Great Deal! Get Instant $10 FREE in Account on First Order + 10% Cashback on Every Order Order Now

Attention follow the rule, you have to answer each question according to the instruction, before deliver. The document MUST BE RUN 100% ,and the stetment are well organized in each code (when you...

1 answer below »

Attention follow the rule, you have to answer each question according to the instruction, before deliver.

The document MUST BE RUN 100% ,and the stetment are well organized in each code (when you coding each question ,you have to answer Why/Why-not.

The assignment is in the form of py and ipynb

  1. Both Gradient Boosting and Random Forests have a regression version of the algorithms as well. Try them out on the Boston ,diabetes, andcalifornia housingdatasets. How do they compare verse Ridge Regression? Do you think the feature importances make sense? Why/Why-not.
  2. On the regression datasets: Use RandomForest's feature importance scores to help you try and do some of your own feature engineering. This could involve making new features, or removing features. Once you've got your new features: compare Ridge Regression, Decision Trees, and Random Forest on the original features and your new ones. How does performance change for each algorithm? Why do you think your changes helped/hurt?
  3. (Optional) One of the most popular and well engineered Boosting algorithms is calledXGBoost. You can import it with the comandimport xgboost as xgb. XGBoost has better support for sparse datasets, and is often faster and more accurate than other Boosting implementations. Traing XGBoost on the same datasets you've used in this homework. How does it compare in terms of runtime and accuracy?

##############

  1. RandomForest, AdaBoost, and Gradient Boosting all provide methods for measuring feature importance. Use all three on the Forest Cover dataset. Do they agree about feature importances? Try to interperet the results, and tell me what you think.

