Fr

F#, the functional first programming language, enables

developers to write simple code to solve complex problems.
With F#, developers create consistent and predictable
programs that are easier to test and reuse, simpler
to parallelize, and less prone to bugs.
This book aims to democratize machine learning concepts
for all C# and F# developers.
Starting with an introduction to the various categories on
machine learning, you will quickly learn how the different
types of learning algorithms work. You will gradually
move on to understanding and implementing supervised
learning algorithms, which forms the crux of the book.
The book then focuses the applied aspects of machine
learning and covers how to integrate .NET libraries such as
WekaSharp, Accord.Net, and Math.Net. You will also learn
to build a recommender system for your e-commerce site
from scratch. Finally, you will dive into advanced topics
such as performing sentiment analysis and implementing
anomaly detection algorithms in F#.

If you are a C# or F# developer who now wants to explore

the area of machine learning, then this book is for you.
No prior knowledge of machine learning is assumed.

Build a set of classification systems using

Accord.NET, WekaSharp, and F#
Gain an understanding of how anomaly
detection algorithms work
Perform mathematical operations on
matrices and vectors using Math.NET
Use a recommender system for your
own domain
Figure out techniques to find symmetric
and asymmetric similarity measures among
several entities and learn how to use them
Categorize a real-world problem as a
machine learning problem of a given kind,
such as supervised, clustering, and more

$ 39.99 US
25.99 UK

community experience distilled

P U B L I S H I N G

Prices do not include

local sales tax or VAT
where applicable

Visit www.PacktPub.com for books, eBooks,

code, downloads, and PacktLib.

Sudipta Mukherjee

Who this book is written for

What you will learn from this book

F# for Machine Learning Essentials

F# for Machine Learning

Essentials

ee

Sa
m

pl

C o m m u n i t y

E x p e r i e n c e

D i s t i l l e d

F# for Machine Learning

Essentials
Get up and running with machine learning with F# in a fun and
functional way
Foreword by Dr. Ralf Herbrich, Director of Machine Learning Science at Amazon

Sudipta Mukherjee

In this package, you will find:

The author biography

A preview chapter from the book, Chapter 1 'Introduction to
Machine Learning'
A synopsis of the books content
More information on F# for Machine Learning Essentials

About the Author

Sudipta Mukherjee was born in Kolkata and migrated to Bangalore. He is an

electronics engineer by education and a computer engineer/scientist by profession

and passion. He graduated in 2004 with a degree in electronics and communication
engineering.
He has a keen interest in data structure, algorithms, text processing, natural language
processing tools development, programming languages, and machine learning at
large. His first book on Data Structure using C has been received quite well. Parts
of the book can be read on Google Books at http://goo.gl/pttSh. The book was
also translated into simplified Chinese, available from Amazon.cn at http://goo.
gl/lc536. This is Sudipta's second book with Packt Publishing. His first book,
.NET 4.0 Generics (http://goo.gl/MN18ce), was also received very well. During
the last few years, he has been hooked to the functional programming style. His
book on functional programming, Thinking in LINQ (http://goo.gl/hm0lNF), was
released last year. Last year, he also gave a talk at @FuConf based on his LINQ book
(https://goo.gl/umdxIX). He lives in Bangalore with his wife and son.
Sudipta can be reached via e-mail at [email protected] and via Twitter at

@samthecoder.

Preface
Machine learning (ML) is more prevalent now than ever before. Every day a lot of
data is being generated. Machine learning algorithms perform heavy duty number
crunching to improve our lives every day. The following image captures the major
tasks that machine learning algorithms perform. These are the classes or types of
problems that ML algorithms solve.

Our lives are more and more driven by the output of these ML algorithms than we
care to admit. Let me walk you through the image once:

Computers everywhere: Now your smartphone can beat a vintage

supercomputer, and computer are everywhere: in your phone,
camera, car, microwave, and so on.

Clustering: Clustering is the task of identifying groups of items from a given

list that seem to be similar to the others in the group. Clustering has many
diverse uses. However, it is heavily used in market segment analysis to
identify different categories of customers.

