#Analytics

A few months ago, I faced a significant challenge: streamlining the handling of business logic in our application. My goal was to extract the business logic from the code and hand it over to analysts. Dealing with a multitude of rules could easily result in a code littered with countless "if" statements, especially if the coder lacked an understanding of cyclomatic complexity. Such code becomes a source of pain for those working with it—difficult to write, test, and develop.

Hi Developers!

As you know the application errors live in ^ERRORS global. They appear there if you call:

d e.Log() 

in a Catch section of Try-Catch.

With @Robert.Cemper1003's approach, you can now use SQL to examine it.

Inspired by Robert's module I introduced a simple IRIS Analytics module which shows these errors in a dashboard:

Hi developers!

How to build an analytics solution with InterSystems IRIS?

To begin with, let's agree on the points of what is the analytics solution - and this could be a very wide topic. Let's limit the set of solutions to those you can present in the Analytics contest.

There are three kinds of analytics solutions that we will review here: monitoring, interactive analytics, and reporting.

Monitoring

The typical monitoring solution consists of an online dashboard with KPIs that are being actively updated.

The key use case is of monitoring is to visually observe the KPI of fresh data every moment to react in case of an emergency.

Interactive Analytics

This solution supposes a set of interactive dashboards with filters and drill-downs.

The key use case is to explore the data with filters and drill-downs making business decisions upon graph and table data visualization.

Reporting

Reporting solution provides a set of static (usually) reports in a form of HTML or pdf documents that deliver the data in graph and text form in a predesigned form and could be sent via email.

The typical use case of a reporting system is to obtain reports on a given period that will illustrate the status of the product, process, service, sales, etc that is crucial for the business.

How InterSystems products could be used to build such solutions? Let's discuss this below!

There are several options how to deliver user interface(UI) for DeepSee BI solutions. The most common approaches are:

• use native DeepSee Dashboards, get web UI in Zen and deliver it in your web apps.
• use DeepSee REST API, get and build your own UI widgets and dashboards.

The 1st approach is good because of the possibility to build BI dashboards without coding relatively fast, but you are limited with preset widgets library which is expandable but with a lot of development efforts.

The 2nd provides you the way to use any comprehensive js framework (D3, Highcharts, etc) to visualize your DeepSee data, but you need to code widgets and dashboards on your own.

Today I want to tell you about yet another approach which combines both listed above and provides Angular based web UI for DeepSee Dashboards - DeepSee Web library.

Today we will talk about InterSystems Reports. This is a BI system that provides you with tools to create static reports and export them to different file formats. We will see how it works using the DC Analytics public analytical sample as an example. In this article, we will examine how to familiarize yourself with the reports available in the repository, how to make a new report based on a ready-made data structure, and how to prepare a data structure from scratch.

Hi Community,

In a hard work of data curation and data quality, the Health Dataset application deploy to you the above datasets.

These datasets can be used in your ML applications/models, AutoML and analytics projects. See more details here:

The InterSystems IRIS has a very nice container class to allows you have your Dashboards as classes source code. It is %DeepSee.UserLibrary.Container.

With this class is possible group all your dashboard and pivot table definitions.

This is useful to automatically create your dashboards when you build your docker project and other automation scenarios.

See:

Hi, Community!

This is the 3rd part of DeepSee Web story - Angular base UI for DeepSee Dashboards, see the beginning here.

​

By design, DSW provides an implementation for every widget in DeepSee library. But there are some extra features in DSW which make solutions built with DSW dashboards more functional. This article describes it.

I'm happy to share with the community a web server log dataset from our longtime customer, an operating company.

Their webserver operates on Apache webserver and contains data which can be useful to analyse a load and search engines activity.

After installing the project, you will get the data for a few months that can show a typical load and activity of clients, robots and also you can see how it depends on day of week, holidays and time of a day.

The Cube is also included in package.

Hi guys!

I'd like to present you my new project: iris-analytics-notebook, a notebook approach to use IRIS analytics capabilities.

Project description

In past few years, notebooks tools like Jupyter are gaining popularity due its natural way to express ideias.

An almost unipresent tool for data scientists, notebook can also help to improve the impact of analytics tools for all sort of users.

The following post outlines a more flexible architectural design for DeepSee. As in the previous example, this implementation includes separate databases for storing the DeepSee cache, DeepSee implementation and settings, and synchronization globals. This example introduces one new databases to store the DeepSee indices. We will redefine the global mappings so that the DeepSee indices are not mapped together with the fact and dimension tables.

When analyzing data, there is often a need to look at specific indicators more thoroughly and to highlight sections of information of particular interest to a user.

For instance, examining the data dynamics for specific regions or dates can help us uncover some hidden trends and patterns that will allow us to make an informed decision about our project in the future.

A few months ago, I read this interesting article from MIT Technology Review, explaing how COVID-19 pandemic are issuing challenges to IT teams worldwide regarding their machine learning (ML) systems.

Such article inspire me to think about how to deal with performance issues after a ML model was deployed.