We tried Python web scraping project using scrapy and text mining project using TFIDF in past. This time, we are going to raise the bar, by combing two projects together. So we have our — text mining web scraper. Like our early post in the CodeAStar blog, it is always good to build something useful with […]
Word Cloud for Job Seekers in Python Read More »
Every business owner wants to make revenue prediction, so he or she can have better marketing decisions. On Kaggle, the data science community site, there is a challenge on making a store’s revenue prediction. And that is the topic we are looking for. The store in this challenge is none other than the Google Merchandise Store.
Revenue Prediction in Google Store Read More »
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, there was a security flaw which exposed users’
Social Network Journey for Google Plus replacement Read More »
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 were training our model. When we added more training data or
AWS Tutorial: Deep Learning on Amazon Web Services Read More »
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 geophysical images that contain salt. Oh wait, does it sound weird? Actually
U-Net and IoU for Object Detection in Image Processing Read More »
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 are going to deploy the app globally
Amazon Tutorial: Deploy a Flask Docker image in ECS Read More »
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 good or bad?
Blending, the Dark Side in Data Science Competition Read More »
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 that a seller can make a
TFIDF technique and Deal Probability Prediction (in Russian) Read More »
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 and fast learning model — LGB and the
The Great Migration to GitLab in Open Source community Read More »
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’s leaderboard, I find that most of the high scoring
LGB, the winning Gradient Boosting model Read More »
