Press "Enter" to skip to content

Category: Data Science

Using Spark For Investigation

Sean Owen tries to unravel the Tamam Shud mystery:

Several people have approached these letters as a cryptographic cipher. The odd circumstances of death do sound like something out of a John Le Carré spy novel. Some of the best attempts, however, fail to produce anything but truly convoluted parsings.

Another possibility may already have occurred to you: Are they the first letters of words in a sentence (aninitialism)? Some suspect this death was a suicide, and that the message is merely some form of final note. With this morbid scenario in mind, it’s easy to imagine many phrases, like “My Life Is All But Over,” that fit the letters because indeed their frequency seems to match that of English text.

This lead has been picked up a few times. These writeups (example) present indications that the message is indeed an initialism. However, they don’t apply what is arguably the clear statistical tool for this job. And they don’t take advantage of big data. So, let’s do both.

Read on for Chi Square testing and book parsing examples using Spark.  Spoiler alert:  Sean doesn’t solve the mystery, but it’s still a fun read.

Comments closed

Chi Square Tests

Mala Mahadevan discusses how to perform a Chi Square test:

For any dataset to lend itself to the Chi Square test it has to fit the following conditions  –

1 Both  variables are categorical (in this case – exposure to smoking – yes/no, and health condition – sick/not sick are both categorical).
2 Researchers used a random sample to collect data.
3 Researchers had an adequate sample size.Generally the sample size should be at least 100.
4 The number of respondents in each cell should be at least 5.

This is an easy case for using R over T-SQL—the Chi Square test is built in, whereas you have to roll your own T-SQL code.  Mala does show you how to do this from within SQL Server R Services as well.

Comments closed

Graphing Customer Churn

Fang Zhou and Wee Hyong Tok have released a case study on a telephone company’s customer churn:

In the case of telco customer churn, we collected a combination of the call detail record data and customer profile data from a mobile carrier, and then followed the data science process —  data exploration and visualization, data pre-processing and feature engineering, model training, scoring and evaluation — in order to achieve the churn prediction. With a churn indicator in the dataset taking value 1 when the customer is churned and taking value 0 when the customer is non-churned, we addressed the problem as a binary classification problem and tried varioustree-based models along with methods like bagging, random forests and boosting. Because the number of churned customers is much less than that of non-churned customers (making the data set quite unbalanced), SMOTE (Synthetic Minority Oversampling Technique) was applied to adjust the proportion of majority class over minority class in the training data set, thus further improving model performance, especially precision and recall.

All the above data science procedures could be implemented with base R. Rather than moving the data out from the database to an external machine running R, we instead run R scripts directly on SQL Server data by leveraging the in-database analytics capability provided by SQL Server R Services, taking advantage of the rich and powerful CRAN R packages plus the parallel external memory algorithms in the RevoScaleR library. In what follows, we will describe the specific R packages and algorithms that we used to implement the data science solution for predicting telco customer churn.

They have provided the relevant materials in GitHub as well.

Comments closed

Not Catching Them All

Hanjo Odendaal explains clustering techniques using Pokemon:

To collect the data on all the first generation pokemon, I employ Hadley Wickam’s rvest package. I find it very intuitive and can handle all of my needs in collecting and extracting the data from a pokemon wiki. I will grab all the Pokemon up until to Gen II, which constitutes 251 individuals. I did find the website structure a bit of a pain as each pokemon had very different looking web pages. But, with some manual hacking, I eventually got the data in a nice format.

This probably means a lot more to you if you grew up in front of a Game Boy, but there’s some good technique in here regardless.

Comments closed

Analytic Tool Usage

Alex Woodie notes the increased popularity of Python for data analysis:

According to the results of the 2016 survey, R is the preferred tool for 42% of analytics professionals, followed by SAS at 39% and Python at 20%. While Python’s placing may at first appear to relegate the language to Bronze Medal status, it’s the delta here that really matters.

It’s interesting to see the breakdowns of who uses which language, comparing across industry, education, work experience, and geographic lines.

Comments closed

Markov Chains

Sergey Bryl has an introductory-level post on what Markov chains are and how they work:

Using Markov chains allow us to switch from heuristic models to probabilistic ones. We can represent every customer journey (sequence of channels/touchpoints) as a chain in a directed Markov graph where each vertex is a possible state (channel/touchpoint) and the edges represent the probability of transition between the states (including conversion.) By computing the model and estimating transition probabilities we can attribute every channel/touchpoint.

Let’s start with a simple example of the first-order or “memory-free” Markov graph for better understanding the concept. It is called “memory-free” because the probability of reaching one state depends only on the previous state visited.

Markov chains are great for behavior prediction and sentence formation.  This is part one of a series I will eagerly anticipate.  H/T R Bloggers.

Comments closed

Understanding ROC Curves

Bob Horton explains ROC curves and shows how to create them in R:

ROC curves are commonly used to characterize the sensitivity/specificity tradeoffs for a binary classifier. Most machine learning classifiers produce real-valued scores that correspond with the strength of the prediction that a given case is positive. Turning these real-valued scores into yes or no predictions requires setting a threshold; cases with scores above the threshold are classified as positive, and cases with scores below the threshold are predicted to be negative. Different threshold values give different levels of sensitivity and specificity. A high threshold is more conservative about labelling a case as positive; this makes it less likely to produce false positive results but more likely to miss cases that are in fact positive (lower rate of true positives). A low threshold produces positive labels more liberally, so it is less specific (more false positives) but also more sensitive (more true positives). The ROC curve plots true positive rate against false positive rate, giving a picture of the whole spectrum of such tradeoffs.

ROC curves are one of the primary techniques for figuring out if a binary classifier “works.”

Comments closed

SQL Saturday Attendee Distances

I have a long, long post on figuring out how far SQL Saturday attendees tend to drive:

Before I begin, allow me to perform the data science Airing of Grievances.  This is an important part of data analysis which most people gloss over, instead jumping right into the “clean up the dirty data” phase.  But no, let’s revel in its filth for just a few moments.

Despite my protestations and complaints, I think there are some reasonable conclusions.  If you need to look like you’re working for a couple of hours (or at least want to play around a bit with SQL and R), this is the post for you.

Comments closed

Intro To Data Analytics

Stacia Varga has a follow-up to her Gentle Introduction to Data Analytics:

Q: How is data analytics on SAS different from R support for SQL2016?

A: I’ve not used SAS (although I did go to their campus to teach MDX to their engineers once upon a time… beautiful campus!), so I can’t say with any specificity. SAS also has multiple products so it would be difficult to describe differences. In general – and please understand there may be something new in SAS that I don’t know about – I think the difference is that R in SQL 2016 allows you to run functions on data inside the database, thereby leveraging database resources and also server resources for parallelization. I’d love to get input from readers to expand on this topic.

I can confirm that SAS has a beautiful campus.

Comments closed