assets/files/notebook/2_MODEL_TRAINING.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5783d108",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/Yuvraj-Dhepe/ML_Web_Project/blob/main/2_MODEL_TRAINING.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "92e48866",
   "metadata": {},
   "source": [
    "## Model Training"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "25791a74",
   "metadata": {},
   "source": [
    "#### 1.1 Import Data and Required Packages\n",
    "##### Importing Pandas, Numpy, Matplotlib, Seaborn and Warings Library."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "d895bb2d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[0;31mInit signature:\u001b[0m\n",
      "\u001b[0mLasso\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0malpha\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1.0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m*\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mfit_intercept\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mprecompute\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mcopy_X\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mmax_iter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1000\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mtol\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.0001\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mwarm_start\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mpositive\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mrandom_state\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mselection\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'cyclic'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mSource:\u001b[0m        \n",
      "\u001b[0;32mclass\u001b[0m \u001b[0mLasso\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mElasticNet\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m\"\"\"Linear Model trained with L1 prior as regularizer (aka the Lasso).\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    The optimization objective for Lasso is::\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        (1 / (2 * n_samples)) * ||y - Xw||^2_2 + alpha * ||w||_1\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    Technically the Lasso model is optimizing the same objective function as\u001b[0m\n",
      "\u001b[0;34m    the Elastic Net with ``l1_ratio=1.0`` (no L2 penalty).\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    Read more in the :ref:`User Guide <lasso>`.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    Parameters\u001b[0m\n",
      "\u001b[0;34m    ----------\u001b[0m\n",
      "\u001b[0;34m    alpha : float, default=1.0\u001b[0m\n",
      "\u001b[0;34m        Constant that multiplies the L1 term, controlling regularization\u001b[0m\n",
      "\u001b[0;34m        strength. `alpha` must be a non-negative float i.e. in `[0, inf)`.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        When `alpha = 0`, the objective is equivalent to ordinary least\u001b[0m\n",
      "\u001b[0;34m        squares, solved by the :class:`LinearRegression` object. For numerical\u001b[0m\n",
      "\u001b[0;34m        reasons, using `alpha = 0` with the `Lasso` object is not advised.\u001b[0m\n",
      "\u001b[0;34m        Instead, you should use the :class:`LinearRegression` object.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    fit_intercept : bool, default=True\u001b[0m\n",
      "\u001b[0;34m        Whether to calculate the intercept for this model. If set\u001b[0m\n",
      "\u001b[0;34m        to False, no intercept will be used in calculations\u001b[0m\n",
      "\u001b[0;34m        (i.e. data is expected to be centered).\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    precompute : bool or array-like of shape (n_features, n_features),\\\u001b[0m\n",
      "\u001b[0;34m                 default=False\u001b[0m\n",
      "\u001b[0;34m        Whether to use a precomputed Gram matrix to speed up\u001b[0m\n",
      "\u001b[0;34m        calculations. The Gram matrix can also be passed as argument.\u001b[0m\n",
      "\u001b[0;34m        For sparse input this option is always ``False`` to preserve sparsity.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    copy_X : bool, default=True\u001b[0m\n",
      "\u001b[0;34m        If ``True``, X will be copied; else, it may be overwritten.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    max_iter : int, default=1000\u001b[0m\n",
      "\u001b[0;34m        The maximum number of iterations.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    tol : float, default=1e-4\u001b[0m\n",
      "\u001b[0;34m        The tolerance for the optimization: if the updates are\u001b[0m\n",
      "\u001b[0;34m        smaller than ``tol``, the optimization code checks the\u001b[0m\n",
      "\u001b[0;34m        dual gap for optimality and continues until it is smaller\u001b[0m\n",
      "\u001b[0;34m        than ``tol``, see Notes below.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    warm_start : bool, default=False\u001b[0m\n",
      "\u001b[0;34m        When set to True, reuse the solution of the previous call to fit as\u001b[0m\n",
