第25月第5天 Hands-on Machine Learning with Scikit-Learn and TensorFlow

1.apachecn视频(机器学习实战)

https://github.com/apachecn/AiLearning

https://space.bilibili.com/97678687/#/channel/detail?cid=22486

2.莫烦

https://morvanzhou.github.io/tutorials/machine-learning/sklearn/2-2-general-pattern/

https://github.com/MorvanZhou/tutorials/tree/master/sklearnTUT

源代码在sklean 0.20.0 运行问题

from sklearn.learning_curve import 改为 from sklearn.model_selection import

scoring='mean_squared_error' 改为 scoring='neg_mean_squared_error'

http://sklearn.apachecn.org/cn/stable/modules/model_evaluation.html

#-------------------------------------
用Python开始机器学习(sklearn)

https://blog.csdn.net/lsldd/article/details/41357931

机器学习之路

https://www.cnblogs.com/Lin-Yi/p/8970527.html

https://github.com/linyi0604/MachineLearning

20181004还在学习的人

https://blog.csdn.net/dingming001/article/details/82935715

3.Hands-on Machine Learning with Scikit-Learn and TensorFlow

https://github.com/apachecn/hands_on_Ml_with_Sklearn_and_TF

https://www.jianshu.com/p/49bfb59b96b7

https://github.com/ageron/handson-ml

ubuntu安装

从清华大学开源软件网站上选择合适的源文件并下载

https://blog.csdn.net/hgdwdtt/article/details/78633232

命令

 anaconda search -t conda tensorflow

conda源更改：

conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/

conda config --set show_channel_urls yes

vi ~/.condarc 

删除default

conda info 

https://jingyan.baidu.com/article/1876c8527be1c3890a137645.html

4.anaconda

Using Anaconda

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

$ conda create -n mlbook python=3.5 anaconda
$ source activate mlbook

This creates a fresh Python 3.5 environment called mlbook (you can change the name if you want to), and it activates it. This environment contains all the scientific libraries that come with Anaconda. This includes all the libraries we will need (NumPy, Matplotlib, Pandas, Jupyter and a few others), except for TensorFlow, so let's install it:

$ conda install -n mlbook -c conda-forge tensorflow

This installs the latest version of TensorFlow available for Anaconda (which is usually not the latest TensorFlow version) in the mlbook environment (fetching it from the conda-forge repository). If you chose not to create an mlbook environment, then just remove the -n mlbook option.

Next, you can optionally install Jupyter extensions. These are useful to have nice tables of contents in the notebooks, but they are not required.

$ conda install -n mlbook -c conda-forge jupyter_contrib_nbextensions

Starting Jupyter

If you want to use the Jupyter extensions (optional, they are mainly useful to have nice tables of contents), you first need to install them:

$ jupyter contrib nbextension install --user

Then you can activate an extension, such as the Table of Contents (2) extension:

$ jupyter nbextension enable toc2/main

Okay! You can now start Jupyter, simply type:

$ jupyter notebook

Enviroment setup

Create an enviroment from the enviroment.yml file

conda env create -f environment.yml

activate enviroment

source activate supervised

Update enviroment

conda env export > environment.yml

source