--- 
 
# required metadata 
title: "count_select: Machine Learning Count Mode Feature Selection Transform" 
description: "Selects the features for which the count of non-default values is greater than or equal to a threshold." 
keywords: "feature, selection, count" 
author: WilliamDAssafMSFT
ms.author: wiassaf 
manager: "cgronlun" 
ms.date: 07/15/2019
ms.topic: "reference" 
ms.prod: "sql"
ms.technology: "machine-learning-services" 
ms.service: "" 
ms.assetid: "" 
 
# optional metadata 
ROBOTS: "" 
audience: "" 
ms.devlang: "Python" 
ms.reviewer: "" 
ms.suite: "" 
ms.tgt_pltfrm: "" 
ms.custom: "" 
monikerRange: ">=sql-server-2017||>=sql-server-linux-ver15"
 
---

# *microsoftml.count_select*: Feature selection based on counts





## Usage



```
microsoftml.count_select(cols: [list, str], count: int = 1, **kargs)
```





## Description

Selects the features for which the count of non-default values is greater than or equal to a threshold.


## Details

When using the count mode in feature selection transform, a feature is
selected if the number of examples have at least the specified count
examples of non-default values in the feature. The count mode feature
selection transform is very useful when applied together with a categorical
hash transform (see also, `categorical_hash`. The count feature
selection can remove those features generated by hash transform that have no
data in the examples.


## Arguments


### cols

Specifies character string or list of the names of the variables to select.


### count

The threshold for count based feature selection. A feature is
selected if and only if at least `count` examples have non-default
value in the feature. The default value is 1.


### kargs

Additional arguments sent to compute engine.


## Returns

An object defining the transform.


## See also

[`mutualinformation_select`](mutualinformation-select.md)