skql 0.0.2

Usage

Install the package

pip install skql

Import skql package

import skql

Initialize the ‘DecisionTreeClassifierConverter’ instance with a valid scikit-learn DecisionTreeClassifier model object.

dtConverter = skql.DecisionTreeClassifierConverter( clf )

Classes of the tree are: [‘“Setosa”’ ‘“Versicolor”’ ‘“Virginica”’] Choose class index accordingly if probability values are required. :)

A message is displayed after initialization, as shown above. The message shows the classes, the model wa tarined with in a particular order. If a SQL query is to be generated that outputs the probability value for a particular class, the index of the class for which probability values are needed is slected from this list. starting from 0. For example of the SQL query to be generated need propabilty output for class “Versicolor”, the index to be entered is 1.

Get the list of columns that were used to train the data-set (without the target valriable)

used_columns = iris.drop([‘variety’], axis=1).columns

[‘sepal_length’, ‘sepal_width’, ‘petal_length’, ‘petal_width’]

If a SQL query is to be generated that classifies the dataset into respective classes.

sql = dtConverter.fit( cols = used_columns )

print(sql)

If a SQL query needs to be generated that gives probability values for class “Setosa”, given that that class order is [‘“Setosa”’ ‘“Versicolor”’ ‘“Virginica”’] as shown when initialsing the DecisionTreeClassifierConverter instance.

sql = dtConverter.fit( cols = used_columns, vbh_classes = False, class_index = 0 )

print(sql)

Credits

Created and manageed by: Aditya Kumar adityakumar3008@gmail.com https://www.linkedin.com/in/nullp0inter/

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.