{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Regression Miniproject" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This miniproject is for groups of size 2.\n", "\n", "Find a dataset appropriate for regression analysis and, well, analyze it using regression:\n", "- Identify the input variables and the output variable. For simplicity, ignore categorical variables in your data. Also if one of the variables that you care about has invalid values in a row (e.g., '?' or nan), discard that row. Your dataset should be such that after this step you have at least 4 input variables.\n", "- Find the coefficients $\\theta$, assuming the sum of squares of errors as your cost function.\n", "- Identify which 2 input variables give the smallest error.\n", "- Is there anything that your analysis tells you that you did not know before?\n", "\n", "Some possible sources for data:\n", "- [UCI Machine Learning Repository](http://archive.ics.uci.edu/ml/datasets.html?task=reg)\n", "- [Scraping the web with beautifulsoup](https://www.crummy.com/software/BeautifulSoup/)\n", "- [Kaggle](https://www.kaggle.com/datasets)\n", "\n", "**Your team must submit the following:**\n", "- Submit any code you write, either in this notebook or as a seprate file.\n", "- Summarize your work in one or two slides in this [Google Presenation](https://docs.google.com/presentation/d/1Mh_TxKfMGvK6HWPiNTlNUFuk2x7uvaqisHt3W_Hw9LM/edit?usp=sharing). All groups will add their work to the same presenation and so everyone can see work done by others. \n", "\n", "**Grading:**\n", "- This miniproject has weight equal to half of a regular lab.\n", "- 80% of the grade will be based on my evaluation of your work.\n", "- 20% of the grade will be based on peer evaluation (more instructions will be provided later)." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.2" } }, "nbformat": 4, "nbformat_minor": 2 }