Isolation of Data, Methods and IndexesThe selection of the software of Data Science changes for what we want to do.
There are 3 types for Statistics , Multi-Variable Analysis and Data Mining .
This type is similar to MS-Word and MS-Excel.
This type is useful for Cause and Effect Analysis .
Free software : Weka Explorer, R Commander and Natto
Each block is each process for data. We make the flow diagram of data analysis.
This type is useful to do same process for many times.
Free software : RapidMiner, Knime, Orange, Weka KnowledgeFlow
The page,
Difference of Output by Methods
, was made by RapidMiner.
This type is not easy for daily use because we need to study many commands.
Free software : R and Python
Many people make the tools of R. So we can try many methods easily.
R and Python are not only the data analysis software but also programming languages. They are used as the engine of other software. And they are used one of the algorithm of systems. If we want to make systems using Machine Learning , this type is used.
It is the newest type of software.
Shiny is famous. R-EDA1 is also a type of this.
I often use Excel for data analysis. In many cases, I do not use other software.
Excel is used as Database, Data Literacy, Statistics, Simulation, visualization, and reporting. For the Linking different source data , Excel is useful. Other software is used to help Excel.
NEXT Isolation of Data, Methods and Indexes
Tweet