One of the most important roles of data scientists & analysts is to present data and insights in an understandable way to stakeholders. Creating dashboards is a great way to display what you are discovering in your data exploration and machine learning modeling. Plotly offers a robust open-source version of their library for building dashboards called Dash. In addition, there are multiple additional open-source libraries that make building a dashboard in Dash easy. This tutorial is an overview of one way to implement your first multi-page Dashboard app using Dash.
What is Dash?
Dash is a framework that allows you to create highly…
An explanation of the math behind facebook profit and how to tune the model using COVID-19 data as an example.
Time series data can be difficult and frustrating to work with, and the various algorithms that generate models can be quite finicky and difficult to tune. This is particularly true if you are working with data that has multiple seasonalities. In addition, traditional time series models like SARIMAX have many stringent data requirements like stationarity and equally spaced values. Other time series models like Recurring Neural Networks with Long-Short Term Memory (RNN-LSTM) can be highly complex and difficult to work with if you don’t have a significant level of understanding about neural network architecture. So for the average data analyst…
Cron allows you to schedule repeat tasks, making it a great tool to run data collection scripts
A major concern when collecting time series data is ensuring that all data is collected at equal time intervals. Without equal time intervals, you will be unable to use most methods for time series analysis. Unfortunately, not all data comes so clean and evenly spaced. Whether you are webscraping or using an API to collect your data, you may be stuck with a live feed of current data when evenly spaced historical data is unavailable. Or perhaps, you need to repeatedly grab the most up-to-date data for your dashboard or project. …
Getting Started
Using pre-existing computer vision models for object detection
In my last blog, I discussed some basics concepts of computer vision and how to create a facial recognition filter using OpenCV. But what if you want to detect in an image something other than faces? There are two possible ways forward:
- Train your own model: If you have a lot of images ready to go of the object you are trying to identify, using OpenCV’s built-in functions (like k-Nearest-Neighbors) or more powerful machine learning libraries like PyTorch and TensorFlow you could build your own model. However, this would mean that you need hundreds if not thousands of images at…
Hands-on Tutorials
Over the past 10 years, Facial recognition technology has developed rapidly and has quickly developed a variety of uses. From the utilitarian (unlocking your phone), to playful (Instagram filters), to the controversial (security, surveillance, and policing), our faces can be used by tech in many ways. Curious about how to create some facial recognition tech yourself? Facebook offers the SparkAR platform to create facial recognition filters for Facebook and Instagram. However, we can pretty easily create one ourselves using the OpenCV package in python, so we can use facial recognition anywhere.
Background Info: How do computers “see”?
To a computer, images are just a series of…
The COVID-19 pandemic has brought a lot of changes to New York City from its usual day to day hustle & bustle. Subway ridership is down 90% of its usual riders, rents in Manhattan are falling quickly while apartment vacancies are at a peak, and even foot traffic is down in many NYC neighborhoods. In the early days of the pandemic, New Yorkers were encouraged to stay at home by Governor Cuomo’s NY on Pause initiative. …
Mitchell Krieger
Mitch Krieger lives in NYC // Board of Directors at L!FE Leaders Inc. // Formerly: NYU Tisch and CITYterm at the Masters School // Hampshire College alum
