├── .gitignore ├── LICENSE ├── README.md ├── Versions.ipynb ├── chapter_1 ├── 1_Probability_Sampling.ipynb └── 2_Stratified_Sampling .ipynb ├── chapter_10 ├── 3_Autocorrelation_mean_variance_ccf.ipynb ├── 4_noise.ipynb ├── 5_Stationary.ipynb └── airline-passengers.csv ├── chapter_11 ├── 1_arma.ipynb ├── 2_arima.ipynb ├── 3_more_on_model_evaluation.ipynb └── COCO COLA.csv ├── chapter_12 ├── 1_cross_correlation.ipynb ├── 2_arimax.ipynb └── 3_var.ipynb ├── chapter_14 ├── 1_kaplan_meier.ipynb ├── 2_Exponential_Models.ipynb └── 3_Cox_Proportional_Hazards.ipynb ├── chapter_2 ├── 1_types_of_data.ipynb ├── 2_distributions.ipynb ├── 3_Bootstrapping.ipynb ├── 4_1_Permutations_and_Combinations.ipynb ├── 4_2_Permutation_Testing.ipynb └── 5_Transformation.ipynb ├── chapter_3 ├── 3_1_Zscore_and _Zstatistics.ipynb ├── 3_2_Ztest_for_Means.ipynb ├── 3_3_Ztest_for_Proportions.ipynb └── 4_statistical_power.ipynb ├── chapter_4 ├── 1_assumptions.ipynb ├── 2_t-tests.ipynb ├── 3_multiple_tests_and_anova.ipynb └── 4_pearson_correlation.ipynb ├── chapter_5 ├── 1_permutation_test.ipynb ├── 2_rank-sum_test.ipynb ├── 3_Signed-Rank_Test.ipynb ├── 4_Kruskal-Wallis_Test.ipynb └── 5_6_Chi_Square_and_Spearman_Corr.ipynb ├── chapter_6 ├── 1_Ordinary_Least_Squares.ipynb ├── 3_linear_model_assumptions.ipynb └── 4_5_ModelValidation_RegressionVariations.ipynb ├── chapter_7 ├── 1_multiple_linear_regression.ipynb ├── 2_feature_selection.ipynb ├── 3_Shrinkage.ipynb ├── 4_Dimension_Reduction.ipynb └── Data │ └── Hitters.csv ├── chapter_8 ├── 1_Probit_and_Logit_Models.ipynb ├── 2_Multinomial_Logit_Model.ipynb ├── 3_poisson_model.ipynb └── 4_Negative_Binomial_Regression.ipynb ├── chapter_9 ├── 2_Linear_Discriminant_Analysis.ipynb └── 3_Quadratic_discriminant_analysis.ipynb └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | 3 | # standard python git ignore from 4 | # https://github.com/github/gitignore/blob/main/Python.gitignore 5 | 6 | # Byte-compiled / optimized / DLL files 7 | __pycache__/ 8 | *.py[cod] 9 | *$py.class 10 | 11 | # C extensions 12 | *.so 13 | 14 | # Distribution / packaging 15 | .Python 16 | build/ 17 | develop-eggs/ 18 | dist/ 19 | downloads/ 20 | eggs/ 21 | .eggs/ 22 | lib/ 23 | lib64/ 24 | parts/ 25 | sdist/ 26 | var/ 27 | wheels/ 28 | share/python-wheels/ 29 | *.egg-info/ 30 | .installed.cfg 31 | *.egg 32 | MANIFEST 33 | 34 | # PyInstaller 35 | # Usually these files are written by a python script from a template 36 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 37 | *.manifest 38 | *.spec 39 | 40 | # Installer logs 41 | pip-log.txt 42 | pip-delete-this-directory.txt 43 | 44 | # Unit test / coverage reports 45 | htmlcov/ 46 | .tox/ 47 | .nox/ 48 | .coverage 49 | .coverage.* 50 | .cache 51 | nosetests.xml 52 | coverage.xml 53 | *.cover 54 | *.py,cover 55 | .hypothesis/ 56 | .pytest_cache/ 57 | cover/ 58 | 59 | # Translations 60 | *.mo 61 | *.pot 62 | 63 | # Django stuff: 64 | *.log 65 | local_settings.py 66 | db.sqlite3 67 | db.sqlite3-journal 68 | 69 | # Flask stuff: 70 | instance/ 71 | .webassets-cache 72 | 73 | # Scrapy stuff: 74 | .scrapy 75 | 76 | # Sphinx documentation 77 | docs/_build/ 78 | 79 | # PyBuilder 80 | .pybuilder/ 81 | target/ 82 | 83 | # Jupyter Notebook 84 | .ipynb_checkpoints 85 | 86 | # IPython 87 | profile_default/ 88 | ipython_config.py 89 | 90 | # pyenv 91 | # For a library or package, you might want to ignore these files since the code is 92 | # intended to run in multiple environments; otherwise, check them in: 93 | # .python-version 94 | 95 | # pipenv 96 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 97 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 98 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 99 | # install all needed dependencies. 100 | #Pipfile.lock 101 | 102 | # poetry 103 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 104 | # This is especially recommended for binary packages to ensure reproducibility, and is more 105 | # commonly ignored for libraries. 106 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 107 | #poetry.lock 108 | 109 | # pdm 110 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 111 | #pdm.lock 112 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 113 | # in version control. 114 | # https://pdm.fming.dev/#use-with-ide 115 | .pdm.toml 116 | 117 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 118 | __pypackages__/ 119 | 120 | # Celery stuff 121 | celerybeat-schedule 122 | celerybeat.pid 123 | 124 | # SageMath parsed files 125 | *.sage.py 126 | 127 | # Environments 128 | .env 129 | .venv 130 | env/ 131 | venv/ 132 | ENV/ 133 | env.bak/ 134 | venv.bak/ 135 | 136 | # Spyder project settings 137 | .spyderproject 138 | .spyproject 139 | 140 | # Rope project settings 141 | .ropeproject 142 | 143 | # mkdocs documentation 144 | /site 145 | 146 | # mypy 147 | .mypy_cache/ 148 | .dmypy.json 149 | dmypy.json 150 | 151 | # Pyre type checker 152 | .pyre/ 153 | 154 | # pytype static type analyzer 155 | .pytype/ 156 | 157 | # Cython debug symbols 158 | cython_debug/ 159 | 160 | # PyCharm 161 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 162 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 163 | # and can be added to the global gitignore or merged into this file. For a more nuclear 164 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 165 | #.idea/ -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2022 Packt 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 |

Machine Learning Summit 2025

2 | 3 | ## Machine Learning Summit 2025 4 | **Bridging Theory and Practice: ML Solutions for Today’s Challenges** 5 | 6 | 3 days, 20+ experts, and 25+ tech sessions and talks covering critical aspects of: 7 | - **Agentic and Generative AI** 8 | - **Applied Machine Learning in the Real World** 9 | - **ML Engineering and Optimization** 10 | 11 | 👉 [Book your ticket now >>](https://packt.link/mlsumgh) 12 | 13 | --- 14 | 15 | ## Join Our Newsletters 📬 16 | 17 | ### DataPro 18 | *The future of AI is unfolding. Don’t fall behind.* 19 | 20 |

DataPro QR

21 | 22 | Stay ahead with [**DataPro**](https://landing.packtpub.com/subscribe-datapronewsletter/?link_from_packtlink=yes), the free weekly newsletter for data scientists, AI/ML researchers, and data engineers. 23 | From trending tools like **PyTorch**, **scikit-learn**, **XGBoost**, and **BentoML** to hands-on insights on **database optimization** and real-world **ML workflows**, you’ll get what matters, fast. 24 | 25 | > Stay sharp with [DataPro](https://landing.packtpub.com/subscribe-datapronewsletter/?link_from_packtlink=yes). Join **115K+ data professionals** who never miss a beat. 26 | 27 | --- 28 | 29 | ### BIPro 30 | *Business runs on data. Make sure yours tells the right story.* 31 | 32 |

BIPro QR

33 | 34 | [**BIPro**](https://landing.packtpub.com/subscribe-bipro-newsletter/?link_from_packtlink=yes) is your free weekly newsletter for BI professionals, analysts, and data leaders. 35 | Get practical tips on **dashboarding**, **data visualization**, and **analytics strategy** with tools like **Power BI**, **Tableau**, **Looker**, **SQL**, and **dbt**. 36 | 37 | > Get smarter with [BIPro](https://landing.packtpub.com/subscribe-bipro-newsletter/?link_from_packtlink=yes). Trusted by **35K+ BI professionals**, see what you’re missing. 38 | 39 | 40 | ### [Packt Conference : Put Generative AI to work on Oct 11-13 (Virtual)](https://packt.link/JGIEY) 41 | 42 |

[![Packt Conference](https://hub.packtpub.com/wp-content/uploads/2023/08/put-generative-ai-to-work-packt.png)](https://packt.link/JGIEY)

 43 | 3 Days, 20+ AI Experts, 25+ Workshops and Power Talks 44 | 45 | Code: USD75OFF 46 | 47 | # Building Statistical Models in Python 48 | 49 | Building Statistical Models in Python 50 | 51 | This is the code repository for [Building Statistical Models in Python](https://www.packtpub.com/product/building-statistical-models-in-python/9781804614280), published by Packt. 52 | 53 | **Develop useful models for regression, classification, time series, and survival analysis** 54 | 55 | ## What is this book about? 56 | 57 | The ability to proficiently perform statistical modeling is a fundamental skill for data scientists and essential for businesses reliant on data insights. Building Statistical Models with Python is a comprehensive guide that will empower you to leverage mathematical and statistical principles in data assessment, understanding, and inference generation. 58 | 59 | 60 | This book covers the following exciting features: 61 | * Explore the use of statistics to make decisions under uncertainty 62 | * Answer questions about data using hypothesis tests 63 | * Understand the difference between regression and classification models 64 | * Build models with stats models in Python 65 | * Analyze time series data and provide forecasts 66 | * Discover Survival Analysis and the problems it can solve 67 | 68 | If you feel this book is for you, get your [copy](https://www.amazon.in/Building-Statistical-Models-Python-classification-ebook/dp/B0C7GV7FNN/ref=monarch_sidesheet) today! 69 | 70 | https://www.packtpub.com/ 71 | 72 | ## Instructions and Navigations 73 | All of the code is organized into folders. 74 | 75 | The code will look like the following: 76 | ``` 77 | A = [3,5,4] 78 | B = [43,41,56,78,54] 79 | permutation_testing(A,B,n_iter=10000) 80 | ``` 81 | **Following is what you need for this book:** 82 | 83 | If you are looking to get started with building statistical models for your data sets, this book is for you! Building Statistical Models in Python bridges the gap between statistical theory and practical application of Python. Since you’ll take a comprehensive journey through theory and application, no previous knowledge of statistics is required, but some experience with Python will be useful. 84 | 85 | With the following software and hardware list you can run all code files present in the book (Chapter 1-14). 86 | 87 | ### Software and Hardware List 88 | 89 | | Chapter | Software required | OS required | 90 | | -------- | -------------------------------------------------------------------------------------| -----------------------------------| 91 | | 1-14 | Python version ≥ 3.8 | Any OS | 92 | | 1-14 | Statsmodels 0.13.2 | Any OS | 93 | | 1-14 | SciPy 1.8.1 | Any OS | 94 | | 1-14 | lifelines 0.27.4 | Any OS | 95 | | 1-14 | scikit-learn 1.1.1 | Any OS | 96 | | 1-14 | pmdarima 2.02 | Any OS | 97 | | 1-14 | Sktime 0.15.0 | Any OS | 98 | | 1-14 | Pandas 1.4.3 | Any OS | 99 | | 1-14 | Matplotlib 3.5.2 | Any OS | 100 | | 1-14 | Numpy 1.23.0 | Any OS | 101 | 102 | 103 | ### Related products 104 | * Hands-On Simulation Modeling with Python - Second Edition [[Packt]](https://www.packtpub.com/product/hands-on-simulation-modeling-with-python-second-edition/9781804616888) [[Amazon]](https://www.amazon.in/Hands-Simulation-Modeling-Python-decision-making/dp/1804616885/ref=sr_1_4?keywords=Hands-On+Simulation+Modeling+with+Python&sr=8-4) 105 | 106 | * Modern Time Series Forecasting with Python [[Packt]](https://www.packtpub.com/product/modern-time-series-forecasting-with-python/9781803246802) [[Amazon]](https://www.amazon.in/Modern-Time-Forecasting-Python-industry-ready/dp/1803246804/ref=sr_1_1?keywords=Modern+Time+Series+Forecasting+with+Python&sr=8-1) 107 | 108 | ## Get to Know the Author(s) 109 | **Huy Hoang Nguyen** is a mathematician and data scientist with extensive experience in advanced mathematics, strategic leadership, and applied machine learning research. He holds a PhD in Mathematics, as well as two Master’s degrees in Applied Mathematics and Data Science. His previous work focused on Partial Differential Equations, Functional Analysis, and their applications in Fluid Mechanics. After transitioning from academia to the healthcare industry, he has undertaken a variety of data science projects, ranging from traditional machine learning to deep learning. 110 | 111 | **Paul Adams** is a Data Scientist with a background primarily in the healthcare industry, on both the provider and insurance sides of business. Paul applies statistics and machine learning in multiple areas of industry, focusing on projects in process engineering, process improvement, metrics and business rules development, anomaly detection, forecasting, clustering and classification. Paul holds a Master of Science in Data Science from Southern Methodist University. 112 | 113 | **Stuart Miller** is a Machine Learning Engineer with degrees in Data Science, Electrical Engineering, and Engineering Physics. Stuart has worked at several Fortune 500 companies, including Texas Instruments and StateFarm, where he built software that utilized statistical and machine learning techniques. Stuart is currently an engineer at Toyota Connected helping to build a more modern cockpit experience for drivers using machine learning 114 | ## Setup Instructions 115 | 116 | To install the packages required for this book, 117 | enter the following commands in a terminal. 