We code therefore we are
In case you don't know, I am an avid Google+ user. On 8th October, 2018, Google announced to close Google+ around Summer 2019. The company revealed that Google+ has low usage and engagement --- 90 percent of Google+ user sessions are less than five seconds. And most important,
We code therefore we are
So far, we have entered several Kaggle's machine learning competitions. Most of the time, we use Kaggle's free kernel to solve the puzzles. From the Deal Probability Prediction challenge, we reached the limit of Kaggle's kernel --- the 17 GB RAM limit, while we
Learn Machine Learning
Other than our last hand writing challenge, there is another Kaggle challenge featuring image recognition -- TGS Salt Identification Challenge. But this time, we are going for an "upgrade". As we are dealing with object detection. It is all about salt. In this challenge, our mission is finding
We code therefore we are
We have learnt how to build a weather forecast Flask app. We have learnt how to deploy the Flask app to a Raspberry Pi using Docker. But we mostly focus on deploying our app in a local machine or a private network. In order to step up our game, we
Learn Machine Learning
In our past machine learning topic, "Ensemble Modeling", we mentioned how blending helps on improving our prediction. Then in another topic, "Why are people frustrated on Kaggle’s challenge?", we mentioned how blending ruins a data science competition. Okay, we have a question here, is blending
Learn Machine Learning
Our topic this time is too Russia, so my water just turned into Vodka :]] . Actually, this is all about Kaggle's competition: Avito Demand Prediction Challenge. Avito is the biggest classified site in the Mother Russia, just likes the Craigslist. Our mission for this time is, predicting the rate
We code therefore we are
GitHub / GitLab / Bitbucket are homes for developers to share their open source projects to the public for free. We have seen so many great projects there in GitHub. Like the winning data science learning model -- XGB, Python's micro web framework -- Flask, Microsoft's own light
Learn Machine Learning
Last time, we tried the Kaggle's TalkingData Click Fraud Detection challenge. And we used limited resources to handle a 200 million records sized dataset. Although we can make our classification with Random Forest model, we still want a better scoring result. Inside the Click Fraud Detection challenge'
Learn Machine Learning
You have probably read the above comic in 9gag or imgur before. It is a funny joke, but on the other hand, it is also a material for our Machine Learning topic. It sounds weird? Oh yeah, sometimes knowledge comes from strange ideas. The Comic Here is the comic, for
Learn Machine Learning
The Story After finished the Kaggle's TalkingData Click Fraud Detection challenge, people were frustrated. As few days before the final submission, there was a public kernel which blended outputs from others and got a nice 0.9812 score. Then people just copied that kernel and submitted to Kaggle.
Learn Machine Learning
Up to now, we have tried 3 different Kaggle journeys, the Titanic Survivors, the Iowa House Prices and the hand written digits recognition. Those journeys covered popular Machine Learning topics, such as classification, regression, deep learning, and so on. I would suggest fans of Machine Learning to start with those
Have a pie, Raspberry Pi(e)
We have just installed Docker on our Raspberry Pi, now it is time to bring into action. Do you remember the EZW, Easy Weather Forecast Flask app? Yes, we are going to deploy this EZW flask app. Of course, we do it in the Docker way! Prerequisites 1. Docker installed