      "\u001b[0;34m        initialization, otherwise, just erase the previous solution.\u001b[0m\n",
      "\u001b[0;34m        See :term:`the Glossary <warm_start>`.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    positive : bool, default=False\u001b[0m\n",
      "\u001b[0;34m        When set to ``True``, forces the coefficients to be positive.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    random_state : int, RandomState instance, default=None\u001b[0m\n",
      "\u001b[0;34m        The seed of the pseudo random number generator that selects a random\u001b[0m\n",
      "\u001b[0;34m        feature to update. Used when ``selection`` == 'random'.\u001b[0m\n",
      "\u001b[0;34m        Pass an int for reproducible output across multiple function calls.\u001b[0m\n",
      "\u001b[0;34m        See :term:`Glossary <random_state>`.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    selection : {'cyclic', 'random'}, default='cyclic'\u001b[0m\n",
      "\u001b[0;34m        If set to 'random', a random coefficient is updated every iteration\u001b[0m\n",
      "\u001b[0;34m        rather than looping over features sequentially by default. This\u001b[0m\n",
      "\u001b[0;34m        (setting to 'random') often leads to significantly faster convergence\u001b[0m\n",
      "\u001b[0;34m        especially when tol is higher than 1e-4.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    Attributes\u001b[0m\n",
      "\u001b[0;34m    ----------\u001b[0m\n",
      "\u001b[0;34m    coef_ : ndarray of shape (n_features,) or (n_targets, n_features)\u001b[0m\n",
      "\u001b[0;34m        Parameter vector (w in the cost function formula).\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    dual_gap_ : float or ndarray of shape (n_targets,)\u001b[0m\n",
      "\u001b[0;34m        Given param alpha, the dual gaps at the end of the optimization,\u001b[0m\n",
      "\u001b[0;34m        same shape as each observation of y.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    sparse_coef_ : sparse matrix of shape (n_features, 1) or \\\u001b[0m\n",
      "\u001b[0;34m            (n_targets, n_features)\u001b[0m\n",
      "\u001b[0;34m        Readonly property derived from ``coef_``.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    intercept_ : float or ndarray of shape (n_targets,)\u001b[0m\n",
      "\u001b[0;34m        Independent term in decision function.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    n_iter_ : int or list of int\u001b[0m\n",
      "\u001b[0;34m        Number of iterations run by the coordinate descent solver to reach\u001b[0m\n",
      "\u001b[0;34m        the specified tolerance.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    n_features_in_ : int\u001b[0m\n",
      "\u001b[0;34m        Number of features seen during :term:`fit`.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        .. versionadded:: 0.24\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    feature_names_in_ : ndarray of shape (`n_features_in_`,)\u001b[0m\n",
      "\u001b[0;34m        Names of features seen during :term:`fit`. Defined only when `X`\u001b[0m\n",
      "\u001b[0;34m        has feature names that are all strings.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        .. versionadded:: 1.0\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    See Also\u001b[0m\n",
      "\u001b[0;34m    --------\u001b[0m\n",
      "\u001b[0;34m    lars_path : Regularization path using LARS.\u001b[0m\n",
      "\u001b[0;34m    lasso_path : Regularization path using Lasso.\u001b[0m\n",
      "\u001b[0;34m    LassoLars : Lasso Path along the regularization parameter using LARS algorithm.\u001b[0m\n",
      "\u001b[0;34m    LassoCV : Lasso alpha parameter by cross-validation.\u001b[0m\n",
      "\u001b[0;34m    LassoLarsCV : Lasso least angle parameter algorithm by cross-validation.\u001b[0m\n",
      "\u001b[0;34m    sklearn.decomposition.sparse_encode : Sparse coding array estimator.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    Notes\u001b[0m\n",
      "\u001b[0;34m    -----\u001b[0m\n",
      "\u001b[0;34m    The algorithm used to fit the model is coordinate descent.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    To avoid unnecessary memory duplication the X argument of the fit method\u001b[0m\n",
      "\u001b[0;34m    should be directly passed as a Fortran-contiguous numpy array.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    Regularization improves the conditioning of the problem and\u001b[0m\n",
      "\u001b[0;34m    reduces the variance of the estimates. Larger values specify stronger\u001b[0m\n",
      "\u001b[0;34m    regularization. Alpha corresponds to `1 / (2C)` in other linear\u001b[0m\n",
      "\u001b[0;34m    models such as :class:`~sklearn.linear_model.LogisticRegression` or\u001b[0m\n",
      "\u001b[0;34m    :class:`~sklearn.svm.LinearSVC`. If an array is passed, penalties are\u001b[0m\n",
      "\u001b[0;34m    assumed to be specific to the targets. Hence they must correspond in\u001b[0m\n",
      "\u001b[0;34m    number.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    The precise stopping criteria based on `tol` are the following: First, check that\u001b[0m\n",
