testes.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.linear_model import LinearRegression, Lasso, Ridge, RidgeCV, ElasticNet, SGDRegressor,TweedieRegressor\n",
    "from sklearn.model_selection import train_test_split, RandomizedSearchCV, KFold, cross_val_score, validation_curve\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.metrics import explained_variance_score, r2_score,max_error, mean_absolute_error\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "from sklearn.neural_network import MLPRegressor\n",
    "from sklearn.svm import SVR\n",
    "from sklearn.tree import DecisionTreeRegressor\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.preprocessing import StandardScaler, MinMaxScaler\n",
    "import time\n",
    "from scipy.stats import randint\n",
    "from sklearn.preprocessing import PolynomialFeatures\n",
    "\n",
    "from sklearn.feature_selection import RFECV\n",
    "from sklearn.model_selection import StratifiedKFold\n",
    "\n",
    "from numpy import mean\n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.model_selection import RepeatedKFold\n",
    "from sklearn.feature_selection import RFE\n",
    "from sklearn.tree import DecisionTreeRegressor\n",
    "from sklearn.pipeline import Pipeline\n",
    "\n",
    "import xgboost as xgb\n",
    "from sklearn.metrics import mean_squared_error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"0.02_ENEM.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['Unnamed: 0', 'CO_MUNICIPIO_RESIDENCIA', 'CO_UF_RESIDENCIA', 'NU_IDADE',\n",
      "       'TP_SEXO', 'TP_ST_CONCLUSAO', 'TP_ANO_CONCLUIU', 'TP_ENSINO',\n",
      "       'IN_TREINEIRO', 'CO_ESCOLA', 'CO_MUNICIPIO_ESC', 'NO_MUNICIPIO_ESC',\n",
      "       'CO_UF_ESC', 'SG_UF_ESC', 'TP_DEPENDENCIA_ADM_ESC',\n",
      "       'TP_LOCALIZACAO_ESC', 'NU_NOTA_CN', 'NU_NOTA_CH', 'NU_NOTA_LC',\n",
      "       'NU_NOTA_MT', 'TX_RESPOSTAS_CN', 'TX_RESPOSTAS_CH', 'TX_RESPOSTAS_LC',\n",
      "       'TX_RESPOSTAS_MT', 'TP_LINGUA', 'TX_GABARITO_CN', 'TX_GABARITO_CH',\n",
      "       'TX_GABARITO_LC', 'TX_GABARITO_MT', 'TP_STATUS_REDACAO',\n",
      "       'NU_NOTA_COMP1', 'NU_NOTA_COMP2', 'NU_NOTA_COMP3', 'NU_NOTA_COMP4',\n",
      "       'NU_NOTA_COMP5', 'NU_NOTA_REDACAO', 'Q001', 'Q002', 'Q003', 'Q004',\n",
      "       'Q005', 'Q006', 'Q007', 'Q008', 'Q009', 'Q010', 'Q011', 'Q012', 'Q013',\n",
      "       'Q014', 'Q015', 'Q016', 'Q017', 'Q018', 'Q019', 'Q020', 'Q021', 'Q022',\n",
      "       'Q023', 'Q024', 'Q025', 'NOTA_MEDIA', 'TP_ESCOLA-0', 'TP_ESCOLA-1',\n",
      "       'TP_ESCOLA-2', 'TP_ESTADO_CIVIL-0', 'TP_ESTADO_CIVIL-1',\n",
      "       'TP_ESTADO_CIVIL-2', 'TP_ESTADO_CIVIL-3', 'TP_ESTADO_CIVIL-4',\n",
      "       'TP_COR_RACA-0', 'TP_COR_RACA-1', 'TP_COR_RACA-2', 'TP_COR_RACA-3',\n",
      "       'TP_COR_RACA-4', 'TP_COR_RACA-5'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [],
   "source": [
    "def na(x,t):\n",
    "    if np.isnan(x):\n",
    "        return 0\n",
    "    elif t:\n",
    "        return x/10000\n",
    "    else:\n",
    "        return x\n",
    "\n",
    "df[\"CO_ESCOLA\"] = df[\"CO_ESCOLA\"].map(lambda x: na(x,True))\n",
    "df[\"TP_LOCALIZACAO_ESC\"] = df[\"TP_LOCALIZACAO_ESC\"].map(lambda x: na(x,False))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['CO_MUNICIPIO_RESIDENCIA', 'NU_IDADE', 'TP_ANO_CONCLUIU', 'TP_SEXO', 'IN_TREINEIRO', 'TP_LINGUA', 'Q001', 'Q002', 'Q003', 'Q004', 'Q005', 'Q006', 'Q007', 'Q008', 'Q009', 'Q010', 'Q011', 'Q012', 'Q013', 'Q014', 'Q015', 'Q016', 'Q017', 'Q018', 'Q019', 'Q020', 'Q021', 'Q022', 'Q023', 'Q024', 'Q025', 'TP_ESCOLA-0', 'TP_ESCOLA-1', 'TP_ESCOLA-2', 'TP_ESTADO_CIVIL-0', 'TP_ESTADO_CIVIL-1', 'TP_ESTADO_CIVIL-2', 'TP_ESTADO_CIVIL-3', 'TP_ESTADO_CIVIL-4', 'TP_COR_RACA-0', 'TP_COR_RACA-1', 'TP_COR_RACA-2', 'TP_COR_RACA-3', 'TP_COR_RACA-4', 'TP_COR_RACA-5']\n"
     ]
    }
   ],
   "source": [
    "t = []\n",
    "t = ['CO_MUNICIPIO_RESIDENCIA','NU_IDADE','TP_ANO_CONCLUIU','TP_SEXO',\"IN_TREINEIRO\",\"TP_LINGUA\"]\n",
    "t.extend(df.columns.tolist()[36:61])\n",
    "t.extend(df.columns.tolist()[62:])\n",
    "print(t)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "260003 111430\n"
     ]
    }
   ],
   "source": [
    "y = df[\"NOTA_MEDIA\"]\n",
    "X = df[t]\n",
    "xtrain, xtest, ytrain, ytest = train_test_split(X,y,test_size=0.3)\n",
    "\n",
    "print(len(ytrain),len(ytest))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.3599987030029297 [0.3086603328122458, 0.3086606635871526, 0.046927446004317766, 0.29665519292885983]\n"
     ]
    }
   ],
   "source": [
    "model = LinearRegression()\n",
    "\n",
    "time0 = time.time()\n",
    "md = model.fit(xtrain,ytrain)\n",
    "time1 = time.time() - time0\n",
    "ypredict = md.predict(xtest)\n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "\n",
    "print(time1,scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-11-2ede4e530e20>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      8\u001b[0m \u001b[0mpoly_reg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_poly\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mytrain\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      9\u001b[0m \u001b[0mlin_reg2\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mLinearRegression\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 10\u001b[1;33m \u001b[0mmd\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlin_reg2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_poly\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mytrain\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     11\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     12\u001b[0m \u001b[0mypredict\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_poly_test\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_base.py\u001b[0m in \u001b[0;36mfit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m    567\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    568\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcoef_\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_residues\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrank_\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msingular_\u001b[0m \u001b[1;33m=\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 569\u001b[1;33m                 \u001b[0mlinalg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlstsq\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    570\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcoef_\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcoef_\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mT\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    571\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\scipy\\linalg\\basic.py\u001b[0m in \u001b[0;36mlstsq\u001b[1;34m(a, b, cond, overwrite_a, overwrite_b, check_finite, lapack_driver)\u001b[0m\n\u001b[0;32m   1197\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mreal_data\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1198\u001b[0m                 \u001b[0mlwork\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0miwork\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_compute_lwork\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlapack_lwork\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mm\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnrhs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcond\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1199\u001b[1;33m                 x, s, rank, info = lapack_func(a1, b1, lwork,\n\u001b[0m\u001b[0;32m   1200\u001b[0m                                                iwork, cond, False, False)\n\u001b[0;32m   1201\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m  \u001b[1;31m# complex data\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "# Regressão Polinomial\n",
    "\n",
    "lin_reg=LinearRegression()\n",
    "lin_reg.fit(xtrain,ytrain)\n",
