Machine Learning with Python

A Step-by-Step Guide to Learn and Master Python Machine Learning
Narrated by: William Bahl
Length: 1 hr and 40 mins
5 out of 5 stars (25 ratings)

Audible membership

$14.95 a month

Free with a 30-day trial
1 audiobook of your choice.
A monthly selection of Audible Originals.
$14.95 a month after 30 days. Cancel anytime.
Buy for $6.95

Buy for $6.95

Pay using card ending in
By confirming your purchase, you agree to Audible's Conditions of Use and Amazon's Privacy Notice. Taxes where applicable.

Publisher's Summary

Are you stuck in getting started with machine learning with Python? A Step-by-Step Guide to Learn and Master Python Machine Learning walks you through steps for getting started with machine learning with Python. 

Python is a popular and open-source programming language. In addition, it is one of the most applied languages in artificial intelligence and other scientific fields. On the other hand, machine learning is a branch of AI that applies algorithms to learn from data and create predictions. Machine learning is important in predicting the world around us. All the way from self-driving cars to predictions in the stock market, there is no place where machine learning cannot be utilized. 

Today, it is a top skill in high demand in the job market. For that reason, why not grab A Step-by-Step Guide to Learn and Master Python Machine Learning

You’ll discover the steps required to develop a successful machine-learning application using Python and Scikit-learn library. As a discipline, ML tries to design and understand computer programs for purpose of prediction. With A Step-by-Step Guide to Learn and Master Python Machine Learning, you’ll learn: 

  • The important concepts and real-world application of machine learning
  • Pros and cons of most popular machine-learning algorithms 
  • The basics of Python 
  • Learn about data preprocessing, analysis, and visualization 
  • Preprocessing techniques to use in data 
  • Regression methods 
  • Clustering 
  • Recommendation engines 
  • And many more 

If you are serious about machine learning with Python and don’t know how to get started, A Step-by-Step Guide to Learn and Master Python Machine Learning is your best tool to use.

©2018 Hein Smith (P)2018 Hein Smith

What listeners say about Machine Learning with Python

Average Customer Ratings
Overall
  • 5 out of 5 stars
  • 5 Stars
    20
  • 4 Stars
    5
  • 3 Stars
    0
  • 2 Stars
    0
  • 1 Stars
    0
Performance
  • 5 out of 5 stars
  • 5 Stars
    20
  • 4 Stars
    4
  • 3 Stars
    1
  • 2 Stars
    0
  • 1 Stars
    0
Story
  • 5 out of 5 stars
  • 5 Stars
    20
  • 4 Stars
    5
  • 3 Stars
    0
  • 2 Stars
    0
  • 1 Stars
    0

Reviews - Please select the tabs below to change the source of reviews.

Sort by:
Filter by:
  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Learn by doing

Throughout the book, the material is clearly presented and requires no previous introduction to machine learning. That said, while there are no mathematical proofs, and there is some mathematical notation, the reader will need to be comfortable with charts, graphs, and mathematical concepts and terminology.

Mr. Smith covers machine learning from the perspective of developing predictive machine learning models. He discusses many techniques for developing classification and regression models using well chosen examples and explanations. His writing style is informal and enjoyable.

I really appreciated Hein's approach to the ever present stack/tool chain issue that stands as a stumbling block to people getting started. The information is relevant, up to date and approaches many of the same data science/ML hello world type scenarios with a very deep functional perspective. To go further, I had a question about one of the external libraries...

19 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Machine learning, code, examples

Although ML is a field in computer science, it is not the same as the traditional computational methods. When you look at traditional computing, algorithms are described as a set of programmed instructions. These instructions provide solutions to a problem.

ML algorithms make computers to learn from data inputs and apply statistical analysis to display values found in a given range. Therefore, ML allows computers to create a model from a data sample so that it can permit the automation of decisions based on the type of data entered.

Nowadays, technology users hugely benefit from the idea of machine learning. For example, the facial recognition technology provides opportunities to social media networks so that their users can tag and share photos with their friends.

16 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Balance between theory and practice

In this book, you’ll learn all the important topics that you need to know for you to implement machine learning with Python. You’ll learn how to download, install Python, and get the best package for machine learning in Python. You’ll also load a dataset and understand its structure using data visualization and summaries. If you are new to machine learning and looking to eventually launch a career in Python, this book was designed for you. Python is a powerful interpreted language. Unlike other languages such as R, Python is a complete language and platform where you can apply both research and development production. Still, there are many modules and libraries which you can select from and generate different ways to perform each task. Methods in machine learning are popularly used in a wide variety of fields such as engineering, sciences, physics, and computer systems. Additionally, it is also used by commercial websites for the recommendation system, advertising, and predicting the actions of a customer. Machine Learning has popped out as a major engine of most commercial applications and research endeavors. But this particular branch does not exclude large research companies. In this book, you’ll get an in-depth introduction to the field of machine learning from linear models to deep learning and reinforcement learning. You will understand the principles behind machine learning problems like regression, reinforcement learning, and classification.