      "\u001b[0;34m    that maximum coordinate update, i.e. :math:`\\\\max_j |w_j^{new} - w_j^{old}|`\u001b[0m\n",
      "\u001b[0;34m    is smaller than `tol` times the maximum absolute coefficient, :math:`\\\\max_j |w_j|`.\u001b[0m\n",
      "\u001b[0;34m    If so, then additionally check whether the dual gap is smaller than `tol` times\u001b[0m\n",
      "\u001b[0;34m    :math:`||y||_2^2 / n_{\\\\text{samples}}`.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    The target can be a 2-dimensional array, resulting in the optimization of the\u001b[0m\n",
      "\u001b[0;34m    following objective::\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        (1 / (2 * n_samples)) * ||Y - XW||^2_F + alpha * ||W||_11\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    where :math:`||W||_{1,1}` is the sum of the magnitude of the matrix coefficients.\u001b[0m\n",
      "\u001b[0;34m    It should not be confused with :class:`~sklearn.linear_model.MultiTaskLasso` which\u001b[0m\n",
      "\u001b[0;34m    instead penalizes the :math:`L_{2,1}` norm of the coefficients, yielding row-wise\u001b[0m\n",
      "\u001b[0;34m    sparsity in the coefficients.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    Examples\u001b[0m\n",
      "\u001b[0;34m    --------\u001b[0m\n",
      "\u001b[0;34m    >>> from sklearn import linear_model\u001b[0m\n",
      "\u001b[0;34m    >>> clf = linear_model.Lasso(alpha=0.1)\u001b[0m\n",
      "\u001b[0;34m    >>> clf.fit([[0,0], [1, 1], [2, 2]], [0, 1, 2])\u001b[0m\n",
      "\u001b[0;34m    Lasso(alpha=0.1)\u001b[0m\n",
      "\u001b[0;34m    >>> print(clf.coef_)\u001b[0m\n",
      "\u001b[0;34m    [0.85 0.  ]\u001b[0m\n",
      "\u001b[0;34m    >>> print(clf.intercept_)\u001b[0m\n",
      "\u001b[0;34m    0.15...\u001b[0m\n",
      "\u001b[0;34m    \"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0m_parameter_constraints\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mdict\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m**\u001b[0m\u001b[0mElasticNet\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parameter_constraints\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0m_parameter_constraints\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpop\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"l1_ratio\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mpath\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstaticmethod\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0menet_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0malpha\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1.0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m*\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mfit_intercept\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mprecompute\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mcopy_X\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mmax_iter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1000\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mtol\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1e-4\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mwarm_start\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mpositive\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mrandom_state\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mselection\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"cyclic\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0malpha\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0malpha\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0ml1_ratio\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1.0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mfit_intercept\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfit_intercept\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mprecompute\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprecompute\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mcopy_X\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcopy_X\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mmax_iter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmax_iter\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mtol\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtol\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mwarm_start\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mwarm_start\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mpositive\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpositive\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mrandom_state\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrandom_state\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mselection\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mselection\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mFile:\u001b[0m           ~/side_projects/Projects/End_to_End_ML_Project/venv/lib/python3.8/site-packages/sklearn/linear_model/_coordinate_descent.py\n",
      "\u001b[0;31mType:\u001b[0m           ABCMeta\n",
      "\u001b[0;31mSubclasses:\u001b[0m     MultiTaskElasticNet"