118 | 119 | ```bash 120 | # clone repo 121 | git clone git@github.com:PacktPublishing/Implementing-Statistical-Modeling-with-Python.git 122 | 123 | # navigate to the folder 124 | cd Implementing-Statistical-Modeling-with-Python 125 | 126 | # setup python environment 127 | # (this installs the packages used in the book) 128 | python3 -m venv venv 129 | source venv/bin/activate 130 | pip install -r requirements.txt 131 | ``` 132 | 133 | *Note:* Installation instructions for Anaconda are provided in Chapter 1. 134 | -------------------------------------------------------------------------------- /Versions.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "07c418a4-15aa-47f9-879f-6f16f0541466", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import numpy as np\n", 11 | "import scipy as sp\n", 12 | "import pandas as pd\n", 13 | "import statsmodels as sm\n", 14 | "import matplotlib\n", 15 | "import sklearn" 16 | ] 17 | }, 18 | { 19 | "cell_type": "code", 20 | "execution_count": 2, 21 | "id": "fb043b27-88b6-4cda-97c6-5e99d6304393", 22 | "metadata": {}, 23 | "outputs": [ 24 | { 25 | "name": "stdout", 26 | "output_type": "stream", 27 | "text": [ 28 | "numpy version: 1.23.0\n", 29 | "scipy version: 1.8.1\n", 30 | "pandas version: 1.4.3\n", 31 | "statsmodels version: 0.13.2\n", 32 | "matplotlib version: 3.5.2\n", 33 | "sklearn version: 1.1.1\n" 34 | ] 35 | } 36 | ], 37 | "source": [ 38 | "print(f\"numpy version: {np.__version__}\")\n", 39 | "print(f\"scipy version: {sp.__version__}\")\n", 40 | "print(f\"pandas version: {pd.__version__}\")\n", 41 | "print(f\"statsmodels version: {sm.__version__}\")\n", 42 | "print(f\"matplotlib version: {matplotlib.__version__}\")\n", 43 | "print(f\"sklearn version: {sklearn.__version__}\")" 44 | ] 45 | } 46 | ], 47 | "metadata": { 48 | "kernelspec": { 49 | "display_name": "Python 3 (ipykernel)", 50 | "language": "python", 51 | "name": "python3" 52 | }, 53 | "language_info": { 54 | "codemirror_mode": { 55 | "name": "ipython", 56 | "version": 3 57 | }, 58 | "file_extension": ".py", 59 | "mimetype": "text/x-python", 60 | "name": "python", 61 | "nbconvert_exporter": "python", 62 | "pygments_lexer": "ipython3", 63 | "version": "3.8.0" 64 | } 65 | }, 66 | "nbformat": 4, 67 | "nbformat_minor": 5 68 | } 69 | -------------------------------------------------------------------------------- /chapter_1/1_Probability_Sampling.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "fbdd15f6-13a4-4a10-85d4-91f1eb43ff97", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import numpy as np " 11 | ] 12 | }, 13 | { 14 | "cell_type": "code", 15 | "execution_count": 2, 16 | "id": "e13e95dd-8962-4726-9a28-e62edec570d3", 17 | "metadata": {}, 18 | "outputs": [], 19 | "source": [ 20 | "# setup generator for reproducibility \n", 21 | "random_generator = np.random.default_rng(2020) " 22 | ] 23 | }, 24 | { 25 | "cell_type": "code", 26 | "execution_count": 3, 27 | "id": "449621a5-a5ab-4be8-805d-c3aa853cd531", 28 | "metadata": {}, 29 | "outputs": [ 30 | { 31 | "name": "stdout", 32 | "output_type": "stream", 33 | "text": [ 34 | "[1 8 5]\n" 35 | ] 36 | } 37 | ], 38 | "source": [ 39 | "population = np.arange(1, 10 + 1) \n", 40 | "sample = random_generator.choice( \n", 41 | " population, # sample from population \n", 42 | " size=3, # number of samples to take \n", 43 | " replace=False # only allow to sample individuals once \n", 44 | ") \n", 45 | "print(sample) \n", 46 | "# array([1, 8, 5]) " 47 | ] 48 | } 49 | ], 50 | "metadata": { 51 | "kernelspec": { 52 | "display_name": "Python 3 (ipykernel)", 53 | "language": "python", 54 | "name": "python3" 55 | }, 56 | "language_info": { 57 | "codemirror_mode": { 58 | "name": "ipython", 59 | "version": 3 60 | }, 61 | "file_extension": ".py", 62 | "mimetype": "text/x-python", 63 | "name": "python", 64 | "nbconvert_exporter": "python", 65 | "pygments_lexer": "ipython3", 66 | "version": "3.9.7" 67 | } 68 | }, 69 | "nbformat": 4, 70 | "nbformat_minor": 5 71 | } 72 | -------------------------------------------------------------------------------- /chapter_1/2_Stratified_Sampling .ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "b6096342-9963-495e-a8df-95a396e4a59e", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import numpy as np " 11 | ] 12 | }, 13 | { 14 | "cell_type": "code", 15 | "execution_count": 2, 16 | "id": "5a4b7682-9534-4c70-8fe6-024a1b7946a8", 17 | "metadata": {}, 18 | "outputs": [], 19 | "source": [ 20 | "# setup generator for reproducibility \n", 21 | "random_generator = np.random.default_rng(2020)\n", 22 | " " 23 | ] 24 | }, 25 | { 26 | "cell_type": "code", 27 | "execution_count": 3, 28 | "id": "ff34a34d-70a9-4868-b4e5-7b42717ae2f8", 29 | "metadata": {}, 30 | "outputs": [], 31 | "source": [ 32 | " \n", 33 | "population = [ \n", 34 | " 1, \"A\", 3, 4, \n", 35 | " 5, 2, \"D\", 8, \n", 36 | " \"C\", 7, 6, \"B\" \n", 37 | "] \n", 38 | "# group strata \n", 39 | "strata = { \n", 40 | " 'number' : [], \n", 41 | " 'string' : [], \n", 42 | "} \n", 43 | " " 44 | ] 45 | }, 46 | { 47 | "cell_type": "code", 48 | "execution_count": 4, 49 | "id": "27f6d1c6-dcc9-49c8-bbc4-9f964470710b", 50 | "metadata": {}, 51 | "outputs": [ 52 | { 53 | "name": "stdout", 54 | "output_type": "stream", 55 | "text": [ 56 | "{'number': array([4, 1, 2, 8]), 'string': array(['D', 'C'], dtype='" 36 | ] 37 | }, 38 | "metadata": { 39 | "needs_background": "light" 40 | }, 41 | "output_type": "display_data" 42 | } 43 | ], 44 | "source": [ 45 | "label = ['model A', 'model B']\n", 46 | "counts = [3, 5]\n", 47 | "\n", 48 | "edu_label = ['BS', 'MS', 'PhD']\n", 49 | "edu_counts = [10, 5, 2]\n", 50 | "\n", 51 | "fig, ax = plt.subplots(1,2, figsize=(12, 5))\n", 52 | "\n", 53 | "ax[0].bar(label, counts)\n", 54 | "ax[0].set_title('Counts of Machine Models')\n", 55 | "ax[0].set_ylabel('Count')\n", 56 | "ax[0].set_xlabel('Machine Model')\n", 57 | "\n", 58 | "ax[1].bar(edu_label, edu_counts)\n", 59 | "ax[1].set_title('Counts of Education Level')\n", 60 | "ax[1].set_ylabel('Count')\n", 61 | "ax[1].set_xlabel('Education Level')\n", 62 | "\n", 63 | "fig.savefig('figure2.2.png', dpi=300);" 64 | ] 65 | }, 66 | { 67 | "cell_type": "markdown", 68 | "id": "d65b37de-a8c6-4bee-b59b-c60740289677", 69 | "metadata": {}, 70 | "source": [ 71 | "Wait time example histogram." 72 | ] 73 | }, 74 | { 75 | "cell_type": "code", 76 | "execution_count": 5, 77 | "id": "af15610e-1465-4821-85de-7d0c43a4402e", 78 | "metadata": {}, 79 | "outputs": [ 80 | { 81 | "data": { 82 | "image/png": "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", 83 | "text/plain": [ 84 | "
" 85 | ] 86 | }, 87 | "metadata": { 88 | "needs_background": "light" 89 | }, 90 | "output_type": "display_data" 91 | } 92 | ], 93 | "source": [ 94 | "a = 4\n", 95 | "x = skewnorm.rvs(a, size=3000) + 0.5\n", 96 | "x = x[x > 0]\n", 97 | "\n", 98 | "# dfw highs for april and may 2022\n", 99 | "# retrieved from https://www.iweathernet.com/texas-dfw-weather-records\n", 100 | "dfw_highs = [\n", 101 | " 85, 87, 75, 88, 80, 86, 90, 94 , 93, 92, 90, 92, 94,\n", 102 | " 93, 97, 90, 95, 96, 96, 95, 92, 70, 79, 73, 88, 92,\n", 103 | " 94, 93, 95, 76, 78, 86, 81, 95, 77, 71, 69, 88, 86,\n", 104 | " 89, 84, 82, 77, 84, 81, 79, 75, 75, 91, 86, 86, 84,\n", 105 | " 82, 68, 75, 78, 82, 83, 85\n", 106 | "]\n", 107 | "\n", 108 | "fig, ax = plt.subplots(1,2, figsize=(12, 5))\n", 109 | "\n", 110 | "ax[0].hist(x, bins=30)\n", 111 | "ax[0].set_xlabel('Wait Time (hr)')\n", 112 | "ax[0].set_ylabel('Frequency')\n", 113 | "ax[0].set_title('Wait Times');\n", 114 | "\n", 115 | "ax[1].hist(dfw_highs, bins=7)\n", 116 | "ax[1].set_title('High Temperatures for DFW (4/2022-5/2022)')\n", 117 | "ax[1].set_ylabel('Frequency')\n", 118 | "ax[1].set_xlabel('Temperature (F)');\n", 119 | "\n", 120 | "fig.savefig('figure2.3.png', dpi=300);" 121 | ] 122 | }, 123 | { 124 | "cell_type": "code", 125 | "execution_count": null, 126 | "id": "8d4b06ff", 127 | "metadata": {}, 128 | "outputs": [], 129 | "source": [] 130 | } 131 | ], 132 | "metadata": { 133 | "kernelspec": { 134 | "display_name": "Python 3 (ipykernel)", 135 | "language": "python", 136 | "name": "python3" 137 | }, 138 | "language_info": { 139 | "codemirror_mode": { 140 | "name": "ipython", 141 | "version": 3 142 | }, 143 | "file_extension": ".py", 144 | "mimetype": "text/x-python", 145 | "name": "python", 146 | "nbconvert_exporter": "python", 147 | "pygments_lexer": "ipython3", 148 | "version": "3.8.0" 149 | }, 150 | "vscode": { 151 | "interpreter": { 152 | "hash": "c98c9082bd23a1abe952c03d7cf1f940136afe77006f0c5f53f05fb13ab2661a" 153 | } 154 | } 155 | }, 156 | "nbformat": 4, 157 | "nbformat_minor": 5 158 | } 159 | -------------------------------------------------------------------------------- /chapter_2/4_1_Permutations_and_Combinations.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "f831728b-1ef5-46e9-b0e9-8f985ecc21d3", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "# Permutations\n", 11 | "\n", 12 | "from itertools import permutations " 13 | ] 14 | }, 15 | { 16 | "cell_type": "code", 17 | "execution_count": 2, 18 | "id": "7756e167-5876-40c1-a48a-070bb5793acc", 19 | "metadata": {}, 20 | "outputs": [ 21 | { 22 | "name": "stdout", 23 | "output_type": "stream", 24 | "text": [ 25 | "There are 720 ways to distribute the prizes!\n" 26 | ] 27 | } 28 | ], 29 | "source": [ 30 | "# list of 10 people in the party \n", 31 | "people = ['P1','P2','P3','P4','P5','P6','P7','P8','P9','P10'] \n", 32 | "# all the ways that the 3 prizes are distributed \n", 33 | "perm = permutations(people, 3) \n", 34 | "list_perm = list(perm) \n", 35 | "print(f\"There are {len(list_perm)} ways to distribute the prizes!\")" 36 | ] 37 | }, 38 | { 39 | "cell_type": "code", 40 | "execution_count": 3, 41 | "id": "a528fa69-6239-4ea2-bdda-8c04a168e8e1", 42 | "metadata": {}, 43 | "outputs": [ 44 | { 45 | "name": "stdout", 46 | "output_type": "stream", 47 | "text": [ 48 | "There are 3628800 ways to distribute the prizes!\n" 49 | ] 50 | } 51 | ], 52 | "source": [ 53 | "# list of 10 people in the party \n", 54 | "people = ['P1','P2','P3','P4','P5','P6','P7','P8','P9','P10'] \n", 55 | "# all the ways that the 10 different gifts are distributed \n", 56 | "perm = permutations(people) \n", 57 | "list_perm = list(perm) \n", 58 | "print(f\"There are {len(list_perm)} ways to distribute the prizes!\")" 59 | ] 60 | }, 61 | { 62 | "cell_type": "code", 63 | "execution_count": null, 64 | "id": "4ec9ff2d-1abb-4ec5-8509-ecdbe5fba469", 65 | "metadata": {}, 66 | "outputs": [], 67 | "source": [] 68 | }, 69 | { 70 | "cell_type": "code", 71 | "execution_count": 4, 72 | "id": "efbbcfe3-fcd0-4ce8-8464-6f77538db7ae", 73 | "metadata": {}, 74 | "outputs": [], 75 | "source": [ 76 | "# Combinations\n", 77 | "from itertools import combinations" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": 5, 83 | "id": "d92604c5-4005-4e3c-9353-cdc73d42157f", 84 | "metadata": {}, 85 | "outputs": [ 86 | { 87 | "name": "stdout", 88 | "output_type": "stream", 89 | "text": [ 90 | "There are 120 ways to distribute the prizes!\n" 91 | ] 92 | } 93 | ], 94 | "source": [ 95 | "# list of 10 people in the party \n", 96 | "people = ['P1','P2','P3','P4','P5','P6','P7','P8','P9','P10'] \n", 97 | "# all the ways that the 3 prizes are distributed \n", 98 | "comb = combinations(people, 3) \n", 99 | "list_comb = list(comb) \n", 100 | "print(f\"There are {len(list_comb)} ways to distribute the prizes!\") " 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "execution_count": null, 106 | "id": "362da4e7-e3ec-47f2-9458-6663ea0a66f3", 107 | "metadata": {}, 108 | "outputs": [], 109 | "source": [] 110 | } 111 | ], 112 | "metadata": { 113 | "kernelspec": { 114 | "display_name": "Python 3 (ipykernel)", 115 | "language": "python", 116 | "name": "python3" 117 | }, 118 | "language_info": { 119 | "codemirror_mode": { 120 | "name": "ipython", 121 | "version": 3 122 | }, 123 | "file_extension": ".py", 124 | "mimetype": "text/x-python", 125 | "name": "python", 126 | "nbconvert_exporter": "python", 127 | "pygments_lexer": "ipython3", 128 | "version": "3.9.7" 129 | } 130 | }, 131 | "nbformat": 4, 132 | "nbformat_minor": 5 133 | } 134 | -------------------------------------------------------------------------------- /chapter_2/4_2_Permutation_Testing.