Book Image

Clojure for Data Science

By : Garner
Book Image

Clojure for Data Science

By: Garner

Overview of this book

The term “data science” has been widely used to define this new profession that is expected to interpret vast datasets and translate them to improved decision-making and performance. Clojure is a powerful language that combines the interactivity of a scripting language with the speed of a compiled language. Together with its rich ecosystem of native libraries and an extremely simple and consistent functional approach to data manipulation, which maps closely to mathematical formula, it is an ideal, practical, and flexible language to meet a data scientist’s diverse needs. Taking you on a journey from simple summary statistics to sophisticated machine learning algorithms, this book shows how the Clojure programming language can be used to derive insights from data. Data scientists often forge a novel path, and you’ll see how to make use of Clojure’s Java interoperability capabilities to access libraries such as Mahout and Mllib for which Clojure wrappers don’t yet exist. Even seasoned Clojure developers will develop a deeper appreciation for their language’s flexibility! You’ll learn how to apply statistical thinking to your own data and use Clojure to explore, analyze, and visualize it in a technically and statistically robust way. You can also use Incanter for local data processing and ClojureScript to present interactive visualisations and understand how distributed platforms such as Hadoop sand Spark’s MapReduce and GraphX’s BSP solve the challenges of data analysis at scale, and how to explain algorithms using those programming models. Above all, by following the explanations in this book, you’ll learn not just how to be effective using the current state-of-the-art methods in data science, but why such methods work so that you can continue to be productive as the field evolves into the future.
Table of Contents (12 chapters)
11
Index

Visualizing the Russian election data

We previously saw that a histogram of the UK election turnout was approximately normal (albeit with light tails). Now that we've loaded and transformed the Russian election data, let's see how it compares:

(defn ex-1-30 []
  (-> (i/$ :turnout (load-data :ru-victors))
      (c/histogram :x-label "Russia turnout"
                   :nbins 20)
      (i/view)))

The preceding example generates the following histogram:

Visualizing the Russian election data

This histogram doesn't look at all like the classic bell-shaped curves we've seen so far. There's a pronounced positive skew, and the voter turnout actually increases from 80 percent towards 100 percent—the opposite of what we would expect from normally-distributed data.

Given the expectations set by the UK data and by the central limit theorem, this is a curious result. Let's visualize the data with a Q-Q plot instead:

(defn ex-1-31 []
  (->> (load-data :ru-victors)
       (i/$ :turnout)
       (c/qq-plot)
       (i/view)))

This returns the following plot:

Visualizing the Russian election data

This Q-Q plot is neither a straight line nor a particularly S-shaped curve. In fact, the Q-Q plot suggests a light tail at the top end of the distribution and a heavy tail at the bottom. This is almost the opposite of what we see on the histogram, which clearly indicates an extremely heavy right tail.

In fact, it's precisely because the tail is so heavy that the Q-Q plot is misleading: the density of points between 0.5 and 1.0 on the histogram suggests that the peak should be around 0.7 with a right tail continuing beyond 1.0. It's clearly illogical that we would have a percentage exceeding 100 percent but the Q-Q plot doesn't account for this (it doesn't know we're plotting percentages), so the sudden absence of data beyond 1.0 is interpreted as a clipped right tail.

Given the central limit theorem, and what we've observed with the UK election data, the tendency towards 100 percent voter turnout is curious. Let's compare the UK and Russia datasets side-by-side.