Day 80 is a data analysis / machine learning capstone. The project is about Boston 1970 Real Estate analysis. I honestly don’t understand a bunch of what it is taught, and because I am not super interested, I just literally copied and pasted and get it done with. While I know this is not the right way to do it, I am not going to kill myself over it. When I am interested (or forced to), I might come back and learn it then.
Day 79’s project is a history lesson, with 19th century birth and death rate analysis. The point is, before finding bacteria, doctors does not wash hand, and help give birth, and women died from the infections. This one teaches the differences for checking the result, some new graphs, some new commands. The most interesting one for me is the numpy.where() command. All the others are some copy from previous days, and because I am not super interested in this, I didn’t spend a lot of time (or even concentration) on it…
I wonder, is it because I am not interested in this topic, or is it because it’s getting close to the end of it, or even worse, is it because it’s been a while so I am tired of it??
Day 78, the project is Nobel Price Country/Org/Age analysis. Today’s lesson contains a bunch of reviews, with different graphs. I found I really am NOT interested in Data Science. Even though it is a big topic nowadays, I am still not fund of it (or have the energy to really dig into it). There are a few concepts, like the .agg(), we have mentioned it a few times but I just didn’t get it (or didn’t do it right). I have to double think this few projects (or even the future ones) for Data Science, and see how I should treat them.
Day 77 project is movies analysis of budget and revenue, with seaborn and sklearn.linear_model. There are a few functions for pandas and matplotlib that’s new, and two new modules. I am not super interested in this, but since this is the future, I might as well get to know it a bit…
Day 76 is not really a “project” per se, it’s more a tutorial of Numpy and PIL image packages. There are some useful things to learn, and the image manipulation actually matches Harvard’s CS50 in a very close matter. I don’t know if it’s me or what, so far, I am not super fond of Data Science…
Day 75, the project is Google App store analysis. The idea is fun, but today is the most frustrated day so far. The new plot tool Plotly is not easy to understand, and a lot of the concept that’s requested to do it, I just don’t get it. I just followed the example, but even that is not easy. I am just gonna take my rest, and come back to it some other time. This is not a failure, it’s just a block in the road. I will just have to find a way around it, or better yet, over it.
Today’s project is a lot of graphs that are analysis of Google search result, like TSLA stock price (against search index), Bitcoin price, and eventually, US Unemployment rate. The course is teaching analysis by holding hands, and I know I can come back to this to get ideas or even copy code. But can this eventually become second nature? I don’t really know. I hope so though.
Day 73 is a LEGO sets analysis project with Pandas and more matplotlib. This is not a lot of hard things, it’s just new that we have to try a bit. Nothing super challenging here. But my concern is, if I am doing this all by myself, can I do it just like that?
Day 72 is a continuation of yesterday, a bit more Pandas. But today we added Matplotlib, and made some graphics. The project is something I have checked before, but is a good exercise to work on it.
Day 71 is not really a project, but a pandas tutorial per se. It seems that it was covered before, but then it’s not bad to cover it again. And another thing is I didn’t know Google has a tool for jupyter notebook! You learn something new everyday.