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "e17c8e22-7fc5-437b-9e3f-ae0e643a7089", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import numpy as np" 11 | ] 12 | }, 13 | { 14 | "cell_type": "code", 15 | "execution_count": 2, 16 | "id": "c1c628e4-f2fc-466f-9a25-c8b63fabd0cd", 17 | "metadata": {}, 18 | "outputs": [], 19 | "source": [ 20 | "# create permutation testing function \n", 21 | "def permutation_testing(A,B,n_iter=1000):\n", 22 | "#A, B are 2 lists of samples to test the hypothesis,  \n", 23 | "#n_iter is number of iterations with the default is 1000  \n", 24 | " differences = []\n", 25 | " P = np.array(A+B)\n", 26 | " original_mean = np.array(A).mean()-np.array(B).mean()\n", 27 | " for i in range(n_iter):\n", 28 | " np.random.shuffle(P) # create a random permutation of P\n", 29 | " A_new = P[:len(A)] # having the same size of A \n", 30 | " B_new = P[-len(B):] # having the same size of B \n", 31 | " differences.append(A_new.mean()-B_new.mean()) \n", 32 | " #Calculate p_value \n", 33 | " p_value = round(1-(float(len(np.where(differences<=original_mean)[0]))/float(n_iter)),2) \n", 34 | " return p_value " 35 | ] 36 | }, 37 | { 38 | "cell_type": "code", 39 | "execution_count": 3, 40 | "id": "e96b6297-e200-435f-8e6c-ff44bd431445", 41 | "metadata": {}, 42 | "outputs": [ 43 | { 44 | "data": { 45 | "text/plain": [ 46 | "0.98" 47 | ] 48 | }, 49 | "execution_count": 3, 50 | "metadata": {}, 51 | "output_type": "execute_result" 52 | } 53 | ], 54 | "source": [ 55 | "A = [3,5,4]\n", 56 | "B = [43,41,56,78,54]\n", 57 | "\n", 58 | "permutation_testing(A,B,n_iter=10000)" 59 | ] 60 | }, 61 | { 62 | "cell_type": "code", 63 | "execution_count": null, 64 | "id": "e530312a-2b4f-498e-b386-535e9768842d", 65 | "metadata": {}, 66 | "outputs": [], 67 | "source": [] 68 | } 69 | ], 70 | "metadata": { 71 | "kernelspec": { 72 | "display_name": "Python 3 (ipykernel)", 73 | "language": "python", 74 | "name": "python3" 75 | }, 76 | "language_info": { 77 | "codemirror_mode": { 78 | "name": "ipython", 79 | "version": 3 80 | }, 81 | "file_extension": ".py", 82 | "mimetype": "text/x-python", 83 | "name": "python", 84 | "nbconvert_exporter": "python", 85 | "pygments_lexer": "ipython3", 86 | "version": "3.9.7" 87 | } 88 | }, 89 | "nbformat": 4, 90 | "nbformat_minor": 5 91 | } 92 | -------------------------------------------------------------------------------- /chapter_2/5_Transformation.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "3c9672c4-507e-4b42-99d3-3804e2b44906", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import numpy as np\n", 11 | "import matplotlib.pyplot as plt" 12 | ] 13 | }, 14 | { 15 | "cell_type": "code", 16 | "execution_count": 2, 17 | "id": "6549417b-8adc-4860-ab39-9aa7a4a91b0e", 18 | "metadata": {}, 19 | "outputs": [], 20 | "source": [ 21 | "np.random.seed(42) # for reproducible purpose \n", 22 | "\n", 23 | "# create a random data  \n", 24 | "df = np.random.beta(a=1,b=10,size=10000)\n", 25 | "df_log = np.log(df) #log transformation\n", 26 | "df_sqrt = np.sqrt(df) # Square Root transformation \n", 27 | "df_cbrt = np.cbrt(df) # Cube Root transformation " 28 | ] 29 | }, 30 | { 31 | "cell_type": "code", 32 | "execution_count": 3, 33 | "id": "cdd5ec94-7342-4690-b050-11b9385a3544", 34 | "metadata": {}, 35 | "outputs": [ 36 | { 37 | "data": { 38 | "image/png": "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\n", 39 | "text/plain": [ 40 | "
" 41 | ] 42 | }, 43 | "metadata": { 44 | "needs_background": "light" 45 | }, 46 | "output_type": "display_data" 47 | } 48 | ], 49 | "source": [ 50 | "#Plots \n", 51 | "\n", 52 | "plt.figure(figsize=(10,10))\n", 53 | "plt.subplot(2,2,1)\n", 54 | "plt.hist(df)\n", 55 | "plt.title(\"Original Data\")\n", 56 | "plt.subplot(2,2,2) \n", 57 | "plt.hist(df_log) \n", 58 | "plt.title(\"Log Transformation\") \n", 59 | "plt.subplot(2,2,3) \n", 60 | "plt.hist(df_sqrt) \n", 61 | "plt.title(\"Square Root Transformation\") \n", 62 | "plt.subplot(2,2,4) \n", 63 | "plt.hist(df_cbrt) \n", 64 | "plt.title(\"Cube Root Transformation\") \n", 65 | "plt.show()" 66 | ] 67 | }, 68 | { 69 | "cell_type": "code", 70 | "execution_count": null, 71 | "id": "acd71a93-36e5-4efb-b86e-877b9101f7d6", 72 | "metadata": {}, 73 | "outputs": [], 74 | "source": [] 75 | } 76 | ], 77 | "metadata": { 78 | "kernelspec": { 79 | "display_name": "Python 3 (ipykernel)", 80 | "language": "python", 81 | "name": "python3" 82 | }, 83 | "language_info": { 84 | "codemirror_mode": { 85 | "name": "ipython", 86 | "version": 3 87 | }, 88 | "file_extension": ".py", 89 | "mimetype": "text/x-python", 90 | "name": "python", 91 | "nbconvert_exporter": "python", 92 | "pygments_lexer": "ipython3", 93 | "version": "3.9.7" 94 | } 95 | }, 96 | "nbformat": 4, 97 | "nbformat_minor": 5 98 | } 99 | -------------------------------------------------------------------------------- /chapter_3/3_1_Zscore_and _Zstatistics.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "aa4f724c-1bcb-46f8-b555-f63e09128118", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import pandas as pd \n", 11 | "import numpy as np \n", 12 | "import scipy.stats as stats \n", 13 | "import math " 14 | ] 15 | }, 16 | { 17 | "cell_type": "code", 18 | "execution_count": 2, 19 | "id": "fb4c9ca9-1110-4b2e-8292-fb92f213bbe7", 20 | "metadata": {}, 21 | "outputs": [ 22 | { 23 | "data": { 24 | "text/html": [ 25 | "
\n", 26 | "\n", 39 | "\n", 40 | " \n", 41 | " \n", 42 | " \n", 43 | " \n", 44 | " \n", 45 | " \n", 46 | " \n", 47 | " \n", 48 | " \n", 49 | " \n", 50 | " \n", 51 | " \n", 52 | " \n", 53 | " \n", 54 | " \n", 55 | " \n", 56 | " \n", 57 | " \n", 58 | " \n", 59 | " \n", 60 | " \n", 61 | " \n", 62 | " \n", 63 | " \n", 64 | " \n", 65 | " \n", 66 | " \n", 67 | " \n", 68 | " \n", 69 | " \n", 70 | " \n", 71 | " \n", 72 | " \n", 73 | " \n", 74 | " \n", 75 | " \n", 76 | " \n", 77 | " \n", 78 | " \n", 79 | " \n", 80 | " \n", 81 | " \n", 82 | " \n", 83 | " \n", 84 | " \n", 85 | " \n", 86 | " \n", 87 | " \n", 88 | " \n", 89 | " \n", 90 | " \n", 91 | " \n", 92 | " \n", 93 | " \n", 94 | " \n", 95 | " \n", 96 | " \n", 97 | " \n", 98 | " \n", 99 | "
IQ scorez-score
090-0.860663
178-1.721326
21100.573775
31100.573775
499-0.215166
51150.932385
61302.008214
7100-0.143444
895-0.502053
993-0.645497
\n", 100 | "
" 101 | ], 102 | "text/plain": [ 103 | " IQ score z-score\n", 104 | "0 90 -0.860663\n", 105 | "1 78 -1.721326\n", 106 | "2 110 0.573775\n", 107 | "3 110 0.573775\n", 108 | "4 99 -0.215166\n", 109 | "5 115 0.932385\n", 110 | "6 130 2.008214\n", 111 | "7 100 -0.143444\n", 112 | "8 95 -0.502053\n", 113 | "9 93 -0.645497" 114 | ] 115 | }, 116 | "execution_count": 2, 117 | "metadata": {}, 118 | "output_type": "execute_result" 119 | } 120 | ], 121 | "source": [ 122 | "IQ = np.array([90, 78,110, 110, 99, 115,130, 100, 95, 93]) \n", 123 | "z_score = stats.zscore(IQ) \n", 124 | " \n", 125 | "# Create dataframe \n", 126 | " \n", 127 | "data_zscore = { \n", 128 | " \"IQ score\": IQ, \n", 129 | " \"z-score\": z_score \n", 130 | "} \n", 131 | " \n", 132 | "IQ_zscore = pd.DataFrame(data_zscore) \n", 133 | "IQ_zscore " 134 | ] 135 | }, 136 | { 137 | "cell_type": "code", 138 | "execution_count": 3, 139 | "id": "4c556684-f3a1-49d0-bb71-b405193cb49d", 140 | "metadata": {}, 141 | "outputs": [ 142 | { 143 | "name": "stdout", 144 | "output_type": "stream", 145 | "text": [ 146 | "The probability that the taken score between 95 and 104 is 29.02%!\n" 147 | ] 148 | } 149 | ], 150 | "source": [ 151 | "#calculate z scores at x=95 and 104 \n", 152 | "zscore_95 = round((95-98)/12,2) \n", 153 | "zscore_104 = round((104-98)/12,2) \n", 154 | " \n", 155 | "#calculate cdf and probability \n", 156 | "cdf_95 = stats.norm.cdf(zscore_95) \n", 157 | "cdf_104 = stats.norm.cdf(zscore_104) \n", 158 | "prob = abs(cdf_95-cdf_104) \n", 159 | " \n", 160 | "#print the probability \n", 161 | "print(f\"The probability that the taken score between 95 and 104 is {round(prob*100,2)}%!\") " 162 | ] 163 | }, 164 | { 165 | "cell_type": "code", 166 | "execution_count": 4, 167 | "id": "032b6685-ef70-4bbf-9d70-a42660e3c3c6", 168 | "metadata": {}, 169 | "outputs": [ 170 | { 171 | "name": "stdout", 172 | "output_type": "stream", 173 | "text": [ 174 | "The probability that the taken score between 95 and 104 is 53.28%!\n" 175 | ] 176 | } 177 | ], 178 | "source": [ 179 | " # standard error \n", 180 | "n= 4 \n", 181 | "sigma = 12 \n", 182 | "se = sigma/math.sqrt(n) \n", 183 | " \n", 184 | "#calculate z scores at x=95 and 104 \n", 185 | "zscore_95 = round((95-98)/se,2) \n", 186 | "zscore_104 = round((104-98)/se,2) \n", 187 | " \n", 188 | "#calculate cdf and probability \n", 189 | "cdf_95 = stats.norm.cdf(zscore_95) \n", 190 | "cdf_104 = stats.norm.cdf(zscore_104) \n", 191 | "prob = abs(cdf_95-cdf_104) \n", 192 | " \n", 193 | "#print the probability \n", 194 | "print(f\"The probability that the taken score between 95 and 104 is {round(prob*100,2)}%!\") " 195 | ] 196 | } 197 | ], 198 | "metadata": { 199 | "kernelspec": { 200 | "display_name": "Python 3 (ipykernel)", 201 | "language": "python", 202 | "name": "python3" 203 | }, 204 | "language_info": { 205 | "codemirror_mode": { 206 | "name": "ipython", 207 | "version": 3 208 | }, 209 | "file_extension": ".py", 210 | "mimetype": "text/x-python", 211 | "name": "python", 212 | "nbconvert_exporter": "python", 213 | "pygments_lexer": "ipython3", 214 | "version": "3.9.7" 215 | } 216 | }, 217 | "nbformat": 4, 218 | "nbformat_minor": 5 219 | } 220 | -------------------------------------------------------------------------------- /chapter_3/3_2_Ztest_for_Means.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "id": "ae1383f5-2299-49bc-ae1f-f17393b852bc", 6 | "metadata": {}, 7 | "source": [ 8 | "## One-sample Z-test" 9 | ] 10 | }, 11 | { 12 | "cell_type": "code", 13 | "execution_count": 1, 14 | "id": "5e1e577e-a737-4196-859d-577273d5357e", 15 | "metadata": {}, 16 | "outputs": [], 17 | "source": [ 18 | "import scipy.stats \n", 19 | "import numpy as np\n", 20 | "import math\n", 21 | "from statsmodels.stats.weightstats import ztest as ztest " 22 | ] 23 | }, 24 | { 25 | "cell_type": "code", 26 | "execution_count": 2, 27 | "id": "0c48d248-4ce4-4820-8be6-92b7ee90b1ad", 28 | "metadata": {}, 29 | "outputs": [ 30 | { 31 | "data": { 32 | "text/plain": [ 33 | "0.0038" 34 | ] 35 | }, 36 | "execution_count": 2, 37 | "metadata": {}, 38 | "output_type": "execute_result" 39 | } 40 | ], 41 | "source": [ 42 | "#find p-value associated with a z-score of -2.67 in a left-tailed test. \n", 43 | "round(scipy.stats.norm.sf(abs(-2.67)),4)" 44 | ] 45 | }, 46 | { 47 | "cell_type": "code", 48 | "execution_count": 3, 49 | "id": "2643b01a-7689-47ae-87aa-2e9afada8bf7", 50 | "metadata": {}, 51 | "outputs": [ 52 | { 53 | "data": { 54 | "text/plain": [ 55 | "0.007585124695370977" 56 | ] 57 | }, 58 | "execution_count": 3, 59 | "metadata": {}, 60 | "output_type": "execute_result" 61 | } 62 | ], 63 | "source": [ 64 | "#find p-value for two-tailed test \n", 65 | "scipy.stats.norm.sf(abs(2.67))*2 " 66 | ] 67 | }, 68 | { 69 | "cell_type": "code", 70 | "execution_count": 4, 71 | "id": "2c2119f8-27f3-476c-acab-cbb8fb4001e9", 72 | "metadata": {}, 73 | "outputs": [ 74 | { 75 | "name": "stdout", 76 | "output_type": "stream", 77 | "text": [ 78 | " The critical value is -1.6448536269514729\n", 79 | " The critical value is 1.6448536269514722\n", 80 | " The critical values are -1.959963984540054 and 1.959963984540054\n" 81 | ] 82 | } 83 | ], 84 | "source": [ 85 | "# To compute the critical value \n", 86 | "#The following is the implementation of the code in Python for left-tailed, right-tailed and two-tailed tests. \n", 87 | "\n", 88 | "alpha = 0.05 # level of significance \n", 89 | " \n", 90 | "#find Z critical value for left-tailed test \n", 91 | "print(f\" The critical value is {scipy.stats.norm.ppf(alpha)}\") \n", 92 | " \n", 93 | "#find Z critical value for left-tailed test \n", 94 | "print(f\" The critical value is {scipy.stats.norm.ppf(1-alpha)}\") \n", 95 | " \n", 96 | "##find Z critical value for two-tailed test \n", 97 | "print(f\" The critical values are {-scipy.stats.norm.ppf(1-alpha/2)} and {scipy.stats.norm.ppf(1-alpha/2)}\") " 98 | ] 99 | }, 100 | { 101 | "cell_type": "code", 102 | "execution_count": 5, 103 | "id": "467617c0-0a3e-4174-8e03-79903e78ff3a", 104 | "metadata": {}, 105 | "outputs": [ 106 | { 107 | "data": { 108 | "text/plain": [ 109 | "104.16666666666667" 110 | ] 111 | }, 112 | "execution_count": 5, 113 | "metadata": {}, 114 | "output_type": "execute_result" 115 | } 116 | ], 117 | "source": [ 118 | "# Example of IQ test scores again in the high school in Dallas \n", 119 | "IQscores = [95,110, 105, 120, 125, 110, 98, 90, 99, 100, \n", 120 | " 110, 112, 106, 92, 108, 97, 95, 99, 100, 100, \n", 121 | " 103, 125, 122, 110, 112, 102, 92, 97, 89, 102] \n", 122 | " \n", 123 | "IQmean = np.array(IQscores).mean() \n", 124 | "IQmean" 125 | ] 126 | }, 127 | { 128 | "cell_type": "code", 129 | "execution_count": 6, 130 | "id": "de560509-8959-4264-b348-d2e0fecdbbaa", 131 | "metadata": {}, 132 | "outputs": [], 133 | "source": [ 134 | "# with level of significance 0.05\n", 135 | "\n", 136 | "n=30 #number of students \n", 137 | "sigma =12 #population standard deviation \n", 138 | "IQmean = 104.17 # IQ mean of 30 students after the training \n", 139 | "mu = 98 # population mean \n", 140 | " \n", 141 | "z = (IQmean-mu)/(sigma/math.sqrt(n)) #z = 2.81620681650573\n", 142 | "\n", 143 | "# Since the test statistic value 2.8162 > 1.64485, we reject the null hypothesis. \n", 144 | "# This means that the training does affect the IQ levels of these students and helps them improve their IQ scores. " 145 | ] 146 | }, 147 | { 148 | "cell_type": "code", 149 | "execution_count": 7, 150 | "id": "6ffbb49e-5bcc-4fa4-bb83-594aa7765555", 151 | "metadata": {}, 152 | "outputs": [ 153 | { 154 | "name": "stdout", 155 | "output_type": "stream", 156 | "text": [ 157 | "The test statistic is 3.397499328379722 and the corresponding p-value is 0.00034002377451735716.