Answered Same Day Mar 14, 2021

Solution

Ximi answered on Mar 14 2021
160 Votes
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.metrics import mean_squared_e
or"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Boston Dataset\n",
"1. GRADIENT BOOSTING\n",
"2. RANDOM FOREST REGRESSION \n",
"3. RIDGE REGRESSION\n",
"4. FEATURE IMPORTANCES"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"MSE for Gradient Boosting: 6.6579\n"
]
},
{
"data": {
"image/png": "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
lE7Gf6AKgTxt063AbA3XeH57bZS9tvMLMsM5scll1sI0iyYc+fy6cxr0t+d0Dwmcv73QHBz+iRmJ/PKqAYOLSieCQ5lERL2jCzIwlucrMJbpjd3b1p+Gji7rE3z5KSjhHAG2FiXfZ69YCHCcoyDnX3pgRf65UdoFOejcBXQIdyjn1E0BPdNOZxgLtPjv/Tiogk5B6C8oULgKfdPTbhfACYAxzm7k2AO/nmfc7Lu2ic98mDzOyAmO12wMflXO4j4Ndl7o0N3f1fcX/KxBxWJqZdBPfujwmSVQDMzMJz18WcX
nUXb7OwS/X4YQlPxll1wujrg+Ao6o4NgpZX5G9d193V7OlyRSEi0pz8wOtGCg4EzgPg/q/P5BUJd3SHhOGzOLreWbCZwMXMFeeqGBukA9YANQZGanhG32Key5mA78ycxah70SR4W/cO4j6AUfGu6vb8EgxbYJf3gRkfjcQ5DQfY9gxo5YjYHN7v6VmfUnSADjFe998mYzq2tmxxDUT/+7nHP+AVwe9oybmR1gwaDHxgnEk4gLzCwn/EZyEvBQ2HM9CzjNzE40szrAj4CvgZcruNZ69kx8G4dtNhF8M3pLAnE9DrQys/EWDJJvbGYDwmN3Ar82s/YAZnawmY1I4NpSjZRESyp7zMy2E/xlfgPwJ4JBLRDUHb8DLAy/SpsHlA5kcfdPgFcIBv09WN7F3X07MI7ghvo5wS+WOQnEdx2wHHgN2Az8Fqjl7h8R9FD8jOAXz0fAj9H
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
33V0XIPProo+Tm5tK7d29ycnKYNm1ahec
zzLFy4sNxj06ZN4+CDD6ZPnz506tSJYcOG7fXceNxwww3Mnz+/0u1FRET2RTXRIimgefPmFBQUADBx4kQaNWrEddddt8c57o67U6tW+X/7/vOf/9zn+1x55ZX7Hyzw9ddfc8UVV5Cfn0
1q35+uuv+eCDiuenf/7552nRogUDBw4s9/j555/P
fdBsC8efMYMWIEL774Ip07d044vl
+tcJtxEREUmEeqJFUtg777xDTk4O559/Pt27d+eTTz5h7Nix5OXl0b17dyZNmlR67tFHH01BQQFFRUU0bdqUCRMm0Lt3b4466ig+++wzAG688cbSRPXoo49mwoQJ9O/fny5duvDyyy8D8OWXX3L22WeTk5PDt7/9bfLy8koT/BJbt27F3WnWrBkA9erVK012169fz1lnnUVeXh79+/dn4cKFvPvuu0ybNo3f
735Obmlr7X3gwZMoRLL72Uf/zjHwCsXr2aoUOH0q9fP4499ljefvttNm/ezOGHH467A7B9+3batWtHUVERF1xwAbNnzwbgpptu4sgjj6RHjx5cfvnlpefv7fMXFRVxzTXX0KNHD3r16sVf
pXAF577TWOO+44+vXrxymnnML69esr808qIiIZQj3RImWMHw9lcsb9lpsLYe6asDfffJN77rmHvLw8ACZPnkyzZs0oKipi8ODBfPvb3yYnJ2ePNlu3buW4445j8uTJXHvttUyfPp0JEyZ849ruzqJFi5gzZw6TJk3iqaee4v