Preface

Classification: This is the ML algorithm that works hard to keep your spam
e-mails away from your priority inbox. The same algorithm can be used to
identify objects from images or videos and surprisingly, the same algorithm
can be used to predict whether a patient has cancer or not. Generally, a lot of
data is provided to the algorithm, from which it learns. That's why this set
of algorithms is sometime referred to as supervised learning algorithms,
and this constitutes the vast majority of machine learning algorithms.

Predictions: There are several ML algorithms that perform predictions for

several situations that are important in life. For example, there are predictors
that predict fuel price in the near future. This family of algorithms is known
as regressions.

Anomaly detection: Anomaly, as the name suggests, relates to items that

have attributes that are not similar to normal ones. Anomaly detection
algorithms use statistical methods to find out the anomalous items from
a given list automatically. This is an example of unsupervised learning.
Anomaly detection has several diverse uses, such as finding faulty items in
factories to finding intruders on a video stream coming from a surveillance
camera, and so on.

Recommendations: Every time you visit Amazon and rate a product, the site
recommends some items to you. Under the hood is a clever machine learning
algorithm in action called collaborative filtering, which takes cues from other
users purchasing similar items as you are. Recommender systems are a very
active research topic now and several other algorithms are being considered.

Sentiment analysis: Whenever a product hits the market, the company that
brought it into the market wants to know how the market is reacting towards
it. Is it positive or negative? Sentiment analysis techniques help to identify
these reactions. Also, in review websites, people post several comments,
and the website might be interested in publishing a generalized positive
or negative rating for the item under review. Here, sentiment analysis
techniques can be quite helpful.

Information retrieval: Whenever you hit the search button on your favorite
search engine, a plethora of information retrieval algorithms are used under
the hood. These algorithms are also used in the content-based filtering that is
used in recommender systems.

Preface

Now that you have a top-level idea of what ML algorithms can do for you, let's see
why F# is the perfect fit for the implementations. Here are my reasons for using F#
to implement machine learning algorithms:

What this book covers

Chapter 1, Introduction to Machine Learning, introduces machine learning concepts.
Chapter 2, Linear Regression, introduces and implements several linear regression
models using F#.
Chapter 3, Classification Techniques, introduces classification as a formal problem and
then solves some use cases using F#.
Chapter 4, Information Retrieval, provides implementations of several information
retrieval distance metrics that can be useful in several situations.
Chapter 5, Collaborative Filtering, explains the workhorse algorithm for recommender
systems, provides an implementation using F#, and then shows how to evaluate
such a system.
Chapter 6, Sentiment Analysis, explains sentiment analysis and after positioning it as a
formal problem statement, solves it using several state-of-the-art algorithms.
Chapter 7, Anomaly Detection, explains and poses the anomaly detection problem
statement and then gives several algorithms and their implementation in F#.

Introduction to Machine
Learning
"To learn is to discover patterns."
You have been using products that employ machine learning, but maybe you've
never realized that the systems or programs that you have been using, use machine
learning under the hood. Most of what machine learning does today is inspired by
sci-fi movies. Machine learning scientists and researchers are on a perpetual quest
to make the gap between the sci-fi movies and the reality disappear. Learning about
machine learning algorithms can be fun.
This is going to be a very practical book about machine learning. Throughout the
book I will be using several machine learning frameworks adopted by the industry.
So I will cut the theory of machine learning short and will get away with just enough
to implement it. My objective in this chapter is to get you excited about machine
learning by showing how you can use these techniques to solve real world problems.

Objective
After reading this chapter, you will be able to understand the different terminologies
used in machine learning and the process of performing machine learning activities.
Also, you will be able to look at a problem statement and immediately identify which
problem domain the problem belongs to; whether it is a classification or a regression
problem, and such. You will find connections between seemingly disparate sets of
problems. You will also find basic intuition behind some of the major algorithms
used in machine learning today. Finally, I wrap up this chapter with a motivating
example of identifying hand written digits using a supervised learning algorithm.
This is analogous to your Hello world program.
[1]

Introduction to Machine Learning

Getting in touch
I have created the following Twitter account for you (my dear reader) to get in touch
with me. If you want to ask a question, post errata, or just have a suggestion, tag this
twitter ID and I will surely get back as soon as I can.
https://twitter.com/fsharpforml

I will post contents here that will augment the content in the book.