\n" 158 | ] 159 | } 160 | ], 161 | "source": [ 162 | "# Example of IQ test scores again in the high school in Dallas\n", 163 | "\n", 164 | " \n", 165 | "#IQ scores after training sections \n", 166 | "IQscores = [95,110, 105, 120, 125, 110, 98, 90, 99, 100, \n", 167 | " 110, 112, 106, 92, 108, 97, 95, 99, 100, 100, \n", 168 | " 103, 125, 122, 110, 112, 102, 92, 97, 89, 102] \n", 169 | " \n", 170 | "#perform one sample z-test \n", 171 | "z_statistic, p_value = ztest(IQscores, value=98, alternative = 'larger') \n", 172 | " \n", 173 | "print(f\"The test statistic is {z_statistic} and the corresponding p-value is {p_value}.\") " 174 | ] 175 | }, 176 | { 177 | "cell_type": "markdown", 178 | "id": "ddaa8d82-63d7-4131-9478-d84417f6f704", 179 | "metadata": {}, 180 | "source": [ 181 | "## Two-sample Z-test" 182 | ] 183 | }, 184 | { 185 | "cell_type": "code", 186 | "execution_count": 8, 187 | "id": "b1943883-f085-4f99-a3fb-2ceb5ca5b6e7", 188 | "metadata": {}, 189 | "outputs": [ 190 | { 191 | "name": "stdout", 192 | "output_type": "stream", 193 | "text": [ 194 | "The test statistic is 1.7572688143960962 and the corresponding p-value is 0.07887200072419194.\n" 195 | ] 196 | } 197 | ], 198 | "source": [ 199 | "#IQ score \n", 200 | "A= [95,110, 105, 120, 125, 110, 98, 90, 99, 100, \n", 201 | " 110, 112, 106, 92, 108, 97, 95, 99, 100, 100, \n", 202 | " 103, 125, 122, 110, 112, 102, 92, 97, 89, 102] # school A \n", 203 | "B = [98, 90, 100, 93, 91, 79, 90, 100, 121, 89, \n", 204 | " 101, 98, 75, 90, 95, 99, 100, 120, 121, 95, \n", 205 | " 96, 89, 115, 99, 95, 121, 122, 98, 97, 97] # school B \n", 206 | " \n", 207 | "#perform two- sample z-test \n", 208 | "z_statistic, p_value = ztest(A, B, value=0, alternative = 'two-sided') \n", 209 | " \n", 210 | "print(f\"The test statistic is {z_statistic} and the corresponding p-value is {p_value}.\") " 211 | ] 212 | }, 213 | { 214 | "cell_type": "code", 215 | "execution_count": null, 216 | "id": "5b276a6e-8d5c-4378-8a0a-3deee6f01662", 217 | "metadata": {}, 218 | "outputs": [], 219 | "source": [] 220 | } 221 | ], 222 | "metadata": { 223 | "kernelspec": { 224 | "display_name": "Python 3 (ipykernel)", 225 | "language": "python", 226 | "name": "python3" 227 | }, 228 | "language_info": { 229 | "codemirror_mode": { 230 | "name": "ipython", 231 | "version": 3 232 | }, 233 | "file_extension": ".py", 234 | "mimetype": "text/x-python", 235 | "name": "python", 236 | "nbconvert_exporter": "python", 237 | "pygments_lexer": "ipython3", 238 | "version": "3.9.7" 239 | } 240 | }, 241 | "nbformat": 4, 242 | "nbformat_minor": 5 243 | } 244 | -------------------------------------------------------------------------------- /chapter_3/3_3_Ztest_for_Proportions.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "id": "37dabfbf-b6cd-408b-b1ec-e901f4e64d07", 6 | "metadata": {}, 7 | "source": [ 8 | "## One-proportion Z-test" 9 | ] 10 | }, 11 | { 12 | "cell_type": "code", 13 | "execution_count": 1, 14 | "id": "dccd35bc-d8f0-43c0-b615-1dd8f1edcda7", 15 | "metadata": {}, 16 | "outputs": [ 17 | { 18 | "name": "stdout", 19 | "output_type": "stream", 20 | "text": [ 21 | "The test statistic is -2.236067977499786 and the corresponding p-value is 0.0253473186774685.\n" 22 | ] 23 | } 24 | ], 25 | "source": [ 26 | "#import proportions_ztest function \n", 27 | "from statsmodels.stats.proportion import proportions_ztest \n", 28 | " \n", 29 | "count = 0.8*500 \n", 30 | "nobs = 500 \n", 31 | "value = 0.84 \n", 32 | " \n", 33 | "#perform one proportion two-tailed z-test \n", 34 | "z_statistic, p_value = proportions_ztest(count, nobs, value, alternative = 'two-sided') \n", 35 | " \n", 36 | "print(f\"The test statistic is {z_statistic} and the corresponding p-value is {p_value}.\") " 37 | ] 38 | }, 39 | { 40 | "cell_type": "markdown", 41 | "id": "6171c637-ef73-440e-b56d-e112d239db24", 42 | "metadata": {}, 43 | "source": [ 44 | "## Two-proportion Z-test" 45 | ] 46 | }, 47 | { 48 | "cell_type": "code", 49 | "execution_count": 2, 50 | "id": "a00f60dd-a51e-4b9b-9289-7578e1b0d520", 51 | "metadata": {}, 52 | "outputs": [ 53 | { 54 | "name": "stdout", 55 | "output_type": "stream", 56 | "text": [ 57 | "The test statistic is 1.6329931618554536 and the p-value for two tailed test is 0.1024704348597491.\n" 58 | ] 59 | } 60 | ], 61 | "source": [ 62 | "import math \n", 63 | "import scipy \n", 64 | "p_1bar = 0.8 \n", 65 | "p_2bar = 0.7 \n", 66 | "n1 = 100.0 \n", 67 | "n2 = 100.0 \n", 68 | " \n", 69 | "p= (p_1bar*n1 + p_2bar*n2)/(n1+n2) # the total pooled proportion \n", 70 | " \n", 71 | "z = (p_1bar-p_2bar)/math.sqrt(p*(1-p)*(1/n1+1/n2)) \n", 72 | "pval = scipy.stats.norm.sf(abs(z))*2 \n", 73 | " \n", 74 | "print(f\"The test statistic is {z} and the p-value for two tailed test is {pval}.\") " 75 | ] 76 | }, 77 | { 78 | "cell_type": "code", 79 | "execution_count": null, 80 | "id": "b890aadc-d4b3-4350-88bc-1d08e8be32c4", 81 | "metadata": {}, 82 | "outputs": [], 83 | "source": [] 84 | } 85 | ], 86 | "metadata": { 87 | "kernelspec": { 88 | "display_name": "Python 3 (ipykernel)", 89 | "language": "python", 90 | "name": "python3" 91 | }, 92 | "language_info": { 93 | "codemirror_mode": { 94 | "name": "ipython", 95 | "version": 3 96 | }, 97 | "file_extension": ".py", 98 | "mimetype": "text/x-python", 99 | "name": "python", 100 | "nbconvert_exporter": "python", 101 | "pygments_lexer": "ipython3", 102 | "version": "3.9.7" 103 | } 104 | }, 105 | "nbformat": 4, 106 | "nbformat_minor": 5 107 | } 108 | -------------------------------------------------------------------------------- /chapter_5/3_Signed-Rank_Test.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "4fc0559a-59b5-42a6-a910-75dd3be64047", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import scipy.stats as stats \n", 11 | "import numpy as np \n" 12 | ] 13 | }, 14 | { 15 | "cell_type": "code", 16 | "execution_count": 2, 17 | "id": "3bded326-b845-4fce-bf70-17bbb4f10d2d", 18 | "metadata": {}, 19 | "outputs": [ 20 | { 21 | "data": { 22 | "text/plain": [ 23 | "WilcoxonResult(statistic=41.5, pvalue=0.013671875)" 24 | ] 25 | }, 26 | "execution_count": 2, 27 | "metadata": {}, 28 | "output_type": "execute_result" 29 | } 30 | ], 31 | "source": [ 32 | "before_treatment = np.array([37, 14, 22, 12, 24, 35, 35, 51,39]) \n", 33 | "after_treatment = np.array([38,17, 19, 7, 15, 25, 24, 38,19]) \n", 34 | " \n", 35 | "# Signed Rank Test \n", 36 | "stats.wilcoxon(before_treatment, after_treatment, alternative = 'greater') " 37 | ] 38 | }, 39 | { 40 | "cell_type": "code", 41 | "execution_count": null, 42 | "id": "75ebbeac-5da0-4731-ba91-5aaf51e4c0b7", 43 | "metadata": {}, 44 | "outputs": [], 45 | "source": [] 46 | } 47 | ], 48 | "metadata": { 49 | "kernelspec": { 50 | "display_name": "Python 3 (ipykernel)", 51 | "language": "python", 52 | "name": "python3" 53 | }, 54 | "language_info": { 55 | "codemirror_mode": { 56 | "name": "ipython", 57 | "version": 3 58 | }, 59 | "file_extension": ".py", 60 | "mimetype": "text/x-python", 61 | "name": "python", 62 | "nbconvert_exporter": "python", 63 | "pygments_lexer": "ipython3", 64 | "version": "3.9.7" 65 | } 66 | }, 67 | "nbformat": 4, 68 | "nbformat_minor": 5 69 | } 70 | -------------------------------------------------------------------------------- /chapter_5/4_Kruskal-Wallis_Test.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "d4eddd39-c814-4b43-bfdd-87559b1e649d", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "from scipy import stats " 11 | ] 12 | }, 13 | { 14 | "cell_type": "code", 15 | "execution_count": 2, 16 | "id": "707949a6-8144-4dd1-b4f6-f4848dc70e7c", 17 | "metadata": {}, 18 | "outputs": [ 19 | { 20 | "data": { 21 | "text/plain": [ 22 | "KruskalResult(statistic=5.7342701722574905, pvalue=0.056861597028239855)" 23 | ] 24 | }, 25 | "execution_count": 2, 26 | "metadata": {}, 27 | "output_type": "execute_result" 28 | } 29 | ], 30 | "source": [ 31 | "group1 = [8, 13, 13, 15, 12, 10, 6, 15, 13, 9] \n", 32 | "group2 = [16, 17, 14, 14, 15, 12, 9, 12, 11, 9] \n", 33 | "group3 = [7, 8, 9, 9, 4, 15, 13, 9, 11, 9] \n", 34 | "#Kruskal-Wallis Test \n", 35 | "stats.kruskal(group1, group2, group3) " 36 | ] 37 | }, 38 | { 39 | "cell_type": "code", 40 | "execution_count": null, 41 | "id": "fd24c334-fd3d-4ea5-aa65-8961680ae39b", 42 | "metadata": {}, 43 | "outputs": [], 44 | "source": [] 45 | } 46 | ], 47 | "metadata": { 48 | "kernelspec": { 49 | "display_name": "Python 3 (ipykernel)", 50 | "language": "python", 51 | "name": "python3" 52 | }, 53 | "language_info": { 54 | "codemirror_mode": { 55 | "name": "ipython", 56 | "version": 3 57 | }, 58 | "file_extension": ".py", 59 | "mimetype": "text/x-python", 60 | "name": "python", 61 | "nbconvert_exporter": "python", 62 | "pygments_lexer": "ipython3", 63 | "version": "3.9.7" 64 | } 65 | }, 66 | "nbformat": 4, 67 | "nbformat_minor": 5 68 | } 69 | -------------------------------------------------------------------------------- /chapter_6/1_Ordinary_Least_Squares.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 2, 6 | "id": "2382f06f-bab5-4a22-a303-826328f945cb", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import numpy as np\n", 11 | "import matplotlib.pyplot as plt" 12 | ] 13 | }, 14 | { 15 | "cell_type": "code", 16 | "execution_count": 3, 17 | "id": "07e759ca-10e3-4486-bc10-67624e60ec95", 18 | "metadata": {}, 19 | "outputs": [ 20 | { 21 | "data": { 22 | "image/png": "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\n", 23 | "text/plain": [ 24 | "
" 25 | ] 26 | }, 27 | "metadata": { 28 | "needs_background": "light" 29 | }, 30 | "output_type": "display_data" 31 | } 32 | ], 33 | "source": [ 34 | "# Plot - The relationship between x and y\n", 35 | "\n", 36 | "error = np.random.normal(0,1,50)\n", 37 | "x = np.linspace(0,10,50)\n", 38 | "y = 2*x+3 +error\n", 39 | "\n", 40 | "# plot the results\n", 41 | "plt.figure(figsize = (10,8))\n", 42 | "plt.scatter(x,y,color='blue',label='Actual Values')\n", 43 | "plt.plot(x, 2*x + 3, color='red',label='Line of Best Fit')\n", 44 | "plt.xlabel('x')\n", 45 | "plt.ylabel('y')\n", 46 | "plt.title('The relationship between x and y')\n", 47 | "plt.legend()\n", 48 | "plt.tight_layout()\n", 49 | "plt.show()\n" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": 4, 55 | "id": "3b9e347a-a464-423b-bff0-5c2631597bac", 56 | "metadata": {}, 57 | "outputs": [], 58 | "source": [ 59 | "# Function to find beta_0_hat and beta_1_hat\n", 60 | "\n", 61 | "def least_squares_method(x,y): \n", 62 | " x_mean=x.mean() \n", 63 | " y_mean=y.mean() \n", 64 | " beta1 = ((x-x_mean)*(y-y_mean)).sum(axis=0)/ ((x-x.mean())**2).sum(axis=0) \n", 65 | " beta0 = y_mean-(beta1*x_mean) \n", 66 | " return beta0, beta1 " 67 | ] 68 | }, 69 | { 70 | "cell_type": "code", 71 | "execution_count": null, 72 | "id": "fb898304-d686-4a78-8ece-dd5cebcd062e", 73 | "metadata": {}, 74 | "outputs": [], 75 | "source": [] 76 | } 77 | ], 78 | "metadata": { 79 | "kernelspec": { 80 | "display_name": "Python 3 (ipykernel)", 81 | "language": "python", 82 | "name": "python3" 83 | }, 84 | "language_info": { 85 | "codemirror_mode": { 86 | "name": "ipython", 87 | "version": 3 88 | }, 89 | "file_extension": ".py", 90 | "mimetype": "text/x-python", 91 | "name": "python", 92 | "nbconvert_exporter": "python", 93 | "pygments_lexer": "ipython3", 94 | "version": "3.9.7" 95 | } 96 | }, 97 | "nbformat": 4, 98 | "nbformat_minor": 5 99 | } 100 | -------------------------------------------------------------------------------- /chapter_7/3_Shrinkage.