     ]
    }
   ],
   "source": [
    "Lasso??"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b080dfb2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Basic Import\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt \n",
    "import seaborn as sns\n",
    "# Modelling\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "from sklearn.tree import DecisionTreeRegressor\n",
    "from sklearn.ensemble import RandomForestRegressor,AdaBoostRegressor\n",
    "from sklearn.svm import SVR\n",
    "from sklearn.linear_model import LinearRegression, Ridge,Lasso\n",
    "from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error\n",
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "from catboost import CatBoostRegressor\n",
    "from xgboost import XGBRegressor\n",
    "import warnings"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e45079ad",
   "metadata": {},
   "source": [
    "#### Import the CSV Data as Pandas DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "e11c6255",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('../data/StudentsPerformance.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "20634923",
   "metadata": {},
   "source": [
    "#### Show Top 5 Records"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "e7e412a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.head()\n",
    "df.rename(columns={'parental level of education':'parental_level_of_education','test preparation course':'test_preparation_course','math score':'math_score','reading score':'reading_score','writing score':'writing_score','race/ethnicity':'race_ethnicity'},inplace=True) "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fbd32281",
   "metadata": {},
   "source": [
    "#### Preparing X and Y variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "56d72fde",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df.drop(columns=['math_score'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "cd613177",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gender</th>\n",
       "      <th>race_ethnicity</th>\n",
       "      <th>parental_level_of_education</th>\n",
       "      <th>lunch</th>\n",
       "      <th>test_preparation_course</th>\n",
       "      <th>reading_score</th>\n",
       "      <th>writing_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>female</td>\n",
       "      <td>group B</td>\n",
       "      <td>bachelor's degree</td>\n",
       "      <td>standard</td>\n",
       "      <td>none</td>\n",
       "      <td>72</td>\n",
       "      <td>74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>female</td>\n",
       "      <td>group C</td>\n",
       "      <td>some college</td>\n",
       "      <td>standard</td>\n",
       "      <td>completed</td>\n",
       "      <td>90</td>\n",
       "      <td>88</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>female</td>\n",
       "      <td>group B</td>\n",
       "      <td>master's degree</td>\n",
       "      <td>standard</td>\n",
       "      <td>none</td>\n",
       "      <td>95</td>\n",
       "      <td>93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>male</td>\n",
       "      <td>group A</td>\n",
       "      <td>associate's degree</td>\n",
       "      <td>free/reduced</td>\n",
       "      <td>none</td>\n",
       "      <td>57</td>\n",
       "      <td>44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>male</td>\n",
       "      <td>group C</td>\n",
       "      <td>some college</td>\n",
       "      <td>standard</td>\n",
       "      <td>none</td>\n",
       "      <td>78</td>\n",
       "      <td>75</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender race_ethnicity parental_level_of_education         lunch  \\\n",
       "0  female        group B           bachelor's degree      standard   \n",
       "1  female        group C                some college      standard   \n",
       "2  female        group B             master's degree      standard   \n",
       "3    male        group A          associate's degree  free/reduced   \n",
       "4    male        group C                some college      standard   \n",
       "\n",
       "  test_preparation_course  reading_score  writing_score  \n",
       "0                    none             72             74  \n",
       "1               completed             90             88  \n",
       "2                    none             95             93  \n",
       "3                    none             57             44  \n",
       "4                    none             78             75  "
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "f237ea14",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Categories in 'gender' variable:  ['female' 'male']\n",
      "Categories in 'race_ethnicity' variable:  ['group B' 'group C' 'group A' 'group D' 'group E']\n",
      "Categories in'parental level of education' variable:  [\"bachelor's degree\" 'some college' \"master's degree\" \"associate's degree\"\n",
      " 'high school' 'some high school']\n",
      "Categories in 'lunch' variable:  ['standard' 'free/reduced']\n",
      "Categories in 'test preparation course' variable:  ['none' 'completed']\n"
