Cover......Page 1
Copyright......Page 3
Credits......Page 4
Foreword......Page 6
About the Author......Page 8
Acknowledgments......Page 9
About the Reviewers......Page 10
www.PacktPub.com......Page 11
Table of Contents......Page 12
Preface......Page 16
Objective......Page 22
Different areas where machine learning is being used......Page 23
Why use F#?......Page 24
Training and test dataset/corpus......Page 26
Some motivating real life examples of supervised learning......Page 27
Distance metrics......Page 28
Decision tree algorithms......Page 29
Unsupervised learning......Page 34
Machine learning for fun and profit......Page 36
Recognizing handwritten digits โ your "Hello World" ML program......Page 37
How does this work?......Page 41
Summary......Page 43
Different types of linear regression algorithms......Page 44
Math.NET Numerics for F# 3.7.0......Page 45
The basics of matrices and vectors (a short and sweet refresher)......Page 46
Creating a matrix......Page 47
Finding the inverse of a matrix......Page 49
QR decomposition of a matrix......Page 50
SVD of a matrix......Page 51
Linear regression method of least square......Page 53
Finding linear regression coefficients using F#......Page 54
Putting it together with Math.NET and FsPlot......Page 61
Multiple linear regression......Page 63
Multiple linear regression and variations using Math.NET......Page 65
Weighted linear regression......Page 66
Plotting the result of multiple linear regression......Page 68
Ridge regression......Page 70
Multivariate multiple linear regression......Page 71
Feature scaling......Page 73
Summary......Page 74
Objective......Page 76
Binary classification using k-NN......Page 77
Finding cancerous cells using k-NN: a case study......Page 81
Understanding logistic regression......Page 84
The sigmoid function chart......Page 85
Binary classification using logistic regression (using Accord.NET)......Page 88
Multiclass classification using logistic regression......Page 90
Multiclass classification using decision trees......Page 94
Obtaining and using WekaSharp......Page 95
How does it work?......Page 97
Predicting a traffic jam using a decision tree: a case study......Page 98
Summary......Page 101
Different IR algorithms you will learn......Page 102
Information retrieval using tf-idf......Page 103
Generating a PDF from a histogram......Page 105
Minkowski family......Page 107
L1 family......Page 108
Intersection family......Page 110
Inner Product family......Page 113
Fidelity family or squared-chord family......Page 115
Squared L2 family......Page 117
Shannon's Entropy family......Page 120
Similarity of asymmetric binary attributes......Page 124
Finding similar cookies using asymmetric binary similarity measures......Page 129
Grouping/clustering color images based on Canberra distance......Page 131
Summary......Page 132
Different classification algorithms you will learn......Page 134
Baseline predictors......Page 135
Basis of User-User collaborative filtering......Page 137
Implementing basic user-user collaborative filtering using F#......Page 140
Code walkthrough......Page 142
Variations of gap calculations and similarity measures......Page 144
Item-item collaborative filtering......Page 146
Evaluating recommendations......Page 149
Prediction accuracy......Page 150
Confusion matrix (decision support)......Page 151
Prediction-rating correlation......Page 155
Working with real movie review data (Movie Lens)......Page 156
Summary......Page 157
Objective......Page 158
A baseline algorithm for SA using SentiWordNet lexicons......Page 159
Handling negations......Page 162
Identifying praise or criticism with sentiment orientation......Page 166
Pointwise Mutual Information......Page 167
Using SO-PMI to find sentiment analysis......Page 168
Summary......Page 170
Different classification algorithms......Page 172
The different types of anomalies......Page 173
Detecting point anomalies using IQR (Interquartile Range)......Page 175
Detecting point anomalies using Grubb's test......Page 176
Grubb's test for multivariate data using Mahalanobis distance......Page 178
Chi-squared statistic to determine anomalies......Page 180
Detecting anomalies using density estimation......Page 181
Strategy to convert a collective anomaly to a point anomaly problem......Page 183
Dealing with categorical data in collective anomalies......Page 184
Summary......Page 185
Index......Page 186