    "poly_reg=PolynomialFeatures(degree=2)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "lin_reg2=LinearRegression()\n",
    "md = lin_reg2.fit(X_poly,ytrain)\n",
    "\n",
    "ypredict = md.predict(X_poly_test)\n",
    "ypredict = list(ypredict)\n",
    "ytrain = list(ytrain)\n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[11:42:20] WARNING: C:/Jenkins/workspace/xgboost-win64_release_0.90/src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[0.3674071979103358, 0.3674099232628255, 0.044882315018184106, 0.2700301819324493]\n"
     ]
    }
   ],
   "source": [
    "# instanciar o modelo XGBoost\n",
    "model = xgb.XGBRegressor()\n",
    " \n",
    "# chamar o fit para o modelo\n",
    "model.fit(xtrain, ytrain, verbose=False)\n",
    " \n",
    "# fazer previsões em cima do dataset de teste\n",
    "ypredict = model.predict(xtest)\n",
    " \n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[22:21:36] WARNING: C:/Jenkins/workspace/xgboost-win64_release_0.90/src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[0.25368585519888953, 0.25572469810678733, 0.04943542119718055, 0.27228094272613523]\n"
     ]
    }
   ],
   "source": [
    "xg_reg = xgb.XGBRegressor(objective ='reg:linear', colsample_bytree = 0.3, learning_rate = 0.1,\n",
    "                max_depth = 5, alpha = 10, n_estimators = 10)\n",
    "\n",
    "xg_reg.fit(xtrain,ytrain)\n",
    "\n",
    "ypredict = xg_reg.predict(xtest)\n",
    "\n",
    "\n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[22:15:53] WARNING: C:/Jenkins/workspace/xgboost-win64_release_0.90/src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[0.27334469277420426, 0.27529948550863914, 0.04866134576175796, 0.2709536872863769]\n"
     ]
    }
   ],
   "source": [
    "# Regressão Polinomial\n",
    "\n",
    "poly_reg=PolynomialFeatures(degree=2)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "\n",
    "md = xg_reg.fit(X_poly,ytrain)\n",
    "\n",
    "ypredict = md.predict(X_poly_test)\n",
    "ypredict = list(ypredict)\n",
    "ytrain = list(ytrain)\n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Reduzindo as colunas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.20998037 0.21434209 0.21118126 0.20796232 0.20999009 0.2120656\n",
      " 0.20570783 0.20919031 0.21299194 0.21336269 0.20977293 0.21546043\n",
      " 0.21100689 0.20844896 0.20880371]\n",
      "0.21546043279071592 0.21068449461543412\n"
     ]
    }
   ],
   "source": [
    "# create pipeline\n",
    "rfe = RFE(LinearRegression(), n_features_to_select=5)\n",
    "model = LinearRegression()\n",
    "pipeline = Pipeline(steps=[('s',rfe),('m',model)])\n",
    "# evaluate model\n",
    "cv = RepeatedKFold(n_splits=5, n_repeats=3, random_state=5)\n",
    "n_scores = cross_val_score(pipeline, xtrain, ytrain, scoring='r2', cv=cv, n_jobs=-1)\n",
    "\n",
    "pipeline.fit(xtrain, ytrain)\n",
    "\n",
    "print(n_scores)\n",
    "\n",
    "print(max(n_scores),mean(n_scores))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 204,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Indice: 0, Column Name CO_MUNICIPIO_RESIDENCIA, Selected False Rank: 41\n",
      "Indice: 1, Column Name NU_IDADE, Selected False Rank: 25\n",
      "Indice: 2, Column Name TP_ANO_CONCLUIU, Selected False Rank: 24\n",
      "Indice: 3, Column Name TP_LINGUA, Selected False Rank: 16\n",
      "Indice: 4, Column Name Q001, Selected False Rank: 8\n",
      "Indice: 5, Column Name Q002, Selected False Rank: 5\n",
      "Indice: 6, Column Name Q003, Selected False Rank: 9\n",
      "Indice: 7, Column Name Q004, Selected False Rank: 2\n",
      "Indice: 8, Column Name Q005, Selected False Rank: 3\n",
      "Indice: 9, Column Name Q006, Selected False Rank: 10\n",
      "Indice: 10, Column Name Q007, Selected False Rank: 22\n",
      "Indice: 11, Column Name Q008, Selected True Rank: 1\n",
      "Indice: 12, Column Name Q010, Selected False Rank: 11\n",
      "Indice: 13, Column Name Q011, Selected False Rank: 19\n",
      "Indice: 14, Column Name Q012, Selected False Rank: 21\n",
      "Indice: 15, Column Name Q013, Selected True Rank: 1\n",
      "Indice: 16, Column Name Q014, Selected False Rank: 15\n",
      "Indice: 17, Column Name Q015, Selected False Rank: 7\n",
      "Indice: 18, Column Name Q016, Selected True Rank: 1\n",
      "Indice: 19, Column Name Q018, Selected True Rank: 1\n",
      "Indice: 20, Column Name Q021, Selected False Rank: 12\n",
      "Indice: 21, Column Name Q023, Selected True Rank: 1\n",
      "Indice: 22, Column Name Q024, Selected False Rank: 4\n",
      "Indice: 23, Column Name Q025, Selected False Rank: 13\n"
     ]
    }
   ],
   "source": [
    "cols = set()\n",
    "j = 0\n",
    "for i in range(xtrain.shape[1]):\n",
    "\tprint('Indice: '+ str(j)+\", Column Name \" + str(list(xtrain.columns)[i]) + ', Selected ' +str(rfe.support_[i]) + ' Rank: '+ str(rfe.ranking_[i]))\n",
    "\tif rfe.ranking_[i] == 1:\n",
    "\t\tcols.add(j)\n",
    "\tj += 1\n",
    "j=0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 205,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{11, 15, 18, 19, 21}\n"
     ]
    }
   ],
   "source": [
    "print(cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 207,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21, 23, 26, 28, 29, 30}\n"
     ]
    }
   ],
   "source": [
    "cols.add(11)\n",
    "cols.add(15)\n",
    "cols.add(18)\n",
    "cols.add(19)\n",
    "cols.add(21)\n",
    "cols.add(26)\n",
    "cols.add(9)\n",
    "cols.add(8)\n",
    "cols.add(7)\n",
    "cols.add(6)\n",
    "cols.add(5)\n",
    "cols.add(4)\n",
    "cols.add(3)\n",
    "cols.add(2)\n",
    "cols.add(1)\n",
    "cols.add(0)\n",
    "cols.add(16)\n",
    "cols.add(17)\n",
    "cols.add(18)\n",
    "cols.add(11)\n",
    "cols.add(10)\n",
    "cols.add(20)\n",
    "cols.add(12)\n",
    "cols.add(15)\n",
    "cols.add(23)\n",
    "cols.add(13)\n",
    "cols.add(29)\n",
    "cols.add(28)\n",
    "cols.add(29)\n",
    "cols.add(30)\n",
    "\n",
    "#cols.add(22)\n",
    "#cols.add(24)\n",
    "#cols.add(25)\n",
    "#cols.add(27)\n",
    "\n",
    "# cols.add(31)\n",
    "# cols.add(32)\n",
    "# cols.add(33)\n",
    "# cols.add(34)\n",
    "# cols.add(35)\n",
    "# cols.add(36)\n",
    "# cols.add(37)\n",
    "# cols.add(38)\n",
    "\n",
    "\n",
    "# cols.add(39)\n",
    "# cols.add(40)\n",
    "# cols.add(41)\n",
    "# cols.add(42)\n",
    "# cols.add(43)\n",
    "# cols.add(44)\n",
    "\n",
    "print(cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 186,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['CO_MUNICIPIO_RESIDENCIA', 'NU_IDADE', 'TP_ANO_CONCLUIU', 'TP_SEXO', 'IN_TREINEIRO', 'TP_LINGUA', 'Q001', 'Q002', 'Q003', 'Q004', 'Q005', 'Q006', 'Q007', 'Q008', 'Q009', 'Q010', 'Q011', 'Q012', 'Q013', 'Q014', 'Q015', 'Q016', 'Q017', 'Q018', 'Q019', 'Q020', 'Q021', 'Q022', 'Q023', 'Q024', 'Q025', 'TP_ESCOLA-0', 'TP_ESCOLA-1', 'TP_ESCOLA-2', 'TP_ESTADO_CIVIL-0', 'TP_ESTADO_CIVIL-1', 'TP_ESTADO_CIVIL-2', 'TP_ESTADO_CIVIL-3', 'TP_ESTADO_CIVIL-4', 'TP_COR_RACA-0', 'TP_COR_RACA-1', 'TP_COR_RACA-2', 'TP_COR_RACA-3', 'TP_COR_RACA-4', 'TP_COR_RACA-5']\n",
      "45\n"
     ]
    }
   ],
   "source": [
    "print(t)\n",
    "print(len(t))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 208,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['CO_MUNICIPIO_RESIDENCIA', 'NU_IDADE', 'TP_ANO_CONCLUIU', 'TP_SEXO', 'IN_TREINEIRO', 'TP_LINGUA', 'Q001', 'Q002', 'Q003', 'Q004', 'Q005', 'Q006', 'Q007', 'Q008', 'Q010', 'Q011', 'Q012', 'Q013', 'Q014', 'Q015', 'Q016', 'Q018', 'Q021', 'Q023', 'Q024', 'Q025']\n"
     ]
    }
   ],
   "source": [
    "newCols= []\n",
    "for i in cols:\n",
    "    newCols.append(t[i])\n",
    "\n",
    "print(newCols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 209,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "260003 111430\n"
     ]
    }
   ],
   "source": [
    "y = df[\"NOTA_MEDIA\"]\n",
    "X = df[newCols]\n",
    "xtrain, xtest, ytrain, ytest = train_test_split(X,y,test_size=0.3)\n",
