Bagging Classifier with Under Sampling
Project description
# USBaggingClassifier # Overview Bagging Classifier with Under Sampling. This approach is good for classification imbalanced data. You can use both of Binary or Multi-Class Classification. Methods could use looks like sci-kit learn’s APIs. Only use in python 3.x # Usage ## Parameters * base_estimator : object Classifier looks like sklearn.XXClassifier. Classifier must have methods [fit(X, y), predict(X)]. It is not nesessary predict_proba(X), but if it has this method, you could select ‘soft voting’ option and get predict probability. * n_estimators : int (default=10) The number of base estimators. * voting : str {‘hard’,’soft’} (default=’hard’) hard : use majority rule voting soft : argmax of the sums of prediction probabilities * n_jobs : int (default=1) number of jobs to run in parallel for fit. If -1, equals to number of cores. ## methods * fit(X, y) X : pandas.DataFrame y : pandas.Series return : None * predict(X) X : pandas.DataFrame return : predicted y : numpy.array * predict_proba(X) X : pandas.DataFrame return : predicted probabilities (mean of all bagged models)
# LICENSE This software is released under the MIT License, see [LICENSE](/LICENSE)
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
Built Distribution
Hashes for usbclassifier-0.1.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5590b57b601dfefe0cb58003ccb66a019e228370ed3a757653ce89c7e4ad2f0c |
|
MD5 | f240000dcd2cad7ae07030c928572346 |
|
BLAKE2b-256 | 1b460fa0b3727258f55654ba01ef826c4e769f8c327bbd28a00ec09aebc4d2a0 |