Elevating machine learning models and data science products with efficient code and python classes. — For data scientists, code is the backbone of analysis and decision-making. As data science applications grow more intricate, from machine learning models embedded in software to complex data pipelines orchestrating vast amounts of information, developing clean, organized, and maintainable code becomes crucial. Object-oriented programming (OOP) unlocks flexibility and efficiencies that…

A digestible introduction to how quantum computers work and why they are essential in evolving AI and ML systems. Gain a simple understanding of the quantum principles that power these machines. Quantum computing is a rapidly accelerating field with the power to revolutionize artificial intelligence (AI) and machine learning (ML)…

User guide to deploying Uber’s new model for sales forecasting — In a world of growing data consumption, time-series analysis has become an increasingly common and essential technique for data scientists. This step-by-step user guide to leveraging Uber’s new time-series model ORBIT is a continuation from 5 Machine Learning Techniques for Sales Forecasting. …

An easy way to use your knowledge of Python or R to efficiently learn the other. — As a native English speaker, when I started learning Spanish as a child, three key practices helped me go from awkwardly trying to translate my English words into Spanish to thinking and responding (occasionally even dreaming) directly in Spanish. Connecting the new Spanish word to the English word I already…

Comparing Linear Regression, Random Forest Regression, XGBoost, LSTMs, and ARIMA Time Series Forecasting In Python — Forecasting sales is a common and essential use of machine learning (ML). Sales forecasts can be used to identify benchmarks and determine incremental impacts of new initiatives, plan resources in response to expected demand, and project future budgets. In this article, I will show how to implement 5 different ML…

What Google’s mobility reports tell us about behavioral changes in response to COVID-19 — According to the CDC, the best way to prevent the spread of COVID-19 is to maintain a significant distance, at least 6 feet, from other people.¹ This helps to avoid passing the disease from an infected person when droplets from their nose or mouth are expelled into the air through…

Leveraging the Surprise package to build a collaborative filtering recommender in Python — To understand the power of recommendation systems, it is easiest to focus on Netflix, whose state of the art recommendation system keeps us in front of our TVs for hours. However, recommenders are extremely diverse, playing a role in cross-selling products, identifying employee candidates who have similar skill sets, and…

Performing EDA, topic modeling, and sentiment analysis on NPR’s top 350 commencement speeches — Every year leaders around the country stand up to inspire the next generation through emotional, political, and encouraging commencement speeches. As this year’s speeches near, I decided to explore how those leaders inspire youth and if gender plays a role in their approach. Design To build my corpus, I began by…

Using a Random Forest Classifier to Triage Patients in the ICU — Although this year’s WiDS Datathon asked data scientists to predict patient survival in the intensive care unit, I decided to ask a different question of the dataset. …