What is Azure Machine Learning Studio? Azure기계학습 스튜디오란 무엇인가요? (2)

What is Azure Machine Learning Studio? 
Azure기계학습 스튜디오란 무엇인가요?

By garyericson Last updated: 04/22/2015

Contributors Edit on GitHub

 

 By mayast업데이트: 09-11-2014

In this article:

 

 

In this article:

• The Machine Learning Studio interactive workspace
• Get started with Machine Learning Studio
• Components of an experiment
• 2 Comments

Microsoft Azure Machine Learning Studio is a collaborative, drag-and-drop tool you can use to build, test, and deploy predictive analytics solutions on your data. 
Azure ML 스튜디오는 데이터에 대해 작동하는 예측 분석 솔루션 을 빌드, 테스트, 배포 할 수 있는 공동 작업 시각적 개발 환경입니다. 

Machine Learning Studio publishes models as web services that can easily be consumed by custom apps or BI tools such as Excel. 
기계 학습 서비스와 개발 환경은 클라우드를 기반으로 하고, 계산 리소스와 메모리 유연성을 제공하며, 웹 브라우저를 통해 작업하므로 설정 및 설치 문제가 없습니다. 

Machine Learning Studio - sometimes called "Azure ML Studio" - is where data science, predictive analytics, cloud resources, and your data meet.기계학습 스튜디오는 데이터 과학, 예측 분석, 클라우드 리소스 및 데이터가 만나는 장소입니다.

The Machine Learning Studio interactive workspace 
기계학습 스튜디오 대화형 작업장

To develop a predictive analysis model, you typically use data from one or more sources, transform and analyze that data through various data manipulation and statistical functions, and generate a set of results. Developing a model like this is an iterative process. As you modify the various functions and their parameters, your results converge until you are satisfied that you have a trained, effective model.
예측 분석 모델을 개발하려면 일반적으로 원본 하나 이상의 데이터를 사용하고, 다양한 데이터 조작과 통계함수를 통해 해당 데이터를 변환 및 분석하고, 결과 집합을 생성합니다. 이와 같은 모델을 개발하는 과정은 반복 프로세스이며 다양한 함수와 해당 매개 변수를 수정할 때 학습된 효과적인 모델을 마련했다고 만족할때까지 결과가 수렴됩니다.

Azure Machine Learning Studio gives you an interactive, visual workspace to easily build, test, and iterate on a predictive analysis model. You drag-and-drop datasets and analysis modules onto an interactive canvas, connecting them together to form an experiment, which you run in Machine Learning Studio. To iterate on your model design, you edit the experiment, save a copy if desired, and run it again. When you're ready, you can publish your experiment as a web service so that your model can be accessed by others.기계학습 스튜디오에서는 예측분석모델을 간편하게 빌드, 테스트, 반복할 수 있는 대화형 시각적 작업 영역을 제공합니다. 데이터집합과 분석 모듈을 대화형 캔버스로 끌어서 놓고 함께 연결하여 실험을 생성하고 기계 학습 스튜디오에서 실행합니다. 모델 디자인을 반복하려면 실험을 편집하고 필요에 따라 복사본을 저장하고 실험을 다시 실행합니다. 준비가 되면 실험 모델에 다른 사용자가 액세스할 수 있도록 웹 서비스로 게시할 수 있습니다.

There is no programming required, just visually connecting datasets and modules to construct your predictive analysis model.  프로그래밍이 필요하지 않고 데이터 집합과 모듈을 시각적으로 연결하면 예측 분석 모델을 구성할 수 있습니다.

Get started with Machine Learning Studio  
기계학습 스튜디오 시작

When you first enter Machine Learning Studio, you see the following tabs on the left: 기계 학습 스튜디오를 처음 시작하면 왼쪽에 다음 탭이 표시됩니다.

·      Studio Home - A set of links to documentation and other resources. 스튜디오 홈 - 설명서 및 기타 리소스에 대한 링크 집합

·      EXPERIMENTS - Experiments that have been created, run, and saved as drafts. 실험 - 만들고 실행하고 초안으로 저장한 실험입니다.

·      WEB SERVICES - A list of experiments that you have published. 웹서비스 - 게시한 실험 목록입니다.

·      SETTINGS - A collection of settings that you can use to configure your account and resources. 설정 - 계정과 리소스를 구성하는 데 사용할 수 있는 설정 모음입니다.

 

NOTE: When you are constructing an experiment, a working list of available datasets and modules is displayed to the left of the canvas. That is the list of components you use to build your model.  NOTE: 실험을 생성할 때 사용 가능한 데이터 집합 및 모듈의 작업 목록이 캔버스의 왼쪽에 표시됩니다. 이 목록은 모델을 빌드하는 데 사용할 구성 요소 목록입니다.