Different areas where machine learning is

being used

The preceding image shows some of the areas where machine learning techniques
are used extensively. In this book, you will learn about most of these usages.
Machines learn almost the same way as we humans do. We learn in three different
ways.
As kids our parents taught us the alphabets and thus we can distinguish between the
A's and H's. The same is true with machines. Machines are also taught the same way
to recognize characters. This is known as supervised learning.
While growing up, we taught ourselves the differences between the teddy bear toy
and an actual bear. This is known as unsupervised learning, because there is no
supervision required in the process of the learning. The main type of unsupervised
learning is called clustering; that's the art of finding groups in unlabeled datasets.
Clustering has several applications, one of them being customer base segmentation.

[2]

Chapter 1

Remember those days when you first learnt how to take the stairs? You probably
fell many times before successfully taking the stairs. However, each time you fell,
you learnt something useful that helped you later. So your learning got re-enforced
every time you fell. This process is known as reinforcement learning. Ever saw
those funky robots crawling uneven terrains like humans. That's the result of
re-enforcement learning. This is a very active topic of research.
Whenever you shop online at Amazon or on other sites, the site recommends back
to you other stuff that you might be interested in. This is done by a set of algorithms
known as recommender systems.
Machine learning is very heavily used to determine whether suspicious credit
card transactions are fraudulent or not. The technique used is popularly known as
anomaly detection. Anomaly detection works on the assumption that most of the
entries are proper and that the entry that is far (also called an outlier) from the other
entries is probably fraudulent.
In the coming decade, machine learning is going to be very commonplace and it's
about time to democratize the machine learning techniques. In the next few sections,
I will give you a few examples where these different types of machine learning
algorithms are used to solve several problems.

Why use F#?

F# is an open source, functional-first, general purpose programming language and is
particularly suitable for developing mathematical models that are an integral part of
machine learning algorithm development.

[3]

Introduction to Machine Learning

Code written in F# is generally very expressive and is close to its actual algorithm
description. That's why you shall see more and more mathematically inclined
domains adopting F#.
At every stage of a machine learning activity, F# has a feature or an API to help.
Following are the major steps in a machine learning activity:
Major step in
machine learning
activity

How F# can help

Data Acquisition

F# type providers are great at it. (Refer to http://blogs.

msdn.com/b/dsyme/archive/2013/01/30/twelve-typeproviders-in-pictures.aspx)
F# can help you get the data from the following resources using F#
type providers:
Databases (SQL Server and such)
XML
CSV
JSON
World Bank
Cloud Storages
Hive

Data Scrubbing/
Data Cleansing

F# list comprehensions are perfect for this task.

Learning the
Model

WekaSharp is an F# wrapper on top of Weka to help with machine

learning tasks such as regression, clustering, and so on.

Deedle (http://bluemountaincapital.github.io/
Deedle/) is an API written in F#, primarily for exploratory data
analysis. This framework also has lot of features that can help in the
data cleansing phase.

Accord.NET is a massive framework for performing a very diverse

set of machine learning.
Data Visualization

F# charts are very interactive and intuitive to easily generate high

quality charts. Also, there are several APIs, such as FsPlot, that take
the pain of conforming to standards when it comes to plugging data
to visualization.

F# has a way to name a variable the way you want if you wrap it with double back
quotes like"my variable". This feature can make the code much more readable.

