPy, Sci-kit Learn and Pandas already installed, the grimlock package is pip-installable:

$ pip install grimlock

Cleaning Missing Data

Mesh of pandas.fillna() and sklearn Imputer

from grimlock import clean_missing
clean_missing(dataframe, column, clean_type='zero')

Parameters

• dataframe: dataframe variable
• column: column name (string)
• clean_type: 'zero' (default), 'mean', 'mode', 'most_frequent' (string)

Convert Categorical

Quick conversion for categorical features (non-ordinal)

from grimlock import convert_categorical
convert_categorical(dataframe, column, target_column)

Parameters

• dataframe: dataframe variable
• column: column name (string)
• target_column: target column name (string)

Feature Scaling

coming soon