-
It's logical to display a confusion matrix for classification tasks. But, this may be assumed as functionality that shouldn't be implemented in VW bcs some 3rd party software may be used to build thes…
-
I just noticed that there are some requests for integration with PySpark http://dmlc.ml/2016/03/14/xgboost4j-portable-distributed-xgboost-in-spark-flink-and-dataflow.html
I also received some emails …
-
I've recently see more people using "balanced accuracy" for imbalanced binary and multi-class problems. I think it is the same as macro average recall. If so, I think we might want to create an alias,…
-
Hello,
I suggest allowing a document class (or category) dependent pruning of vocabularies.
Example: I have document multi-class classification problem at hand that is highly imbalanced
``
n(cla…
-
I can not understand the configuration 1 for the exercises 2.
You say that we need to report these performance measures:
model a - train - [performance measures][0:4]
model a - test - [perfor…
-
I would appreciate if you could fix the error.
Code:
```
from collections import Counter
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split,Stra…
-
Hello,
I found out that the data is quite biased. I mean we only have limited data (500-600 records) with respect to people who left the company whereas we have more than 7000 active employee recor…
-
to replace OpenML100
-
#### Description
When I used OneSidedSelection with a *dict* ratio, it showed two *DeprecationWarning*s and the result was weird.
#### Steps/Code to Reproduce
Example:
```
from collections…
-
https://dx.doi.org/10.1093/bioinformatics/btw255