mlots package

Subpackages

• mlots.models package
  • Module contents
• mlots.transformation package
  • Module contents

mlots.utilities module

mlots.utilities.from_pandas_dataframe(d_frame=None, target=None, test_size=None, shuffle=False, random_seed=1992)

NAME: from_pandas_dataframe

This is a utility provided in mlots package. The function helps representing a pandas dataframe into numpy arrays.

Parameters

• d_frame (pandas.DataFrame (default None)) – The pandas DataFrame that needs to be transformed.

• target (str or int (default None)) – The column name of the target (y) variable.

• test_size (float or int (default None)) – The value is the percentage of the data to be split for the test set.

• shuffle (bool (default False)) – If True, the data is shuffled randomly.

• random_seed (int (default 1992)) – The initial seed to be used by random function.

Returns

X_train, X_test, y_train, y_test (ndarray, ndarray, ndarray, ndarray) –

If target is None:

only X is returned.

If test_size is None:

no train and test split is performed.

Examples

>>> from mlots.utilities import from_pandas_dataframe
>>> X_train, X_test, y_train, y_test = from_pandas_dataframe(d_frame, target="labels", test_size=0.33, shuffle=True)