examples/lesson14/snippets_ipynb/14_04.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 14.4 Case Study: Time Series and Simple Linear Regression \n",
    "### Loading the Average High Temperatures into a `DataFrame` \n",
    "\n",
    "**We added `%matplotlib inline` to enable Matplotlib in this notebook.**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "nyc = pd.read_csv('ave_hi_nyc_jan_1895-2018.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "nyc.columns = ['Date', 'Temperature', 'Anomaly']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "nyc.Date = nyc.Date.floordiv(100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "nyc.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Splitting the Data for Training and Testing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "     nyc.Date.values.reshape(-1, 1), nyc.Temperature.values, \n",
    "     random_state=11)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Training the Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LinearRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "linear_regression = LinearRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "linear_regression.fit(X=X_train, y=y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "linear_regression.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "linear_regression.intercept_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Testing the Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predicted = linear_regression.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "expected = y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for p, e in zip(predicted[::5], expected[::5]):\n",
    "     print(f'predicted: {p:.2f}, expected: {e:.2f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Predicting Future Temperatures and Estimating Past Temperatures "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict = (lambda x: linear_regression.coef_ * x + \n",
    "                      linear_regression.intercept_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict(2019)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict(1890)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Visualizing the Dataset with the Regression Line"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "axes = sns.scatterplot(data=nyc, x='Date', y='Temperature',\n",
    "     hue='Temperature', palette='winter', legend=False)\n",
    "\n",
    "axes.set_ylim(10, 70)\n",
    "\n",
    "import numpy as np\n",
    "\n",
    "x = np.array([min(nyc.Date.values), max(nyc.Date.values)])\n",
    "\n",
    "y = predict(x)\n",
    "\n",
    "import matplotlib.pyplot as plt \n",
    "\n",
    "line = plt.plot(x, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This placeholder cell was added because we had to combine \n",
    "# the sections snippets 22-28 for the visualization to work in Jupyter\n",
    "# and want the subsequent snippet numbers to match the book"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Placeholder cell "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Placeholder cell "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Placeholder cell "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Placeholder cell "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Placeholder cell "
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "### Overfitting/Underfitting"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# More Info \n",
    "* See **video** Lesson 14 in [**Python Fundamentals LiveLessons** on Safari Online Learning](https://learning.oreilly.com/videos/python-fundamentals/9780135917411)\n",
    "* See **book** Chapter 14 in [**Python for Programmers** on Safari Online Learning](https://learning.oreilly.com/library/view/python-for-programmers/9780135231364/), or see **book** Chapter 15 in **Intro to Python for Computer Science and Data Science**\n",
    "* Interested in a print book? Check out:\n",
    "\n",
    "| Python for Programmers | Intro to Python for Computer<br>Science and Data Science\n",
    "| :------ | :------\n",
    "| <a href=\"https://amzn.to/2VvdnxE\"><img alt=\"Python for Programmers cover\" src=\"../images/PyFPCover.png\" width=\"150\" border=\"1\"/></a> | <a href=\"https://amzn.to/2LiDCmt\"><img alt=\"Intro to Python for Computer Science and Data Science: Learning to Program with AI, Big Data and the Cloud\" src=\"../images/IntroToPythonCover.png\" width=\"159\" border=\"1\"></a>\n",
    "\n",
    ">Please **do not** purchase both books&mdash;our professional book **_Python for Programmers_** is a subset of our college textbook **_Intro to Python for Computer Science and Data Science_**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "##########################################################################\n",
    "# (C) Copyright 2019 by Deitel & Associates, Inc. and                    #\n",
    "# Pearson Education, Inc. All Rights Reserved.                           #\n",
    "#                                                                        #\n",
    "# DISCLAIMER: The authors and publisher of this book have used their     #\n",
    "# best efforts in preparing the book. These efforts include the          #\n",
    "# development, research, and testing of the theories and programs        #\n",
    "# to determine their effectiveness. The authors and publisher make       #\n",
    "# no warranty of any kind, expressed or implied, with regard to these    #\n",
    "# programs or to the documentation contained in these books. The authors #\n",
    "# and publisher shall not be liable in any event for incidental or       #\n",
    "# consequential damages in connection with, or arising out of, the       #\n",
    "# furnishing, performance, or use of these programs.                     #\n",
    "##########################################################################\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}