Different Time Series Charts in Orange

Time Series has its own specific graphs than other techniques. Orange Data Mining tool has the capability to generate all these figures. The following Orange Mining task allows displaying of different graphs 

Following are few graphs for the time series. 

Line charts are the figures that show you the value over time which is a traditional figure.

Spirolgram is an extremely important visualization. By the density of the colour, a user can tell how data is distributed. For example, in the below figure, you can see milk production is high in January. 

ACF and PACF graph very important when defining the AR, MA parameters. These two graphs are looking at the correlation of the time series with the previous values. As you can see in the below figure, correlation is seasonal for the selected dataset.

Time Series Forecasting Algorithms

 Time Series Forecasting is a complex algorithm and therefore there are many different algorithms for Time Series forecasting. These algorithms can be divided in Classical Statistical Time Series Linear Methos, Supervised Machine Learning, Regression, Deep Learning Methods.

Every category has many algorithms as shown in the below figures. 

Time Series Cheat Sheet v 5.1.0.0

Minor changes were done after the last release. 

 

Azure Machine Learning: Named Entity Recognition in Text Analytics

 

Recognition of Entities in Text Analytics is an important process in Text Analytics in order to find People, Places and Organizations. Named Entity Recognition in Azure Machine Learning is used to identify the name of entities such as people, locations, and organizations, etc. The Named Entity Recognition control will provide where the particular entity exists as well as this technique will help us to understand the context of a text.

The latest article explains how to recognize Named Entities in Azure Machine Learning. Following are the rest of the articles in the series.

Introduction to Azure Machine Learning using Azure ML Studio

Data Cleansing in Azure Machine Learning

Prediction in Azure Machine Learning

Feature Selection in Azure Machine Learning

Data Reduction Technique: Principal Component Analysis in Azure Machine Learning

Prediction with Regression in Azure Machine Learning

Prediction with Classification in Azure Machine Learning

Comparing models in Azure Machine Learning

Cross Validation in Azure Machine Learning

Clustering in Azure Machine Learning

Tune Model Hyperparameters for Azure Machine Learning models

Time Series Anomaly Detection in Azure Machine Learning

Designing Recommender Systems in Azure Machine Learning

Language Detection in Azure Machine Learning with basic Text Analytics Techniques

Design and Implementation of Data Warehouse for a Higher Educational Institute in Sri Lanka

In any organization, the leadership is responsible for taking decisions that will lift the said organization to a better place. The problem-solving abilities of the management are mostly depending on the ability to grasp all the required information in a clean and actionable format. Building a well-designed data warehouse leads to answer that problem. When data sourced from different sourcing systems, it's very important that the aggregated data is relevant and supporting the decision-making by the leadership. This research aims at mitigating the issues that are hindering such organizations to make correct decisions.

Read the research paper at https://ieeexplore.ieee.org/document/9417820 

Managing SQL Server Express Edition

Due to the cost implications, most organizations use SQL Server Express Edition. Since SQL Server Express can handle a 10 GB amount of data. The latest article describes, how to manage your SQL Server Express Instances. 

This is the 12th article published for the year. 

Things you should avoid when designing a Data Warehouse

Language Detection in Azure Machine Learning with basic Text Analytics Techniques

Designing Recommender Systems in Azure Machine Learning

Multi-language support for SSAS

Time Series Anomaly Detection in Azure Machine Learning

Tune Model Hyperparameters for Azure Machine Learning models

Customizing Differential and Transaction Log backups

Elastic Jobs in Azure SQL Database

Dynamic Data Masking in SQL Server

Clustering in Azure Machine Learning

Cross-Validation in Azure Machine Learning

Azure AutoML

As you are aware, Machine Learning is not a simple task. It has many tasks such as Feature Engineering, Feature Selection, Algorithm Selection, Hyper Tune Parameters, Evaluation etc. Due to these many complexities in the Machine Learning process, machine learning is still a little far away from people who not excellent at Mathematics and Statistics. For example, you are looking for a classification problem, there many algorithms that you can choose such as Decision Trees, Random Forest, Naive Bayes, SVM, ANN etc. Sometimes, you may have to perform this process multiple iterations in order to achieve better results as shown in the following figure. 

source: https://towardsdatascience.com/understanding-feature-engineering-part-1-continuous-numeric-data-da4e47099a7b

AutoML or Automated ML or Automated Machine Learning provides, you to submit dataset provide you with a better algorithm and relevant parameters. There are many AutoML frameworks available. Microsoft too has an AutoML framework that is available in the Azure Machine Learning Platform.

By following this link, you can watch videos, research papers on AutoMLdone by Microsoft Research. 

https://www.microsoft.com/en-us/research/project/automl/

Experiments in Azure Machine Learning

Following are all the experiments that are built by me in Azure Machine Learning. 

Time Series Anomaly Detection

Recommender System for Restaurant

Recommender System with live data

Latent Dirichlet Allocation

Recommender System for Customer Review Data

Language Detection 

Named Entity Recognition - News

Anomaly Detection of Sri Lanka Paddy Production

Log File in SQL Server Database

A logfile is an important component in a Database. The log file is part of a lot of operations in a database such as Writing to the Database, Transactions, Recovery. Further, there are important features that can be utilized with log files such as Replication, Mirroring, and Log Shipping. 

Due to the many usages of the Transaction Log file, it is important to understand the behaviour of the transaction log file. The transaction log behaviour will be determined by the Recover Models which are discussed in this article.

The Transaction Log file is extremely useful to handle Point in Time Recovery in live or production environments to recover from accidental data deletes and other operations. This article describes how to configure point in time recovery. Further, log shipping can be configured to enable data disaster recovery.  

In the later version of SQL Server, provides the mechanism to customized Transaction Log Backups.