Today, Huawei and Deutsche Telekom jointly announced that Deutsche Telekom selected Huawei NE9000 core routers to simplify its network connections and enable cloud-and-network synergy, automated service provisioning, and agile bandwidth adjustment. With innovative information and communications technology and its dedication to continually improving its solutions, Deutsche Telekom provides its users with robust, convenient, stable, and secure cloud services. http://bit.ly/2BLoKXs #Huawei #BigData #AI
A Common Data Analysis Pattern with a Simple Solution in R
It seems that much of the data analysis work I’ve done over the last few months has followed a “script”. First, identify data, often government-sponsored and freely-available, that’s of keen interest. Next, find the websites that house the data and download the relevant files to my notebook. The downloads might ultimately be one-off or included in the data analysis programs. Finally, load the data into either R or python and have at it with queries, visualizations, and statistical/learning models.
Several examples of recent work come to mind. The first involves data from the Bureau of Labor Statistics on jobs and educational attainment from 1992-2017. On this site, 24 spreadsheets are available detailing monthly statistics on six measures of employment by 4 levels of educational attainment. For a previous blog, I downloaded 12 of these files, including measurements laborforce, employed, and unemployed by educational levels no HS, HS grad, some college, and college grad. I renamed the spreadsheets on my SSD to include indicators of dimension – eg “clf_laborforce_collegegrad.xls”.
The second example, the topic of this blog, has to do with Medicare charges summarized by hospital and diagnostic related group (DRG). At this point there are five files (either csv or spreadsheet) available for download, representing the years 2011-2015. Year is embedded in the website file names.
A third illustration, and the topic of a coming blog, revolves on census data from the American Community Survey.
The pattern behind the three cases includes:
* readily downloadable files, generally either csv or xls. These files can either be copied by hand or moved programmatically.
* multiple of these files, often dimensioned by time or other variable(s).
* a common, consistent format to the files, so that “reads” will work similarly on each.
* a structured file naming convention, either given or assigned, that provides dimensional info for data loads. Date/Time is the most common diemnsion.
In this article, I looked at the Medicare charges data that consists of five yearly csv files. I expect the next year in the sequence, 2016, to be posted in the near future. I first downloaded the five files to my laptop, programmatically in this case. I then used Jupyter Notebook and R 3.4 to analyze the data with code that takes advantage of the commonalities. The data.table package along with the tidyverse ecosystem and fast file compression, read/write library fst, plus a functional approach, are central to the work.
This is not your older sibling’s R. None of the highly-performant packages used here are included in core R. Rather, they are the bounty of an exhuberant and capable R ecosystem of developers. Incidentally, if this notebook were written in python, I’d be giving similar accolades to its community.
The remainder of the notebook details the R code to implement the loading of this data into R and some simple subsequent analysis. The structure of the code in this instance is very similar to that of the other examples cited.
To read entire content, click here https://goo.gl/71mCCX #DataScience #Cloud
Topology Data Analysis (TDA)
Topology is the branch of pure mathematics that studies the notion of shape. In the context of large, complex, and high dimensional data sets, topology takes on two main tasks, the measurement of shape and the representation of shape. One can measure shape related properties within the data, and create compressed representations of data sets retaining features which reflect the relationships among the points in the data set. The representation is in the form of a topological network or combinatorial graph. In the study of high dimensional and complex data sets, combinatorial representations provides a compressed representation of the data that retains information about the geometric relationships between data points. Also, the representations are a useful and simple way to examine the data, as well as understand the primary variables characterizing various subgroups. The three properties of topological analysis include: coordinate invariance, deformation invariance and compressed representations.
Topological Data Analysis (TDA) allows you to interact with and represent structured and unstructured data through a topological network. A topological network provides a map of all the points in the data set, so that nearby points are more similar than distant points and clarifies the structure of the data set without having to query it or to perform any algebraic analysis on only a subset of variables. In essence, one can discover the true meaning of the data by analyzing a compressed representation of the data set retaining all of the subtle features and data points that have a degree of similarity to each other.
Topological networks are a framework for Machine Learning. A topological network represents data by grouping similar data points into nodes, and connecting those nodes by an edge if the corresponding collections have a data point in common. Because each node represents multiple data points, the network gives a compressed version of extremely high dimensional data. Topological networks allow individuals to easily examine machine-learning outputs and understand the “shape” of complex data sets. Topological methods provide a quick way to understand the structure of the data and obtain knowledge from data. Topology can be used to develop methods for recognizing shapes, which it does through a set of tools called homology or for “point clouds" called persistent homology. Point cloud processing is extremely efficient when dealing with huge data volumes, because one uses patterns occurring in a shape to distinguish shapes from each other. With point clouds, all points have the same components (which are the analogs of the feature attributes), and the data types of the components are the same. This allows processing points not one by one, but in huge chunks, without inspecting whether there are any differences in their data structure. https://goo.gl/aF7j6P #DataScience #Cloud
