Skip to content
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
Jupyter Notebook Other
Branch: master
Clone or download
Latest commit 2adec01 Nov 10, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
datasets Update README.md Jan 17, 2018
docker fixes docker build issue Sep 12, 2019
images Add clustering, density estimation and anomaly detection to chapter 8 Apr 4, 2018
.gitignore Add *.old, *.dot and lifesat.csv (generated) to .gitignore May 7, 2018
01_the_machine_learning_landscape.ipynb Add missing import, fixes #510 Nov 10, 2019
02_end_to_end_machine_learning_project.ipynb In Python 3, we can use os.makedirs(..., exist_ok=True) Aug 27, 2019
03_classification.ipynb import matplotlib as mpl and use mpl.rc() Jan 8, 2019
04_training_linear_models.ipynb Crop long outputs to make it easier to visualize the notebooks on git… Apr 23, 2019
05_support_vector_machines.ipynb Crop long outputs to make it easier to visualize the notebooks on git… Apr 23, 2019
06_decision_trees.ipynb import matplotlib as mpl and use mpl.rc() Jan 8, 2019
07_ensemble_learning_and_random_forests.ipynb bst_n_estimators should be argmin(errors) + 1, fixes #445 Jun 8, 2019
08_dimensionality_reduction.ipynb Crop long outputs to make it easier to visualize the notebooks on git… Apr 23, 2019
09_up_and_running_with_tensorflow.ipynb Use tensorflow_graph_in_jupyter.py in notebooks, fixes #223 May 18, 2018
10_introduction_to_artificial_neural_networks.ipynb Crop long outputs to make it easier to visualize the notebooks on git… Apr 23, 2019
11_deep_learning.ipynb Crop long outputs to make it easier to visualize the notebooks on git… Apr 23, 2019
12_distributed_tensorflow.ipynb Add a quick intro to the Data API in notebook 12 May 7, 2018
13_convolutional_neural_networks.ipynb Use fc1_drop instead of fc1, fixes #304 Aug 13, 2019
14_recurrent_neural_networks.ipynb Small spelling improvements to the RNN chapter Aug 14, 2019
15_autoencoders.ipynb Crop long outputs to make it easier to visualize the notebooks on git… Apr 23, 2019
16_reinforcement_learning.ipynb add chapter 16 exercise 9 solution Oct 2, 2019
LICENSE First notebook added: matplotlib Feb 16, 2016
README.md Refresh the whole README.md, in particular use only Python 3 + simpli… Oct 28, 2019
book_equations.ipynb Fix equation 16-6 (max_alpha'=>max_a') May 7, 2018
environment.yml Add environment file to generate the conda env Oct 26, 2019
extra_autodiff.ipynb Improve formatting May 18, 2018
extra_capsnets-cn.ipynb Crop long outputs to make it easier to visualize the notebooks on git… Apr 23, 2019
extra_capsnets.ipynb made initial weights higher-variance Feb 10, 2018
extra_gradient_descent_comparison.ipynb Add intro paragraph, tx to Daniel and minor formatting fixes Sep 17, 2018
extra_tensorflow_reproducibility.ipynb Crop long outputs to make it easier to visualize the notebooks on git… Apr 23, 2019
future_encoders.py Add ColumnTransformer to future_encoders.py Jul 31, 2018
index.ipynb Remove nbextensions from installation instructions, fixes #401 Apr 9, 2019
math_linear_algebra.ipynb Right angle is pi/2, not pi/4. One reason why tau > pi ;) Oct 27, 2017
ml-project-checklist.md add ml-project-checklist (Appendix B of the book) Mar 13, 2019
requirements.txt Bump pillow from 5.4.1 to 6.2.0 Oct 23, 2019
tensorflow_graph_in_jupyter.py Use tensorflow_graph_in_jupyter.py in notebooks, fixes #223 May 18, 2018
tools_matplotlib.ipynb fixed typo in tools_matplotlib.ipynb Mar 4, 2016
tools_numpy.ipynb Fix small typo in numpy notebook Mar 24, 2018
tools_pandas.ipynb Upgrade to latest pandas version, update resampling API Jan 5, 2018

README.md

Machine Learning Notebooks

This project aims at teaching you the fundamentals of Machine Learning in python. It contains the example code and solutions to the exercises in my O'Reilly book Hands-on Machine Learning with Scikit-Learn and TensorFlow:

book

Simply open the Jupyter notebooks you are interested in:

  • Using jupyter.org's notebook viewer
  • by cloning this repository and running Jupyter locally. This option lets you play around with the code. In this case, follow the installation instructions below,
  • or by running the notebooks in Deepnote. This allows you to play around with the code online in your browser. For example, here's a link to the first chapter:

Installation

First, you will need to install git, if you don't have it already.