[4]

Chapter 1

Supervised machine learning

Supervised machine learning algorithms are mostly broadly classified into two major
categories: classification and regression.
Supervised machine learning algorithms work with labeled datasets. This means that
the algorithm takes a lot of labeled data sets, where the data represents the instance
and the label represents the class of the data. Sometimes these labels are finite in
number and sometimes they are continuous numbers. When the labels belong to a
finite set, then the problem of identifying the label of an unknown/new instance is
known as a classification problem. On the other hand, if the label is a continuous
number, then the problem of finding the continuous value for a new instance is
known as a regression problem. Given a set of records for cancer patients, with
test results and labels (B for benign and M for malignant) predicting whether a new
patient's case is B or M, is a classification problem. On the other hand, predicting the
price of a house, given the area in square feet and the number of bedrooms in the
house, is an example of a regression problem.
I found the following analogy to geometry very useful when thinking about
these algorithms.
Let's say you have two points in 2D. You can calculate the Euclidean distance
between those two and if that distance is small, you can conclude that those points
are close to each other. In other words, if those two points represent two cities in a
country, you might conclude that they are in the same district.
Now if you extrapolate this theory to the N dimension, you can immediately see that
any measurement can be represented as a point with the N dimension or as a vector
of size N and a label can be associated with it. Then an algorithm can be deployed
to learn the associativity or the pattern, and thus it learns to predict the label for an
unseen/unknown/new instance represented in the similar format.

Training and test dataset/corpus

The phase when an algorithm runs over a labeled data set is known as training, and
the labeled data is known as training dataset. Sometimes it is loosely referred to as
training corpus. Later in the process, the algorithm must be tested with similar unlabeled datasets or for which the label is hidden from the algorithm. This dataset is
known as test dataset or test corpus. Typically, an 80-20 split is used to generate the
training and test set from a randomly shuffled labeled data set. This means that 80%
of the randomly shuffled labeled data is generally treated as training data and the
remaining 20% as test data.

[5]

Introduction to Machine Learning

Some motivating real life examples of supervised

learning
Supervised learning algorithms have several applications. Following are some of
those. This is by no means a comprehensive list, but it is indicative.

Classification

Spam filtering in your mailbox

Cancer prediction from the previous patient records

Identifying objects in images/videos

Identifying flowers from measurements

Identifying hand written digits on cheques

Predicting whether there will be a traffic jam in a city

Making recommendations to the users based on their and similar

user's preferences

Regression

Predicting the price of houses based on several features, such as the

number of bedrooms in the house

Finding cause-effect relationships between several variables

Supervised learning algorithms

Nearest Neighbor algorithm

Support Vector Machine

Decision Tree

Linear Regression

Logistic Regression

Nave Bayes Classifier

Neural Networks

Recommender systems algorithms

Anomaly Detection

Sentiment Analysis

In the next few sections, I will walk you through the overview of a few of these
algorithms and their mathematical basis. However, we will get away with as
minimal math as possible, since the objective of the book is to help you use
machine learning in the real settings.
[6]

Chapter 1

Nearest Neighbour algorithm (a.k.a k-NN algorithm)

As the name suggests, k-Nearest Neighbor is an algorithm that works on the
distance between two projected points. It relies on the distance of k-nearest
neighbors (thus the name) to determine the class/category of the unknown/new
test data.
As the name suggests the nearest neighbor algorithm relies on the distance of two
data points projected in N-Dimensional space. Let's take a popular example where
the k-NN can be used to determine the class. The dataset https://archive.ics.
uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.
data stores data about several patients who were either unfortunate and diagnosed as

"Malignant" cases (which are represented as M in the dataset), or were fortunate and
diagnosed as "Benign" (non-harmful/non-cancerous) cases (which are represented as
B in the dataset). If you want to understand what all the other fields mean, take a look
at https://archive.ics.uci.edu/ml/machine-learning-databases/breastcancer-wisconsin/wdbc.names.

Now the question is, given a new entry with all the other records except the tag
M or B, can we predict that? In ML terminology, this value "M" or "B" is sometimes
referred to as "class tag" or just "class". The task of a classification algorithm is to
determine this class for a new data point. K-NN does this in the following way: it
measures the distance from the given data to all the training data and then takes into
consideration the classes for only the k-nearest neighbors to determine the class of
the new entry. So for the current case, if more than 50% of the k-nearest neighbors
is of class "B", then k-NN will conclude that the new entry is of type "B".