     ]
    }
   ],
   "source": [
    "print(\"Categories in 'gender' variable: \",end=\" \" )\n",
    "print(df['gender'].unique())\n",
    "\n",
    "print(\"Categories in 'race_ethnicity' variable: \",end=\" \")\n",
    "print(df['race_ethnicity'].unique())\n",
    "\n",
    "print(\"Categories in'parental level of education' variable: \",end=\" \" )\n",
    "print(df['parental_level_of_education'].unique())\n",
    "\n",
    "print(\"Categories in 'lunch' variable: \",end=\" \" )\n",
    "print(df['lunch'].unique())\n",
    "\n",
    "print(\"Categories in 'test preparation course' variable: \",end=\" \" )\n",
    "print(df['test_preparation_course'].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "924b7f9d",
   "metadata": {},
   "outputs": [],
   "source": [
    "y = df['math_score']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "ffc69816",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      72\n",
       "1      69\n",
       "2      90\n",
       "3      47\n",
       "4      76\n",
       "       ..\n",
       "995    88\n",
       "996    62\n",
       "997    59\n",
       "998    68\n",
       "999    77\n",
       "Name: math_score, Length: 1000, dtype: int64"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "1e290fe3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create Column Transformer with 3 types of transformers\n",
    "num_features = X.select_dtypes(exclude=\"object\").columns\n",
    "cat_features = X.select_dtypes(include=\"object\").columns\n",
    "\n",
    "from sklearn.preprocessing import OneHotEncoder, StandardScaler\n",
    "from sklearn.compose import ColumnTransformer\n",
    "\n",
    "numeric_transformer = StandardScaler()\n",
    "oh_transformer = OneHotEncoder()\n",
    "\n",
    "preprocessor = ColumnTransformer(\n",
    "    [\n",
    "        (\"OneHotEncoder\", oh_transformer, cat_features),\n",
    "         (\"StandardScaler\", numeric_transformer, num_features),        \n",
    "    ]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "9c68f99a",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = preprocessor.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "72459f1d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1000, 19)"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "ed5c4e99",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((800, 19), (200, 19))"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# separate dataset into train and test\n",
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2,random_state=42)\n",
    "X_train.shape, X_test.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4cd80317",
   "metadata": {},
   "source": [
    "#### Create an Evaluate Function to give all metrics after model Training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "8c247bd0",
   "metadata": {},
   "outputs": [],
   "source": [
    "def evaluate_model(true, predicted):\n",
    "    mae = mean_absolute_error(true, predicted)\n",
    "    mse = mean_squared_error(true, predicted)\n",
    "    rmse = np.sqrt(mean_squared_error(true, predicted))\n",
    "    r2_square = r2_score(true, predicted)\n",
    "    return mae, rmse, r2_square"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "79ccb8e7",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Linear Regression\n",
      "Model performance for Training set\n",
      "- Root Mean Squared Error: 5.3271\n",
      "- Mean Absolute Error: 4.2694\n",
      "- R2 Score: 0.8741\n",
      "----------------------------------\n",
      "Model performance for Test set\n",
      "- Root Mean Squared Error: 5.4186\n",
      "- Mean Absolute Error: 4.2195\n",
      "- R2 Score: 0.8793\n",
      "===================================\n",
      "\n",
      "\n",
      "Lasso\n",
      "Model performance for Training set\n",
      "- Root Mean Squared Error: 6.5938\n",
      "- Mean Absolute Error: 5.2063\n",
      "- R2 Score: 0.8071\n",
      "----------------------------------\n",
      "Model performance for Test set\n",
      "- Root Mean Squared Error: 6.5197\n",
      "- Mean Absolute Error: 5.1579\n",
      "- R2 Score: 0.8253\n",
      "===================================\n",
      "\n",
      "\n",
      "Ridge\n",
      "Model performance for Training set\n",
      "- Root Mean Squared Error: 5.3233\n",
      "- Mean Absolute Error: 4.2650\n",
      "- R2 Score: 0.8743\n",
      "----------------------------------\n",
      "Model performance for Test set\n",
      "- Root Mean Squared Error: 5.3904\n",
      "- Mean Absolute Error: 4.2111\n",
      "- R2 Score: 0.8806\n",
      "===================================\n",
      "\n",
      "\n",
      "K-Neighbors Regressor\n",
      "Model performance for Training set\n",
      "- Root Mean Squared Error: 5.7077\n",
      "- Mean Absolute Error: 4.5167\n",
      "- R2 Score: 0.8555\n",
      "----------------------------------\n",
      "Model performance for Test set\n",
      "- Root Mean Squared Error: 7.2530\n",
      "- Mean Absolute Error: 5.6210\n",
      "- R2 Score: 0.7838\n",
      "===================================\n",
      "\n",
      "\n",
      "Decision Tree\n",
