Chapter 1, Getting Started with Predictive Modelling, talks about aspects, scope, and applications of predictive modelling. It also discusses various Python packages commonly used in data science, Python IDEs, and the methods to install these on systems.

Chapter 2, Data Cleaning, describes the process of reading a dataset, getting a bird's eye view of the dataset, handling the missing values in the dataset, and exploring the dataset with basic plotting using the pandas and matplotlib packages in Python. The data cleaning and wrangling together constitutes around 80% of the modelling time.

Chapter 3, Data Wrangling, describes the methods to subset a dataset, concatenate or merge two or more datasets, group the dataset by categorical variables, split the dataset into training and testing sets, generate dummy datasets using random numbers, and create simulations using random numbers.

Chapter 4, Statistical Concepts for Predictive Modelling, explains the basic statistics needed to make sense of the model parameters resulting from the predictive models. This chapter deals with concepts like hypothesis testing, z-tests, t-tests, chi-square tests, p-values, and so on followed by a discussion on correlation.

Chapter 5, Linear Regression with Python, starts with a discussion on the mathematics behind the linear regression validating the mathematics behind it using a simulated dataset. It is then followed by a summary of implications and interpretations of various model parameters. The chapter also describes methods to implement linear regression using the stasmodel.api and scikit-learn packages and handling various related contingencies, such as multiple regression, multi-collinearity, handling categorical variables, non-linear relationships between predictor and target variables, handling outliers, and so on.

Chapter 6, Logistic Regression with Python, explains the concepts, such as odds ratio, conditional probability, and contingency tables leading ultimately to detailed discussion on mathematics behind the logistic regression model (using a code that implements the entire model from scratch) and various tests to check the efficiency of the model. The chapter also describes the methods to implement logistic regression in Python and drawing and understanding an ROC curve.

Chapter 7, Clustering with Python, discusses the concepts, such as distances, the distance matrix, and linkage methods to understand the mathematics and logic behind both hierarchical and k-means clustering. The chapter also describes the methods to implement both the types of clustering in Python and methods to fine tune the number of clusters.

Chapter 8, Trees and Random Forests with Python, starts with a discussion on topics, such as entropy, information gain, gini index, and so on. To illustrate the mathematics behind creating a decision tree followed by a discussion on methods to handle variations, such as a continuous numerical variable as a predictor variable and handling a missing value. This is followed by methods to implement the decision tree in Python. The chapter also gives a glimpse into understanding and implementing the regression tree and random forests.

Chapter 9, Best Practices for Predictive Modelling, entails the best practices to be followed in terms of coding, data handling, algorithms, statistics, and business context for getting good results in predictive modelling.

Appendix, A List of Links, contains a list of sources which have been directly or indirectly consulted or used in the book. It also contains the link to the folder which contains datasets used in the book.

In order to make the best use of this book, you will require the following:

If you wish to learn the implementation of predictive analytics algorithms using Python libraries, then this is the book for you. If you are familiar with coding in Python (or some other programming/statistical/scripting language) but have never used or read about predictive analytics algorithms, this book will also help you. The book will be beneficial to and can be read by any data science enthusiasts. Some familiarity with Python will be useful to get the most out of this book but it is certainly not a pre-requisite.

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

A typical code snippet would look as follows:

def closest_station(lat, longi):
    stations = np.array([[41.995, -87.933],
                         [41.786, -87.752]])
    loc = np.array([lat, longi])
    deltas = stations - loc[None, :]
    dist2 = (deltas**2).sum(1)
    return np.argmin(dist2)

The outputs of the code snippets are generally shown as the screenshots. This is how a screenshot looks:

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: "The plot of Monthly Income and Monthly Expense for a group of 400 people."

URLs are shown as below:

https://pypi.python.org/pypi/pip

A lot of tables have been used to summarize the results of mathematical discussions and illustrate certain concepts.

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

To send us general feedback, simply send an e-mail to <[email protected]>, and mention the book title via 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 on 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.