2020-01-06 (Mon)

2019-07-27 (Sat)

2019-01-08 (Tue)

2018-12-24 (Mon)

2018-11-26 (Mon)

## 一段 Airflow 與資料工程的故事：談如何用 Python 追漫畫連載

2018-08-21 (Tue)

Airflow 是一個以 Python 開發的工作流管理系統，也是資料工程不可或缺的利器之一。近年不管是資料科學家、資料工程師還是任何需要處理數據的軟體工程師，Airflow 都是他們用來建構 ETL 以及處理批量資料的首選之一。這篇文章希望以一個簡易的漫畫連載通知 App 作為引子，讓讀者直觀地了解 Airflow 背後的運作原理、建立資料工程的知識基礎，並在閱讀本文後發揮自己的創意，實際應用 Airflow 來解決並自動化自己及企業的數據問題。

2018-08-03 (Fri)

2018-04-04 (Wed)

## BeautifulSoup 筆記

2018-03-02 (Fri)

Beautifulsoup 是一個可以幫助我們 parse HTML 的函式庫，不管是在寫爬蟲還是做 HTML 檔案的處理都很方便。這篇主要紀錄使用 beautifulsoup 時常用的指令。

2018-03-02 (Fri)

## Find Word Semantic by Using Word2vec in TensorFlow

2017-09-30 (Sat)

Naive Word2vec implementation using Tensorflow

## Simple Convolutional Neural Network using TensorFlow

2017-09-26 (Tue)

The goal here is to practice building convolutional neural networks to classify notMNIST characters using TensorFlow. As image size become bigger and bigger, it become unpractical to train fully-connected NN because there will be just too many parameters and thus the model will overfit very soon. And CNN solve this problem by weight sharing. We will start by building a CNN with two convolutional layers connected by a fully connected layer and then try also pooling layer and other thing to improve the model performance.

## Regularization for Multi-layer Neural Networks in Tensorflow

2017-09-25 (Mon)

The goal of this assignment is to explore regularization techniques.

## Using TensorFlow to Train a Shallow NN with Stochastic Gradient Descent

2017-09-21 (Thu)

The goal here is to progressively train deeper and more accurate models using TensorFlow. We will first load the notMNIST dataset which we have done data cleaning. For the classification problem, we will first train two logistic regression models use simple gradient descent, stochastic gradient descent (SGD) respectively for optimization to see the difference between these optimizers.

## Simple Image Recognition using NotMNIST dataset

2017-09-19 (Tue)

Today we're going to do some simple image recogintion using NotMNIST dataset. But before creating model for prediction, it's more important to explore, clean and normalize our dataset in order to make the learning go smoother when we actually build predictive models.

2017-09-17 (Sun)