Categories
Business Analytics

Sonoma County

Covid-19 Key Indicators

The truth is like a lizard; it leaves its tail in your hand and runs away; it knows that it will shortly grow a new one. – Ivan Turgenev

I acquire coronavirus data daily for certain California county websites, like Sonoma County, that display it [1]. Then I calculate some key indicators for the virus that might be useful to understand and control it. You can find out more about them at Coronavirus Key Indicators Description. According to official California statistics, the population of Sonoma County is 509,142. [1] I use my PHP program CoronavirusScrape.php.

Marin County, adjacent to Sonoma County, has similar data available, and its results are shown at Marin County Coronavirus Key Indicators.

County doubling.rate start.day end.day Date mean R Infections per day
Sonoma 55.81 8 364 2021-03-09 0.86 14.61

Data may be newer than comment below, as I do not comment every day.

Current Comment and KPIs

3/10/21- Mean R is now at 0.86. Infections per day are over 14, down for the first time in a while. Doubling rate is over 55 days.

Sonoma KPI History 2021-03-10Download

I will occasionally refer to a mobility graph, which uses the Google Mobility Report data to show where the county stands on social isolation and social distancing practices. Mobility data appears to be one of the best ways to predict the trend of the virus. Mobility information is at Coronavirus Mobility Indicators.

Continue reading “Sonoma County”
Categories
Outdoors

Visualizing Ducks

We have a lot of ducks, mostly mallards, on the trail near here. I’ve been snapping pics of them as we walk the trail. I’m wondering where the ducks tend to be. Are they evenly distributed, using the entire stream, or do they favor particular places?

Continue reading “Visualizing Ducks”
Categories
Maritime

Maritime Innovation Centers

I’m starting to look at maritime innovations and entrepreneurs and how they are succeeding and getting funded now. My friend Chris Clott and I have in mind a paper on the subject.

We are looking at some data on startups, the maritime areas they are in, and how much money they’ve raised and when.

Fast forward two years and we have written and published the paper. It’s not too favorable to maritime accelerators and incubators unless they are in the software area. Funding for startups with hard products in the maritime arena is harder to come by than funding for software-based startups. We looked at startups that became unicorns, firms valued at over a billion dollars. Those are overwhelmingly in the soft category.

Startups that try to develop equipment for the maritime industry are not so attractive for venture capitalist money. They need a test bed, and therefore often need to partner with an established maritime organization — a ship owner, a port terminal, or a storage yard— and that means they are often bought up if they are successful rather than being marketed openly. Often the investments they garner have strings attached, like ownership of patents, or dedicated rights of use for a period, designed to give the sponsor a competitive advantage.

The graph below shows how soft investments tend to dominate hard investments. And our study shows that many hard investments originate in China rather than the rest of the world.

Categories
Business Analytics

Interpretable Machine Learning

I’m currently working on discovering some facts about making machine learning interpretable. The resources I’ve found include a book by Christoph Molnar. I’m using his iml package in R to explore particularly Shapley Values. For an individual prediction, these numbers show the influence of each feature explaining how the prediction differs from the average. Shapley values are of interest because they meet some conditions of “fairness”.

Continue reading “Interpretable Machine Learning”
Categories
Business Analytics

Run R Here