6dly5Y8/PDDLF26lL59+36j3SGHHMLQoUNp3749J554IqeffjqjRo2iVq1ajBs3jp/85CcMHDiQNWvWMHz4cFasWMFll11GixYtGD9+fFyfu2/fvtx9990AjB07lmnTptGhQwcWLFjAVVddxTPPPENOTg4vvfQSxxxzDHPmzOHUU0+ldu09b2tXX301N998M+7Od77zHZ566ilOOeWUvX7+v/3tb3z88ccsXbqUrKwsNm/ezNdff83VV1/NnDlzaNGiBffffz8
nPmTp1alyfRUREMk9GJtGFhfDii9ClC7Rvn+xoRPZPhw4dShNogH/961/cddddFBUV8fHHH/PGG298I4lu0KBBaaLYr18/XnzxxXKvfdZZZ5Wes2bNGgBeeukl
+egB69+5N9+7dy207Y8YMli1bxrx585g8eTLPPfcc06ZNY968eXvUZn/++ecUFhYm/LlLeoy3bNnCwoULOfvss0uPFRUVATBq1CgefPBBjjnmGGbOnMm11177jes899xz/P73v+e
75i48aNpT3Je/v88+bNY/z48WRlZQHQrFkzCgoKWLlyJUOGDAGguLiYtm3bJvyZREQkc2RkEr11KwwdClOmwA9+kOxoJN1Utsc4KgcccEDp69WrV/PnP/+ZRYsW0bRpUy644IJyp1WrW7du6eusrKzSpLOsevXq7fOcivTq1YtevXrxne98h27dujFt2rTS3t3YGCpjyZIldOvWDXenRYsW3ygpARg5ciQ33XQTN998M8uXL+e4447b4/iOHTu46qqrWLx4MW3atOHGG2/c4+cV7+d3d3r16rXXP0ZkT8vXbSV7whPJDkNEarA1k0+L/D0ysib6kEOgdm1YuzbZkYhUrW3bttG4cWMOPPBAPvnkE55++ukqf49BgwYxa9YsAJYvX84
7xRbhz
e9/S7cLCgpoH37tM2TIEKZMmbLHMYDGjRuzffv2uGKYP38+06dP59JLL+Wggw6iVatWPPLIIwDs3r2bpUuXAnDggQeSm5vL+PHjOeOMM74x6LKwsJBatWrRokULtm/fzsMPP7zP9z7ppJO48847KS4uBmDz5s3k5OSwbt06Fi1aBMDOnTtZuXJlXJ9FREQyU0Ym0bVqQevWsG5dsiMRqVp9+/YlJyeHrl27ctFFFzFo0KAqf48f/vCHrFu3jpycHG6++WZycnJo0qTJHue4O7/5zW/o0qULubm5/OpXv2L69OlAMI3eggUL6NWrFzk5OaWDA0eMGMGsWbPo06dPuQML77
fnJzc+ncuTO
e1vmT17Nl26dAFg5syZ3HnnnaXlJY8
nhpu1GjRnHfffcxatSob1yzefPmjBkzhpycHE455RQGDBiwz8
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
v1ZuHAhxcXFtG/fnm3hlDnuzhFHHMHGjRu58cYbue22YHGOO++8kyOPPJLevXtzzjnnUFhYCMAFF1zA1Vdfzbe+9S2OOOKI0mXAAW655RZ69uxJ7969ueGGGwBYvXo1Q4cOpV+/fhx77LG8/f
+/tPkTbMbFhJOYaZtQSaAxXdDUcDl7l7trtnA4cDJ5lZw8iDFRFJUxnbEw3BDB0q55CEjR8PYa9wlcnNhdsSX8FtxYoVPPLII7z88svUrl2bsWPHMnPmTDp06MDGjRtZvjwYL7ZlyxaaNm3K7bffzh133EFubu43rjV+/Hg6derE4MGDOeWUU7jooouoV68ekyZNYtiwYcyYMYPPP/+cAQMGsGzZMn7xi1+wYsWK0uR2X
27cvtt98OwLhx4/jJT37CwIEDWbNmDcOHD2fFihUMHz6cRx99lAsvvJCXX36Zzp0706JFiz2uc84553D55ZcDMGHCBGbMmMEVV1wBwGeffcaCBQtYvnw55557LmeeeSaPPfYYc+fOZdGiRTRo0IDNmzcDMHbsWKZNm0aHDh1YsGABV111Fc8880zC/wZpoKGZxd7p/gS0Bf5sZl+F+37s7uXW+YSJ8jDg8pJ97v6lmb0EnA48GE3YIiLpLaOT6DZt4LXXkh2FSOXNmzeP1157jby8YAXSwsJCDjvsMIYOHcp
73FuHHjOO200zj55JP3ea2
76ZCy+8kGeeeYZ77rmHBx98kHnz5vHMM88wd+5cJk8Opv796quv+PDDDxOO1f1/3+DPmzdvj3KRzz