    "\n",
    "print(len(ytrain),len(ytest))\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 210,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[13:48:45] WARNING: C:/Jenkins/workspace/xgboost-win64_release_0.90/src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[0.38231970449491304, 0.38232076557246764, 0.044275318448439786, 0.24130636100769043]\n"
     ]
    }
   ],
   "source": [
    "# instanciar o modelo XGBoost\n",
    "model = xgb.XGBRegressor()\n",
    "\n",
    "# chamar o fit para o modelo\n",
    "model.fit(xtrain, ytrain, verbose=False)\n",
    " \n",
    "# fazer previsões em cima do dataset de teste\n",
    "ypredict = model.predict(xtest)\n",
    " \n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.3079363361357984, 0.3079366701674977, 0.04663134228559033, 0.2901574055674606]\n"
     ]
    }
   ],
   "source": [
    "# Regressão Polinomial grau 2\n",
    "\n",
    "poly_reg=PolynomialFeatures(degree=2)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "lin_reg2=LinearRegression()\n",
    "md = lin_reg2.fit(X_poly,ytrain)\n",
    "\n",
    "ypredict = md.predict(X_poly_test)\n",
    "ypredict = list(ypredict)\n",
    "ytrain = list(ytrain)\n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.19797754287719727 [0.2641783017593501, 0.2641783017593501, 0.048665989838223164, 0.2647711768083689] [0.2685497432239674, 0.2685677127462003, 0.048483287205775744, 0.28124647834363997]\n"
     ]
    }
   ],
   "source": [
    "model = LinearRegression()\n",
    "\n",
    "time0 = time.time()\n",
    "md = model.fit(xtrain,ytrain)\n",
    "time1 = time.time() - time0\n",
    "ypredict = md.predict(xtest)\n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "\n",
    "print(time1,scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.3131374289509311, 0.31315367599773425, 0.046827485805797396, 0.26839182775913073]\n"
     ]
    }
   ],
   "source": [
    "# Regressão Polinomial grau 2\n",
    "\n",
    "poly_reg=PolynomialFeatures(degree=2)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "lin_reg2=LinearRegression()\n",
    "md = lin_reg2.fit(X_poly,ytrain)\n",
    "\n",
    "ypredict = md.predict(X_poly_test)\n",
    "ypredict = list(ypredict)\n",
    "ytrain = list(ytrain)\n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.19070298696686305, 0.19074121456416882, 0.050172790242291126, 0.9565010598773269]\n"
     ]
    }
   ],
   "source": [
    "# Regressão Polinomial grau 3\n",
    "\n",
    "poly_reg=PolynomialFeatures(degree=3)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "lin_reg2=LinearRegression()\n",
    "md = lin_reg2.fit(X_poly,ytrain)\n",
    "\n",
    "ypredict = md.predict(X_poly_test)\n",
    "ypredict = list(ypredict)\n",
    "ytrain = list(ytrain)\n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 221,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[('LR', LinearRegression()), ('LASSO', Lasso(random_state=0)), ('EN', ElasticNet(random_state=0)), ('KNN', KNeighborsRegressor()), ('CART', DecisionTreeRegressor(random_state=0)), ('RIDGE', Ridge(random_state=0)), ('RIDGECV', RidgeCV(alphas=array([ 0.1,  1. , 10. ]))), ('MLPR', MLPRegressor(random_state=0)), ('SGDR', SGDRegressor())]\n"
     ]
    }
   ],
   "source": [
    "seed = 0\n",
    "models = []\n",
    "models.append(('LR', LinearRegression()))\n",
    "models.append(('LASSO', Lasso(random_state=seed)))\n",
    "models.append(('EN', ElasticNet(random_state=seed)))\n",
    "models.append(('KNN', KNeighborsRegressor()))\n",
    "models.append(('CART', DecisionTreeRegressor(random_state=seed)))\n",
    "#models.append(('SVR', SVR()))\n",
    "models.append(('RIDGE', Ridge(random_state=seed)))\n",
    "models.append(('RIDGECV', RidgeCV()))\n",
    "models.append(('MLPR', MLPRegressor(random_state=seed)))\n",
    "models.append(('SGDR', SGDRegressor()))\n",
    "\n",
    "print(models)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR 0.15100717544555664 [0.295703589325792, 0.2957152041179827, 0.0474213769007687, 0.27406772215602404]\n",
      "LASSO 0.09499573707580566 [0.029189380583447555, 0.029204763771012776, 0.05659859617229096, 0.2916616866226316]\n",
      "EN 0.08999776840209961 [0.029189397550226204, 0.02920478090929679, 0.05659858149960874, 0.291662084572141]\n",
      "KNN 0.0469965934753418 [0.17506150240841334, 0.17732745884411671, 0.05079588813604954, 0.31850999999999996]\n",
      "CART 2.0299549102783203 [-0.29195045867180003, -0.29186232475511975, 0.06315424495572707, 0.35075]\n",
      "RIDGE 0.07200002670288086 [0.29570379763843646, 0.2957154137310791, 0.04742142822624041, 0.2740675362782249]\n",
      "RIDGECV 0.5789995193481445 [-6.098127566738732, -6.098109582886521, 0.14743384656025435, 0.6126370694709458]\n",
      "MLPR 18.72899341583252 [-312237665.1991043, -29382695.660606995, 1183.4567449003605, 2040.983774201452]\n",
      "SGDR 50.484511613845825 [-4.065984988697133e+43, -3.8246213103068573e+42, 4.270730504866672e+20, 7.3548115474372e+20]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1220: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n",
      "  warnings.warn(\"Maximum number of iteration reached before \"\n"
     ]
    }
   ],
   "source": [
    "results = []\n",
    "names = []\n",
    "times = []\n",
    "for name, model in models:\n",
    "    t0 = time.time()\n",
    "    md = model.fit(xtrain,ytrain)\n",
    "    time1 = time.time() - t0\n",
    "    ypredict = md.predict(xtest)\n",
    "    scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "    results.append(scores)\n",
    "    names.append(name)\n",
    "    times.append(time1)\n",
    "    print(name, time1, scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR 3.059631586074829 [0.332946047108747, 0.3329569793998085, 0.04598694415402519, 0.2728299963257874]\n",
      "LASSO 18.788005352020264 [0.276328830479616, 0.2763404047207527, 0.04817281681392974, 0.27078707688813564]\n",
      "EN 20.189877033233643 [0.2763294741577409, 0.27634104828652706, 0.04817272918431702, 0.27078684850075685]\n",
      "KNN 0.12100481986999512 [0.17473420567949982, 0.1769922378478711, 0.05080238822579198, 0.31850999999999996]\n",
      "CART 33.11529469490051 [-0.2903387746389887, -0.2902457357197983, 0.06307026533847858, 0.3419750000000001]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_ridge.py:147: LinAlgWarning: Ill-conditioned matrix (rcond=9.07436e-32): result may not be accurate.\n",
      "  return linalg.solve(A, Xy, sym_pos=True,\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RIDGE 0.5489513874053955 [0.33450081830002054, 0.3345109962298143, 0.045957982105119435, 0.27233342082632805]\n",
      "RIDGECV 5.308098077774048 [-2.095102187918748e+33, -2.0950969827397602e+33, 2412449123490472.0, 8686231302405250.0]\n",
      "MLPR 25.130954027175903 [-3.4626983348453134e+19, -9.764400971814844e+18, 350867869.6963261, 954222400.5767214]\n",
      "SGDR 98.10699725151062 [-7.58940495094717e+69, -2.1323678714509584e+69, 5.198151524202602e+33, 1.3966427323098537e+34]\n"
     ]
    }
   ],
   "source": [
    "# Regressão Polinomial grau 2\n",
    "\n",
    "poly_reg=PolynomialFeatures(degree=2)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "\n",
    "for name, model in models:\n",
    "    t0 = time.time()\n",
    "    md = model.fit(X_poly,ytrain)\n",
    "    time1 = time.time() - t0\n",
    "    ypredict = md.predict(X_poly_test)\n",
    "    scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "    results.append(scores)\n",
    "    names.append(name)\n",
    "    times.append(time1)\n",
    "    print(name, time1, scores)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['CO_MUNICIPIO_RESIDENCIA', 'NU_IDADE', 'TP_SEXO', 'IN_TREINEIRO', 'Q001', 'Q002', 'Q005', 'Q006', 'Q007', 'Q022', 'Q024', 'Q025', 'TP_COR_RACA-0', 'TP_COR_RACA-1', 'TP_COR_RACA-2', 'TP_COR_RACA-3', 'TP_COR_RACA-4', 'TP_COR_RACA-5']\n"
     ]
    }
   ],
   "source": [
    "cols = [0,1,3,4,5,6,9,10,11,26,28,29]\n",
    "cols.append(38)\n",
    "cols.append(39)\n",
