Chapter 1, Preparing the Data, covers the process of reading and writing from and to various data formats and databases, as well as cleaning the data using OpenRefine and Python.

Chapter 2, Exploring the Data, describes various techniques that aid in understanding the data. We will see how to calculate distributions of variables and correlations between them and produce some informative charts.

Chapter 3, Classification Techniques, introduces several classification techniques, from simple Naïve Bayes classifiers to more sophisticated Neural Networks and Random Tree Forests.

Chapter 4, Clustering Techniques, explains numerous clustering models; we start with the most common k-means method and finish with more advanced BIRCH and DBSCAN models.

Chapter 5, Reducing Dimensions, presents multiple dimensionality reduction techniques, starting with the most renowned PCA, through its kernel and randomized versions, to LDA.

Chapter 6, Regression Methods, covers many regression models, both linear and nonlinear. We also bring back random forests and SVMs (among others) as these can be used to solve either classification or regression problems.

Chapter 7, Time Series Techniques, explores the methods of handling and understanding time series data as well as building ARMA and ARIMA models.

Chapter 8, Graphs, introduces NetworkX and Gephi to handle, understand, visualize, and analyze data in the form of graphs.

Chapter 9, Natural Language Processing, describes various techniques related to the analytics of free-flow text: part-of-speech tagging, topic extraction, and classification of data in textual form.

Chapter 10, Discrete Choice Models, explains the choice modeling theory and some of the most popular models: the Multinomial, Nested, and Mixed Logit models.

Chapter 11, Simulations, covers the concepts of agent-based simulations; we simulate the functioning of a gas station, out-of-power occurrences for electric vehicles, and sheep-wolf predation scenarios.

For this book, you need a personal computer (it can be a Windows machine, Mac, or Linux) with an installed and configured Python 3.5 environment; we use the Anaconda distribution of Python that can be downloaded at https://www.continuum.io/downloads.

Throughout this book, we use various Python modules: pandas, NumPy/SciPy, SciKit-Learn, MLPY, StatsModels, PyBrain, NLTK, BeautifulSoup, Optunity, Matplotlib, Seaborn, Bokeh, PyLab, OpenPyXl, PyMongo, SQLAlchemy, NetworkX, and SimPy. Most of the modules used come preinstalled with Anaconda, but some of them need to be installed via either the conda installer or by downloading the module and using the python setup.py install command. It is fine if some of those modules are not currently installed on your machine; we will guide you through the installation process.

We also use several non-Python tools: OpenRefine to aid in data cleansing and analysis, D3.js to visualize data, Postgres and MongoDB databases to store data, Gephi to visualize graphs, and PythonBiogeme to estimate discrete choice models. We will provide detailed installation instructions where needed.

This book is for everyone who wants to get into the data science field and needs to build up their skills on a set of examples that aim to tackle the problems faced in the corporate world. More advanced practitioners might also find some of the examples refreshing and the more advanced topics covered interesting.

In this book, you will find several headings that appear frequently (Getting ready, How to do it, How it works, There's more, and See also).

To give clear instructions on how to complete a recipe, we use these sections as follows:

In this book, you will find a number of text styles that distinguish between different kinds of information. Here are some examples of these styles and an explanation of their meaning.

Code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles are shown as follows: "We can include other contexts through the use of the include directive."

A block of code is set as follows:

for p in all_disputed_transactions:
    try:
        transactions[p[0]].append(p[2]['amount'])
    except:
        transactions[p[0]] = [p[2]['amount']]

Any command-line input or output is written as follows:

cd networkx
python setup.py install

New terms and important words are shown in bold. Words that you see on the screen, for example, in menus or dialog boxes, appear in the text like this: "We start with using Range on the age filter."

Feedback from our readers is always welcome. Let us know what you think about this book—what you liked or disliked. Reader feedback is important for us as it helps us develop titles that you will really get the most out of.

To send us general feedback, simply e-mail <[email protected]>, and mention the book's title in the subject of your message.

If there is a topic that you have expertise in and you are interested in either writing or contributing to a book, see our author guide at www.packtpub.com/authors.

Now that you are the proud owner of a Packt book, we have a number of things to help you to get the most from your purchase.