一、为什么Kaggle

Kaggle是目前最大的数据科学竞赛与技能分享平台。在Kaggle上你可以查找和发布数据集，探索和构建模型，与其他数据科学家和机器学习工程师合作，并参加竞赛以解决数据科学挑战。参加Kaggle竞赛，你至少可以有以下几种收获：

Backpropagation is the foundation of the deep neural network. Usually, we consider it to be kind of ‘dark magic’ we are not able to understand. However, it should not be the black box which we stay away. In this article, I will try to explain backpropagation as well as the whole neural network step by step in the original mathematical way.

Stochastic Gradient decent is one of the fundamental algorithm in deep learning. It is used when we perform optimization of the cost function.Suppose the function is $ f(x) $

Suppose you got a person’s regist time in one column and his birth date in another column, now you need to calculate his age when he did the registration. There are two ways to reach this result.

We need to rely on pyodbc, the sample code is as belows.

Why embedding

Natural language processing systems traditionally treat words as discrete atomic symbols, and this may lead to some obstacles in word preprocessing:

Tf.data is a high level API provided by tensorflow, it performs as a pipeline for complex input and output. The core data structure of tf.data is Dataset which represents a potentially large set of elements.

Missing data is a common problem in real data preprocessing, luckily pandas has done a lot to help us handle it. This article will show the codes on how to do it.