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "id": "fb29a9cd-e1be-4e12-93c4-09cf274855ee", 6 | "metadata": {}, 7 | "source": [ 8 | "# Prep Data" 9 | ] 10 | }, 11 | { 12 | "cell_type": "code", 13 | "execution_count": 5, 14 | "id": "f0c53df5-4deb-42b6-90e2-fe45ebad939e", 15 | "metadata": {}, 16 | "outputs": [], 17 | "source": [ 18 | "from sklearn.metrics import mean_squared_error as MSE\n", 19 | "from sklearn.model_selection import train_test_split\n", 20 | "from sklearn.preprocessing import StandardScaler\n", 21 | "from sklearn.datasets import fetch_california_housing\n", 22 | "import statsmodels.api as sm\n", 23 | "import pandas as pd\n", 24 | "\n", 25 | "california_housing = fetch_california_housing()\n", 26 | "df_california = pd.DataFrame(california_housing.data, columns = california_housing.feature_names)\n", 27 | "df_california['PRICE'] = california_housing.target\n", 28 | "df_california = sm.add_constant(df_california, prepend=False)" 29 | ] 30 | }, 31 | { 32 | "cell_type": "code", 33 | "execution_count": 6, 34 | "id": "c5cc3dba-1695-48fe-8fa8-1e12bac2a12b", 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "df_california.head().to_clipboard()" 39 | ] 40 | }, 41 | { 42 | "cell_type": "code", 43 | "execution_count": 7, 44 | "id": "ee667fa7-81cf-4be4-8c0e-8c5b2bf18321", 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "X = df_california.drop('PRICE', axis=1)\n", 49 | "y = df_california['PRICE']" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": 8, 55 | "id": "56b54779-ed92-47f6-b205-ac8476cf4d63", 56 | "metadata": {}, 57 | "outputs": [], 58 | "source": [ 59 | "sc = StandardScaler()\n", 60 | "X_scaled = sc.fit_transform(X)" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": 9, 66 | "id": "18ae04e9-cb2b-45a1-8dcb-00f24b022f30", 67 | "metadata": {}, 68 | "outputs": [], 69 | "source": [ 70 | "X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.25, shuffle=True)" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "id": "35991f94-52c3-4822-8617-518f13653096", 76 | "metadata": {}, 77 | "source": [ 78 | "# Ridge Regression" 79 | ] 80 | }, 81 | { 82 | "cell_type": "code", 83 | "execution_count": 10, 84 | "id": "775860e6-ef88-406d-9d21-92d21a5f06e4", 85 | "metadata": {}, 86 | "outputs": [], 87 | "source": [ 88 | "ols_model = sm.OLS(y_train, X_train)\n", 89 | "compiled_model = ols_model.fit()\n", 90 | "compiled_model_ridge = ols_model.fit_regularized(method='elastic_net', L1_wt=0, alpha=0.1,refit=True)" 91 | ] 92 | }, 93 | { 94 | "cell_type": "code", 95 | "execution_count": 11, 96 | "id": "00095601-be50-4238-a586-f288405c5016", 97 | "metadata": {}, 98 | "outputs": [ 99 | { 100 | "name": "stdout", 101 | "output_type": "stream", 102 | "text": [ 103 | "OLS Error: 4.806871781767541\n", 104 | "Ridge Regression Error: 4.862847117128481\n" 105 | ] 106 | } 107 | ], 108 | "source": [ 109 | "print('OLS Error: ', MSE(y_train, compiled_model.predict(X_train)) )\n", 110 | "print('Ridge Regression Error: ', MSE(y_train, compiled_model_ridge.predict(X_train)))" 111 | ] 112 | }, 113 | { 114 | "cell_type": "code", 115 | "execution_count": 12, 116 | "id": "33f7c116-739c-4c22-9201-12c0741694d4", 117 | "metadata": {}, 118 | "outputs": [ 119 | { 120 | "name": "stdout", 121 | "output_type": "stream", 122 | "text": [ 123 | "OLS Error: 4.799965081300563\n", 124 | "Ridge Regression Error: 4.802637071118009\n" 125 | ] 126 | } 127 | ], 128 | "source": [ 129 | "print('OLS Error: ', MSE(y_test, compiled_model.predict(X_test)) )\n", 130 | "print('Ridge Regression Error: ', MSE(y_test, compiled_model_ridge.predict(X_test)))" 131 | ] 132 | }, 133 | { 134 | "cell_type": "code", 135 | "execution_count": 14, 136 | "id": "9a10cd1d-3d79-419d-a240-cae500d60ace", 137 | "metadata": {}, 138 | "outputs": [], 139 | "source": [ 140 | "df_compare = pd.DataFrame({'Before Ridge Regression':compiled_model.params,\n", 141 | " 'After Ridge Regression':compiled_model_ridge.params})\n", 142 | "df_compare.index=list(X.columns)" 143 | ] 144 | }, 145 | { 146 | "cell_type": "code", 147 | "execution_count": 15, 148 | "id": "7409eb33-4c0a-4a62-9c34-2cbf11036a76", 149 | "metadata": {}, 150 | "outputs": [ 151 | { 152 | "data": { 153 | "text/html": [ 154 | "
\n", 155 | "\n", 168 | "\n", 169 | " \n", 170 | " \n", 171 | " \n", 172 | " \n", 173 | " \n", 174 | " \n", 175 | " \n", 176 | " \n", 177 | " \n", 178 | " \n", 179 | " \n", 180 | " \n", 181 | " \n", 182 | " \n", 183 | " \n", 184 | " \n", 185 | " \n", 186 | " \n", 187 | " \n", 188 | " \n", 189 | " \n", 190 | " \n", 191 | " \n", 192 | " \n", 193 | " \n", 194 | " \n", 195 | " \n", 196 | " \n", 197 | " \n", 198 | " \n", 199 | " \n", 200 | " \n", 201 | " \n", 202 | " \n", 203 | " \n", 204 | " \n", 205 | " \n", 206 | " \n", 207 | " \n", 208 | " \n", 209 | "
MedIncHouseAgeAveRoomsAveBedrmsPopulationAveOccupLatitudeLongitudeconst
Before Ridge Regression0.8294970.118072-0.2611750.331459-0.010918-0.027147-0.993947-0.9506860.0
After Ridge Regression0.7366160.159327-0.0744730.0924430.004344-0.027914-0.438714-0.3884920.0
\n", 210 | "
" 211 | ], 212 | "text/plain": [ 213 | " MedInc HouseAge AveRooms AveBedrms Population \\\n", 214 | "Before Ridge Regression 0.829497 0.118072 -0.261175 0.331459 -0.010918 \n", 215 | "After Ridge Regression 0.736616 0.159327 -0.074473 0.092443 0.004344 \n", 216 | "\n", 217 | " AveOccup Latitude Longitude const \n", 218 | "Before Ridge Regression -0.027147 -0.993947 -0.950686 0.0 \n", 219 | "After Ridge Regression -0.027914 -0.438714 -0.388492 0.0 " 220 | ] 221 | }, 222 | "execution_count": 15, 223 | "metadata": {}, 224 | "output_type": "execute_result" 225 | } 226 | ], 227 | "source": [ 228 | "df_compare.T" 229 | ] 230 | }, 231 | { 232 | "cell_type": "code", 233 | "execution_count": 500, 234 | "id": "a77527aa-22e9-416d-8ea7-764124ea62e4", 235 | "metadata": {}, 236 | "outputs": [], 237 | "source": [ 238 | "df_compare.T.to_clipboard()" 239 | ] 240 | }, 241 | { 242 | "cell_type": "markdown", 243 | "id": "3e871245-d817-4047-90ad-0a7d0e36615f", 244 | "metadata": {}, 245 | "source": [ 246 | "# LASSO Regression" 247 | ] 248 | }, 249 | { 250 | "cell_type": "code", 251 | "execution_count": 16, 252 | "id": "a2e5c9bc-ab39-4a0f-8edc-90aa96a78e17", 253 | "metadata": {}, 254 | "outputs": [ 255 | { 256 | "name": "stdout", 257 | "output_type": "stream", 258 | "text": [ 259 | "OLS Error: 4.806871781767541\n", 260 | "LASSO Regression Error: 4.93937023995957\n" 261 | ] 262 | } 263 | ], 264 | "source": [ 265 | "ols_model = sm.OLS(y_train, X_train)\n", 266 | "compiled_model = ols_model.fit()\n", 267 | "compiled_model_lasso = ols_model.fit_regularized(method='elastic_net', L1_wt=1, alpha=0.1,refit=True)\n", 268 | "\n", 269 | "print('OLS Error: ', MSE(y_train, compiled_model.predict(X_train)) )\n", 270 | "print('LASSO Regression Error: ', MSE(y_train, compiled_model_lasso.predict(X_train)))" 271 | ] 272 | }, 273 | { 274 | "cell_type": "code", 275 | "execution_count": 17, 276 | "id": "6217d1b6-6d66-45e5-a051-b31a31e0a6af", 277 | "metadata": {}, 278 | "outputs": [ 279 | { 280 | "name": "stdout", 281 | "output_type": "stream", 282 | "text": [ 283 | "OLS Error: 4.799965081300563\n", 284 | "LASSO Regression Error: 4.870307535710372\n" 285 | ] 286 | } 287 | ], 288 | "source": [ 289 | "print('OLS Error: ', MSE(y_test, compiled_model.predict(X_test)) )\n", 290 | "print('LASSO Regression Error: ', MSE(y_test, compiled_model_lasso.predict(X_test)))" 291 | ] 292 | }, 293 | { 294 | "cell_type": "code", 295 | "execution_count": 18, 296 | "id": "69e05a1c-53c7-491b-ba0f-a62e72810828", 297 | "metadata": {}, 298 | "outputs": [], 299 | "source": [ 300 | "df_compare = pd.DataFrame({'Before LASSO Regression':compiled_model.params,\n", 301 | " 'After LASSO Regression':compiled_model_ridge.params})\n", 302 | "df_compare.index=list(X.columns)" 303 | ] 304 | }, 305 | { 306 | "cell_type": "code", 307 | "execution_count": 19, 308 | "id": "07d0e90d-ca22-4624-91b3-81ddcd027fd6", 309 | "metadata": {}, 310 | "outputs": [ 311 | { 312 | "data": { 313 | "text/html": [ 314 | "
\n", 315 | "\n", 328 | "\n", 329 | " \n", 330 | " \n", 331 | " \n", 332 | " \n", 333 | " \n", 334 | " \n", 335 | " \n", 336 | " \n", 337 | " \n", 338 | " \n", 339 | " \n", 340 | " \n", 341 | " \n", 342 | " \n", 343 | " \n", 344 | " \n", 345 | " \n", 346 | " \n", 347 | " \n", 348 | " \n", 349 | " \n", 350 | " \n", 351 | " \n", 352 | " \n", 353 | " \n", 354 | " \n", 355 | " \n", 356 | " \n", 357 | " \n", 358 | " \n", 359 | " \n", 360 | " \n", 361 | " \n", 362 | " \n", 363 | " \n", 364 | " \n", 365 | " \n", 366 | " \n", 367 | " \n", 368 | " \n", 369 | "
MedIncHouseAgeAveRoomsAveBedrmsPopulationAveOccupLatitudeLongitudeconst
Before LASSO Regression0.8294970.118072-0.2611750.331459-0.010918-0.027147-0.993947-0.9506860.0
After LASSO Regression0.7366160.159327-0.0744730.0924430.004344-0.027914-0.438714-0.3884920.0
\n", 370 | "
" 371 | ], 372 | "text/plain": [ 373 | " MedInc HouseAge AveRooms AveBedrms Population \\\n", 374 | "Before LASSO Regression 0.829497 0.118072 -0.261175 0.331459 -0.010918 \n", 375 | "After LASSO Regression 0.736616 0.159327 -0.074473 0.092443 0.004344 \n", 376 | "\n", 377 | " AveOccup Latitude Longitude const \n", 378 | "Before LASSO Regression -0.027147 -0.993947 -0.950686 0.0 \n", 379 | "After LASSO Regression -0.027914 -0.438714 -0.388492 0.0 " 380 | ] 381 | }, 382 | "execution_count": 19, 383 | "metadata": {}, 384 | "output_type": "execute_result" 385 | } 386 | ], 387 | "source": [ 388 | "df_compare.T" 389 | ] 390 | }, 391 | { 392 | "cell_type": "code", 393 | "execution_count": 20, 394 | "id": "843d4b10-b8a2-4a1b-ad94-be4a61643b35", 395 | "metadata": {}, 396 | "outputs": [], 397 | "source": [ 398 | "df_compare.T.to_clipboard()" 399 | ] 400 | }, 401 | { 402 | "cell_type": "markdown", 403 | "id": "0630faa9-da96-4fbc-9d07-61a4f1cb4925", 404 | "metadata": {}, 405 | "source": [ 406 | "# Elastic Net Regression" 407 | ] 408 | }, 409 | { 410 | "cell_type": "code", 411 | "execution_count": 21, 412 | "id": "1257fbd2-d5e0-445b-8012-088da3358879", 413 | "metadata": {}, 414 | "outputs": [], 415 | "source": [ 416 | "ols_model = sm.OLS(y_train, X_train)\n", 417 | "compiled_model = ols_model.fit()\n", 418 | "compiled_model_elastic = ols_model.fit_regularized(method='elastic_net', L1_wt=0.5, alpha=8,refit=True)" 419 | ] 420 | }, 421 | { 422 | "cell_type": "code", 423 | "execution_count": 22, 424 | "id": "20103009-464c-41c8-a889-9f0cc2a4a456", 425 | "metadata": {}, 426 | "outputs": [ 427 | { 428 | "name": "stdout", 429 | "output_type": "stream", 430 | "text": [ 431 | "OLS Error: 4.806871781767541\n", 432 | "Elastic Net Regression Error: 5.646749280108061\n" 433 | ] 434 | } 435 | ], 436 | "source": [ 437 | "print('OLS Error: ', MSE(y_train, compiled_model.predict(X_train)) )\n", 438 | "print('Elastic Net Regression Error: ', MSE(y_train, compiled_model_elastic.predict(X_train)))" 439 | ] 440 | }, 441 | { 442 | "cell_type": "code", 443 | "execution_count": 23, 444 | "id": "f3348a4c-53b6-4688-8c52-5a525e04a764", 445 | "metadata": {}, 446 | "outputs": [ 447 | { 448 | "name": "stdout", 449 | "output_type": "stream", 450 | "text": [ 451 | "OLS Error: 4.799965081300563\n", 452 | "Elastic Net Regression Error: 5.501684955624825\n" 453 | ] 454 | } 455 | ], 456 | "source": [ 457 | "print('OLS Error: ', MSE(y_test, compiled_model.predict(X_test)) )\n", 458 | "print('Elastic Net Regression Error: ', MSE(y_test, compiled_model_elastic.predict(X_test)))" 459 | ] 460 | }, 461 | { 462 | "cell_type": "code", 463 | "execution_count": 24, 464 | "id": "d43c9e38-9720-4105-90a0-a8194464f99d", 465 | "metadata": {}, 466 | "outputs": [], 467 | "source": [ 468 | "df_compare = pd.DataFrame({'Before Elastic Net Regression':compiled_model.params,\n", 469 | " 'After Elastic Net Regression':compiled_model_ridge.params})\n", 470 | "df_compare.index=list(X.columns)" 471 | ] 472 | }, 473 | { 474 | "cell_type": "code", 475 | "execution_count": 25, 476 | "id": "a4bc06c9-5c52-4f7b-b155-0a4a0b4089bf", 477 | "metadata": {}, 478 | "outputs": [ 479 | { 480 | "data": { 481 | "text/html": [ 482 | "
\n", 483 | "\n", 496 | "\n", 497 | " \n", 498 | " \n", 499 | " \n", 500 | " \n", 501 | " \n", 502 | " \n", 503 | " \n", 504 | " \n", 505 | " \n", 506 | " \n", 507 | " \n", 508 | " \n", 509 | " \n", 510 | " \n", 511 | " \n", 512 | " \n", 513 | " \n", 514 | " \n", 515 | " \n", 516 | " \n", 517 | " \n", 518 | " \n", 519 | " \n", 520 | " \n", 521 | " \n", 522 | " \n", 523 | " \n", 524 | " \n", 525 | " \n", 526 | " \n", 527 | " \n", 528 | " \n", 529 | " \n", 530 | " \n", 531 | " \n", 532 | " \n", 533 | " \n", 534 | " \n", 535 | " \n", 536 | " \n", 537 | "
MedIncHouseAgeAveRoomsAveBedrmsPopulationAveOccupLatitudeLongitudeconst
Before Elastic Net Regression0.8294970.118072-0.2611750.331459-0.010918-0.027147-0.993947-0.9506860.0
After Elastic Net Regression0.7366160.159327-0.0744730.0924430.004344-0.027914-0.438714-0.3884920.0
\n", 538 | "
