Hands-On ML代码与数据集

《Hands-On Machine Learning with Scikit-Learn & TensorFlow》中文译为《Scikit-Learn 与 TensorFlow 机器学习实用指南》的代码和数据集。

这本书总共分为两大部分，第一部分介绍典型的机器学习算法，在介绍理论的同时每章都配备 Scikit-Learn 实战项目；第二部分介绍神经网络与深度学习，同样每章也配备 TensorFlow 实战项目。附录部分内容也非常丰富。整本书兼顾理论与实战，是一本非常适合入门和实战的机器学习书籍。

这本书最大的特色从理论上讲就是言简意赅，全书基本上没有太多复杂的数学公式推导，语言通俗易懂，很容易看得懂、看得下去。更重要的是每一个章节都配备了相应的实战代码，使用 Scikit-Learn、TensorFlow 进行编程。

本书作为 Python Machine Learning 的入门教材，着重介绍了如何使用 Scikit-Learn 和 TensorFlow 建立机器学习的模型和训练，同时兼顾了理论，涉及的内容也很广泛和前沿，有 CNN，RNN，Autoencoder 和 RL，令人读完受益匪浅。

如何使用？

1.进入会员主界面；
2.在【应用与数据】模块中，找到数据并另存到自己的空间；
3.创建相关应用的实例，并将数据另存的目录挂载上；
4.在应用中使用数据；

文件清单

01_the_machine_learning_landscape.ipynb (275 KB)
02_end_to_end_machine_learning_project.ipynb (1.1 MB)
03_classification.ipynb (434 KB)
04_training_linear_models.ipynb (835 KB)
05_support_vector_machines.ipynb (861 KB)
06_decision_trees.ipynb (201 KB)
07_ensemble_learning_and_random_forests.ipynb (544 KB)
08_dimensionality_reduction.ipynb (5.5 MB)
09_up_and_running_with_tensorflow.ipynb (194 KB)
10_introduction_to_artificial_neural_networks.ipynb (135 KB)
11_deep_learning.ipynb (328 KB)
12_distributed_tensorflow.ipynb (25 KB)
13_convolutional_neural_networks.ipynb (4.6 MB)
14_recurrent_neural_networks.ipynb (584 KB)
15_autoencoders.ipynb (340 KB)
16_reinforcement_learning.ipynb (555 KB)
INSTALL.md (6 KB)
LICENSE (9 KB)
README.md (5 KB)
apt.txt (129 B)
book_equations.ipynb (47 KB)
datasets/
datasets/housing/
datasets/housing/README.md (3 KB)
datasets/housing/housing.csv (1.3 MB)
datasets/housing/housing.tgz (399 KB)
datasets/inception/
datasets/inception/imagenet_class_names.txt (30 KB)
datasets/lifesat/
datasets/lifesat/README.md (4 KB)
datasets/lifesat/gdp_per_capita.csv (35 KB)
datasets/lifesat/oecd_bli_2015.csv (395 KB)
environment.yml (1 KB)
extra_autodiff.ipynb (32 KB)
extra_capsnets-cn.ipynb (292 KB)
extra_capsnets.ipynb (251 KB)
extra_gradient_descent_comparison.ipynb (303 KB)
extra_tensorflow_reproducibility.ipynb (38 KB)
future_encoders.py (58 KB)
images/
images/ann/
images/ann/README (34 B)
images/autoencoders/
images/autoencoders/README (34 B)
images/classification/
images/classification/README (34 B)
images/cnn/
images/cnn/README (34 B)
images/cnn/test_image.png (177 KB)
images/decision_trees/
images/decision_trees/README (34 B)
images/deep/
images/deep/README (34 B)
images/distributed/
images/distributed/README (34 B)
images/end_to_end_project/
images/end_to_end_project/README (34 B)
images/end_to_end_project/california.png (9 KB)
images/ensembles/
images/ensembles/README (34 B)
images/fundamentals/
images/fundamentals/README (34 B)
images/rl/
images/rl/README (34 B)
images/rnn/
images/rnn/README (34 B)
images/svm/
images/svm/README (34 B)
images/tensorflow/
images/tensorflow/README (34 B)
images/training_linear_models/
images/training_linear_models/README (34 B)
images/unsupervised_learning/
images/unsupervised_learning/README (34 B)
images/unsupervised_learning/ladybug.png (561 KB)
index.ipynb (5 KB)
math_differential_calculus.ipynb (593 KB)
math_linear_algebra.ipynb (658 KB)
ml-project-checklist.md (7 KB)
requirements.txt (1 KB)
tools_matplotlib.ipynb (1.0 MB)
tools_numpy.ipynb (616 KB)
tools_pandas.ipynb (442 KB)