Distance metrics
The distance metric used is generally Euclidean, that you learnt in high school. For
example, given two points in 3D.

d ( p, q ) =

( p1 q1 ) + ( p2 q2 ) + ( p3 q3 )
2

In this preceding example, p1 and q1 denote their values in the X axis, p2 and q2
denote their values in the Y axis, and p3 and q3 denote their values in the z axis.

[7]

Introduction to Machine Learning

Extrapolating this, we get the following formula for calculating the distance in N
dimension:

d ( p, q ) = d ( q , p ) =

( q1 p1 ) + ( q2 p2 )
2

(q p )
i

+  + ( qn pn )

i =1

Thus, after calculating the distance from all the training set data, we can create a list
of tuples with the distance and the class, as follows. This list is made for the sake of
demonstration. This is not calculated from the actual data.
Distance from test/new data

Class/Tag/Category

0.34235

0.45343

1.34233

6.23433

66.3435

Let's assume that k is set to be 4. Now for each k, we take into consideration the class.
So for the first three entries, we found that the class is B and for the last one, it is M.
Since the number of B's is more than the number of M's, k-NN will conclude that the
new patient's data is of type B.

Decision tree algorithms

Have you ever played the game where you had to guess about a thing that your
friend had been thinking about by asking questions? And you were allowed to guess
only a certain number of times and had to get back to your friend with your answer
about what he/she could probably be thinking about.
The strategy to guess the correct answer is to start asking questions that segregate
the possible answer space as evenly as possible. For example, if your friend told you
that he/she had imagined about something, then probably the first question you
would like to ask him/her is that whether he/she is thinking about an animal or a
thing. That would broadly classify the answer space and then later you can ask more
direct/specific questions based on the answers previously provided by your friend.

[8]

Chapter 1

Decision tree is a set of classification algorithm that uses this approach to determine
the class of an unknown entry. As the name suggests, a decision tree is a tree where
the nodes depict the questions asked and the edges represent the decisions (yes/
no). Leaf nodes determine the final class of the unknown entry. Following is a classic
textbook example of a decision tree:

The preceding figure depicts the decision whether we can play lawn tennis or
not, based on several attributes such as Outlook, Humidity, and Wind. Now the
question that you may have is why outlook was chosen as the root node of the tree.
The reason was that by choosing outlook as the first feature/attribute to split the
dataset, the outcomes were split more evenly than if the split had been done with
other attributes such as "humidity" or "wind".
The process of finding the attribute that can split the dataset more evenly than others
is guided by entropy. Lesser the entropy, better the parameter. Entropy is known as
the measure of information gain. It is calculated by the following formula:

H ( X ) = P ( xi ) I ( xi ) = P ( xi ) log b P ( xi )
i

Here P ( xi ) stands for the probability of xi and I ( xi ) denotes the information gain.
Let's take the example of tennis dataset from Weka. Following is the file in the
CSV format:
outlook,temperature,humidity,wind,playTennis
sunny, hot, high, weak, no
sunny, hot, high, strong, no
overcast, hot, high, weak, yes
rain, mild, high, weak, yes
[9]

Introduction to Machine Learning

rain,cool, normal, weak, yes
rain, cool, normal, strong, no
overcast, cool, normal, strong, yes
sunny, mild, high, weak, no
sunny, cool, normal, weak, yes
rain, mild, normal, weak, yes
sunny, mild, normal, strong, yes
overcast, mild, high, strong, yes
overcast, hot, normal, weak, yes
rain, mild, high, strong, no

You can see from the dataset that out of 14 instances (there are 14 rows in the file), 5
instances had the value no for playTennis and 9 instances had the value yes. Thus,
the overall information is given by the following formula:

9 5
5
9
log 2 + log 2
14 14
14
14
This roughly evaluates to 0.94. Now from the next steps, we must pick the attribute
that maximizes the information gain. Information gain is denoted as the difference
between the total entropy and the entropy calculated for each possible split.
Let's go with one example. For the outlook attribute, there are three possible values:
rain, sunny, and overcast, and for each of these values, the value of the attribute
playTennis is either no or yes.
For rain, out of 5 instances, 3 instances have the value yes for the attribute
playTennis; thus, the entropy is as follows:

3 2
3
log 2 + log 2
5 5
5
This is equal to 0.97.
For overcast, every instance has the value yes:

4
4
log 2
4
4
This is equal to 0.0.