" 539 | ], 540 | "text/plain": [ 541 | " MedInc HouseAge AveRooms AveBedrms \\\n", 542 | "Before Elastic Net Regression 0.829497 0.118072 -0.261175 0.331459 \n", 543 | "After Elastic Net Regression 0.736616 0.159327 -0.074473 0.092443 \n", 544 | "\n", 545 | " Population AveOccup Latitude Longitude \\\n", 546 | "Before Elastic Net Regression -0.010918 -0.027147 -0.993947 -0.950686 \n", 547 | "After Elastic Net Regression 0.004344 -0.027914 -0.438714 -0.388492 \n", 548 | "\n", 549 | " const \n", 550 | "Before Elastic Net Regression 0.0 \n", 551 | "After Elastic Net Regression 0.0 " 552 | ] 553 | }, 554 | "execution_count": 25, 555 | "metadata": {}, 556 | "output_type": "execute_result" 557 | } 558 | ], 559 | "source": [ 560 | "df_compare.T" 561 | ] 562 | }, 563 | { 564 | "cell_type": "code", 565 | "execution_count": 26, 566 | "id": "50ad6baa-0bd0-4417-9399-d07926d6065f", 567 | "metadata": {}, 568 | "outputs": [], 569 | "source": [ 570 | "df_compare.T.to_clipboard()" 571 | ] 572 | } 573 | ], 574 | "metadata": { 575 | "kernelspec": { 576 | "display_name": "Python 3", 577 | "language": "python", 578 | "name": "python3" 579 | }, 580 | "language_info": { 581 | "codemirror_mode": { 582 | "name": "ipython", 583 | "version": 3 584 | }, 585 | "file_extension": ".py", 586 | "mimetype": "text/x-python", 587 | "name": "python", 588 | "nbconvert_exporter": "python", 589 | "pygments_lexer": "ipython3", 590 | "version": "3.8.3" 591 | } 592 | }, 593 | "nbformat": 4, 594 | "nbformat_minor": 5 595 | } 596 | -------------------------------------------------------------------------------- /chapter_7/Data/Hitters.csv: -------------------------------------------------------------------------------- 1 | AtBat,Hits,HmRun,Runs,RBI,Walks,Years,CAtBat,CHits,CHmRun,CRuns,CRBI,CWalks,League,Division,PutOuts,Assists,Errors,Salary,NewLeague 2 | 293,66,1,30,29,14,1,293,66,1,30,29,14,A,E,446,33,20,NA,A 3 | 315,81,7,24,38,39,14,3449,835,69,321,414,375,N,W,632,43,10,475,N 4 | 479,130,18,66,72,76,3,1624,457,63,224,266,263,A,W,880,82,14,480,A 5 | 496,141,20,65,78,37,11,5628,1575,225,828,838,354,N,E,200,11,3,500,N 6 | 321,87,10,39,42,30,2,396,101,12,48,46,33,N,E,805,40,4,91.5,N 7 | 594,169,4,74,51,35,11,4408,1133,19,501,336,194,A,W,282,421,25,750,A 8 | 185,37,1,23,8,21,2,214,42,1,30,9,24,N,E,76,127,7,70,A 9 | 298,73,0,24,24,7,3,509,108,0,41,37,12,A,W,121,283,9,100,A 10 | 323,81,6,26,32,8,2,341,86,6,32,34,8,N,W,143,290,19,75,N 11 | 401,92,17,49,66,65,13,5206,1332,253,784,890,866,A,E,0,0,0,1100,A 12 | 574,159,21,107,75,59,10,4631,1300,90,702,504,488,A,E,238,445,22,517.143,A 13 | 202,53,4,31,26,27,9,1876,467,15,192,186,161,N,W,304,45,11,512.5,N 14 | 418,113,13,48,61,47,4,1512,392,41,205,204,203,N,E,211,11,7,550,N 15 | 239,60,0,30,11,22,6,1941,510,4,309,103,207,A,E,121,151,6,700,A 16 | 196,43,7,29,27,30,13,3231,825,36,376,290,238,N,E,80,45,8,240,N 17 | 183,39,3,20,15,11,3,201,42,3,20,16,11,A,W,118,0,0,NA,A 18 | 568,158,20,89,75,73,15,8068,2273,177,1045,993,732,N,W,105,290,10,775,N 19 | 190,46,2,24,8,15,5,479,102,5,65,23,39,A,W,102,177,16,175,A 20 | 407,104,6,57,43,65,12,5233,1478,100,643,658,653,A,W,912,88,9,NA,A 21 | 127,32,8,16,22,14,8,727,180,24,67,82,56,N,W,202,22,2,135,N 22 | 413,92,16,72,48,65,1,413,92,16,72,48,65,N,E,280,9,5,100,N 23 | 426,109,3,55,43,62,1,426,109,3,55,43,62,A,W,361,22,2,115,N 24 | 22,10,1,4,2,1,6,84,26,2,9,9,3,A,W,812,84,11,NA,A 25 | 472,116,16,60,62,74,6,1924,489,67,242,251,240,N,W,518,55,3,600,N 26 | 629,168,18,73,102,40,18,8424,2464,164,1008,1072,402,A,E,1067,157,14,776.667,A 27 | 587,163,4,92,51,70,6,2695,747,17,442,198,317,A,E,434,9,3,765,A 28 | 324,73,4,32,18,22,7,1931,491,13,291,108,180,N,E,222,3,3,708.333,N 29 | 474,129,10,50,56,40,10,2331,604,61,246,327,166,N,W,732,83,13,750,N 30 | 550,152,6,92,37,81,5,2308,633,32,349,182,308,N,W,262,329,16,625,N 31 | 513,137,20,90,95,90,14,5201,1382,166,763,734,784,A,W,267,5,3,900,A 32 | 313,84,9,42,30,39,17,6890,1833,224,1033,864,1087,A,W,127,221,7,NA,A 33 | 419,108,6,55,36,22,3,591,149,8,80,46,31,N,W,226,7,4,110,N 34 | 517,141,27,70,87,52,9,3571,994,215,545,652,337,N,W,1378,102,8,NA,N 35 | 583,168,17,83,80,56,5,1646,452,44,219,208,136,A,E,109,292,25,612.5,A 36 | 204,49,6,23,25,12,7,1309,308,27,126,132,66,A,W,419,46,5,300,A 37 | 379,106,10,38,60,30,14,6207,1906,146,859,803,571,N,W,72,170,24,850,N 38 | 161,36,0,19,10,17,4,1053,244,3,156,86,107,A,E,70,149,12,NA,A 39 | 268,60,5,24,25,15,2,350,78,5,34,29,18,N,W,442,59,6,90,N 40 | 346,98,5,31,53,30,16,5913,1615,235,784,901,560,A,E,0,0,0,NA,A 41 | 241,61,1,34,12,14,1,241,61,1,34,12,14,N,W,166,172,10,NA,N 42 | 181,41,1,15,21,33,2,232,50,4,20,29,45,A,E,326,29,5,67.5,A 43 | 216,54,0,21,18,15,18,7318,1926,46,796,627,483,N,W,103,84,5,NA,N 44 | 200,57,6,23,14,14,9,2516,684,46,371,230,195,N,W,69,1,1,NA,N 45 | 217,46,7,32,19,9,4,694,160,32,86,76,32,A,E,307,25,1,180,A 46 | 194,40,7,19,29,30,11,4183,1069,64,486,493,608,A,E,325,22,2,NA,A 47 | 254,68,2,28,26,22,6,999,236,21,108,117,118,A,E,359,30,4,305,A 48 | 416,132,7,57,49,33,3,932,273,24,113,121,80,N,W,73,177,18,215,N 49 | 205,57,8,34,32,9,5,756,192,32,117,107,51,A,E,58,4,4,247.5,A 50 | 542,140,12,46,75,41,16,7099,2130,235,987,1089,431,A,E,697,61,9,NA,A 51 | 526,146,13,71,70,84,6,2648,715,77,352,342,289,N,W,303,9,9,815,N 52 | 457,101,14,42,63,22,17,6521,1767,281,1003,977,619,A,W,389,39,4,875,A 53 | 214,53,2,30,29,23,2,226,59,2,32,32,27,N,E,109,7,3,70,N 54 | 19,7,0,1,2,1,4,41,13,1,3,4,4,A,E,0,0,0,NA,A 55 | 591,168,19,80,72,39,9,4478,1307,113,634,563,319,A,W,67,147,4,1200,A 56 | 403,101,12,45,53,39,12,5150,1429,166,747,666,526,A,E,316,6,5,675,A 57 | 405,102,18,49,85,20,6,950,231,29,99,138,64,N,W,161,10,3,415,N 58 | 244,58,9,28,25,35,4,1335,333,49,164,179,194,N,W,142,14,2,340,N 59 | 235,61,3,24,39,21,14,3926,1029,35,441,401,333,A,E,425,43,4,NA,A 60 | 313,78,6,32,41,12,12,3742,968,35,409,321,170,N,W,106,206,7,416.667,N 61 | 627,177,25,98,81,70,6,3210,927,133,529,472,313,A,E,240,482,13,1350,A 62 | 416,113,24,58,69,16,1,416,113,24,58,69,16,A,E,203,70,10,90,A 63 | 155,44,6,21,23,15,16,6631,1634,98,698,661,777,N,E,53,88,3,275,N 64 | 236,56,0,27,15,11,4,1115,270,1,116,64,57,A,W,125,199,13,230,A 65 | 216,53,1,31,15,22,4,926,210,9,118,69,114,N,W,73,152,11,225,N 66 | 24,3,0,1,0,2,3,159,28,0,20,12,9,A,W,80,4,0,NA,A 67 | 585,139,31,93,94,62,17,7546,1982,315,1141,1179,727,A,E,0,0,0,950,A 68 | 191,37,4,12,17,14,4,773,163,16,61,74,52,N,E,391,38,8,NA,N 69 | 199,53,5,29,22,21,3,514,120,8,57,40,39,A,W,152,3,5,75,A 70 | 521,142,20,67,86,45,4,815,205,22,99,103,78,A,E,107,242,23,105,A 71 | 419,113,1,44,27,44,12,4484,1231,32,612,344,422,A,E,211,2,1,NA,A 72 | 311,81,3,42,30,26,17,8247,2198,100,950,909,690,N,W,153,223,10,320,N 73 | 138,31,8,18,21,38,3,244,53,12,33,32,55,N,E,244,21,4,NA,N 74 | 512,131,26,69,96,52,14,5347,1397,221,712,815,548,A,W,119,216,12,850,A 75 | 507,122,29,78,85,91,18,7761,1947,347,1175,1152,1380,A,E,808,108,2,535,A 76 | 529,137,26,86,97,97,15,6661,1785,291,1082,949,989,A,E,280,10,5,933.333,A 77 | 424,119,6,57,46,13,9,3651,1046,32,461,301,112,A,E,224,286,8,850,N 78 | 351,97,4,55,29,39,4,1258,353,16,196,110,117,N,W,226,7,3,210,A 79 | 195,55,5,24,33,30,8,1313,338,25,144,149,153,N,E,83,2,1,NA,N 80 | 388,103,15,59,47,39,6,2174,555,80,285,274,186,A,W,182,9,4,325,A 81 | 339,96,4,37,29,23,4,1064,290,11,123,108,55,A,W,104,213,9,275,A 82 | 561,118,35,70,94,33,16,6677,1575,442,901,1210,608,A,W,463,32,8,NA,A 83 | 255,70,7,49,35,43,15,6311,1661,154,1019,608,820,N,E,51,54,8,450,N 84 | 677,238,31,117,113,53,5,2223,737,93,349,401,171,A,E,1377,100,6,1975,A 85 | 227,46,7,23,20,12,5,1325,324,44,156,158,67,A,W,92,2,2,NA,A 86 | 614,163,29,89,83,75,11,5017,1388,266,813,822,617,N,W,303,6,6,1900,N 87 | 329,83,9,50,39,56,9,3828,948,145,575,528,635,A,W,276,6,2,600,A 88 | 637,174,31,89,116,56,14,6727,2024,247,978,1093,495,N,W,278,9,9,1041.667,N 89 | 280,82,16,44,45,47,2,428,113,25,61,70,63,A,E,148,4,2,110,A 90 | 155,41,12,21,29,22,16,5409,1338,181,746,805,875,A,W,165,9,1,260,A 91 | 458,114,13,67,57,48,4,1350,298,28,160,123,122,A,W,246,389,18,475,A 92 | 314,83,13,39,46,16,5,1457,405,28,156,159,76,A,W,533,40,4,431.5,A 93 | 475,123,27,76,93,72,4,1810,471,108,292,343,267,N,E,226,10,6,1220,N 94 | 317,78,7,35,35,32,1,317,78,7,35,35,32,A,E,45,122,26,70,A 95 | 511,138,25,76,96,61,3,592,164,28,87,110,71,A,W,157,7,8,145,A 96 | 278,69,3,24,21,29,8,2079,565,32,258,192,162,N,W,142,210,10,NA,N 97 | 382,119,13,54,58,36,12,2133,594,41,287,294,227,N,W,59,156,9,595,N 98 | 565,148,24,90,104,77,14,7287,2083,305,1135,1234,791,A,E,292,9,5,1861.46,A 99 | 277,71,2,27,29,14,15,5952,1647,60,753,596,259,N,W,360,32,5,NA,N 100 | 415,115,27,97,71,68,3,711,184,45,156,119,99,N,W,274,2,7,300,N 101 | 424,110,15,70,47,36,7,2130,544,38,335,174,258,N,W,292,6,3,490,N 102 | 495,151,17,61,84,78,10,5624,1679,275,884,1015,709,A,E,1045,88,13,2460,A 103 | 524,132,9,69,47,54,2,972,260,14,123,92,90,A,E,212,327,20,NA,A 104 | 233,49,2,41,23,18,8,1350,336,7,166,122,106,A,E,102,132,10,375,A 105 | 395,106,16,48,56,35,10,2303,571,86,266,323,248,A,E,709,41,7,NA,A 106 | 397,114,23,67,67,53,13,5589,1632,241,906,926,716,A,E,244,2,4,NA,A 107 | 210,37,8,15,19,15,6,994,244,36,107,114,53,A,E,40,115,15,NA,A 108 | 420,95,23,55,58,37,3,646,139,31,77,77,61,N,W,206,10,7,NA,N 109 | 566,154,22,76,84,43,14,6100,1583,131,743,693,300,A,W,316,439,10,750,A 110 | 641,198,31,101,108,41,5,2129,610,92,297,319,117,A,E,269,17,10,1175,A 111 | 215,51,4,19,18,11,1,215,51,4,19,18,11,A,E,116,5,12,70,A 112 | 441,128,16,70,73,80,14,6675,2095,209,1072,1050,695,A,W,97,218,16,1500,A 113 | 325,76,16,33,52,37,5,1506,351,71,195,219,214,N,W,726,87,3,385,A 114 | 490,125,24,81,105,62,13,6063,1646,271,847,999,680,N,E,869,62,8,1925.571,N 115 | 574,152,31,91,101,64,3,985,260,53,148,173,95,N,W,1253,111,11,215,N 116 | 284,64,14,30,42,24,18,7023,1925,348,986,1239,666,N,E,96,4,4,NA,N 117 | 596,171,34,91,108,52,6,2862,728,107,361,401,224,A,W,118,334,21,900,A 118 | 472,118,12,63,54,30,4,793,187,14,102,80,50,A,W,228,377,26,155,A 119 | 283,77,14,45,47,26,16,6840,1910,259,915,1067,546,A,W,144,6,5,700,A 120 | 408,94,4,42,36,66,9,3573,866,59,429,365,410,N,W,282,487,19,535,N 121 | 327,85,3,30,44,20,8,2140,568,16,216,208,93,A,E,91,185,12,362.5,A 122 | 370,96,21,49,46,60,15,6986,1972,231,1070,955,921,N,E,137,5,9,733.333,N 123 | 354,77,16,36,55,41,20,8716,2172,384,1172,1267,1057,N,W,83,174,16,200,N 124 | 539,139,5,93,58,69,5,1469,369,12,247,126,198,A,W,462,9,7,400,A 125 | 340,84,11,62,33,47,5,1516,376,42,284,141,219,N,E,185,8,4,400,A 126 | 510,126,2,42,44,35,11,5562,1578,44,703,519,256,N,W,207,358,20,737.5,N 127 | 315,59,16,45,36,58,13,4677,1051,268,681,782,697,A,W,0,0,0,NA,A 128 | 282,78,13,37,51,29,5,1649,453,73,211,280,138,A,W,670,57,5,500,A 129 | 380,120,5,54,51,31,8,3118,900,92,444,419,240,A,W,237,8,1,600,A 130 | 584,158,15,70,84,42,5,2358,636,58,265,316,134,N,E,331,20,4,662.5,N 131 | 570,169,21,72,88,38,7,3754,1077,140,492,589,263,A,W,295,15,5,950,A 132 | 306,104,14,50,58,25,7,2954,822,55,313,377,187,N,E,116,222,15,750,N 133 | 220,54,10,30,39,31,5,1185,299,40,145,154,128,N,E,50,136,20,297.5,N 134 | 278,70,7,22,37,18,18,7186,2081,190,935,1088,643,A,W,0,0,0,325,A 135 | 445,99,1,46,24,29,4,618,129,1,72,31,48,A,W,278,415,16,87.5,A 136 | 143,39,5,18,30,15,9,639,151,16,80,97,61,N,W,138,15,1,175,N 137 | 185,40,4,23,11,18,3,524,125,7,58,37,47,N,E,97,2,2,90,N 138 | 589,170,40,107,108,69,6,2325,634,128,371,376,238,A,E,368,20,3,1237.5,A 139 | 343,103,6,48,36,40,15,4338,1193,70,581,421,325,A,E,211,56,13,430,A 140 | 284,69,1,33,18,25,5,1407,361,6,139,98,111,A,E,122,140,5,NA,N 141 | 438,103,2,65,32,71,2,440,103,2,67,32,71,A,W,276,7,9,100,N 142 | 600,144,33,85,117,65,2,696,173,38,101,130,69,A,W,319,4,14,165,A 143 | 663,200,29,108,121,32,4,1447,404,57,210,222,68,A,E,241,8,6,250,A 144 | 232,55,9,34,23,45,12,4405,1213,194,702,705,625,N,E,623,35,3,1300,N 145 | 479,133,10,48,72,55,17,7472,2147,153,980,1032,854,N,W,237,5,4,773.333,N 146 | 209,45,0,38,19,42,10,3859,916,23,557,279,478,A,W,132,205,5,NA,A 147 | 528,132,21,61,74,41,6,2641,671,97,273,383,226,N,E,885,105,8,1008.333,N 148 | 160,39,8,18,31,22,14,2128,543,56,304,268,298,A,E,33,3,0,275,A 149 | 599,183,10,80,74,32,5,2482,715,27,330,326,158,A,E,231,374,18,775,A 150 | 497,136,7,58,38,26,11,3871,1066,40,450,367,241,A,E,304,347,10,850,A 151 | 210,70,13,32,51,28,15,4040,1130,97,544,462,551,A,E,0,0,0,365,A 152 | 225,61,5,32,26,26,11,1568,408,25,202,185,257,A,W,132,9,0,NA,A 153 | 151,41,4,26,21,19,2,288,68,9,45,39,35,A,W,28,56,2,95,A 154 | 278,86,4,33,38,45,1,278,86,4,33,38,45,N,W,102,4,2,110,N 155 | 341,95,6,48,42,20,10,2964,808,81,379,428,221,N,W,158,4,5,100,N 156 | 537,147,23,58,88,47,10,2744,730,97,302,351,174,N,E,92,257,20,277.5,N 157 | 399,102,3,56,34,34,5,670,167,4,89,48,54,A,W,211,9,3,80,A 158 | 309,94,5,37,32,26,13,4618,1330,57,616,522,436,N,E,161,3,3,600,N 159 | 401,100,2,60,19,28,4,876,238,2,126,44,55,N,E,193,11,4,NA,N 160 | 336,93,9,35,46,23,15,5779,1610,128,730,741,497,A,W,0,0,0,NA,A 161 | 616,163,27,83,107,32,3,1437,377,65,181,227,82,A,W,110,308,15,200,A 162 | 219,47,8,24,26,17,12,1188,286,23,100,125,63,A,W,260,58,4,NA,A 163 | 579,174,7,67,78,58,6,3053,880,32,366,337,218,N,E,280,479,5,657,N 164 | 165,39,2,13,9,16,3,196,44,2,18,10,18,A,W,332,19,2,75,N 165 | 618,200,20,98,110,62,13,7127,2163,351,1104,1289,564,A,E,330,16,8,2412.5,A 166 | 257,66,5,31,26,32,14,3910,979,33,518,324,382,N,W,87,166,14,250,A 167 | 315,76,13,35,60,25,3,630,151,24,68,94,55,N,E,498,39,13,155,N 168 | 591,157,16,90,78,26,4,2020,541,52,310,226,91,N,E,290,440,25,640,N 169 | 404,92,11,54,49,18,6,1354,325,30,188,135,63,A,E,222,5,5,300,A 170 | 315,73,5,23,37,16,4,450,108,6,38,46,28,A,W,227,15,3,110,A 171 | 249,69,6,32,19,20,4,702,209,10,97,48,44,N,E,103,8,2,NA,N 172 | 429,91,12,41,42,57,13,5590,1397,83,578,579,644,A,W,686,46,4,825,N 173 | 212,54,13,28,44,18,2,233,59,13,31,46,20,A,E,243,23,5,NA,A 174 | 453,101,3,46,43,61,3,948,218,6,96,72,91,N,W,249,444,16,195,N 175 | 161,43,4,17,26,22,3,707,179,21,77,99,76,A,W,300,12,2,NA,A 176 | 