Components of an experiment 실험 구성 요소

An experiment consists of datasets that provide data to analytical modules, which you connect together to construct a predictive analysis model. Specifically, a valid experiment has these characteristics: 

실험은 함께 연결하여 예측 분석 모델을 구성하는 분석 모듈에 데이터를 제공하는 데이터 집합으로 구성됩니다. 특히 유효한 실험에는 다음 특성이 포함됩니다.

·   The experiment has at least one dataset and one module.     데이터 집합 하나 이상과 모듈 하나가 포함됩니다.

·   Datasets may be connected only to modules. 데이터 집합은 모듈에만 연결될 수 있습니다.

·   Modules may be connected to either datasets or other modules. 
모듈은 데이터 집합 또는 다른 모듈에 연결될 수 있습니다.

·   All input ports for modules must have some connection to the data flow. 
모듈에 대한 모든 입력 포트에는 데이터 흐름에 대한 연결이 포함되어야 합니다.

·   All required parameters for a module must be set. 모듈에 대한 모든 필수 매개 변수를 설정해야 합니다.

For an example of creating a simple experiment, see Create a simple experiment in Azure Machine Learning Studio. For a more complete walkthrough of creating a predictive analytics solution, see Develop a predictive solution with Azure Machine Learning. 

간단한 실험을 만드는 예에 대해서는 Azure 기계 학습 스튜디오에서 간단한 실험 만들기를 참조하세요. 예측 분석 솔루션을 만드는 자세한 연습 과정에 대해서는 Azure 기계 학습을 사용한 예측 솔루션 개발을 참조하세요.

Datasets 데이터집합

A dataset is data that has been uploaded to Machine Learning Studio so that it can be used in the modeling process. A number of sample datasets are included with Machine Learning Studio for you to experiment with, and you can upload more datasets as you need them. Here are some examples of included datasets:  

데이터 집합은 모델링 프로세스에서 사용할 수 있도록 기계 학습 스튜디오에 업로드된 데이터입니다. 기계 학습 스튜디오에는 실험에 사용할 다양한 샘플 데이터 집합이 포함되고, 필요할 때 추가 데이터 집합을 업로드할 수 있습니다. 포함된 데이터 집합의 몇 가지 예는 다음과 같습니다.

·     MPG data for various automobiles - Miles per gallon (MPG) values for automobiles identified by number of cylinders, horsepower, etc.
다양한 자동차에 대한 MPG 데이터 - 실린더 수, 마력 등으로 식별되는 자동차에 대한 MPG 값

·      Breast cancer data - Breast cancer diagnosis data. 유방암 데이터 - 유방암 진단 데이터

·      Forest fires data - Forest fire sizes in northeast Portugal. 
 산불 데이터 - 포르투갈 북동부에서 발생한 산불 규모

As you build an experiment, the working list of datasets is available to the left of the canvas.  
실험을 빌드할 때 캔버스의 왼쪽에서 데이터 집합의 작업 목록을 사용할 수 있습니다.

Modules  모듈

A module is an algorithm that you can perform on your data.  
모듈은 데이터에 대해 수행할 수 있는 알고리즘입니다. 
Machine Learning Studio has a number of modules ranging from data ingress functions to training, scoring, and validation processes. 
기계학습 스튜디오에는 데이터 가져오기 함수부터 훈련, 채점 및 유효성검사 프로세스에 이르는 다양한 모듈이 있습니다. 
Here are some examples of included modules:  포함된 모듈의 몇 가지 예는 다음과 같습니다.

·      Convert to ARFF - Converts a .NET serialized dataset to Attribute-Relation File Format (ARFF).  
ARFF로 변환 - .NET 직렬화된 데이터집합을 ARFF 형식으로 변환합니다.

·      Elementary Statistics - Calculates elementary statistics such as mean, standard deviation, etc.  
기본통계 - 평균, 표준편차 등의 기본 통계를 계산합니다.

·      Linear Regression - Creates an online gradient descent-based linear regression model.  
선형회귀 - 온라인 기울기 내리막-기반 선형회귀 모델을 만듭니다.

·      Score Model - Scores a trained classification or regression model.  
모델 채점 - 훈련된 분류 또는 회귀모델의 점수를 매깁니다.

As you build an experiment, the working list of modules is available to the left of the canvas. 
실험을 빌드할 때 캔버스의 왼쪽에서 모듈의 작업 목록을 사용할 수 있습니다.

A module may have a set of parameters that you can use to configure the module's internal algorithms. 
모듈에는 모듈 내부 알고리즘을 구성하는 데 사용할 수 있는 매개변수 집합이 포함될 수 있습니다.

When you select a module on the canvas, the module's parameters are displayed in the pane to the right of the canvas. You can modify the parameters in that pane to tune your model. 
캔버스에서 모듈을 선택할 때 모듈 매개 변수가 캔버스 오른쪽의 창에 표시됩니다. 해당 창에서 매개변수를 수정하여 모델을 튜닝할 수 있습니다.