[ 10 ]

Chapter 1

For sunny, out of 5 instances, only 2 have the value yes:

2 3
3
2
log 2 + log 2
5 5
5
5
So the expected new entropy is given by the following formula:

4
5
5
0.0 + 0.97 + 0.97
14
14
14
This is roughly equal to 0.69. If you follow these steps for the other attributes, you
will find that the new entropies are like as follows:
Attribute

Entropy

Information gain

outlook

0.69

0.94 0.69 => 0.25

temperature

0.91

0.94 0.91 => 0.03

humidity

0.724

0.94 0.725 => 0.215

windy

0.87

0.94 0.87 => 0.07

So the highest information gain is attained if we split the dataset based on the
outlook attribute.
Sometimes multiple trees are constructed by generating a random subset of all the
available features. This technique is known as random forest.

Linear regression
Regression is used to predict the target value of the real valued variable. For
example, let's say we have data about the number of bedrooms and the total area
of many houses in a locality. We also have their prices listed as follows:
Number of Bedrooms

Total Area in square feet

Price

1150

2300000

2500

5600000

1780

4571030

3000

9000000

[ 11 ]

Introduction to Machine Learning

Now let's say we have this data in a real estate site's database and we want to create
a feature to predict the price of a new house with three bedrooms and total area
of 1650 square feet.
Linear regression is used to solve these types of problems. As you can see, these
types of problems are pretty common.
In linear regression, you start with a model where you represent the target variable
the variable for which you want to predict the value. A polynomial model is selected
that minimizes the least square error (this will be explained later in the chapter). Let
me walk you through this example.
Each row of the available data can be represented as a tuple where the first
few elements represent the value of the known/input parameters and the last
parameter shows the value of the price (the target variable). So taking inspiration
from mathematics, we can represent the unknown with x and known as y . Thus,

x , x , x , , x | y

n
each row can be represented as 1 2 3
where x1 to xn represent the
parameters (the total area and the number of bedrooms) and y represents the
target value (the price of the house). Linear regression works on a model where y is
represented with the x values.

The hypothesis is represented by an equation as the following. Here x1 and theta

denotes the input parameters (the number of bedrooms and the total area in square
feet) and h ( x ) represents the predicted value of the new house.

h ( x ) = 0 + 1 x1 + 2 x2
Note that this hypothesis is still a polynomial model and we are just using two
features: the number of bedrooms and the total area represented by x1 and x2 .
So the square error is calculated by the following formula:

(h ( x) y)

The task of linear regression is to choose a set of values for the coefficients
which minimizes this error. The algorithm that minimizes this error is called
gradient descent or batch gradient descent. You will learn more about it in
Chapter 2, Linear Regression.

[ 12 ]

Chapter 1

Logistic regression
Unlike linear regression, logistic regression predicts a Boolean value indicating
the class/tag/category of the target variable. Logistic regression is one of the most
popular binary classifiers and is modelled by the equation that follows. xi and

yi stands for the independent input variables and their classes/tags respectively.

Logistic regression is discussed at length in Chapter 3, Classification Techniques.

1 yi

i
1
1

1 + e xi 1 1 + e xi
i =1

Recommender systems
Whenever you buy something from the web (say Amazon), it recommends you stuff
that you might find interesting and might eventually buy as well. This is the result of
recommender system. Let's take the following example of a movie rating:
Movie

Bob

Lucy

Jane

Jennifer

Jacob

Paper Towns

Focus

Cinderella

Jurrasic World

Die Hard

So in this toy example, we have 5 users and they have rated 5 movies. But not all the
users have rated all the movies. For example, Jane hasn't rated "Focus" and Jacob
hasn't rated "Jurassic World". The task of a recommender system is to initially guess
what would be the ratings for the movies that aren't rated by the user and then
recommend movies that have a guessed rating which is beyond a threshold (say 3).
There are several algorithms to solve this problem. One popular algorithm is known
as collaborative filtering where the algorithm takes clues from the other user ratings.
You will learn more about this in Chapter 5, Collaborative Filtering.