184,47,5,20,28,18,11,3327,890,74,419,382,304,N,W,49,2,0,450,N 177 | 591,184,20,83,79,38,5,1689,462,40,219,195,82,N,W,303,12,5,630,N 178 | 181,58,6,34,23,22,1,181,58,6,34,23,22,N,W,88,0,3,86.5,N 179 | 441,118,28,84,86,68,8,2723,750,126,433,420,309,A,E,190,2,2,1300,A 180 | 490,150,21,69,58,35,14,6126,1839,121,983,707,600,A,E,96,5,3,1000,N 181 | 551,171,13,94,83,94,13,6090,1840,128,969,900,917,N,E,1199,149,5,1800,N 182 | 550,147,29,85,91,71,6,2816,815,117,405,474,319,A,W,1218,104,10,1310,A 183 | 283,74,4,34,29,22,10,3919,1062,85,505,456,283,N,W,145,5,7,737.5,N 184 | 560,161,26,89,96,66,4,1789,470,65,233,260,155,N,W,332,9,8,625,N 185 | 328,91,12,51,43,33,2,342,94,12,51,44,33,N,E,145,59,8,125,N 186 | 586,159,12,72,79,53,9,3082,880,83,363,477,295,N,E,181,13,4,1043.333,N 187 | 503,136,5,62,48,83,10,3423,970,20,408,303,414,N,W,65,258,8,725,N 188 | 344,85,24,69,64,88,7,911,214,64,150,156,187,A,W,0,0,0,300,A 189 | 680,223,31,119,96,34,3,1928,587,35,262,201,91,A,W,429,8,6,365,A 190 | 279,64,0,31,26,30,1,279,64,0,31,26,30,N,W,107,205,16,75,N 191 | 484,127,20,66,65,67,7,3006,844,116,436,458,377,N,E,1231,80,7,1183.333,N 192 | 431,127,8,77,45,58,2,667,187,9,117,64,88,N,E,283,8,3,202.5,N 193 | 283,70,8,33,37,27,12,4479,1222,94,557,483,307,A,E,156,2,2,225,A 194 | 491,141,11,77,47,37,15,4291,1240,84,615,430,340,A,E,239,8,2,525,A 195 | 199,52,9,26,28,21,6,805,191,30,113,119,87,N,W,235,22,5,265,N 196 | 589,149,21,89,86,64,7,3558,928,102,513,471,351,A,E,371,6,6,787.5,A 197 | 327,84,22,53,62,38,10,4273,1123,212,577,700,334,A,E,483,48,6,800,N 198 | 464,128,28,67,94,52,13,5829,1552,210,740,840,452,A,W,0,0,0,587.5,A 199 | 166,34,0,20,13,17,1,166,34,0,20,13,17,N,E,64,119,9,NA,N 200 | 338,92,18,42,60,21,3,682,185,36,88,112,50,A,E,0,0,0,145,A 201 | 508,146,8,80,44,46,9,3148,915,41,571,289,326,A,W,245,5,9,NA,A 202 | 584,157,20,95,73,63,10,4704,1320,93,724,522,576,A,E,276,421,11,420,A 203 | 216,54,2,27,25,33,1,216,54,2,27,25,33,N,W,317,36,1,75,N 204 | 625,179,4,94,60,65,5,1696,476,12,216,163,166,A,E,303,450,14,575,A 205 | 243,53,4,18,26,27,4,853,228,23,101,110,76,N,E,107,3,3,NA,N 206 | 489,131,19,77,55,34,7,2051,549,62,300,263,153,A,W,310,9,9,780,A 207 | 209,56,12,22,36,19,2,216,58,12,24,37,19,N,E,201,6,3,90,N 208 | 407,93,8,47,30,30,2,969,230,14,121,69,68,N,W,172,317,25,150,N 209 | 490,148,14,64,78,49,13,3400,1000,113,445,491,301,A,E,0,0,0,700,N 210 | 209,59,6,20,37,27,4,884,209,14,66,106,92,N,E,415,35,3,NA,N 211 | 442,131,18,68,77,33,6,1416,398,47,210,203,136,A,E,233,7,7,550,A 212 | 317,88,3,40,32,19,8,2543,715,28,269,270,118,A,W,220,16,4,NA,A 213 | 288,65,8,30,36,27,9,2815,698,55,315,325,189,N,E,259,30,10,650,A 214 | 209,54,3,25,14,12,1,209,54,3,25,14,12,A,W,102,6,3,68,A 215 | 303,71,3,18,30,36,3,344,76,3,20,36,45,N,E,468,47,6,100,N 216 | 330,77,19,47,53,27,6,1928,516,90,247,288,161,N,W,149,8,6,670,N 217 | 504,120,28,71,71,54,3,1085,259,54,150,167,114,A,E,103,283,19,175,A 218 | 258,60,8,28,33,18,3,638,170,17,80,75,36,A,W,358,32,8,137,A 219 | 20,1,0,0,0,0,2,41,9,2,6,7,4,N,E,78,220,6,2127.333,N 220 | 374,94,5,36,26,62,7,1968,519,26,181,199,288,N,W,756,64,15,875,N 221 | 211,43,10,26,35,39,3,498,116,14,59,55,78,A,W,463,32,8,120,A 222 | 299,75,6,38,23,26,3,580,160,8,71,33,44,N,E,212,1,2,140,N 223 | 576,167,8,89,49,57,4,822,232,19,132,83,79,N,E,325,12,8,210,N 224 | 381,110,9,61,45,32,7,3015,834,40,451,249,168,N,E,228,7,5,800,N 225 | 288,76,7,34,37,15,4,1644,408,16,198,120,113,N,W,203,3,3,240,N 226 | 369,93,9,43,42,49,5,1258,323,54,181,177,157,A,E,149,1,6,350,A 227 | 330,76,12,35,41,47,4,1367,326,55,167,198,167,N,W,512,30,5,NA,N 228 | 547,137,2,58,47,12,2,1038,271,3,129,80,24,A,W,261,459,22,175,A 229 | 572,152,18,105,49,65,2,978,249,36,168,91,101,A,W,325,13,3,200,A 230 | 359,84,4,46,27,21,12,4992,1257,37,699,386,387,N,W,151,8,5,NA,N 231 | 514,144,0,67,54,79,9,4739,1169,13,583,374,528,N,E,229,453,15,1940,N 232 | 359,80,15,45,48,63,7,1493,359,61,176,202,175,N,W,682,93,13,700,N 233 | 526,163,12,88,50,77,4,1556,470,38,245,167,174,A,W,250,11,1,750,A 234 | 313,83,9,43,41,30,14,5885,1543,104,751,714,535,N,W,58,141,23,450,N 235 | 540,135,30,82,88,55,1,540,135,30,82,88,55,A,W,157,6,14,172,A 236 | 437,123,9,62,55,40,9,4139,1203,79,676,390,364,A,E,82,170,15,1260,A 237 | 551,160,23,86,90,87,5,2235,602,75,278,328,273,A,W,1224,115,11,NA,A 238 | 237,52,0,15,25,30,24,14053,4256,160,2165,1314,1566,N,W,523,43,6,750,N 239 | 236,56,6,41,19,21,5,1257,329,24,166,125,105,A,E,172,1,4,190,A 240 | 473,154,6,61,48,29,6,1966,566,29,250,252,178,A,E,846,84,9,580,A 241 | 309,72,0,33,31,26,5,354,82,0,41,32,26,N,E,117,269,12,130,N 242 | 271,77,5,35,29,33,12,4933,1358,48,630,435,403,A,W,62,90,3,450,A 243 | 357,96,7,50,45,39,5,1394,344,43,178,192,136,A,W,167,2,4,300,A 244 | 216,56,4,22,18,15,12,2796,665,43,266,304,198,A,E,391,44,4,250,A 245 | 256,70,13,42,36,44,16,7058,1845,312,965,1128,990,N,E,41,118,8,1050,A 246 | 466,108,33,75,86,72,3,652,142,44,102,109,102,A,E,286,8,8,215,A 247 | 327,68,13,42,29,45,18,3949,939,78,438,380,466,A,E,659,53,7,400,A 248 | 462,119,16,49,65,37,7,2131,583,69,244,288,150,A,E,866,65,6,NA,A 249 | 341,110,9,45,49,46,9,2331,658,50,249,322,274,A,E,251,9,4,560,A 250 | 608,160,28,130,74,89,8,4071,1182,103,862,417,708,A,E,426,4,6,1670,A 251 | 419,101,18,65,58,92,20,9528,2510,548,1509,1659,1342,A,W,0,0,0,487.5,A 252 | 33,6,0,2,4,7,1,33,6,0,2,4,7,A,W,205,5,4,NA,A 253 | 376,82,21,42,60,35,5,1770,408,115,238,299,157,A,W,0,0,0,425,A 254 | 486,145,11,51,76,40,11,3967,1102,67,410,497,284,N,E,88,204,16,500,A 255 | 186,44,7,28,16,11,1,186,44,7,28,16,11,N,W,99,3,1,NA,N 256 | 307,80,1,42,36,29,7,2421,656,18,379,198,184,A,W,145,2,2,NA,A 257 | 246,76,5,35,39,13,6,912,234,12,102,96,80,A,E,44,0,1,250,A 258 | 205,52,8,31,27,17,12,5134,1323,56,643,445,459,A,E,155,3,2,400,A 259 | 348,90,11,50,45,43,10,2288,614,43,295,273,269,A,E,60,176,6,450,A 260 | 523,135,8,52,44,52,9,3368,895,39,377,284,296,N,W,367,475,19,750,N 261 | 312,68,2,32,22,24,1,312,68,2,32,22,24,A,E,86,150,15,70,A 262 | 496,119,8,57,33,21,7,3358,882,36,365,280,165,N,W,155,371,29,875,N 263 | 126,27,3,8,10,5,4,239,49,3,16,13,14,N,E,190,2,9,190,N 264 | 275,68,5,42,42,61,6,961,238,16,128,104,172,N,E,181,3,2,191,N 265 | 627,178,14,68,76,46,6,3146,902,74,494,345,242,N,E,309,492,5,740,N 266 | 394,86,1,38,28,36,4,1089,267,3,94,71,76,N,E,203,369,16,250,N 267 | 208,57,8,32,25,18,3,653,170,17,98,54,62,N,E,42,94,13,140,N 268 | 382,101,16,50,55,22,1,382,101,16,50,55,22,A,W,200,7,6,97.5,A 269 | 459,113,20,59,57,68,12,5348,1369,155,713,660,735,A,W,0,0,0,740,A 270 | 549,149,7,73,47,42,1,549,149,7,73,47,42,N,W,255,450,17,140,N 271 | 288,63,3,25,33,16,10,2682,667,38,315,259,204,A,W,135,257,7,341.667,A 272 | 303,84,4,35,32,23,2,312,87,4,39,32,23,N,W,179,5,3,NA,N 273 | 522,163,9,82,46,62,13,7037,2019,153,1043,827,535,A,E,352,9,1,1000,A 274 | 512,117,29,54,88,43,6,1750,412,100,204,276,155,A,W,1236,98,18,100,A 275 | 220,66,5,20,28,13,3,290,80,5,27,31,15,A,W,281,21,3,90,A 276 | 522,140,16,73,77,60,4,730,185,22,93,106,86,N,E,1320,166,17,200,N 277 | 461,112,18,54,54,35,2,680,160,24,76,75,49,A,W,111,226,11,135,A 278 | 581,145,17,66,68,21,2,831,210,21,106,86,40,N,E,320,465,32,155,N 279 | 530,159,3,82,50,47,6,1619,426,11,218,149,163,A,W,196,354,15,475,A 280 | 557,142,21,58,81,23,18,8759,2583,271,1138,1299,478,N,W,1160,53,7,1450,N 281 | 439,96,0,44,36,65,4,711,148,1,68,56,99,N,E,229,406,22,150,N 282 | 453,103,8,53,33,52,2,507,123,8,63,39,58,A,W,289,407,6,105,A 283 | 528,122,1,67,45,51,4,1716,403,12,211,146,155,A,W,209,372,17,350,A 284 | 633,210,6,91,56,59,6,3070,872,19,420,230,274,N,W,367,432,16,90,N 285 | 16,2,0,1,0,0,2,28,4,0,1,0,0,A,E,247,4,8,NA,A 286 | 562,169,17,88,73,53,8,3181,841,61,450,342,373,A,E,351,442,17,530,A 287 | 281,76,3,42,25,20,8,2658,657,48,324,300,179,A,E,106,144,7,341.667,A 288 | 593,152,23,69,75,53,6,2765,686,133,369,384,321,A,W,315,10,6,940,A 289 | 687,213,10,91,65,27,4,1518,448,15,196,137,89,A,E,294,445,13,350,A 290 | 368,103,3,48,28,54,8,1897,493,9,207,162,198,N,W,209,246,3,326.667,N 291 | 263,70,1,26,23,30,4,888,220,9,83,82,86,N,E,81,147,4,250,N 292 | 642,211,14,107,59,52,5,2364,770,27,352,230,193,N,W,337,19,4,740,N 293 | 265,68,8,26,30,29,7,1337,339,32,135,163,128,N,W,92,5,3,425,A 294 | 289,63,7,36,41,44,17,7402,1954,195,1115,919,1153,A,W,166,211,7,NA,A 295 | 559,141,2,48,61,73,8,3162,874,16,421,349,359,N,E,352,414,9,925,N 296 | 520,120,17,53,44,21,4,927,227,22,106,80,52,A,W,70,144,11,185,A 297 | 19,4,1,2,3,1,1,19,4,1,2,3,1,N,W,692,70,8,920,A 298 | 205,43,2,24,17,20,7,854,219,12,105,99,71,N,E,131,6,1,286.667,N 299 | 193,47,10,21,29,24,6,1136,256,42,129,139,106,A,W,299,13,5,245,A 300 | 181,46,1,19,18,17,5,937,238,9,88,95,104,A,E,37,98,9,NA,A 301 | 213,61,4,17,22,3,17,4061,1145,83,488,491,244,A,W,178,45,4,235,A 302 | 510,147,10,56,52,53,7,2872,821,63,307,340,174,N,E,810,99,18,1150,N 303 | 578,138,1,56,59,34,3,1399,357,7,149,161,87,N,E,133,371,20,160,N 304 | 200,51,2,14,29,25,23,9778,2732,379,1272,1652,925,N,W,398,29,7,NA,N 305 | 441,113,5,76,52,76,5,1546,397,17,226,149,191,A,W,160,290,11,425,A 306 | 172,42,3,17,14,15,10,4086,1150,57,579,363,406,N,W,65,0,0,900,N 307 | 580,194,9,91,62,78,8,3372,1028,48,604,314,469,N,E,270,13,6,NA,N 308 | 127,32,4,14,25,12,19,8396,2402,242,1048,1348,819,N,W,167,18,6,500,N 309 | 279,69,4,35,31,32,4,1359,355,31,180,148,158,N,E,133,173,9,277.5,N 310 | 480,112,18,50,71,44,7,3031,771,110,338,406,239,N,E,94,270,16,750,N 311 | 600,139,0,94,29,60,2,1236,309,1,201,69,110,N,E,300,12,9,160,N 312 | 610,186,19,107,98,74,6,2728,753,69,399,366,286,N,E,1182,96,13,1300,N 313 | 360,81,5,37,44,37,7,2268,566,41,279,257,246,N,E,170,284,3,525,N 314 | 387,124,1,67,27,36,7,1775,506,6,272,125,194,N,E,186,290,17,550,N 315 | 580,207,8,107,71,105,5,2778,978,32,474,322,417,A,E,121,267,19,1600,A 316 | 408,117,11,66,41,34,1,408,117,11,66,41,34,N,W,942,72,11,120,N 317 | 593,172,22,82,100,57,1,593,172,22,82,100,57,A,W,1222,139,15,165,A 318 | 221,53,2,21,23,22,8,1063,283,15,107,124,106,N,E,325,58,6,NA,N 319 | 497,127,7,65,48,37,5,2703,806,32,379,311,138,N,E,325,9,3,700,N 320 | 492,136,5,76,50,94,12,5511,1511,39,897,451,875,A,E,313,381,20,875,A 321 | 475,126,3,61,43,52,6,1700,433,7,217,93,146,A,W,37,113,7,385,A 322 | 573,144,9,85,60,78,8,3198,857,97,470,420,332,A,E,1314,131,12,960,A 323 | 631,170,9,77,44,31,11,4908,1457,30,775,357,249,A,W,408,4,3,1000,A 324 | -------------------------------------------------------------------------------- /chapter_8/1_Probit_and_Logit_Models.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 2, 6 | "id": "8c161d5e-877e-41eb-9ba1-09251398f4bb", 7 | "metadata": {}, 8 | "outputs": [ 9 | { 10 | "data": { 11 | "text/html": [ 12 | "
\n", 13 | "\n", 26 | "\n", 27 | " \n", 28 | " \n", 29 | " \n", 30 | " \n", 31 | " \n", 32 | " \n", 33 | " \n", 34 | " \n", 35 | " \n", 36 | " \n", 37 | " \n", 38 | " \n", 39 | " \n", 40 | " \n", 41 | " \n", 42 | " \n", 43 | " \n", 44 | " \n", 45 | " \n", 46 | " \n", 47 | " \n", 48 | " \n", 49 | " \n", 50 | " \n", 51 | " \n", 52 | " \n", 53 | " \n", 54 | " \n", 55 | " \n", 56 | " \n", 57 | " \n", 58 | " \n", 59 | " \n", 60 | " \n", 61 | " \n", 62 | " \n", 63 | " \n", 64 | " \n", 65 | " \n", 66 | " \n", 67 | "
AdmittedGPAExp
012.88
113.36
213.75
313.75
413.76
\n", 68 | "
" 69 | ], 70 | "text/plain": [ 71 | " Admitted GPA Exp\n", 72 | "0 1 2.8 8\n", 73 | "1 1 3.3 6\n", 74 | "2 1 3.7 5\n", 75 | "3 1 3.7 5\n", 76 | "4 1 3.7 6" 77 | ] 78 | }, 79 | "execution_count": 2, 80 | "metadata": {}, 81 | "output_type": "execute_result" 82 | } 83 | ], 84 | "source": [ 85 | "import pandas as pd \n", 86 | "\n", 87 | "# create gpa train data \n", 88 | "train = pd.DataFrame({'Admitted': [1, 1, 1,1, 1, 0, 1, 1, 0, 1,1,1, 1,1,0, 1, 0, 0, 0, 0, 0, 0, 0, 0 ,0 ,0, 1,1,1,1, 0], \n", 89 | " 'GPA': [2.8, 3.3, 3.7, 3.7, 3.7, 3.3, 3.7, 3, 1.7, 3.6, 3.3, 4, 3.2, 3.4, 2.8, 4, 1.5, 2.7, 2.3, 2.3, 2.7, 2.2, 3.3,3.3, 4, 2.3, 3.6, 3.4, 4, 3.7, 2.3], \n", 90 | " 'Exp': [8, 6, 5, 5, 6, 3, 4, 2, 1, 5, 5, 3, 6,5, 4, 4, 4, 1, 1, 2, 2, 2, 1, 4, 4, 4, 5, 2, 4, 6, 3]}) \n", 91 | "train.head() " 92 | ] 93 | }, 94 | { 95 | "cell_type": "code", 96 | "execution_count": 3, 97 | "id": "b4b0c9a8-abc6-415a-aade-0458fc3cee07", 98 | "metadata": {}, 99 | "outputs": [ 100 | { 101 | "data": { 102 | "text/html": [ 103 | "
\n", 104 | "\n", 117 | "\n", 118 | " \n", 119 | " \n", 120 | " \n", 121 | " \n", 122 | " \n", 123 | " \n", 124 | " \n", 125 | " \n", 126 | " \n", 127 | " \n", 128 | " \n", 129 | " \n", 130 | " \n", 131 | " \n", 132 | " \n", 133 | " \n", 134 | " \n", 135 | " \n", 136 | " \n", 137 | " \n", 138 | " \n", 139 | " \n", 140 | " \n", 141 | " \n", 142 | " \n", 143 | " \n", 144 | " \n", 145 | " \n", 146 | " \n", 147 | " \n", 148 | " \n", 149 | " \n", 150 | " \n", 151 | " \n", 152 | " \n", 153 | " \n", 154 | " \n", 155 | " \n", 156 | " \n", 157 | " \n", 158 | "
AdmittedGPAExp
012.99
102.41
213.86
303.01
413.34
\n", 159 | "
