Google Colaboratory, often referred to as colab, is a product created by Google to allow anyone to create and run python code in the browser. It has many standard machine and data science libraries built-in including pandas and scikit-learn. You can also install practically any other python library for use in each notebook. To access colab you need to sign up for a Google account and this then gives you free access to the notebook environment and computing resources that include GPU's. Let's walk through a quick demo.

When we create our machine learning models, a common task that falls on us is how to tune them. People end up taking different manual approaches. Some of them work, and some don't, and a lot of time is spent in anticipation and running the code again and again. So that brings us to the quintessential question: Can we automate this process? A while back, I was working on an in-class competition from the "How to win a data science competition" Coursera course.

Employee turn-over (also known as "employee churn") is a costly problem for companies. The true cost of replacing an employee can often be quite large. A study by the Center for American Progress found that companies typically pay about one-fifth of an employee's salary to replace that employee, and the cost can significantly increase if executives or highest-paid employees are to be replaced. In other words, the cost of replacing employees for most employers remains significant. This is due to the amount of time spent to interview and find a replacement, sign-on bonuses, and the loss of productivity for several months while the new employee gets accustomed to the new role. Understanding why and when employees are most likely to leave can lead to actions to improve employee retention as well as possibly planning new hiring in advance.

I had a little difficulty getting a dataset of leaves of diseased plant. I initially had to write a web scraper with Victor Aremu to scrape ecosia.org I finally found this data on Github from spMohanty and settled on it. Here is what my dataset file structure looks like. After downloading the dataset I wrote the code on my system(MacBook pro 2.3 GHz Intel Core i5, 8Gb Ram, Intel HD Graphics 3000 512 MB).

Kaggle Kernels is our hosted data science environment. It allows our users to author, execute, and share code written in Python and R. Kaggle Kernels entered 2018 as a data science scratchpad. In 2018, we added key pieces of functionality that make it a powerful environment. This includes the ability to use a GPU backend and collaborate with other users. We had 346K users author kernels in 2018, up 3.1x from 111K in 2017.

Any Clouderizer project can now be run seamlessly on Kaggle Kernels. What this means is our community project for Fast.ai, can now be run on Kaggle Kernels, just as easily. Following pre-requisite, one time, steps are needed. Now every time you need to start fast.ai Make sure to put an!

Data scientists are expected to know a lot -- machine learning, computer science, statistics, mathematics, data visualization, communication, and deep learning. How should data scientists who want to be in demand by employers spend their learning budget? I scoured job listing websites to find which skills are most in demand for data scientists. I looked at general data science skills and at specific languages and tools separately. I searched job listings on LinkedIn, Indeed, SimplyHired, Monster, and AngelList on October 10, 2018.

In the last article we covered a number of experimental design issues and made some decisions for our experiments. We decided to compare the performance of two simple artificial neural networks on the Iris Flower dataset. The first neural network will be the control arm, and it will consist of a single hidden layer of four neurons. The second neural network will be the experimental arm, and it will consist of a single hidden layer of five neurons. We will train both of these using default configurations supplied by the Keras library and collect thirty accuracy samples per arm. We will then apply the Wilcoxon Rank Sums test to test the significance of our results.

It's a great time to get started doing deep learning with Kaggle Kernels! Recently I had the chance to give my first conference talk, at PyOhio in Columbus. I spoke about getting into deep learning, and I used Kaggle Kernels to demo some material from the first lesson of the fast.ai The next day I came across a Medium article called "Learn deep learning with GPU enabled kaggle kernels and fastai MOOC", and I was excited to see more people recognizing the capabilities of this platform. So I thought, if we're going to make it easy for people to get started with deep learning on Kaggle Kernels, why not make the whole fast.ai

In the last article we introduced Kaggle's primary offerings and proceeded to execute our first "Hello World" program within a Kaggle Kernel. In this article, we're going to move onto conducting our first machine learning experiment within a Kaggle Kernel notebook. To facilitate a gentle learning experience, we will try to rely on (relatively) simple/classic resources in regard to the selected dataset, tools, and algorithms. This article assumes you know what Kaggle is, and how to create a Kaggle Kernel. Note: although this article is focussed on the use of Kaggle Kernels, this experiment can be reproduced in any environment with the required packages.