07_regression.ipynb

    "\n",
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.preprocessing import StandardScaler, PolynomialFeatures\n",
    "from sklearn.kernel_ridge import KernelRidge\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.svm import SVR\n",
    "from sklearn.tree import DecisionTreeRegressor \n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "\n",
    "sockey_indices = features[\"kind\"] == 1\n",
    "features_sockeye = features[sockey_indices]\n",
    "values_sockeye = values[sockey_indices]\n",
    "\n",
    "atlantic_indices = features[\"kind\"] == 0\n",
    "features_atlantic = features[atlantic_indices]\n",
    "values_atlantic = values[atlantic_indices]\n",
    "\n",
    "\n",
    "def eval_clf(clf):\n",
    "    print(clf)\n",
    "    p = make_pipeline(PolynomialFeatures(), PCA(), DecisionTreeRegressor())\n",
    "\n",
    "    param_grid = {'polynomialfeatures__degree': range(3, 12),\n",
    "                  'pca__n_components': range(1, 10),\n",
    "                 }\n",
    "\n",
    "    search = GridSearchCV(p, param_grid, scoring=\"neg_median_absolute_error\", cv=4, n_jobs=4)\n",
    "\n",
    "    search.fit(features, values)\n",
    "    print(\"! FULL DATASET:  best_score    = {:.2f}\".format(search.best_score_))\n",
    "    score_full = search.best_score_\n",
    "\n",
    "    search.fit(features_atlantic, values_atlantic)\n",
    "    print(\"  ATLANTIC    :  best_score    = {:.2f}\".format(search.best_score_))\n",
    "    score_atlantic = search.best_score_\n",
    "\n",
    "    search.fit(features_sockeye, values_sockeye)\n",
    "    print(\"  SOCKEYE     :  best_score    = {:.2f}\".format(search.best_score_))\n",
    "    score_sockeye = search.best_score_\n",
    "\n",
    "    print(\"! COMBINED    :  average_score = {:.2f}\".format((score_atlantic + score_sockeye) / 2.0))\n",
    "    \n",
    "    \n",
    "eval_clf(LinearRegression())\n",
    "print()\n",
    "\n",
    "eval_clf(DecisionTreeRegressor())\n",
    "print()\n",
    "\n",
    "eval_clf(KernelRidge())\n",
    "print()\n",
    "\n",
    "eval_clf(KernelRidge(kernel=\"rbf\"))\n",
    "print()\n",
    "\n",
    "eval_clf(SVR())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.2"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}