Module connectome.models.lgb

wrapper for gradient boosting classification and regression models

Classes

class GB (features: Union[numpy.ndarray, pandas.core.frame.DataFrame], target: numpy.ndarray, feature_names: list = None, classification: bool = True, fit_directly: bool = True, dart: bool = False, **kwargs)

wrapper/class for gradient boosting models

Examples:

>>> from connectome.models.lgb import GB
>>> import pandas as pd
>>> import numpy as np
>>>
>>> # create synthetic data
>>> X, y = make_classification(n_informative=15)
>>> X = pd.DataFrame(
>>>     X,
>>>     columns=["feature_" + str(i)
>>>              for i in range(X.shape[1])])
>>> X_regr, y_regr = make_regression(n_features=20, n_informative=15)
>>> X_regr = pd.DataFrame(
>>>     X_regr,
>>>     columns=["feature_" + str(i)
>>>              for i in range(X_regr.shape[1])])
>>>
>>> # initialize some models
>>> gb_class = GB(X, y, classification=True)
>>> gb_regr = GB(X_regr, y_regr, classification=False)
>>>
>>> # get_fis
>>> print(gb_class.get_feature_importances())
>>> print(gb_regr.get_feature_importances())

Methods

def fit(self, **kwargs)

def get_feature_importances(self)

method to get the ordered feature importances in the form of a DataFrame Returns:

def predict(self, inputs: Union[numpy.ndarray, pandas.core.frame.DataFrame]) ‑> numpy.ndarray

def predict_proba(self, inputs) ‑> numpy.ndarray

def save_model(self, name: str = 'lgb')