|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "code", |
| 5 | + "execution_count": 1, |
| 6 | + "metadata": { |
| 7 | + "collapsed": true, |
| 8 | + "ExecuteTime": { |
| 9 | + "end_time": "2023-06-20T18:31:03.618004Z", |
| 10 | + "start_time": "2023-06-20T18:30:58.700881Z" |
| 11 | + } |
| 12 | + }, |
| 13 | + "outputs": [], |
| 14 | + "source": [ |
| 15 | + "import tensorflow as tf" |
| 16 | + ] |
| 17 | + }, |
| 18 | + { |
| 19 | + "cell_type": "markdown", |
| 20 | + "source": [ |
| 21 | + "# What we're going to cover\n", |
| 22 | + "\n", |
| 23 | + "1. Get time series data (the historical price of Bitcoin)\n", |
| 24 | + "2. Load in time series data using pandas/Python's CSV module\n", |
| 25 | + "3. Format data for a time series problem\n", |
| 26 | + "4. Creating training and test sets (the wrong way)\n", |
| 27 | + "5. Creating training and test sets (the right way)\n", |
| 28 | + "6. Visualizing time series data\n", |
| 29 | + "7. Turning time series data into a supervised learning problem (windowing)\n", |
| 30 | + "8. Preparing univariate and multivariate (more than one variable) data\n", |
| 31 | + "9. Evaluating a time series forecasting model\n", |
| 32 | + "10. Setting up a series of deep learning modelling experiments\n", |
| 33 | + "11. Dense (fully-connected) networks\n", |
| 34 | + "12. Sequence models (LSTM and 1D CNN)\n", |
| 35 | + "13. Ensembling (combining multiple models together)\n", |
| 36 | + "14. Multivariate models\n", |
| 37 | + "15. Replicating the N-BEATS algorithm using TensorFlow layer subclassing\n", |
| 38 | + "16. Creating a modelling checkpoint to save the best performing model during training\n", |
| 39 | + "17. Making predictions (forecasts) with a time series model\n", |
| 40 | + "18. Creating prediction intervals for time series model forecasts\n", |
| 41 | + "19. Discussing two different types of uncertainty in machine learning (data uncertainty and model uncertainty)\n", |
| 42 | + "20. Demonstrating why forecasting in an open system is BS (the turkey problem)" |
| 43 | + ], |
| 44 | + "metadata": { |
| 45 | + "collapsed": false |
| 46 | + } |
| 47 | + }, |
| 48 | + { |
| 49 | + "cell_type": "code", |
| 50 | + "execution_count": null, |
| 51 | + "outputs": [], |
| 52 | + "source": [], |
| 53 | + "metadata": { |
| 54 | + "collapsed": false |
| 55 | + } |
| 56 | + } |
| 57 | + ], |
| 58 | + "metadata": { |
| 59 | + "kernelspec": { |
| 60 | + "display_name": "Python 3", |
| 61 | + "language": "python", |
| 62 | + "name": "python3" |
| 63 | + }, |
| 64 | + "language_info": { |
| 65 | + "codemirror_mode": { |
| 66 | + "name": "ipython", |
| 67 | + "version": 2 |
| 68 | + }, |
| 69 | + "file_extension": ".py", |
| 70 | + "mimetype": "text/x-python", |
| 71 | + "name": "python", |
| 72 | + "nbconvert_exporter": "python", |
| 73 | + "pygments_lexer": "ipython2", |
| 74 | + "version": "2.7.6" |
| 75 | + } |
| 76 | + }, |
| 77 | + "nbformat": 4, |
| 78 | + "nbformat_minor": 0 |
| 79 | +} |
0 commit comments