    "cols.append(40)\n",
    "cols.append(41)\n",
    "cols.append(42)\n",
    "cols.append(43)\n",
    "newCols= []\n",
    "for i in cols:\n",
    "    #print(t[i])\n",
    "    newCols.append(t[i])\n",
    "\n",
    "print(newCols)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "260003 111430\n"
     ]
    }
   ],
   "source": [
    "y = df[\"NOTA_MEDIA\"]\n",
    "X = df[newCols]\n",
    "xtrain, xtest, ytrain, ytest = train_test_split(X,y,test_size=0.3)\n",
    "\n",
    "print(len(ytrain),len(ytest))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR 0.13996529579162598 [0.20662725613335498, 0.20663072105224867, 0.05069943483052532, 0.2735115007305967]\n",
      "LASSO 0.08000040054321289 [0.02951597326090094, 0.029519054105393017, 0.05658457712546899, 0.2932950528470881]\n",
      "EN 0.08699917793273926 [0.02951602792101815, 0.029519108707071195, 0.05658456215216275, 0.2932948142275499]\n",
      "KNN 0.02200007438659668 [0.09116893227260592, 0.09355317313855505, 0.05342614394687248, 0.32174]\n",
      "CART 2.1228244304656982 [-0.3550170949775391, -0.3548824510426478, 0.0647047604886476, 0.37072499999999997]\n",
      "RIDGE 0.051949262619018555 [0.20662745294225116, 0.20663091711307935, 0.050699481188983486, 0.27351191562161936]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_ridge.py:147: LinAlgWarning: Ill-conditioned matrix (rcond=3.92709e-18): result may not be accurate.\n",
      "  return linalg.solve(A, Xy, sym_pos=True,\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RIDGECV 0.4019954204559326 [-18.14469101659705, -18.144625451793846, 0.24314490836547317, 0.9168921993088606]\n",
      "MLPR 15.322998523712158 [-233490.56480518024, -22900.787104835545, 32.3028394580655, 56.92032753435229]\n",
      "SGDR 53.364999532699585 [-8.96800883682344e+42, -8.358861705892703e+41, 2.007354225006394e+20, 3.4563976602972245e+20]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1220: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n",
      "  warnings.warn(\"Maximum number of iteration reached before \"\n"
     ]
    }
   ],
   "source": [
    "results = []\n",
    "names = []\n",
    "times = []\n",
    "for name, model in models:\n",
    "    t0 = time.time()\n",
    "    md = model.fit(xtrain,ytrain)\n",
    "    time1 = time.time() - t0\n",
    "    ypredict = md.predict(xtest)\n",
    "    scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "    results.append(scores)\n",
    "    names.append(name)\n",
    "    times.append(time1)\n",
    "    print(name, time1, scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR 31.950528383255005 [0.2471489761846961, 0.24715104233972796, 0.04917497379065185, 0.27877226623763374]\n"
     ]
    }
   ],
   "source": [
    "poly_reg=PolynomialFeatures(degree=3)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "\n",
    "for name, model in models:\n",
    "    t0 = time.time()\n",
    "    md = model.fit(X_poly,ytrain)\n",
    "    time1 = time.time() - t0\n",
    "    ypredict = md.predict(X_poly_test)\n",
    "    scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "    results.append(scores)\n",
    "    names.append(name)\n",
    "    times.append(time1)\n",
    "    print(name, time1, scores)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"ENEM_data_for_modeling_3.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>Unnamed: 0</th>\n",
       "      <th>CO_MUNICIPIO_RESIDENCIA</th>\n",
       "      <th>CO_UF_RESIDENCIA</th>\n",
       "      <th>NU_IDADE</th>\n",
       "      <th>TP_SEXO</th>\n",
       "      <th>TP_ST_CONCLUSAO</th>\n",
       "      <th>TP_ANO_CONCLUIU</th>\n",
       "      <th>TP_ENSINO</th>\n",
       "      <th>IN_TREINEIRO</th>\n",
       "      <th>CO_ESCOLA</th>\n",
       "      <th>...</th>\n",
       "      <th>TP_ESTADO_CIVIL-1</th>\n",
       "      <th>TP_ESTADO_CIVIL-2</th>\n",
       "      <th>TP_ESTADO_CIVIL-3</th>\n",
       "      <th>TP_ESTADO_CIVIL-4</th>\n",
       "      <th>TP_COR_RACA-0</th>\n",
       "      <th>TP_COR_RACA-1</th>\n",
       "      <th>TP_COR_RACA-2</th>\n",
       "      <th>TP_COR_RACA-3</th>\n",
       "      <th>TP_COR_RACA-4</th>\n",
       "      <th>TP_COR_RACA-5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>4304606</td>\n",
       "      <td>43</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>43038662.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>3304557</td>\n",
       "      <td>33</td>\n",
       "      <td>20.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>4217402</td>\n",
       "      <td>42</td>\n",
       "      <td>16.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>3302858</td>\n",
       "      <td>33</td>\n",
       "      <td>25.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3201209</td>\n",
       "      <td>32</td>\n",
       "      <td>18.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 76 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  CO_MUNICIPIO_RESIDENCIA  CO_UF_RESIDENCIA  NU_IDADE  TP_SEXO  \\\n",
       "0           0                  4304606                43      19.0        0   \n",
       "1           0                  3304557                33      20.0        0   \n",
       "2           0                  4217402                42      16.0        0   \n",
       "3           0                  3302858                33      25.0        1   \n",
       "4           0                  3201209                32      18.0        0   \n",
       "\n",
       "   TP_ST_CONCLUSAO  TP_ANO_CONCLUIU  TP_ENSINO  IN_TREINEIRO   CO_ESCOLA  ...  \\\n",
       "0                2                0        1.0             0  43038662.0  ...   \n",
       "1                1                2        NaN             0         NaN  ...   \n",
       "2                3                0        NaN             1         NaN  ...   \n",
       "3                1                7        NaN             0         NaN  ...   \n",
       "4                2                0        1.0             0         NaN  ...   \n",
       "\n",
       "   TP_ESTADO_CIVIL-1 TP_ESTADO_CIVIL-2  TP_ESTADO_CIVIL-3 TP_ESTADO_CIVIL-4  \\\n",
       "0                1.0               0.0                0.0               0.0   \n",
       "1                1.0               0.0                0.0               0.0   \n",
       "2                1.0               0.0                0.0               0.0   \n",
       "3                1.0               0.0                0.0               0.0   \n",
       "4                1.0               0.0                0.0               0.0   \n",
       "\n",
       "   TP_COR_RACA-0  TP_COR_RACA-1  TP_COR_RACA-2  TP_COR_RACA-3  TP_COR_RACA-4  \\\n",
       "0            0.0            1.0            0.0            0.0            0.0   \n",
       "1            0.0            1.0            0.0            0.0            0.0   \n",
       "2            0.0            1.0            0.0            0.0            0.0   \n",
       "3            0.0            1.0            0.0            0.0            0.0   \n",
       "4            0.0            1.0            0.0            0.0            0.0   \n",
       "\n",
       "   TP_COR_RACA-5  \n",
       "0            0.0  \n",
       "1            0.0  \n",
       "2            0.0  \n",
       "3            0.0  \n",
       "4            0.0  \n",
       "\n",
       "[5 rows x 76 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'df' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-2-19af09ac7144>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"CO_MUNICIPIO_RESIDENCIA\"\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m3106200\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      2\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mNameError\u001b[0m: name 'df' is not defined"
     ]
    }
   ],
   "source": [
    "df = df[df[\"CO_MUNICIPIO_RESIDENCIA\"] == 3106200]\n",
    "\n",
