Learn to forecast mathematical number sequences using machine learning regression techniques in this hands-on video tutorial. Generate number series with various mathematical functions including quadratic equations, exponentials, logarithmic, and trigonometric functions using Python, pandas, and numpy. Apply scikit-learn regression models to predict future numbers based on the source sequences. Visualize data and validate forecasts using matplotlib. Cover topics such as adding noise to sequences, comparing uniform and exponential distributions, and implementing linear regression for different mathematical functions. Gain practical experience in sequence generation, model training, and forecasting for functions like sin(x) and cos(x). Perfect for those looking to enhance their skills in mathematical modeling and machine learning applications.
Forecast Any Mathematical Number Sequence with Regression - Machine Learning
Overview
Syllabus
- Tutorial Starts
- Content Introduction
- First Exercise 1/2 Starts
- Adding noise to number sequence
- Number generator and plot Function
- Uniform vs Exponential sequence
- Side by Side sequence Plotting
- y = x*x function series sequence generation
- y = x*x + x + 1 function series sequence generation
- y = -x*x -x -1 function series sequence generation
- y = -x*x + const function series sequence generation
- y = expx function series sequence generation
- y = logx function series sequence generation
- y = sinx function series sequence generation
- y = cosx function series sequence generation
- y = arctanx function series sequence generation
- Second Exercise 2/2 Starts
- Generating Sequence
- Selecting X and y for ML
- Defining Target Series for forecasting
- Linear Regression with Scikit-learn
- Regression Coefficient
- Generating new number using regression model
- Number Series Validation
- Sequence forecasting for Sinx
- Sequence forecasting for Cosx
- Saving notebooks to GitHub
- Recap
Taught by
Prodramp