Unsupervised learning
As the name suggests, unlike supervised learning, unsupervised learning works
on data that is not labeled or that doesn't have a category associated with each
training example.

[ 13 ]

Introduction to Machine Learning

Unsupervised learning is used to understand data segmentation based on a few

features of the data. For example, a supermarket might want to understand how
many different types of customers they have. For that, they can use the following
two features:

The number of visits per month (number of times the customer shows up)

The average bill amount

The initial data that the supermarket had might look like the following in a
spreadsheet:

So the data plotted in these 2 dimensions, after being clustered, might look like this
following image:

Here you see that there are 4 types of people with two extreme cases that have been
annotated in the preceding image. Those who are very thorough and disciplinarian
and know what they want, go to the store very few times and buy what they want,
and generally their bills are very high. The vast majority falls under the basket where
people make many trips (kind of like darting into a super market for a packet of
chips, maybe) but their bills are really low. This type of information is crucial for
the super market because they can optimize their operations based on these data.

[ 14 ]

Chapter 1

This type of segmenting task has a special name in machine learning. It is called
"clustering". There are several clustering algorithms and K Means Clustering
is quite popular. The only flip side of k Means Clustering is that the number of
possible clusters has to be told in the beginning.

Machine learning frameworks

I will be using the following machine learning frameworks to solve some of the real
problems throughout the book:

Accord.NET (http://accord-framework.net/)

WekaSharp (http://accord-framework.net/)

You are much better off using these frameworks than creating your own because a
lot of work has been done and they are used in the industry. So if you pick up using
these frameworks along the way while learning about machine learning algorithms
in general, that's a great thing. You will be in luck.

Machine learning for fun and profit

Machine learning requires a lot of data and most of the time you, as the developer
of an algorithm, will not have the time to synthesize or obtain good data. However,
you are in luck. Kaggle does that for you. Kaggle is a website where companies
host several machine learning problems and they provide training and test data
to test your algorithm. Some competitions are linked with employment. So if your
model stands out, you stand a chance to interview with the company that hosted
the competition. Here is a short list of companies that are using kaggle for their data
science/machine learning problems:

The next section gets you started with a kaggle competition; getting the data and
solving it.

[ 15 ]

Introduction to Machine Learning

Recognizing handwritten digits your

"Hello World" ML program
Handwritten digits can be recognized with k-nearest neighbor algorithm.
Each handwritten digit is written on a 28*28 matrix. So there are 28*28 -> 784 pixels
and each of these are represented as a single column of the dataset. Thus, the dataset
has 785 columns. The first column is the label/digit and the remaining 784 values are
the pixel values.
Following is a small example. Let's say, if we're to imagine this example as an 8 by
8 matrix, we would have something like the following figure for the digit 2:

A matrix can be represented as a 2-D array where each pixel is represented by each
cell. However, any 2-D array can be visually unwrapped to be a 1-D array where
the length of the array is the product of the length and the breadth of the array. For
example, for the 8 by 8 matrix, the size of the single dimensional array will be 64.
Now if we store several images and their 2D matrix representations, we will have
something as shown in the following spreadsheet:

The header Label denotes the number and the remaining values are the pixel values.
Lesser the pixel values, the darker the cell is in the pictorial representation of the
number 2, as shown previously.
In this program, you will write code to solve the digit recognizer challenge from
Kaggle, available at:
https://www.kaggle.com/c/digit-recognizer.

Once you get there, download the data and save it in some folder. We will be using the
train.csv file (You can get the file from www.kaggle.com/c/digit-recognizer/
data) for training our classifier. In this example, you will implement the k nearest
neighbor algorithm from scratch, and then deploy this algorithm to recognize the digit.

[ 16 ]

Chapter 1

For your convenience, I have pasted the code at https://gist.github.com/

sudipto80/72e6e56d07110baf4d4d.