      "Model performance for Training set\n",
      "- Root Mean Squared Error: 0.2795\n",
      "- Mean Absolute Error: 0.0187\n",
      "- R2 Score: 0.9997\n",
      "----------------------------------\n",
      "Model performance for Test set\n",
      "- Root Mean Squared Error: 8.3078\n",
      "- Mean Absolute Error: 6.6500\n",
      "- R2 Score: 0.7164\n",
      "===================================\n",
      "\n",
      "\n",
      "Random Forest Regressor\n",
      "Model performance for Training set\n",
      "- Root Mean Squared Error: 2.2811\n",
      "- Mean Absolute Error: 1.8263\n",
      "- R2 Score: 0.9769\n",
      "----------------------------------\n",
      "Model performance for Test set\n",
      "- Root Mean Squared Error: 6.0626\n",
      "- Mean Absolute Error: 4.6497\n",
      "- R2 Score: 0.8490\n",
      "===================================\n",
      "\n",
      "\n",
      "XGBRegressor\n",
      "Model performance for Training set\n",
      "- Root Mean Squared Error: 0.9087\n",
      "- Mean Absolute Error: 0.6148\n",
      "- R2 Score: 0.9963\n",
      "----------------------------------\n",
      "Model performance for Test set\n",
      "- Root Mean Squared Error: 6.5889\n",
      "- Mean Absolute Error: 5.0844\n",
      "- R2 Score: 0.8216\n",
      "===================================\n",
      "\n",
      "\n",
      "CatBoosting Regressor\n",
      "Model performance for Training set\n",
      "- Root Mean Squared Error: 3.0427\n",
      "- Mean Absolute Error: 2.4054\n",
      "- R2 Score: 0.9589\n",
      "----------------------------------\n",
      "Model performance for Test set\n",
      "- Root Mean Squared Error: 6.0086\n",
      "- Mean Absolute Error: 4.6125\n",
      "- R2 Score: 0.8516\n",
      "===================================\n",
      "\n",
      "\n",
      "AdaBoost Regressor\n",
      "Model performance for Training set\n",
      "- Root Mean Squared Error: 5.8558\n",
      "- Mean Absolute Error: 4.7971\n",
      "- R2 Score: 0.8479\n",
      "----------------------------------\n",
      "Model performance for Test set\n",
      "- Root Mean Squared Error: 6.0720\n",
      "- Mean Absolute Error: 4.6998\n",
      "- R2 Score: 0.8485\n",
      "===================================\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "models = {\n",
    "    \"Linear Regression\": LinearRegression(),\n",
    "    \"Lasso\": Lasso(),\n",
    "    \"Ridge\": Ridge(),\n",
    "    \"K-Neighbors Regressor\": KNeighborsRegressor(),\n",
    "    \"Decision Tree\": DecisionTreeRegressor(),\n",
    "    \"Random Forest Regressor\": RandomForestRegressor(),\n",
    "    \"XGBRegressor\": XGBRegressor(), \n",
    "    \"CatBoosting Regressor\": CatBoostRegressor(verbose=False),\n",
    "    \"AdaBoost Regressor\": AdaBoostRegressor()\n",
    "}\n",
    "model_list = []\n",
    "r2_list =[]\n",
    "\n",
    "for i in range(len(list(models))):\n",
    "    model = list(models.values())[i]\n",
    "    model.fit(X_train, y_train) # Train model\n",
    "\n",
    "    # Make predictions\n",
    "    y_train_pred = model.predict(X_train)\n",
    "    y_test_pred = model.predict(X_test)\n",
    "    \n",
    "    # Evaluate Train and Test dataset\n",
    "    model_train_mae , model_train_rmse, model_train_r2 = evaluate_model(y_train, y_train_pred)\n",
    "\n",
    "    model_test_mae , model_test_rmse, model_test_r2 = evaluate_model(y_test, y_test_pred)\n",
    "\n",
    "    \n",
    "    print(list(models.keys())[i])\n",
    "    model_list.append(list(models.keys())[i])\n",
    "    \n",
    "    print('Model performance for Training set')\n",
    "    print(\"- Root Mean Squared Error: {:.4f}\".format(model_train_rmse))\n",
    "    print(\"- Mean Absolute Error: {:.4f}\".format(model_train_mae))\n",
    "    print(\"- R2 Score: {:.4f}\".format(model_train_r2))\n",
    "\n",
    "    print('----------------------------------')\n",
    "    \n",
    "    print('Model performance for Test set')\n",
    "    print(\"- Root Mean Squared Error: {:.4f}\".format(model_test_rmse))\n",
    "    print(\"- Mean Absolute Error: {:.4f}\".format(model_test_mae))\n",
    "    print(\"- R2 Score: {:.4f}\".format(model_test_r2))\n",
    "    r2_list.append(model_test_r2)\n",
    "    \n",
    "    print('='*35)\n",
    "    print('\\n')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "06480b5a",
   "metadata": {},
   "source": [
    "### Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "e0159e5f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Model Name</th>\n",
       "      <th>R2_Score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ridge</td>\n",
       "      <td>0.880593</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Linear Regression</td>\n",
       "      <td>0.879342</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>CatBoosting Regressor</td>\n",
       "      <td>0.851632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Random Forest Regressor</td>\n",
       "      <td>0.848954</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>AdaBoost Regressor</td>\n",
       "      <td>0.848485</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Lasso</td>\n",
