1. ‘SAS 컨테이너 런타임’이란? SAS는 SAS Viya 2021.1.1.3에서 SAS 컨테이너 런타임(SAS Container Runtime, 이하 SCR)을 출시했으며, 그 이후 많은 고객이 운영환경에서 SCR을 구현했습니다. 이 혁신적인 런타임 엔진은 SAS 모델과 의사결정을 Open Container Initiative (OCI) 호환 컨테이너에 배포하는 역할을 합니다. SCR은 표준 기술을 사용하여 SAS Viya 외부에서 모델과 의사결정을 실행합니다. 클라우드
Search Results: api (2283)
At SAS, we take a passionate stance in shaping the future of tech leaders. In 2023, we introduced the SAS HBCU+ Fellows Program, inviting faculty from Historically Black Colleges and Universities (HBCUs) and Primarily Black Institutions (PBIs) to gain hands-on experience with SAS and pass on this knowledge to their
El lavado de dinero siempre se ha considerado un mal mayúsculo, pero las cifras actuales son abrumadoras. Al revisar los datos de la Financial Action Task Force (FATF), se revelan pérdidas actuales situadas entre el 2% y el 5% del PIB mundial por este flagelo. El panorama en Colombia, sin
Have you ever been in a meeting and heard, “We should leave that to the IT department to figure out. That’s a system thing”? I have observed this attitude among insurance professionals my whole career. It was almost as if anything that had to do with IT systems was radioactive!
보통 분석모델 관리 프로세스는 모델개발, 모델등록, 배포, 모니터링 및 재학습으로 구성됩니다. 이번 글에서는 SAS Model Manager (MM)가 제공하는 API를 통해 분석모델 관리 프로세스가 어떻게 진행되는지 살펴보겠습니다. SAS MM은 모델 컬렉션의 생성 및 관리를 간소화하는 제품입니다. 이 웹 기반 인터페이스를 사용하면 모델 관리 프로세스를 손쉽게 자동화하고, 사용자가 모델링 프로세스의 각 단계별로 진행
In my previous blog Programmatically export a Visual Analytics report to PDF - SAS Users, I use the SAS Visual Analytics SDK to export a report to PDF, which is quite simple if we have basic knowledge with JavaScript programming. It works for both the latest version of SAS Viya
Tanto en la vida como en los negocios, conocer nuestras limitaciones es importante para progresar. Desarrollar una estrategia analítica figura entre las cosas que pueden generar mucho valor para una empresa, pero es crucial entender lo que nos impide comenzar algo nuevo. En un artículo anterior, invité a ese proceso
Money Laundering has been around for many years. In fact, the term originated in 1920s Chicago, when Al Capone, the original money launderer, “cleaned” the profits of his crimes by cycling the money through a chain of laundrettes that he owned. Nowadays, money laundering uses increasingly innovative and sophisticated techniques,
In this third article, we will introduce an alternative approach that surfaces the CMS-HCC Risk Adjustment Model execution through SASPy integration to a Flask application. We will demonstrate how this integration allows a user to score an individual patient/member on-demand, using inputs to an interactive web form to execute the model score code, surfacing the resulting score to the user.
It feels like yesterday that we were signing a contract with a new vendor, Acclaim, to provide digital badging services for our SAS Certification candidates. That was over five years ago. Since then, Acclaim joined forces with another market leader and became part of Credly. SAS has expanded our badging
Earth’s natural capital deserves protection – for our sake and for the future. Analytics can help.
Im Gespräch mit Norbert Pieper, Sprecher für Versicherungsaufsicht bei der BaFin.
SAS System Engineer Sophia Rowland reveals how to embed decision flows into webpages and applications using APIs for a better customer experience.
Over the past year, it’s become normal for me to order my groceries online, make telehealth appointments for my family and attend dozens of virtual meetings every week. And I am not alone. Last year not only brought an increase in the use of digital technologies. It also brought with
By making requests through API calls you can expand the functionality of the bots you make with SAS Conversation Designer; allowing your bots to query external sources for up-to-date information, score a model, and many other possibilities. This is very beneficial as SAS Conversation Designer is included in many offerings of the modernized SAS Viya platform, meaning you can easily create bots that are integrated with the other services of the SAS Viya platform or third-party services.