    "len(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['CO_MUNICIPIO_RESIDENCIA', 'NU_IDADE', 'TP_ANO_CONCLUIU', 'TP_SEXO', 'IN_TREINEIRO', 'Q001', 'Q002', 'Q003', 'Q004', 'Q005', 'Q006', 'Q007', 'Q008', 'Q009', 'Q010', 'Q011', 'Q012', 'Q013', 'Q014', 'Q015', 'Q016', 'Q017', 'Q018', 'Q019', 'Q020', 'Q021', 'Q022', 'Q023', 'Q024', 'Q025', 'TP_ESCOLA-0', 'TP_ESCOLA-1', 'TP_ESCOLA-2', 'TP_ESTADO_CIVIL-0', 'TP_ESTADO_CIVIL-1', 'TP_ESTADO_CIVIL-2', 'TP_ESTADO_CIVIL-3', 'TP_ESTADO_CIVIL-4', 'TP_COR_RACA-0', 'TP_COR_RACA-1', 'TP_COR_RACA-2', 'TP_COR_RACA-3', 'TP_COR_RACA-4', 'TP_COR_RACA-5']\n"
     ]
    }
   ],
   "source": [
    "t = []\n",
    "t = ['CO_MUNICIPIO_RESIDENCIA','NU_IDADE','TP_ANO_CONCLUIU','TP_SEXO',\"IN_TREINEIRO\"]\n",
    "t.extend(df.columns.tolist()[36:61])\n",
    "t.extend(df.columns.tolist()[62:])\n",
    "print(t)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2589090 1109611\n"
     ]
    }
   ],
   "source": [
    "y = df[\"NOTA_MEDIA\"]\n",
    "X = df[t]\n",
    "xtrain, xtest, ytrain, ytest = train_test_split(X,y,test_size=0.3)\n",
    "\n",
    "print(len(ytrain),len(ytest))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR 0.0740509033203125 [0.33717602275178815, 0.33717602384951395, 0.0511366487262418, 0.23434136556888518]\n",
      "LASSO 0.0482022762298584 [-1.8204635586771545e-05, 0.0, 0.06492042955878224, 0.25132182038896345]\n",
      "EN 0.033782243728637695 [-1.8204635586771545e-05, 0.0, 0.06492042955878224, 0.25132182038896345]\n",
      "KNN 0.010610580444335938 [0.19154420502886282, 0.19934383194661043, 0.05594753378179029, 0.27010999999999985]\n",
      "CART 0.8661315441131592 [-0.24226380292524197, -0.2421981361280785, 0.0686866620935859, 0.31770000000000004]\n",
      "RIDGE 0.045491695404052734 [0.33717831671874066, 0.3371783177171397, 0.051137189813217666, 0.23415400470769188]\n",
      "RIDGECV 0.17117929458618164 [0.33718048211531115, 0.33718048248558974, 0.051142628058926755, 0.23264214128220106]\n",
      "MLPR 3.9367759227752686 [-16255250.56048218, -102.14478384347298, 313.43900070101375, 314.74961702726273]\n",
      "SGDR 15.32766079902649 [-2.5196998983318954e+42, -1.8952841331572796e+28, 1.2340477760961197e+20, 1.2340484035793481e+20]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1220: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n",
      "  warnings.warn(\"Maximum number of iteration reached before \"\n"
     ]
    }
   ],
   "source": [
    "results = []\n",
    "names = []\n",
    "times = []\n",
    "for name, model in models:\n",
    "    t0 = time.time()\n",
    "    md = model.fit(xtrain,ytrain)\n",
    "    time1 = time.time() - t0\n",
    "    ypredict = md.predict(xtest)\n",
    "    scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "    results.append(scores)\n",
    "    names.append(name)\n",
    "    times.append(time1)\n",
    "    print(name, time1, scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR 3.0661089420318604 [0.3503899160866729, 0.3503909977635098, 0.049486446800868965, 0.7913261108398438]\n",
      "LASSO 11.270758867263794 [0.3371798618326557, 0.337179862644266, 0.05113671440936095, 0.23418329401531923]\n",
      "EN 26.375264167785645 [0.3371779610094916, 0.33717796195880123, 0.0511366807832415, 0.23426233022603593]\n",
      "KNN 0.06400251388549805 [0.19187101789258565, 0.1996644810338738, 0.05592630436065381, 0.27010999999999985]\n",
      "CART 18.692577362060547 [-0.26318276965323584, -0.26317781585597544, 0.06931331356582285, 0.35609999999999997]\n",
      "RIDGE 6.058074474334717 [0.37883018893615583, 0.3788308683752659, 0.04920954829146831, 0.22978967677764595]\n",
      "RIDGECV 6.693962097167969 [-218638.5694684157, -218634.76750073885, 25.554716362732368, 240.10163341572715]\n",
      "MLPR 21.50294828414917 [-60645930574895.516, -32491234127782.64, 421948.91904965055, 4168961.114342943]\n",
      "SGDR 186.97028923034668 [-2.0657797738814786e+70, -3.069692150487e+55, 1.1173766071480672e+34, 1.1173768865408788e+34]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_stochastic_gradient.py:1220: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n",
      "  warnings.warn(\"Maximum number of iteration reached before \"\n"
     ]
    }
   ],
   "source": [
    "# Regressão Polinomial grau 2\n",
    "\n",
    "poly_reg=PolynomialFeatures(degree=2)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "\n",
    "for name, model in models:\n",
    "    t0 = time.time()\n",
    "    md = model.fit(X_poly,ytrain)\n",
    "    time1 = time.time() - t0\n",
    "    ypredict = md.predict(X_poly_test)\n",
    "    scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "    results.append(scores)\n",
    "    names.append(name)\n",
    "    times.append(time1)\n",
    "    print(name, time1, scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 217,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['CO_MUNICIPIO_RESIDENCIA', 'NU_IDADE', 'TP_ANO_CONCLUIU', 'TP_SEXO', 'IN_TREINEIRO', 'TP_LINGUA', 'Q001', 'Q002', 'Q003', 'Q004', 'Q005', 'Q006', 'Q007', 'Q008', 'Q010', 'Q011', 'Q012', 'Q013', 'Q014', 'Q015', 'Q016', 'Q018', 'Q021', 'Q023', 'Q024', 'Q025']\n"
     ]
    }
   ],
   "source": [
    "cols = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21, 23, 26, 28, 29, 30}\n",
    "\n",
    "\n",
    "newCols= []\n",
    "for i in cols:\n",
    "    newCols.append(t[i])\n",
    "\n",
    "print(newCols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 218,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "260003 111430\n"
     ]
    }
   ],
   "source": [
    "y = df[\"NU_NOTA_REDACAO\"]\n",
    "X = df[newCols]\n",
    "xtrain, xtest, ytrain, ytest = train_test_split(X,y,test_size=0.3)\n",
    "\n",
    "print(len(ytrain),len(ytest))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 219,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[13:52:08] WARNING: C:/Jenkins/workspace/xgboost-win64_release_0.90/src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[0.20752652504177405, 0.20752686215751803, 0.11954248437330087, 0.8186873197555542]\n"
     ]
    }
   ],
   "source": [
    "# instanciar o modelo XGBoost\n",
    "model = xgb.XGBRegressor()\n",
    "\n",
    "# chamar o fit para o modelo\n",
    "model.fit(xtrain, ytrain, verbose=False)\n",
    " \n",
    "# fazer previsões em cima do dataset de teste\n",
    "ypredict = model.predict(xtest)\n",
    " \n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 220,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.16553978728065255, 0.16553978853557938, 0.12334961193596006, 0.8852306314965829]\n"
     ]
    }
   ],
   "source": [
    "# Regressão Polinomial grau 2\n",
    "\n",
    "poly_reg=PolynomialFeatures(degree=2)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "lin_reg2=LinearRegression()\n",
    "md = lin_reg2.fit(X_poly,ytrain)\n",
    "\n",
    "ypredict = md.predict(X_poly_test)\n",
    "ypredict = list(ypredict)\n",
    "ytrain = list(ytrain)\n",
    "scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "print(scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 223,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR 0.22900152206420898 [0.1524956157881201, 0.15249709229569597, 0.12400107108417173, 0.806648195834884]\n",
      "LASSO 0.11499738693237305 [0.003566596828023849, 0.0035699158105825246, 0.13319366801880772, 0.6026524139619598]\n",