       "      <td>0.825320</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>XGBRegressor</td>\n",
       "      <td>0.821589</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K-Neighbors Regressor</td>\n",
       "      <td>0.783813</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Decision Tree</td>\n",
       "      <td>0.716362</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Model Name  R2_Score\n",
       "2                    Ridge  0.880593\n",
       "0        Linear Regression  0.879342\n",
       "7    CatBoosting Regressor  0.851632\n",
       "5  Random Forest Regressor  0.848954\n",
       "8       AdaBoost Regressor  0.848485\n",
       "1                    Lasso  0.825320\n",
       "6             XGBRegressor  0.821589\n",
       "3    K-Neighbors Regressor  0.783813\n",
       "4            Decision Tree  0.716362"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(list(zip(model_list, r2_list)), columns=['Model Name', 'R2_Score']).sort_values(by=[\"R2_Score\"],ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "357a7c1c",
   "metadata": {},
   "source": [
    "## Linear Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "9a6ad559",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " Accuracy of the model is 87.93\n"
     ]
    }
   ],
   "source": [
    "lin_model = LinearRegression(fit_intercept=True)\n",
    "lin_model = lin_model.fit(X_train, y_train)\n",
    "y_pred = lin_model.predict(X_test)\n",
    "score = r2_score(y_test, y_pred)*100\n",
    "print(\" Accuracy of the model is %.2f\" %score)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d31453e",
   "metadata": {},
   "source": [
    "## Plot y_pred and y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "eb557b0a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(y_test,y_pred);\n",
    "plt.xlabel('Actual');\n",
    "plt.ylabel('Predicted');"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "1e707ec3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.regplot(x=y_test,y=y_pred,ci=None,color ='red');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "79c2fe28",
   "metadata": {},
   "source": [
    "#### Difference between Actual and Predicted Values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "7c9a8b48",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Actual Value</th>\n",
       "      <th>Predicted Value</th>\n",
       "      <th>Difference</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>521</th>\n",
       "      <td>91</td>\n",
       "      <td>76.21875</td>\n",
       "      <td>14.78125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>737</th>\n",
       "      <td>53</td>\n",
       "      <td>59.21875</td>\n",
       "      <td>-6.21875</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>740</th>\n",
       "      <td>80</td>\n",
       "      <td>76.90625</td>\n",
       "      <td>3.09375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>660</th>\n",
       "      <td>74</td>\n",
       "      <td>76.71875</td>\n",
       "      <td>-2.71875</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>411</th>\n",
       "      <td>84</td>\n",
       "      <td>87.90625</td>\n",
       "      <td>-3.90625</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>408</th>\n",
       "      <td>52</td>\n",
       "      <td>43.81250</td>\n",
       "      <td>8.18750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>332</th>\n",
       "      <td>62</td>\n",
       "      <td>62.40625</td>\n",
       "      <td>-0.40625</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>208</th>\n",
       "      <td>74</td>\n",
       "      <td>67.75000</td>\n",
       "      <td>6.25000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>613</th>\n",
       "      <td>65</td>\n",
       "      <td>66.81250</td>\n",
       "      <td>-1.81250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78</th>\n",
       "      <td>61</td>\n",
       "      <td>62.68750</td>\n",
       "      <td>-1.68750</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>200 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Actual Value  Predicted Value  Difference\n",
       "521            91         76.21875    14.78125\n",
       "737            53         59.21875    -6.21875\n",
       "740            80         76.90625     3.09375\n",
       "660            74         76.71875    -2.71875\n",
       "411            84         87.90625    -3.90625\n",
       "..            ...              ...         ...\n",
       "408            52         43.81250     8.18750\n",
       "332            62         62.40625    -0.40625\n",
       "208            74         67.75000     6.25000\n",
       "613            65         66.81250    -1.81250\n",
       "78             61         62.68750    -1.68750\n",
       "\n",
       "[200 rows x 3 columns]"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred_df=pd.DataFrame({'Actual Value':y_test,'Predicted Value':y_pred,'Difference':y_test-y_pred})\n",
    "pred_df"
   ]
  }
 ],
 "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": "3.8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}