How to load a subset of data from a full dataset with given percentages proportions by a column (“Group” in this example) plus how to import/export the Excel data file. Objective:We have n food items from 4 different groups: dairy, fruits, protein, vegetable in an XLSX sheet with a header and 3 columns: Name, Group, […]
Tag: analytics
Finding target values with constraints
In this post, I share an example of a very common challenge in business which is complex to solve just by hand, along with the easy solutions. The Scenario: Let’s start with the scenario. We have a bakery that bakes 4 items that sell at our pre-determined prices as shown below: Cost (each) Bun $3.00 […]
Finding a missing number in a sequence
Imagine having a list of thousands of numbers in a sequence that is supposed to be sequential (incrementing by one) and somewhere there’s a number missing. That number could be an ID or some required piece of information. Also, what if the sequence is not incrementing by one but by some other number (e.g. by […]
Animating Charts in Excel and beyond
Some time ago I demonstrated how to create Time-lapse animations in Excel in my post here. Part of that procedure utilized a short-lived but cool feature called ‘PowerView’. Unfortunately, as of late 2021, Microsoft has removed support for PowerView in Excel (that made this time-lapse animation possible) and instead is encouraging users to use PowerBI […]
Decision Tree and Prediction (Python)
This is an example of a Decision Tree model (very useful and popular method) to make prediction using the power of Machine Learning…using just a normal PC. Here we predict salary (depedendent variable) by giving various types of criteria (different forks in a decision tree). e.g. What’s the salary of a particular gender, of some […]
Derivatives? Why?! Can I code it?
Derivatives are used to find the rate of changes of a quantity with respect to another quantity. The derivative of a variable tells us the rate of change of a function’s output value as it varies from the initial value…how much is it changing? For a straight line (e.g. linear regression), we can calculate the […]
Wanna be a weather reporter? Me neither! So let’s do Machine Learning (AI)! Part 2/2
This is a continuation of weather prediction via ML and is the final part (2/2) where I demonstrate how to write Python code to leverage a neural network algorithm called Neural Prophet, a quite straight-forward and useful model. Be sure to read the first part that focuses on understanding the data in Excel and some […]
Wanna be a weather reporter? Me neither! So let’s do Machine Learning (AI)! Part 1/2
Reporting weather by reading off the predictions is obviously a very different skill than creating the code and models that actually predicts the weather! Not just forecasting for the next 5 days, but actually PREDICTING for any number of period in the future! Is that even possible? Yes, it is albeit there are myriad of […]
Logistic Regression Example (Excel, Python)
In my previous blog on Sigmoid function, I touched on its usefulness and how it’s used to solve Logistic Regression problems either in binary or multiclass classification scenarios. Be sure to check that out http://flyingsalmon.net/?p=3879 first! In this blog, we’ll be using a dataset containing people’s ages and whether or not they bought life insurance […]
What is Sigmoid function and why?
In this blog, I touch on a core function that’s used in many machine learning scenarios whether explicitly or as a part solving a given problem. This is extremely useful for recoding values for classification (binary or multiclass) where we need to map some categorical values into a finite range of values (e.g. 0 or […]