{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Loading Dataset & Quick Overview"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.pylab import rcParams\n",
    "from sklearn.datasets import load_boston\n",
    "\n",
    "%matplotlib inline\n",
    "rcParams['figure.figsize'] = 15, 15\n",
    "\n",
    "data_url = \"http://lib.stat.cmu.edu/datasets/boston\"\n",
    "raw_df = pd.read_csv(data_url, sep=\"\\s+\", skiprows=22, header=None)\n",
    "data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])\n",
    "target = raw_df.values[1::2, 2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(data.shape)  # data.data ==> Features\n",
    "print(target.shape)  # data.target ==> Label"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Plot Features V.S. Y\n",
    "Can you explain the relation between other features with house prices?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import math\n",
    "\n",
    "features = [\n",
    "    'CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX',\n",
    "    'PTRATIO', 'B', 'LSTAT'\n",
    "]\n",
    "\n",
    "fig, axes = plt.subplots(4, 4)\n",
    "for i in range(13):\n",
    "    x_f = i % 4\n",
    "    y_f = math.floor((i) / 4)\n",
    "    axes[x_f, y_f].scatter(data[:, i], target)\n",
    "    axes[x_f, y_f].set_xlabel(features[i])\n",
    "    axes[x_f, y_f].set_ylabel('prices')\n",
    "plt.show()\n",
    "\"\"\"\n",
    "- CRIM     per capita crime rate by town\n",
    "- ZN       proportion of residential land zoned for lots over 25,000 sq.ft.\n",
    "- INDUS    proportion of non-retail business acres per town\n",
    "- CHAS     Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)\n",
    "- NOX      nitric oxides concentration (parts per 10 million)\n",
    "- RM       average number of rooms per dwelling\n",
    "- AGE      proportion of owner-occupied units built prior to 1940\n",
    "- DIS      weighted distances to five Boston employment centres\n",
    "- RAD      index of accessibility to radial highways\n",
    "- TAX      full-value property-tax rate per $10,000\n",
    "- PTRATIO  pupil-teacher ratio by town\n",
    "- B        1000(Bk - 0.63)^2 where Bk is the proportion of blacks by town\n",
    "- LSTAT    % lower status of the population\n",
    "\"\"\"\n",
    "pass"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Predicting Home Prices: SVR\n",
    "在沒有做任何new feature生成的情況下，是否可以讓SVR的performance接近linear regression?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = data\n",
    "y = target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import needed models in scikit-learn by yourself\n",
    "# and fit a linear model using training dataset\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn import svm\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,\n",
    "                                                    y,\n",
    "                                                    test_size=0.25,\n",
    "                                                    random_state=42,\n",
    "                                                    shuffle=True)\n",
    "\n",
    "model = svm.SVR(kernel='poly', gamma=1e-2, degree=2, C=0.1)\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# make prediction here\n",
    "# y_pred = '''make prediction on testing dataset here'''\n",
    "y_pred = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Evaluation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import metrics\n",
    "# visualize the result\n",
    "%matplotlib inline\n",
    "plt.scatter(y_test, y_pred)\n",
    "plt.plot([0, 50], [0, 50], '--k')\n",
    "plt.axis('tight')\n",
    "plt.xlabel('True price ($1000s)')\n",
    "plt.ylabel('Predicted price ($1000s)')\n",
    "print(\"RMS:\", np.sqrt(np.mean((y_pred - y_test)**2)))\n",
    "print('R2:%.2f' % metrics.r2_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.2"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}