Next, clone this repository by opening a terminal and typing the following commands:

$ cd $HOME  # or any other development directory you prefer
$ git clone https://github.com/ageron/handson-ml.git
$ cd handson-ml

If you do not want to install git, you can instead download master.zip, unzip it, rename the resulting directory to handson-ml and move it to your development directory.

If you want to go through chapter 16 on Reinforcement Learning, you will need to install OpenAI gym and its dependencies for Atari simulations.

If you are familiar with Python and you know how to install Python libraries, go ahead and install the libraries listed in requirements.txt and jump to the Starting Jupyter section. If you need detailed instructions, please read on.

Python & Required Libraries

Of course, you obviously need Python. Python 3 is already preinstalled on many systems nowadays. You can check which version you have by typing the following command (you may need to replace python3 with python):

$ python3 --version  # for Python 3

Any Python 3 version should be fine, preferably 3.5 or above. If you don't have Python 3, I recommend installing it. To do so, you have several options: on Windows or MacOSX, you can just download it from python.org. On MacOSX, you can alternatively use MacPorts or Homebrew. If you are using Python 3.6 on MacOSX, you need to run the following command to install the certifi package of certificates because Python 3.6 on MacOSX has no certificates to validate SSL connections (see this StackOverflow question):

$ /Applications/Python\ 3.6/Install\ Certificates.command

On Linux, unless you know what you are doing, you should use your system's packaging system. For example, on Debian or Ubuntu, type:

$ sudo apt-get update
$ sudo apt-get install python3 python3-pip

Another option is to download and install Anaconda. This is a package that includes both Python and many scientific libraries. You should prefer the Python 3 version.

If you choose to use Anaconda, read the next section, or else jump to the Using pip section.

Using Anaconda

Once you have installed Anaconda (or Miniconda), you can run the following command:

$ conda env create -f environment.yml

This will give you a conda environment named mlbook, ready to use! Just activate it and you will have everything setup for you:

$ conda activate mlbook

You are all set! Next, jump to the Starting Jupyter section.

Using pip

If you are not using Anaconda, you need to install several scientific Python libraries that are necessary for this project, in particular NumPy, Matplotlib, Pandas, Jupyter and TensorFlow (and a few others). For this, you can either use Python's integrated packaging system, pip, or you may prefer to use your system's own packaging system (if available, e.g. on Linux, or on MacOSX when using MacPorts or Homebrew). The advantage of using pip is that it is easy to create multiple isolated Python environments with different libraries and different library versions (e.g. one environment for each project). The advantage of using your system's packaging system is that there is less risk of having conflicts between your Python libraries and your system's other packages. Since I have many projects with different library requirements, I prefer to use pip with isolated environments. Moreover, the pip packages are usually the most recent ones available, while Anaconda and system packages often lag behind a bit.

These are the commands you need to type in a terminal if you want to use pip to install the required libraries. Note: in all the following commands, if you chose to use Python 2 rather than Python 3, you must replace pip3 with pip, and python3 with python.

First you need to make sure you have the latest version of pip installed:

$ python3 -m pip install --user --upgrade pip

The --user option will install the latest version of pip only for the current user. If you prefer to install it system wide (i.e. for all users), you must have administrator rights (e.g. use sudo python3 instead of python3 on Linux), and you should remove the --user option. The same is true of the command below that uses the --user option.

Next, you can optionally create an isolated environment. This is recommended as it makes it possible to have a different environment for each project (e.g. one for this project), with potentially very different libraries, and different versions:

$ python3 -m pip install --user --upgrade virtualenv
$ python3 -m virtualenv -p `which python3` env

This creates a new directory called env in the current directory, containing an isolated Python environment based on Python 3. If you installed multiple versions of Python 3 on your system, you can replace `which python3` with the path to the Python executable you prefer to use.

Now you must activate this environment. You will need to run this command every time you want to use this environment.

$ source ./env/bin/activate

On Windows, the command is slightly different:

$ .\env\Scripts\activate

Next, use pip to install the required python packages. If you are not using virtualenv, you should add the --user option (alternatively you could install the libraries system-wide, but this will probably require administrator rights, e.g. using sudo pip3 instead of pip3 on Linux).

$ python3 -m pip install --upgrade -r requirements.txt

Great! You're all set, you just need to start Jupyter now.

Starting Jupyter

Okay! You can now start Jupyter, simply type:

$ jupyter notebook

This should open up your browser, and you should see Jupyter's tree view, with the contents of the current directory. If your browser does not open automatically, visit 127.0.0.1:8888. Click on index.ipynb to get started!

Congrats! You are ready to learn Machine Learning, hands on!

Contributors

I would like to thank everyone who contributed to this project, either by providing useful feedback, filing issues or submitting Pull Requests. Special thanks go to Steven Bunkley and Ziembla who created the docker directory.

You can’t perform that action at this time.