14 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Helpful for AI novices

Artificial Neural Network describes a set of connected input/output where every connection is linked to a particular weight. In the learning phase, the network adjusts the weights so that it can predict the right class label of input tuples. There are a lot of network architectures present now. Some of them include the Feed-forward, Recurrent, Convolutional, etc. The correct architecture depends on the model application. In most cases, the feed-forward models provide a reasonably accurate result and mostly for image processing applications. There can be many hidden layers in a model based on the complexity of the function that is to be wrapped by the model. If you have a lot of hidden layers, it will facilitate the modeling of complex relationships like deep neural networks. However, the presence of many hidden layers increases the time it takes to train and adjust weights. Another drawback is the poor interpretability when compared to other models such as Decision Trees. Despite this, ANN has performed well in the majority of the real-world applications. It has an intensive persistence to noisy data and can categorize untrained patterns. Generally, ANN works better with continuous-valued inputs and outputs.

13 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Python based machine learning book out there

While both data and computational analysis cause an individual to start to think like they aren’t being objective, being biased on a given data doesn’t mean that the output from the machine learning is neutral. The human bias affects the organization of data and algorithms that determine how ML should use data. If you decide to use historical photographs of scientists in your specific computer training, a computer might fail to classify scientists. Although machine learning is continuously applied in the business, biases that go unnoticed can lead to a systematic problem that can prevent people from receiving loans and many other things. In short, human biases can negatively impact other people. This is very important to underline and work towards removing it as possible. One particular method which you can use to achieve zero biases is to ensure that several people work on a project. Since machine learning is an area which is continuously being improved, it is essential to remember that algorithms, approaches, and methods continue to change.

10 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Up there with Mr Hein's Courses

The most important step when getting started with Machine Learning is to ensure that the data available is of great quality. You can collect data from genuine sources such as Kaggle, data.gov.in, and UCI dataset repository. For example, when students are getting ready to take a competitive exam, they always find the best resources to use to ensure they attain good results. Similarly, accurate and high-quality data will simplify the learning process of the model. This means that during the time of testing, the model would output the best results.

A great amount of time, capital, and resources are involved in data collection. This means that organizations and researchers have to select the correct type of data which they want to implement or research.

For instance, to work on the Facial Expression Recognition requires a lot of images that have different human expressions. A good data will make sure that the results of the model are correct and genuine.

7 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Rich

Clustering is the process of gathering entities with similar characteristics together. This technique belongs to unsupervised machine learning whose target is to identify similarities in the data point and group the same data points together. By grouping similar entities in one place allows one to identify the attributes of different groups. In other words, this generates insight into the underlying patterns of various groups. There are countless application areas of grouping unlabeled data. For example, it is possible to select different groups of customers and market every group differently to take advantage of the revenue. Another example may include grouping documents together that belong to similar topics. Additionally, clustering is used to reduce the dimensionality of the data when you handle various copious variables. The phrase cluster doesn’t have an accurate definition. A cluster describes a set of points whereby any point in the cluster is close to any other point in the cluster than a point absent in the cluster. Sometimes, a threshold is used to de?ine all points in a cluster close to one another. A partitioning method will first create an original set of K-partitions where kparameter is the number of partitions to construct. Next, it applies an iterative relocation approach which tries to enhance the partitioning by shifting objects from one group to another. These clustering techniques help generate a one-level partitioning of data points. There are various partitioning-based clustering like Kmeans, fuzzy C-, means, and K-medoids. This will look at K-mean clustering.

4 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Love it! Only wish I read it earlier

Sometimes, data already prepared can be in the form which the machine cannot read, in this case, it has to be converted into readable form. For conversion to take place, it is important for a specific algorithm to be present.

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

On daily basis

If you didn’t know, Pandas is an important data analysis library in Python. This library has been key to improving the application of Python in the data science community. Our example uses Pandas to read a data set from an analytics Vidhya competition, run an exploratory analysis, and create a first categorization algorithm to solve this problem.

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Very Clear Exposition

The decision tree has a graphical representation of the problem and different alternatives in an easy and simple way to help any person understand without asking for an explanation.

Sort by:
Filter by:
  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for  Derek
  • Derek
  • 07-18-20

ML and TF combination

Most e-commerce and retail companies are taking advantage of the massive potential of data to boost sales by implementing a Recommender system on their particular websites.

These systems focus on suggesting to the user’s items that they may like or have interest in.

The data needed for recommendation engines comes from explicit user ratings to watch a movie or listen to a song from implicit search engine purchase histories and queries. Sites such as YouTube, Spotify, and Netflix have data to use to recommend playlists.

18 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Nicole  Dunigan
  • Nicole Dunigan
  • 07-20-20

by a Master Teacher

Unlike supervised learning where data is labeled, with unsupervised learning, you deal with unlabeled data. This means that it is the task of the learning algorithm to identify similar features in the data that it is supplied. Since unlabeled data is very popular compared to labeled data, techniques of machine learning are among the most valuable in the industry. The aim of unsupervised learning is very simple.

