pydata

Keep Looking, Don't Settle

Numpy Introduction 02

Summary: this is the introduction and summary of numpy array/matrix manipulation. Some are with very detailed explaination which I think is more detailed than the numpy document.

weighted avarage, aggrefated function with apply and agg

suppose we want to calculate the weighted average probability of default of all risk rating weighted by the number of borrowers on each pd risk rating(or a little more, grouped by industry or portfolio), we need this weighted average function on each group. Pandas has groupby to split data, and then apply function to calculate and summarize.

tensorflow简介--04

前面几章我们讨论了给定一些features,比如房屋面积,怎么通过TF的线性回归来预测结果,比如说房屋价格。下面会讨论logistic regression,它会通过输入的features来实现分类。比如说通过输入的图片,来进行0-9的分类。

tensorflow简介--03

经过前面介绍的单feature的线性模型,损失函数,梯度下降(part 1),epoch, learn-rate, 可变梯度下降(part 2),我们可以继续介绍TF下面多特征(multi-feature)的线性回归。

tensorflow简介--02

上一章讨论了怎么在TF里面训练机器学习模型,以及基本的tensorflow代码。这为接下来讨论各种训练变化比如stochastic/mini-batch/batch, 以及adaptive learning rate gradient descent预铺了道路.

tensorflow简介--01

python的群里有人询问深度学习的基本概念,正好最近看到一篇非常简洁明了的介绍TF的基本概念的文章,尝试把它翻译成中文。以下为原文翻译:Tensorflow(TF)是google开源的深度学习框架。它有初级高级两个教程实例。然后那两个例子把ML和TF放在一起解决一个多feature的问题--图像识别。本文尝试从最简单的线性模型来介绍一个单feature的问题,然后从这儿开始扩展下去。