The model management process, which is part of ModelOps, consists of registration, deployment, monitoring and retraining. This post is part of a series examining the model management process, orchestrated through the Model Manager (MM) APIs. The focus of part one is on model registration, specifically on using the APIs from
There are three types of visualization APIs defined in the SAS Viya REST API reference documetation: Reports, Report Images and Report Transforms. You may have seen the posts on how to use Reports and Report Images. In this post, I'm going to show you how to use the Report Transforms
SAS Viya is an open analytics platform accessible from interfaces or various coding languages. REST API is one of the widely used interfaces. Multiple resources exist on how to access SAS Visual Analytics reports using SAS Viya REST API. For example Programmatically listing data sources in SAS Visual Analytics by
I think we can all agree that lifelong learning is the future, for all of us. We know that we need to learn and develop all the time, simply to stay abreast. The world is changing fast, and we must change with it. Investing in analytics talent is an investment
Rapid demand response forecasting techniques are forecasting processes that can incorporate key information quickly enough to act upon in real time by agile supply chains. Retailers and consumer goods suppliers are urgently trying to determine how changes in consumer behavior will affect their regions, channels, categories, brands and products during
I think that this pandemic has put digital transformation at the top of every executive agenda.
With increasing interest in Continuous Integration/Continuous Delivery (CI/CD), many SAS Users want to know what can be done for Visual Analytics reports. In this article, I will explain how to use Python and SAS Viya REST APIs to extract a report from a SAS Viya environment and import it into another environment.
Mathematical optimization can help business leaders make better decisions in every aspect of their business. After a model has been built, end users are usually interested in doing some sort of scenario analysis to test its robustness and visualizing key performance metrics. SAS has various products that can work with
Although we are still learning about all the negative health impacts on the body, it is important to remember that vaping is dangerous. And it is especially dangerous for our youth as their developing brains are much more susceptible to addiction. There is a lot of misinformation out there so
While growing up in the 80's, I watched The Golden Girls on TV with my Grandma Betty. Now, when my sister visits, we binge watch reruns on TV Land. I was excited when I saw for this Halloween, you could buy Golden Girls costumes! Too bad they sold out right
Editor's Note: This article was translated and edited by SAS USA and was originally written by Makoto Unemi. The original text is here. SAS previously provided SAS Scripting Wrapper for Analytics Transfer (SWAT), a package for using SAS Viya functions from various general-purpose programming languages such as Python. In addition
En los últimos años y en particular este año, la mayoría de las empresas financieras han estado experimentando un significativo cambio de paradigma: pasar de la “medición del riesgo” a la gestión del negocio a partir de su riesgo. Los desafíos, que imponen actualmente la economía mundial y regulaciones de
SAS Viyaのディープラーニング機能をPythonから利用するためのハイレベルAPIパッケージの最新版であるDLPy1.1では、主にCNN(Convolutional Neural Network)に関連する機能が拡張されています。 主な拡張機能: ・新たに3つのネットワーク構造に対応 【U-Net】 元々は、医療用画像のセグメンテーション向けに開発されたネットワークです。 (出典:https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/) 【MobileNet】 モバイル端末のようなリソースの少ない環境でも、畳み込み計算を分割(Depthwise Separable Convolution)することで、軽快に、素早く、そして精度の高い結果を得ることができると言われているネットワークです。 左が一般的な畳み込み構造。右が、MobileNetの構造。(出典:https://arxiv.org/pdf/1704.04861.pdf) 【ShuffleNet】 MobileNet同様に軽量軽快なネットワークですが、MobileNetでの畳み込みの分割に加えて、その名の通り、チャンネルをシャッフルしてチャンネル間での畳み込みを行い、特徴抽出を効率化するネットワーク構造です。 (出典:https://arxiv.org/pdf/1707.01083.pdf) ・上記ネットワーク構造に伴う、畳み込み層機能の拡張 【transpose convolution(転置畳み込み)】 Deconvolution(逆畳み込み)とも言われ、元となる画像に0 paddingして拡大してから畳み込む手法です。(上記U-Netに関連) 【group convolution(グループ化畳み込み)】 入力層をチャンネル方向にグループ分割して、グループごとに畳み込みを行い、最後に結合して出力する手法です。分割することで計算量を小さくすることができます。(上記MobileNet、ShuffleNetに関連) ・画像解析手法の拡張 【物体検出(Object Detection)手法にFaster R-CNNを追加】 R-CNNからFast R-CNN、そしてFaster R-CNNへと処理時間の短縮と精度向上が図られ進化してきているアルゴリズムです。 (出典:https://arxiv.org/pdf/1506.01497.pdf) DLPyの従来版からサポートしているYOLOに比べると処理時間はかかりますが、より高い精度を得ることができます。 【新たにセグメンテーション(Semantic Segmentation)に対応】 セグメンテーションは、画像中に存在する複数の物体や領域に対して、ピクセルレベルで推定する問題です。画像を入力すると、各画素に対して識別結果が付与された画像を出力します。一般的には、 Nクラスのセグメンテーションモデルは、Nチャンネルの出力画像を出力し、各チャンネルの画素値は各クラスの確率を表します。(上記U-Netに関連) 以上のように、PythonユーザーがDLPyを通して活用することができる、SAS Viyaのディープラーニング(CNN)機能が拡張されています。 ※DLPyの詳細に関しては、Githubサイトでご覧いただけます。 ※Enterprise Open Analytics Platform 「SAS Viya」 を知りたいなら「特設サイト」へGO!
More and more organizations are moving to the cloud, but for some moving data isn’t an option. With a remote managed software and services (RMSS) solution deployment, however, it’s still possible to experience the benefits of cloud, without the data or solution ever leaving your premises or existing cloud provider.
SAS Viyaの分析機能をPythonから利用するためのハイレベルAPIパッケージであるDLPyでは、kerasと同等の簡潔なコーディングで、複雑な画像処理やディープラーニングを実行することができます。 そして、DLPyでは、kerasと同様に、2つの手法でディープラーニングのモデルを構築することができます。 Sequential modelとfunctional API modelです。 Sequentialとは、その名の通り、レイヤーを順序通りに積み重ねて、順序通りに実行していくモデルです。 以下は、DLPyを用いて、PythonからSAS Viyaのディープラーニング機能を使用して画像分類向けsequential modelのネットワークを定義している例です。 In [10]: model1 = Sequential(sess, model_table='Simple_CNN') model1.add(InputLayer(3, 224, 224, offsets=tr_img.channel_means)) model1.add(Conv2d(8, 7)) model1.add(Pooling(2)) model1.add(Conv2d(8, 7)) model1.add(Pooling(2)) model1.add(Dense(16)) model1.add(OutputLayer(act='softmax', n=2)) In [11]: model1.print_summary() Out[11]: In [12]: model1.plot_network() Out[12]: 一方、functional APIは、sequentialでは、表現することが難しい、より複雑な構造のモデルを構築する際に利用されます。 以下は、kerasの公式サイトに記載されている文面です。 “functional APIは,複数の出力があるモデルや有向非巡回グラフ,共有レイヤーを持ったモデルなどの複雑なモデルを定義するためのインターフェースです.” そして、DLPyでは、kerasと同様にsequential modelだけでなく、functional API modelの構築も可能になっています。 以下はその一例として、複数の入力と出力を持つような画像分類のためのディープラーニングモデルのネットワーク例です。 まず、テンソルオブジェクトを返すInput()によって、2つのテンソル、グレースケール画像とカラー(RGB)画像、を定義します。 グレースケール画像は2つの畳み込み層に送り込まれます。カラー画像はそれらとは別の畳み込み層に送り込まれます。