      "EN 0.1419997215270996 [0.003566618220395501, 0.003569937194339623, 0.13319368046472746, 0.6026535512138115]\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-223-e073f613bff7>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      6\u001b[0m     \u001b[0mmd\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mxtrain\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mytrain\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      7\u001b[0m     \u001b[0mtime1\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mt0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 8\u001b[1;33m     \u001b[0mypredict\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mxtest\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      9\u001b[0m     \u001b[0mscores\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mr2_score\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mytest\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mypredict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mexplained_variance_score\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mytest\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mypredict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mmean_absolute_error\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mytest\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mypredict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mmax_error\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mytest\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mypredict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     10\u001b[0m     \u001b[0mresults\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mscores\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\neighbors\\_regression.py\u001b[0m in \u001b[0;36mpredict\u001b[1;34m(self, X)\u001b[0m\n\u001b[0;32m    206\u001b[0m         \u001b[0mX\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcheck_array\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maccept_sparse\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'csr'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    207\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 208\u001b[1;33m         \u001b[0mneigh_dist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mneigh_ind\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkneighbors\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    209\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    210\u001b[0m         \u001b[0mweights\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_get_weights\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mneigh_dist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mweights\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\neighbors\\_base.py\u001b[0m in \u001b[0;36mkneighbors\u001b[1;34m(self, X, n_neighbors, return_distance)\u001b[0m\n\u001b[0;32m    703\u001b[0m                 \u001b[0mkwds\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0meffective_metric_params_\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    704\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 705\u001b[1;33m             chunked_results = list(pairwise_distances_chunked(\n\u001b[0m\u001b[0;32m    706\u001b[0m                 \u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_fit_X\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mreduce_func\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mreduce_func\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    707\u001b[0m                 \u001b[0mmetric\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0meffective_metric_\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mn_jobs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\pairwise.py\u001b[0m in \u001b[0;36mpairwise_distances_chunked\u001b[1;34m(X, Y, reduce_func, metric, n_jobs, working_memory, **kwds)\u001b[0m\n\u001b[0;32m   1621\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1622\u001b[0m             \u001b[0mX_chunk\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0msl\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1623\u001b[1;33m         D_chunk = pairwise_distances(X_chunk, Y, metric=metric,\n\u001b[0m\u001b[0;32m   1624\u001b[0m                                      n_jobs=n_jobs, **kwds)\n\u001b[0;32m   1625\u001b[0m         if ((X is Y or Y is None)\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36minner_f\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     61\u001b[0m             \u001b[0mextra_args\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     62\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[1;33m<=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 63\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     64\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     65\u001b[0m             \u001b[1;31m# extra_args > 0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\pairwise.py\u001b[0m in \u001b[0;36mpairwise_distances\u001b[1;34m(X, Y, metric, n_jobs, force_all_finite, **kwds)\u001b[0m\n\u001b[0;32m   1788\u001b[0m         \u001b[0mfunc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpartial\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdistance\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcdist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmetric\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmetric\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1789\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1790\u001b[1;33m     \u001b[1;32mreturn\u001b[0m \u001b[0m_parallel_pairwise\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mY\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mn_jobs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1791\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1792\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\pairwise.py\u001b[0m in \u001b[0;36m_parallel_pairwise\u001b[1;34m(X, Y, func, n_jobs, **kwds)\u001b[0m\n\u001b[0;32m   1357\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1358\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0meffective_n_jobs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1359\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mY\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1360\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1361\u001b[0m     \u001b[1;31m# enforce a threading backend to prevent data communication overhead\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36minner_f\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     61\u001b[0m             \u001b[0mextra_args\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     62\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[1;33m<=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 63\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     64\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     65\u001b[0m             \u001b[1;31m# extra_args > 0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\pairwise.py\u001b[0m in \u001b[0;36meuclidean_distances\u001b[1;34m(X, Y, Y_norm_squared, squared, X_norm_squared)\u001b[0m\n\u001b[0;32m    270\u001b[0m            [1.41421356]])\n\u001b[0;32m    271\u001b[0m     \"\"\"\n\u001b[1;32m--> 272\u001b[1;33m     \u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mY\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcheck_pairwise_arrays\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mY\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    273\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    274\u001b[0m     \u001b[1;31m# If norms are passed as float32, they are unused. If arrays are passed as\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36minner_f\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     61\u001b[0m             \u001b[0mextra_args\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     62\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[1;33m<=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 63\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     64\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     65\u001b[0m             \u001b[1;31m# extra_args > 0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\pairwise.py\u001b[0m in \u001b[0;36mcheck_pairwise_arrays\u001b[1;34m(X, Y, precomputed, dtype, accept_sparse, force_all_finite, copy)\u001b[0m\n\u001b[0;32m    147\u001b[0m                         \u001b[0mcopy\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcopy\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mforce_all_finite\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mforce_all_finite\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    