Following are the steps to create the classifier:

1. Open Visual Studio 2013.
2. Create a new project:

3. Select F# and give a name for the console app:

[ 17 ]

Introduction to Machine Learning

4. Once you create the project by clicking "OK", your program.fs file will look
as the following image:

5. Add the following functions and types in your file:

[ 18 ]

Chapter 1

6. Finally, in the main method, add the following code:

[ 19 ]

Introduction to Machine Learning

When this program runs, it will produce the following output:

How does this work?

The distance function is based on the Euclidean distance function, as mentioned
earlier in the chapter. Now you see that a general purpose Euclidean distance
function is coded in the distance function. You might have noticed that there is a
small difference between the formula and the implementation. The implementation
finds the squared Euclidean distance given by the following formula:

d 2 ( p, q ) = ( p1 q1 ) + ( p2 q2 ) +  + ( pi qi ) +  + ( pn qn )
2

Here p and q denote the two vectors. In this case, p might denote one example
from the training set and q might denote the test example or the new uncategorized
data that we have depicted by newEntry in the preceding code.
The loadValues function loads the pixel values and the category for each training/
test data, and creates a list of Entry types from the CSV file.
The k-NN algorithm is implemented in the kNN function. Refer to the following line
of code:
|> List.map( fun x -> ( x.Label, distance
(newEntry) |>Array.toList )))

[ 20 ]

(x.Values, snd

Chapter 1

This preceding code creates a list of tuples where the first element is the category of
the entry and the second is the distance square value for the test data from each of
the training entry. So it might look as follows:

Now consider the following line:

|> List.sortBy ( fun x -> snd x)

It sorts this list of tuples based on the increasing distance from the test data. Thus,
the preceding list will become as shown in the following image:

If you see, there are four 9s and three 4s in this list. The following line transforms this
list into a histogram:
|> Seq.countBy (fun x -> fst x)

So if k is chosen to be 5, then we will have four 9s and one 4. Thus, k nearest

neighbor will conclude that the digit is probably a "9" since most of the nearest
neighbors are "9".
The drawDigit function draws the digit pixel by pixel and writes out the guessed
label for the digit. It does so by drawing each pixel on a tile size of 20.

[ 21 ]

Introduction to Machine Learning

Summary
In this chapter, you have learnt about several different types of machine learning
techniques and their possible usages. Try to spot probable machine learning
algorithms that might be deployed deep inside some applications. Following are
some examples of machine learning. Your mailbox is curated by an automatic
spam protector and it learns every time you move an e-mail from your inbox to the
spam folder. This is an example of a supervised classification algorithm. When you
apply for a health insurance, then based on several parameters, they (the insurance
company) try to fit your data and predict what premium you might have to pay.
This is an example of linear regression. Sometimes when people buy baby diapers at
supermarkets, they get a discount coupon for buying beer. Sounds crazy, right! But
the machine learning algorithm figured out that people who buy the diapers buy
beer too. So they want to provoke the users to buy more. There is lot of buzz right
now about predictive analytics. It is nothing but predicting an event in the future by
associating a probability score. For example, figuring out how long will a shopper
take to return to the store for her next purchase. These data are extracted from the
visit patterns. That's unsupervised learning working in the background.
Sometimes one simple algorithm doesn't provide the needed accuracy. So then
several methods are used and a special class of algorithm, known as Ensemble
method, is used to club the individual results. In loose terms, it kind of resonates
with the phrase "crowd-smart". You will learn about some ensemble methods in
a later chapter.
I want to wrap up this chapter with the following tip. When you have a problem that
you want to solve and you think machine learning can help, follow the following
steps. Break the problem into smaller chunks and then try to locate a class of machine
learning problem domain for this smaller problem. Then find the best method in
that class to solve. Iterate over and over until your error rates are within permissible
limits. And then wrap it in a nice application/user interface.

[ 22 ]

Get more information F# for Machine Learning Essentials

Where to buy this book

You can buy F# for Machine Learning Essentials from the Packt Publishing website.
Alternatively, you can buy the book from Amazon, BN.com, Computer Manuals and most internet
book retailers.
Click here for ordering and shipping details.

www.PacktPub.com

Stay Connected: