All Posts
Will the real Pareto distribution please stand up? SAS supports three different distributions that are named "Pareto." The Wikipedia page for the Pareto distribution lists five different "Pareto" distributions, including the three that SAS supports. This article shows how to fit the two-parameter Pareto distribution in SAS and discusses the
In their new book, SAS Viya: the R Perspective, Kevin Smith and Xiangxiang Meng provide an overview of using R with the SAS Viya platform. Read on to see how R programmers can use CAS.
Los avances tecnológicos, las expectativas de los clientes y las regulaciones que redefinen el mercado, han sido puntos clave para que el sector de los seguros se enfoque en el crecimiento de sus ventas, su rentabilidad y la lealtad y el cuidado de sus clientes. ¿Qué ha pasado entonces? las
Who says technical people can't have fun!?! Similar to Throwback Thursday / #TBT (when people post one of their old/nostalgic photos on social media), I like the tradition of Fun Friday when I use a fun data topic to test our software - a test can be just as rigorous using
Health care is facing an unprecedented need to reform, drive quality and cut costs. Growth in targeted, specific treatments and diagnostic technology, coupled with a rise in people with long-term and multiple chronic conditions, is creating unsustainable demand on the system. To thrive – or even merely survive – health
SASでは、従来からオープン・AIプラットフォームであるSAS Viyaの機能をPythonから効率的に活用いただくためのハイレベルなPython向けAPIパッケージであるDLPyを提供してきました。 従来のDLPyは、Viya3.3以降のディープラーニング(CNN)と画像処理(image action set)のために作成された、Python API向けハイレベルパッケージです。 DLPyではKerasに似たAPIを提供し、より簡潔なコーディングで高度な画像処理やCNNモデリングが可能でした。 そして、この度、このDLPyが大幅に機能拡張されました。 最新版DLPy1.0では、以下の機能が拡張されています。 ■ 従来からの画像データに加え、テキスト、オーディオ、そして時系列データを解析可能 ■ 新たなAPIの提供: ・ RNN に基づくタスク: テキスト分類、テキスト生成、そして 系列ラベリング(sequence labeling) ・ 一般物体検出(Object Detection) ・ 時系列処理とモデリング ・ オーディオファイルの処理と音声認識モデル生成 ■ 事前定義ネットワーク(DenseNet, DarkNet, Inception, and Yolo)の追加 ■ データビジュアライゼーションとメタデータハンドリングの拡張 今回はこれらの拡張機能の中から「一般物体検出(Object Detection)」機能を覗いてみましょう。 SAS Viyaでは従来から画像分類(資料画像1.の左から2番目:Classification)は可能でした。例えば、画像に映っている物体が「猫」なのか「犬」なのかを認識・分類するものです。 これに加えて、DLPy1.0では、一般物体検出(資料画像1.の左から3番目:Object Detection)が可能になりました。 資料画像1. (引用:Fei-Fei Li & Justin Johnson & Serena Yeung’s Lecture
The TEXT plot was introduced with SAS 9.4M2 to facilitate placement of text strings in a graph. This replaces the MARKERCHAR feature of the SCATTER plot statement, which is still available, but it is better to use TEXT plot in most cases. The syntax is: text x=column y=column text=column </
¿Quién, en ocasiones festivas y/o momentos especiales, no ha escuchado o repetido alguna vez y casi de manera automática: “Brindo por la salud”, “Lo importante es la salud, lo demás va y viene”? Al parecer, son escasos los momentos de nuestra vida, donde nos acordamos de nuestra propia salud, salvo
SAS Technical Support has had several requests from customers who want to use SAS® software to help download their files from a website when there is no application programming interface (API) to do it. This post shows how to automate downloads using PROC HTTP and DATA step, and how to use the HTTP DEBUG statement.
Innovation is born from curiosity. And at SAS, curiosity is in our values, our DNA, and in our history. Curiosity drove our founders to create SAS, and it all started with a simple question: Is there a better way to analyze data? Year after year, we continued to grow by
Vivimos en un mundo cada vez más digitalizado, donde sacar provecho a los miles o millones de datos que se producen a cada instante se ha convertido en una necesidad para las empresas. Hacerlo de forma ágil y efectiva es su principal objetivo. En este escenario, las soluciones de analítica
We have updated our software for improved interpretability since this post was written. For the latest on this topic, read our new series on model-agnostic interpretability. While some machine learning models – like decision trees – are transparent, the majority of models used today – like deep neural networks, random forests, gradient boosting
Artificial intelligence often seems misunderstood, especially in fraud. The same is true of machine learning. One of the amazing things about them is they ask the unasked questions. This occurs as artificial intelligence (AI) and machine learning (ML) go about their daily work. So, what is the unasked question? Too
President Donald Trump - people seem to either love him or hate him. Which makes for an interesting data-analysis topic ... tracking Trump's approval rating. Follow along as I explore some data! I'll start with what I consider the 'best' approval-rating graph I've found so far. Here's a screen-capture of