148\u001b[0m                         estimator=estimator)\n\u001b[1;32m--> 149\u001b[1;33m         Y = check_array(Y, accept_sparse=accept_sparse, dtype=dtype,\n\u001b[0m\u001b[0;32m    150\u001b[0m                         \u001b[0mcopy\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcopy\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mforce_all_finite\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mforce_all_finite\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    151\u001b[0m                         estimator=estimator)\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36minner_f\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     61\u001b[0m             \u001b[0mextra_args\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     62\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[1;33m<=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 63\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     64\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     65\u001b[0m             \u001b[1;31m# extra_args > 0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36mcheck_array\u001b[1;34m(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator)\u001b[0m\n\u001b[0;32m    661\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    662\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mforce_all_finite\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 663\u001b[1;33m             _assert_all_finite(array,\n\u001b[0m\u001b[0;32m    664\u001b[0m                                allow_nan=force_all_finite == 'allow-nan')\n\u001b[0;32m    665\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36m_assert_all_finite\u001b[1;34m(X, allow_nan, msg_dtype)\u001b[0m\n\u001b[0;32m     94\u001b[0m     \u001b[1;31m# safely to reduce dtype induced overflows.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     95\u001b[0m     \u001b[0mis_float\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkind\u001b[0m \u001b[1;32min\u001b[0m \u001b[1;34m'fc'\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 96\u001b[1;33m     \u001b[1;32mif\u001b[0m \u001b[0mis_float\u001b[0m \u001b[1;32mand\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0misfinite\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_safe_accumulator_op\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msum\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     97\u001b[0m         \u001b[1;32mpass\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     98\u001b[0m     \u001b[1;32melif\u001b[0m \u001b[0mis_float\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\extmath.py\u001b[0m in \u001b[0;36m_safe_accumulator_op\u001b[1;34m(op, x, *args, **kwargs)\u001b[0m\n\u001b[0;32m    687\u001b[0m         \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfloat64\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    688\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 689\u001b[1;33m         \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    690\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    691\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m<__array_function__ internals>\u001b[0m in \u001b[0;36msum\u001b[1;34m(*args, **kwargs)\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\numpy\\core\\fromnumeric.py\u001b[0m in \u001b[0;36msum\u001b[1;34m(a, axis, dtype, out, keepdims, initial, where)\u001b[0m\n\u001b[0;32m   2245\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mres\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2246\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2247\u001b[1;33m     return _wrapreduction(a, np.add, 'sum', axis, dtype, out, keepdims=keepdims,\n\u001b[0m\u001b[0;32m   2248\u001b[0m                           initial=initial, where=where)\n\u001b[0;32m   2249\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\numpy\\core\\fromnumeric.py\u001b[0m in \u001b[0;36m_wrapreduction\u001b[1;34m(obj, ufunc, method, axis, dtype, out, **kwargs)\u001b[0m\n\u001b[0;32m     85\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[0mreduction\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mout\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mout\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mpasskwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     86\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 87\u001b[1;33m     \u001b[1;32mreturn\u001b[0m \u001b[0mufunc\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreduce\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mout\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mpasskwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     88\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     89\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "results = []\n",
    "names = []\n",
    "times = []\n",
    "for name, model in models:\n",
    "    t0 = time.time()\n",
    "    md = model.fit(xtrain,ytrain)\n",
    "    time1 = time.time() - t0\n",
    "    ypredict = md.predict(xtest)\n",
    "    scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "    results.append(scores)\n",
    "    names.append(name)\n",
    "    times.append(time1)\n",
    "    print(name, time1, scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 224,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR 5.231963872909546 [0.16553978728065255, 0.16553978853557938, 0.12334961193596006, 0.8852306314965829]\n",
      "LASSO 34.9809992313385 [0.13781008091379388, 0.13781120024075488, 0.12477816735941304, 0.9065448944063363]\n",
      "EN 37.017786264419556 [0.13788464254978816, 0.13788576960952315, 0.12477433828675046, 0.9064874873888447]\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-224-ed664c9270c7>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     10\u001b[0m     \u001b[0mmd\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_poly\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mytrain\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     11\u001b[0m     \u001b[0mtime1\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mt0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 12\u001b[1;33m     \u001b[0mypredict\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_poly_test\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     13\u001b[0m     \u001b[0mscores\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mr2_score\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mytest\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mypredict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mexplained_variance_score\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mytest\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mypredict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mmean_absolute_error\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mytest\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mypredict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mmax_error\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mytest\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mypredict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     14\u001b[0m     \u001b[0mresults\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mscores\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\neighbors\\_regression.py\u001b[0m in \u001b[0;36mpredict\u001b[1;34m(self, X)\u001b[0m\n\u001b[0;32m    206\u001b[0m         \u001b[0mX\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcheck_array\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maccept_sparse\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'csr'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    207\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 208\u001b[1;33m         \u001b[0mneigh_dist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mneigh_ind\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkneighbors\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    