nMLCQkaNGsXvfvc7LrzwQmbOnMmoUaO+cZ2SBH7Lli1s376d4cOHlx4bOXIkZkavXr1YF37NNG/ePL773e/SoEEDAJo1a8aWLVtYuHAhZ599dmnboqKihD9TOnD3vX2jeG0FbY6Peb0DaFbOOWeV2c6uXIQiIpkp45Pozz6DnTuhbt1kRyNpoxI9xlFxd7773e+WOwhw2bJlzJ07lylTpvDwww8zderUfV6vY8eOdOzYkcsuu4wWLVqwdetW3J3Zs2fToUOHPc7973
m1CsS5YsoVu3bqVxL1q0iLpl/sc75phjuPjii9m0aRNz5swp93NddNFFzJ07lx49ejBt2jQWLlxYeqxevf+NjYtN2styd1q0aFFaZy4iIlLVMromumTBlY8/Tm4cIpU1ZMgQZs2axcaNwfoWmzZt4sMPP2TDhg24O+eccw6TJk1i8eLFADRu3Jjt27eXe60nnniiNPFcvXo19erVo3HjxgwdOrS0DAOCZHhf1yqroKCAW265pXSA4JAhQ5gyZcoexwHMjBEjRjB+/Hh69+5N06bfnHntyy+/pGXLluzatYsHHnhgn+990kknMX369NLa6c2bN3PQQQfRqlWr0
p3bt3s3Tp0rg+i4iISDwyOonWXNGS7nr27MlNN93EkCFD6NWrFyeffDLr16/no48+4thjjyU3N5dLLrmEW265BYBLLrmEyy67rNyBhTNmzKBr167k5uZy8cUX88ADD1CrVi1uuukmvvzyS3r27En37t2ZOHEiACeccAJLly6lT58+5Q4snD9/Pn369KFLly6MGzeOv/71r6Uzc0yZMoUFCxbQq1cvcnJy+Mc
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
yITAwXFK2EDgRyAfmA98mmKFjDPBohDGUJtG7d0OtjJ7QT/ZH27ZtWbt2LZUtHRKpX78+bUtGM9dwy9dtJXvCE8kOQ0RiVHa2Ctm7yJJod3/VzB4CFgNFwBJgKvAEMNPMfhXuuyuqGCAo59i1CzZuhEMOifKdJJ3VqVOHww8/PNlhiIiISJqIdNlvd78JuKnM7veA/lG+b6ySBVfWrlUSLSIiIiJVI+MLHNq1C54
DC5cYiIiIhI5sj4JLp9++BZSbSIiIiIVJWMT6KbN4cGDZREi4iUx8yKzazAzFaY2WNm1jTcn21mHo5fKTm3hZntMrM7khexiEhqyPgk2iwo6fjgg2RHIiKSkgrdPdfdewCbgStjjr0PxA7pPwdYWZ3BiYikqoxPoiFIotUTLSKyT6+w5yqyO4BVZpYXbo8CZlV7VCIiKahGJNHt2yuJFhGpiJllEcznP6fMoZnAeWZ2GFAMfFzdsYmIpKIakUS3aweffgpff53sSEREUk4DMysAPgUOBZ4tc/wp4CTgPODBvV3EzMaaWb6Z5Rfv2BpZsCIiqaLGJNEAH32U3DhERFJQobvnAu0BY8+aaNx9J/A68CPgob1dxN2nunueu+dlNWwSZbwiIimhRiXRKukQESmfu+8AxgE/MrOyC3H9Ebje3TdXf2QiIqmpRiTRmitaRGTf3H0JsAwYXW
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
E11cDB99lOxIRERERCQd1cgkWnNFi4iIiMj+qJFJdMlc0RpcKCIiIiKVUSOT6LZtg1po9USLiIiISGXUyGF1WVnQrp16okVEorB83VayJzxRJddaowGKIpKiamRPNECHDvDuu8mOQkRERETSUY1Nojt1gtWrwT3ZkYiIiIhIuqmxSXTHjrBlC2zalOxIRERERCTd1NgkulOn4Hn16uTGISIiIiLpR0m0kmgRERERSVCNTaIPPxxq1YJ33kl2JCIi0TIzN7M/xmxfZ2YTY7bHmtmb4WORmR0d7s8ys9fN7NiYc58xs3Oq9QOIiKSgGptE160L2dnqiRaRGuFr4Cwza1H2gJkNB74PHO3uXYHLgQfMrKW7FwM/AO4wszpmNhrY7e7
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