" 160 | ], 161 | "text/plain": [ 162 | " Admitted GPA Exp\n", 163 | "0 1 2.9 9\n", 164 | "1 0 2.4 1\n", 165 | "2 1 3.8 6\n", 166 | "3 0 3.0 1\n", 167 | "4 1 3.3 4" 168 | ] 169 | }, 170 | "execution_count": 3, 171 | "metadata": {}, 172 | "output_type": "execute_result" 173 | } 174 | ], 175 | "source": [ 176 | "# create a testing dataset for this model. \n", 177 | "test = pd.DataFrame({'Admitted': [1, 0, 1, 0, 1], \n", 178 | " 'GPA': [2.9, 2.4, 3.8, 3, 3.3], \n", 179 | " 'Exp': [9, 1, 6, 1,4 ]}) \n", 180 | "test.head() " 181 | ] 182 | }, 183 | { 184 | "cell_type": "code", 185 | "execution_count": 4, 186 | "id": "362805e2-f7e2-45d5-ad48-766935ed307e", 187 | "metadata": {}, 188 | "outputs": [ 189 | { 190 | "name": "stdout", 191 | "output_type": "stream", 192 | "text": [ 193 | "Optimization terminated successfully.\n", 194 | " Current function value: 0.316480\n", 195 | " Iterations 7\n" 196 | ] 197 | }, 198 | { 199 | "data": { 200 | "text/html": [ 201 | "\n", 202 | "\n", 203 | "\n", 204 | " \n", 205 | "\n", 206 | "\n", 207 | " \n", 208 | "\n", 209 | "\n", 210 | " \n", 211 | "\n", 212 | "\n", 213 | " \n", 214 | "\n", 215 | "\n", 216 | " \n", 217 | "\n", 218 | "\n", 219 | " \n", 220 | "\n", 221 | "\n", 222 | " \n", 223 | "\n", 224 | "
Logit Regression Results
Dep. Variable: Admitted No. Observations: 31
Model: Logit Df Residuals: 28
Method: MLE Df Model: 2
Date: Fri, 07 Jul 2023 Pseudo R-squ.: 0.5403
Time: 21:16:53 Log-Likelihood: -9.8109
converged: True LL-Null: -21.342
Covariance Type: nonrobust LLR p-value: 9.818e-06
\n", 225 | "\n", 226 | "\n", 227 | " \n", 228 | "\n", 229 | "\n", 230 | " \n", 231 | "\n", 232 | "\n", 233 | " \n", 234 | "\n", 235 | "\n", 236 | " \n", 237 | "\n", 238 | "
coef std err z P>|z| [0.025 0.975]
Intercept -11.4485 4.320 -2.650 0.008 -19.915 -2.982
GPA 2.7606 1.291 2.139 0.032 0.231 5.290
Exp 0.7569 0.383 1.977 0.048 0.006 1.507
" 239 | ], 240 | "text/plain": [ 241 | "\n", 242 | "\"\"\"\n", 243 | " Logit Regression Results \n", 244 | "==============================================================================\n", 245 | "Dep. Variable: Admitted No. Observations: 31\n", 246 | "Model: Logit Df Residuals: 28\n", 247 | "Method: MLE Df Model: 2\n", 248 | "Date: Fri, 07 Jul 2023 Pseudo R-squ.: 0.5403\n", 249 | "Time: 21:16:53 Log-Likelihood: -9.8109\n", 250 | "converged: True LL-Null: -21.342\n", 251 | "Covariance Type: nonrobust LLR p-value: 9.818e-06\n", 252 | "==============================================================================\n", 253 | " coef std err z P>|z| [0.025 0.975]\n", 254 | "------------------------------------------------------------------------------\n", 255 | "Intercept -11.4485 4.320 -2.650 0.008 -19.915 -2.982\n", 256 | "GPA 2.7606 1.291 2.139 0.032 0.231 5.290\n", 257 | "Exp 0.7569 0.383 1.977 0.048 0.006 1.507\n", 258 | "==============================================================================\n", 259 | "\"\"\"" 260 | ] 261 | }, 262 | "execution_count": 4, 263 | "metadata": {}, 264 | "output_type": "execute_result" 265 | } 266 | ], 267 | "source": [ 268 | "# We will use Logit from statsmodels. \n", 269 | "\n", 270 | "import statsmodels.formula.api as smf \n", 271 | "#fit logistic regression \n", 272 | "model = smf.logit('Admitted ~ GPA + Exp', data =train).fit() \n", 273 | "#summary \n", 274 | "model.summary() " 275 | ] 276 | }, 277 | { 278 | "cell_type": "code", 279 | "execution_count": 5, 280 | "id": "1fd280f6-6411-4ee0-a270-5fe9add8b30a", 281 | "metadata": {}, 282 | "outputs": [ 283 | { 284 | "name": "stdout", 285 | "output_type": "stream", 286 | "text": [ 287 | "Test accuracy = 1.0\n" 288 | ] 289 | }, 290 | { 291 | "data": { 292 | "image/png": "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\n", 293 | "text/plain": [ 294 | "
" 295 | ] 296 | }, 297 | "metadata": { 298 | "needs_background": "light" 299 | }, 300 | "output_type": "display_data" 301 | } 302 | ], 303 | "source": [ 304 | "# confusion_matrix and accuracy_score to compute the accuracy of the model on the test set\n", 305 | "\n", 306 | "from sklearn.metrics import confusion_matrix, accuracy_score, ConfusionMatrixDisplay \n", 307 | "# X_test and y_test \n", 308 | "X_test = test[['GPA', 'Exp']] \n", 309 | "y_test = test['Admitted'] \n", 310 | "# \n", 311 | "y_hat = model.predict(X_test) \n", 312 | "pred = list(map(round, y_hat)) \n", 313 | "# confusion matrix \n", 314 | "cm = confusion_matrix(y_test, pred) \n", 315 | "ConfusionMatrixDisplay(cm).plot() \n", 316 | "\n", 317 | "# Accuracy \n", 318 | "print('Test accuracy = ', accuracy_score(y_test, pred))" 319 | ] 320 | }, 321 | { 322 | "cell_type": "code", 323 | "execution_count": null, 324 | "id": "dc9d0684-3cee-4771-8f31-e3a90fde0089", 325 | "metadata": {}, 326 | "outputs": [], 327 | "source": [] 328 | } 329 | ], 330 | "metadata": { 331 | "kernelspec": { 332 | "display_name": "Python 3 (ipykernel)", 333 | "language": "python", 334 | "name": "python3" 335 | }, 336 | "language_info": { 337 | "codemirror_mode": { 338 | "name": "ipython", 339 | "version": 3 340 | }, 341 | "file_extension": ".py", 342 | "mimetype": "text/x-python", 343 | "name": "python", 344 | "nbconvert_exporter": "python", 345 | "pygments_lexer": "ipython3", 346 | "version": "3.9.7" 347 | } 348 | }, 349 | "nbformat": 4, 350 | "nbformat_minor": 5 351 | } 352 | -------------------------------------------------------------------------------- /chapter_8/2_Multinomial_Logit_Model.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "51670ec2-6846-406e-a022-a421870a0417", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "# import packages \n", 11 | "\n", 12 | "import numpy as np \n", 13 | "import pandas as pd \n", 14 | "from sklearn import datasets \n", 15 | "from sklearn.model_selection import train_test_split \n", 16 | "from sklearn.linear_model import LogisticRegression \n", 17 | "from sklearn.metrics import confusion_matrix, accuracy_score, ConfusionMatrixDisplay \n", 18 | "import statsmodels.discrete.discrete_model as sm " 19 | ] 20 | }, 21 | { 22 | "cell_type": "code", 23 | "execution_count": 2, 24 | "id": "73b145a2-43dc-4c08-98e6-bbb4c6222b75", 25 | "metadata": {}, 26 | "outputs": [ 27 | { 28 | "name": "stdout", 29 | "output_type": "stream", 30 | "text": [ 31 | "['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']\n", 32 | "['setosa' 'versicolor' 'virginica']\n" 33 | ] 34 | } 35 | ], 36 | "source": [ 37 | "# import Iris data \n", 38 | "\n", 39 | "iris = datasets.load_iris() \n", 40 | "print(iris.feature_names) \n", 41 | "print(iris.target_names) " 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 3, 47 | "id": "3b8a03c5-454e-4a97-b6fc-121dcd1b19ad", 48 | "metadata": {}, 49 | "outputs": [ 50 | { 51 | "data": { 52 | "text/html": [ 53 | "
\n", 54 | "\n", 67 | "\n", 68 | " \n", 69 | " \n", 70 | " \n", 71 | " \n", 72 | " \n", 73 | " \n", 74 | " \n", 75 | " \n", 76 | " \n", 77 | " \n", 78 | " \n", 79 | " \n", 80 | " \n", 81 | " \n", 82 | " \n", 83 | " \n", 84 | " \n", 85 | " \n", 86 | " \n", 87 | " \n", 88 | " \n", 89 | " \n", 90 | " \n", 91 | " \n", 92 | " \n", 93 | " \n", 94 | " \n", 95 | " \n", 96 | " \n", 97 | " \n", 98 | " \n", 99 | " \n", 100 | " \n", 101 | " \n", 102 | " \n", 103 | " \n", 104 | " \n", 105 | " \n", 106 | " \n", 107 | " \n", 108 | " \n", 109 | " \n", 110 | " \n", 111 | " \n", 112 | " \n", 113 | " \n", 114 | " \n", 115 | " \n", 116 | " \n", 117 | " \n", 118 | " \n", 119 | " \n", 120 | "
sepal_lengthsepal_widthpetal_lengthpetal_widthtarget
05.13.51.40.20
14.93.01.40.20
24.73.21.30.20
34.63.11.50.20
45.03.61.40.20
\n", 121 | "
" 122 | ], 123 | "text/plain": [ 124 | " sepal_length sepal_width petal_length petal_width target\n", 125 | "0 5.1 3.5 1.4 0.2 0\n", 126 | "1 4.9 3.0 1.4 0.2 0\n", 127 | "2 4.7 3.2 1.3 0.2 0\n", 128 | "3 4.6 3.1 1.5 0.2 0\n", 129 | "4 5.0 3.6 1.4 0.2 0" 130 | ] 131 | }, 132 | "execution_count": 3, 133 | "metadata": {}, 134 | "output_type": "execute_result" 135 | } 136 | ], 137 | "source": [ 138 | "#create dataframe \n", 139 | "\n", 140 | "df = pd.DataFrame(iris.data, columns = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width']) \n", 141 | "df['target'] = iris.target \n", 142 | "df.head() \n", 143 | " " 144 | ] 145 | }, 146 | { 147 | "cell_type": "code", 148 | "execution_count": 4, 149 | "id": "46084f27-5ab8-4b2a-a8ae-d5935845fb7d", 150 | "metadata": {}, 151 | "outputs": [ 152 | { 153 | "data": { 154 | "text/plain": [ 155 | "sepal_length 0\n", 156 | "sepal_width 0\n", 157 | "petal_length 0\n", 158 | "petal_width 0\n", 159 | "target 0\n", 160 | "dtype: int64" 161 | ] 162 | }, 163 | "execution_count": 4, 164 | "metadata": {}, 165 | "output_type": "execute_result" 166 | } 167 | ], 168 | "source": [ 169 | "# check missing values \n", 170 | "\n", 171 | "df.isna().sum() " 172 | ] 173 | }, 174 | { 175 | "cell_type": "code", 176 | "execution_count": 5, 177 | "id": "bd487617-2c6e-42af-b6f2-be479f6ddab3", 178 | "metadata": {}, 179 | "outputs": [], 180 | "source": [ 181 | "# create train and test data \n", 182 | "\n", 183 | "X = df.drop('target', axis=1) \n", 184 | "y = df['target'] \n", 185 | "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size =0.2, random_state =1) " 186 | ] 187 | }, 188 | { 189 | "cell_type": "code", 190 | "execution_count": 6, 191 | "id": "87541aa8-b7a9-4b49-ac4f-9885fe24f62c", 192 | "metadata": {}, 193 | "outputs": [ 194 | { 195 | "name": "stdout", 196 | "output_type": "stream", 197 | "text": [ 198 | "Test accuracy = 0.9666666666666667\n" 199 | ] 200 | }, 201 | { 202 | "data": { 203 | "image/png": "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\n", 204 | "text/plain": [ 205 | "
" 206 | ] 207 | }, 208 | "metadata": { 209 | "needs_background": "light" 210 | }, 211 | "output_type": "display_data" 212 | } 213 | ], 214 | "source": [ 215 | "# fit the model using sklearn \n", 216 | "\n", 217 | "model_sk = LogisticRegression(solver = 'newton-cg', multi_class = 'multinomial') \n", 218 | "model_sk.fit(X_train, y_train) \n", 219 | "y_hat_sk = model_sk.predict(X_test) \n", 220 | "pred_sk = list(map(round, y_hat_sk)) \n", 221 | "# confusion matrix \n", 222 | "cm_sk = confusion_matrix(y_test, pred_sk) \n", 223 | "ConfusionMatrixDisplay(cm_sk).plot() \n", 224 | "# Accuracy \n", 225 | "print('Test accuracy = ', accuracy_score(y_test, pred_sk)) " 226 | ] 227 | }, 228 | { 229 | "cell_type": "code", 230 | "execution_count": 7, 231 | "id": "8ca9004b-8403-45fc-8918-0a6ab6bee307", 232 | "metadata": {}, 233 | "outputs": [ 234 | { 235 | "name": "stdout", 236 | "output_type": "stream", 237 | "text": [ 238 | "Warning: Maximum number of iterations has been exceeded.\n", 239 | " Current function value: 0.073466\n", 240 | " Iterations: 35\n", 241 | " Function evaluations: 37\n", 242 | " Gradient evaluations: 37\n", 243 | "Test accuracy = 0.9666666666666667\n" 244 | ] 245 | }, 246 | { 247 | "name": "stderr", 248 | "output_type": "stream", 249 | "text": [ 250 | "/Users/hoangnguyen/opt/anaconda3/lib/python3.9/site-packages/statsmodels/base/model.py:566: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n", 251 | " warnings.warn(\"Maximum Likelihood optimization failed to \"\n" 252 | ] 253 | }, 254 | { 255 | "data": { 256 | "image/png": "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\n", 257 | "text/plain": [ 258 | "
" 259 | ] 260 | }, 261 | "metadata": { 262 | "needs_background": "light" 263 | }, 264 | "output_type": "display_data" 265 | } 266 | ], 267 | "source": [ 268 | "#fit the model using statsmodels \n", 269 | "\n", 270 | "model_stat = sm.MNLogit(y_train, X_train).fit(method='bfgs') \n", 271 | "model_stat.summary() \n", 272 | "y_hat_stat = model_stat.predict(X_test) \n", 273 | "pred_stat = np.asarray(y_hat_stat).argmax(1) \n", 274 | "# confusion matrix \n", 275 | "cm_stat = confusion_matrix(y_test, pred_stat) \n", 276 | "ConfusionMatrixDisplay(cm_stat).plot() \n", 277 | "# Accuracy \n", 278 | "print('Test accuracy = ', accuracy_score(y_test, pred_stat)) " 279 | ] 280 | }, 281 | { 282 | "cell_type": "code", 283 | "execution_count": null, 284 | "id": "a533d9e7-6197-4c0d-b505-b1e7e49e973b", 285 | "metadata": {}, 286 | "outputs": [], 287 | "source": [] 288 | } 289 | ], 290 | "metadata": { 291 | "kernelspec": { 292 | "display_name": "Python 3 (ipykernel)", 293 | "language": "python", 294 | "name": "python3" 295 | }, 296 | "language_info": { 297 | "codemirror_mode": { 298 | "name": "ipython", 299 | "version": 3 300 | }, 301 | "file_extension": ".py", 302 | "mimetype": "text/x-python", 303 | "name": "python", 304 | "nbconvert_exporter": "python", 305 | "pygments_lexer": "ipython3", 306 | "version": "3.9.7" 307 | } 308 | }, 309 | "nbformat": 4, 310 | "nbformat_minor": 5 311 | } 312 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | # core packages 2 | numpy==1.23.0 3 | scipy==1.8.1 4 | statsmodels==0.13.2 5 | pandas==1.4.3 6 | scikit-learn==1.1.1 7 | matplotlib==3.5.2 8 | # specialized 9 | seaborn==0.12.1 10 | sktime==0.15.0 11 | pmdarima==2.0.2 12 | lifelines==0.27.4 13 | pyreadr==0.4.6 14 | # jupyter 15 | jupyter 16 | notebook 17 | jupyterlab --------------------------------------------------------------------------------