The largest application of unsupervised learning is within the transactional data. There can be a massive data set made up of customers and the products which they purchase, but since you are a human, you can’t manage to extract meaning and similarity from customer profile and their purchase history.

The best time to apply unsupervised machine learning is when you don’t have data on expected outcomes, like defining a target market for a new product that your business has never sold before, but if you are attempting to understand your consumer base, supervised learning is the right technique.

15 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for  Andrew Miura
  • Andrew Miura
  • 07-21-20

Intuitive and Comprehensive

Customer segments will make you understand the patterns which distinguish your customers. While you can analyze your own customer base, soon it shall be clear that there are different groups that have customized requirements. This allows you to build a deeper understanding of your customers and ?ind out what makes them tick. It is no gem that a customer is always more pro?itable compared to others. However, to be profitable, businesses should have a better understanding of the way profitability relates to customer segmentation. Discovering the difference between customers will permit one to personalize your method to the desires of the customer segments. Customer segmentation describes the practice of categorizing a customer base into different groups of individuals similar in a given way. Customer segments are often determined based on similarities such as personal characteristics, behaviors, and preferences. By understanding your customers and their differences, it becomes one of the most important stages of measuring the customers’ relationship.

12 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Tegan
  • Tegan
  • 07-26-20

Part of my core library

Before you can get started with Machine Learning with Python, you must have Python installed on your computer, however, you might not need to download it. So, the first thing to do is to confirm that Python is not installed by typing “Python” in a command window. When you see a response from a Python interpreter, it will consist of a version number in its original display. In general, any recent version will work because Python tries to maintain backward compatibility. Companies which apply the Recommender system concentrate on raising the sales due to the personalized offers and improved customer experience. Recommendations usually increase searches and make it easy for users to access content which they are interested in, and surprise them with offers that they have never searched before. What is interesting is that companies can now gain and retain customers by sending out email links to new offers that fulfill the interests of their profiles. By creating an added advantage to users through suggesting products and systems, it creates a great feeling among buyers. This is a great thing because it will allow companies to stay ahead of their competitors.

10 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Cynthia Johnson
  • Cynthia Johnson
  • 07-29-20

Set to launch your first ML project.

With some knowledge of basic Python, machine learning skills, and Python libraries, you are now set to launch your first machine learning project with Python. Consider learning the open-source Python libraries. The scientific Python libraries will help you complete easy machine learning tasks. However, the choice of some of these libraries can be completely subjective and highly debatable by many people in the industry.

All in all, we recommend you to start by exploring Scikit-learn library. Make sure you are familiar with its concepts and how to use it. Once you are done with it, you can dive deep into advanced machine learning topics such as complex data transformation and vector machines.

Just like how a child learns how to walk is the same with learning Machine Learning with Python. You need to practice many times before you can become better. Practice different algorithms and use different datasets to improve your knowledge and overall problem-solving skills.

6 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Ronal
  • Ronal
  • 08-02-20

Generative deep learning

The content of a particular item is abstract and provides more options. You can use many different variables. For instance, for a book, you can include the genre, author, the text of the book and many other factors. Once you know which content you will factor. You need to convert all the data into a vector space model, which is an algebraic representation of text documents. You perform this using a Bag of Words model which represents documents disregarding the sequence of words. In this particular model, every document appears like a bag with some words. Therefore, this method will permit word modeling with respect to dictionaries, where every bag has some words from the dictionary. An exact implementation of a Bag of Words is the TF-IDF representation. In full, TF stands for Term Frequency and IDF stands for Inverse Document Frequency. This particular model combines the significance of the word in the document with the significance of the world in the corpus. This was just a general aspect of Content-based recommendation engines. It is important to recognize that a Bag of Words representation doesn’t factor in the context of words. If it is necessary to include that, Semantic Content Representation becomes useful.

2 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for  Holmes
  • Holmes
  • 08-06-20

You will love it!

SciPy is designed on NumPy. It is among the most important library for different high-level science and engineering modules such as Linear Algebra, Sparse matrices, and Fourier transform.

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Allison Barron
  • Allison Barron
  • 08-03-20

Absurdly good

The regression’s dependent variable has many different names. Some names include outcome variable, criterion variable, and many others. The independent variable can be called exogenous variable or repressors.

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Joseph Lawson
  • Joseph Lawson
  • 08-01-20

Great book for non matematicians

The data collected can be in raw form. Raw data cannot be directly fed into a machine. Instead, something has to be done on the data first. The preparation stage involves gathering data from a wide array of sources, analyzing the datasets, and then building a new data set for additional processing and exploration. Preparation can be done manually or automatically and the data should be prepared in a numerical form to improve the rate of learning of the model.

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Hall
  • Hall
  • 07-31-20

Really good - I'm learning a lot

The control flow in a program highlights the order of program execution. In a Python program, control low is carried out by function calls, conditional statements, and loops. This section will deal with the If Statement, While and For loops.