Book Image

Data Science Algorithms in a Week

By : Dávid Natingga

Book Image

Data Science Algorithms in a Week

By: Dávid Natingga

Overview of this book

<p>Machine learning applications are highly automated and self-modifying, and they continue to improve over time with minimal human intervention as they learn with more data. To address the complex nature of various real-world data problems, specialized machine learning algorithms have been developed that solve these problems perfectly. Data science helps you gain new knowledge from existing data through algorithmic and statistical analysis.</p> <p>This book will address the problems related to accurate and efficient data classification and prediction. Over the course of 7 days, you will be introduced to seven algorithms, along with exercises that will help you learn different aspects of machine learning. You will see how to pre-cluster your data to optimize and classify it for large datasets. You will then find out how to predict data based on the existing trends in your datasets.</p> <p>This book covers algorithms such as: k-Nearest Neighbors, Naive Bayes, Decision Trees, Random Forest, k-Means, Regression, and Time-series. On completion of the book, you will understand which machine learning algorithm to pick for clustering, classification, or regression and which is best suited for your problem.</p>

Preface

What this book covers

What you need for this book

Who this book is for

Reader feedback

Customer support

Free Chapter

Classification Using K Nearest Neighbors

Classification Using K Nearest Neighbors

Mary and her temperature preferences

Implementation of k-nearest neighbors algorithm

Map of Italy example - choosing the value of k

House ownership - data rescaling

Text classification - using non-Euclidean distances

Text classification - k-NN in higher-dimensions

Naive Bayes

Medical test - basic application of Bayes' theorem

Proof of Bayes' theorem and its extension

Playing chess - independent events

Implementation of naive Bayes classifier

Playing chess - dependent events

Gender classification - Bayes for continuous random variables

Decision Trees

Swim preference - representing data with decision tree

Information theory

ID3 algorithm - decision tree construction

Classifying with a decision tree

Playing chess - analysis with decision tree

Going shopping - dealing with data inconsistency

Random Forest

Overview of random forest algorithm

Swim preference - analysis with random forest

Implementation of random forest algorithm

Playing chess example

Going shopping - overcoming data inconsistency with randomness and measuring the level of confidence

Clustering into K Clusters

Clustering into K Clusters

Household incomes - clustering into k clusters

Gender classification - clustering to classify

Implementation of the k-means clustering algorithm

House ownership – choosing the number of clusters

Document clustering – understanding the number of clusters k in a semantic context

Regression

Fahrenheit and Celsius conversion - linear regression on perfect data

Weight prediction from height - linear regression on real-world data

Gradient descent algorithm and its implementation

Flight time duration prediction from distance

Ballistic flight analysis – non-linear model

Time Series Analysis

Time Series Analysis

Business profit - analysis of the trend

Electronics shop's sales - analysis of seasonality

Statistics

Bayesian Inference

Cross-validation

R Reference

Linear regression

Python Reference

Python Reference

Glossary of Algorithms and Methods in Data Science

Glossary of Algorithms and Methods in Data Science

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Summary

We can think of variables as being dependent on each other in a functional way. For example, the variable y is a function of x denoted by y=f(x). The function f(x) has constant parameters. For example, if y depends on x linearly, then f(x)=a*x+b, where a and b are constant parameters in the function f(x). Regression is a method to estimate these constant parameters in such a way that the estimated f(x) follows y as closely as possible. This is formally measured by the squared error between f(x) and y for the data samples x.

The gradient descent method minimizes this error by updating the constant parameters in the direction of the steepest descent (that is, the partial derivative of the error), ensuring that the parameters converge to the values resulting in the minimal error in the quickest possible way.

The statistical software R supports the estimation of the linear...