At Belfox, we don’t place an emphasis on the technology we use. We let the kind of dataset that we are analyzing pick the tools for us.
In general, most of our projects are tackled with R and Python with pandas.
However, our data science toolbox contains a plethora of tools. If you need a project done with a particular tool, we would gladly oblige.
Here is a sketch of the tools our teams use from specific use cases.
|Data Collection||Scripts in R and Python, Embedded Systems|
|Tidying the Data||R, Python|
|Exploratory Analysis||R, Python|
|Statistical Modelling and Inference||CRAN, pandas|
|Prediction and Machine Learning||CRAN, pandas|
|Data Visualization||GGPlots, pandas|
|Data Product Development||Shiny, .NET Framework, Django, Python QT|
|Reporting||Jupyter Notebooks, R Markdown, Latex|
|Data Storage||MySQL, CSVs, SQlite|
|Big Data||Hadoop Infrastructure|
Dealing with Big Data
In some case, the data is too large for traditional data analysis tools. In such cases, we engage the power of the Hadoop infrastructure – A multi parallel data processing infrastructure for all our needs including machine learning and prediction.