209\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    210\u001b[0m         \u001b[0mweights\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_get_weights\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mneigh_dist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mweights\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\neighbors\\_base.py\u001b[0m in \u001b[0;36mkneighbors\u001b[1;34m(self, X, n_neighbors, return_distance)\u001b[0m\n\u001b[0;32m    703\u001b[0m                 \u001b[0mkwds\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0meffective_metric_params_\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    704\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 705\u001b[1;33m             chunked_results = list(pairwise_distances_chunked(\n\u001b[0m\u001b[0;32m    706\u001b[0m                 \u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_fit_X\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mreduce_func\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mreduce_func\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    707\u001b[0m                 \u001b[0mmetric\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0meffective_metric_\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mn_jobs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\pairwise.py\u001b[0m in \u001b[0;36mpairwise_distances_chunked\u001b[1;34m(X, Y, reduce_func, metric, n_jobs, working_memory, **kwds)\u001b[0m\n\u001b[0;32m   1621\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1622\u001b[0m             \u001b[0mX_chunk\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0msl\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1623\u001b[1;33m         D_chunk = pairwise_distances(X_chunk, Y, metric=metric,\n\u001b[0m\u001b[0;32m   1624\u001b[0m                                      n_jobs=n_jobs, **kwds)\n\u001b[0;32m   1625\u001b[0m         if ((X is Y or Y is None)\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36minner_f\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     61\u001b[0m             \u001b[0mextra_args\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     62\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[1;33m<=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 63\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     64\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     65\u001b[0m             \u001b[1;31m# extra_args > 0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\pairwise.py\u001b[0m in \u001b[0;36mpairwise_distances\u001b[1;34m(X, Y, metric, n_jobs, force_all_finite, **kwds)\u001b[0m\n\u001b[0;32m   1788\u001b[0m         \u001b[0mfunc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpartial\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdistance\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcdist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmetric\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmetric\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1789\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1790\u001b[1;33m     \u001b[1;32mreturn\u001b[0m \u001b[0m_parallel_pairwise\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mY\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mn_jobs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1791\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1792\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\pairwise.py\u001b[0m in \u001b[0;36m_parallel_pairwise\u001b[1;34m(X, Y, func, n_jobs, **kwds)\u001b[0m\n\u001b[0;32m   1357\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1358\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0meffective_n_jobs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1359\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mY\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1360\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1361\u001b[0m     \u001b[1;31m# enforce a threading backend to prevent data communication overhead\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36minner_f\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     61\u001b[0m             \u001b[0mextra_args\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     62\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[1;33m<=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 63\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     64\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     65\u001b[0m             \u001b[1;31m# extra_args > 0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\pairwise.py\u001b[0m in \u001b[0;36meuclidean_distances\u001b[1;34m(X, Y, Y_norm_squared, squared, X_norm_squared)\u001b[0m\n\u001b[0;32m    311\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    312\u001b[0m         \u001b[1;31m# if dtype is already float64, no need to chunk and upcast\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 313\u001b[1;33m         \u001b[0mdistances\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m-\u001b[0m \u001b[1;36m2\u001b[0m \u001b[1;33m*\u001b[0m \u001b[0msafe_sparse_dot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mY\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mT\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdense_output\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    314\u001b[0m         \u001b[0mdistances\u001b[0m \u001b[1;33m+=\u001b[0m \u001b[0mXX\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    315\u001b[0m         \u001b[0mdistances\u001b[0m \u001b[1;33m+=\u001b[0m \u001b[0mYY\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36minner_f\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     61\u001b[0m             \u001b[0mextra_args\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     62\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[1;33m<=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 63\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     64\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     65\u001b[0m             \u001b[1;31m# extra_args > 0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\extmath.py\u001b[0m in \u001b[0;36msafe_sparse_dot\u001b[1;34m(a, b, dense_output)\u001b[0m\n\u001b[0;32m    150\u001b[0m             \u001b[0mret\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0ma\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mb\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    151\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 152\u001b[1;33m         \u001b[0mret\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0ma\u001b[0m \u001b[1;33m@\u001b[0m \u001b[0mb\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    153\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    154\u001b[0m     if (sparse.issparse(a) and sparse.issparse(b)\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "# Regressão Polinomial grau 2\n",
    "\n",
    "poly_reg=PolynomialFeatures(degree=2)\n",
    "X_poly=poly_reg.fit_transform(xtrain)\n",
    "X_poly_test = poly_reg.fit_transform(xtest)\n",
    "poly_reg.fit(X_poly,ytrain)\n",
    "\n",
    "for name, model in models:\n",
    "    t0 = time.time()\n",
    "    md = model.fit(X_poly,ytrain)\n",
    "    time1 = time.time() - t0\n",
    "    ypredict = md.predict(X_poly_test)\n",
    "    scores = [r2_score(ytest,ypredict),explained_variance_score(ytest,ypredict),mean_absolute_error(ytest,ypredict),max_error(ytest,ypredict)]\n",
    "    results.append(scores)\n",
    "    names.append(name)\n",
    "    times.append(time1)\n",
    "    print(name, time1, scores)\n"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "b3ba2566441a7c06988d0923437866b63cedc61552a5af99d1f4fb67d367b25f"
  },
  "kernelspec": {
   "display_name": "Python 3.8.8 64-bit ('base': conda)",
   "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": "3.8.8"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}