Abxe0QlmVh8YADy1l1McmAcMBUYQzPFf0fVKV5kt3rE18YhFRNKMkujQwQdDs2ZKokUk43UwswJgPfCJuy+r4NyZBCUd5wH/quii7j7V3fPcPS+rYZOqi1ZEJEVlZhLtDuvXw9b4e0PMNEOHiGSMlUC/vRwrqYnuAPQzszP2dhF3X0RQO93C3d+u+jBFRNJXZibRH3wALVvCrFkJNevaVTXRIpIRngfqmdnYkh1m1gs4rGTb3TcCEwgGHFZkAvCzKIIUEUlnmZlEt2sH9erBW28l1KxbN9iwATZtiiguEZFq4O4OnAkMCae4Wwn8Bvi0zKmzgYZmdkwF15
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
M9vFltl8gvNeH2/8B
PPoEVEaph4yzl2uXvZkSJe1cFEplu34DnBuuhOnaBhQw0uFBEREZE9xdsTvdLMvgNkmVkngpq7l6MLq4o1awaHHppwEp2VBb17a3ChiIiIiOwp3p7oHxLMC/o18ACwFRgfVVCR6NYt4SQagsGFBQUJj0kUERERkQwWVxLt7jvc/QZ3PzJ83OjuX0UdXJXq2RNWrIDi4oSa9ekD27cnvGq4iIiIiGSwuMo5zOxZ4Bx33xJuH0Qwef/QKIOrUrm58OWX8M470CX+mfpiBxd2TGThXRGRGqpnmybkTz4t2WGIiEQq3nKOFiUJNIC7fw4cEk1IESnJhgsSm5mpe3eoXVt10SIiIiLyP/Em0bvNrF3JRjhRf
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
5BTfT27RHEJSKSPCOAp9z9bWCTmfUrOeDuW4DJwG+AK5MUn4hIyok3iW7g7s8B5u4fuPtEIH2XmhowIKjLSFD
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
d/EcQmIiIiIpFTEl1ZV1wRLAP+z38m3HTUKDjooKA3WkRERETSj5LoyurVC44+OsiEd+9OqGmDBkFt9H/+A598ElF8IiIiIhIZJdH74wc/gHffrdTEz5dfHkzucdddEcQlIiIiIpFSEr0/zjoLDjkE/vrXhJt26gQnnQR
3vCM+WJiIiISJIpid4f9erB974Hjz8O77yTcPO
gqWAP/PfyKITUQkhpkVm1mBma0ws8fMrGmZ4+PN7CszaxKz73gz22pmS8zsLTP7r5kN
7oRURSj5Lo/XXllVC7Ntx2W8JNhw+Hjh3hj3/UdHciErlCd8919x7AZuDKMsdHA68BZ5XZ/6K793H3LsA44A4zOzH6cEVEUpuS6P3VqlWw+Mr06bBxY0JNa9WCa66BRYvglVciik9E5JteAdqUbJhZB6ARcCNBMl0udy8AJgFXRR2giEiqUxJdFX70IygsrNScdWPGBNPd/elPEcQlIlKGmWUBJwJzYnafB8wEXgS6mNmhFVxiMdC1nOuONbN8M8sv3qHFVkQk8ymJrgrdu8Opp8LttwdzRyfggAOCmToeeSSY6ENEJCINzKwA+BQ4FHg25thoYKa77wYeBs6p4DpW3k53n+ruee6el9WwSXmniIhkFCXRVeW662DDBrjnnoS
vCHUKcOTJ4cQVwiIoFCd88F2hMkwlcCmFlPoBPwrJmtIeiV3mtJB9AHWBVtqCIiqU9JdFU5/njo1y8YJZjg4iutWsGll8Ldd8OHH0YTnogIgLvvIBgg+CMzq02QME909+zw0RpobWbty7Y1s17Az4Ep1Rq0iEgKUhJdVcyC3ui334ZHH024+fXXB8+/+10VxyUiUoa7LwGWESTQ5wGPlDnlkXA/wDElU9wRJM/j3P25agtWRCRFmafB3Gp5eXmen5+f7DD2ragIunaFJk0gPz9IrBPwve/BvffC++8HvdMikv7M7HV3z0t2HNWpXqtO/vUnq5MdhohIwhK5Z6snuirVrg033ACLF8OTTybc/Kc/DfLw3/8+gthEREREpMooia5qF1wA2dkwaVLCK6gccQScfz7ceSd89lk04YmIiIjI/lMSXdXq1IE
wxWUHmkbJnhvv3sZ8EseeqNFhEREUldSqKjMGYM5OTAhAmwa1dCTbt0gQsvDKac1kwdIpKOe
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
3KOgcpuZlSIH0cV0/aa14j4AAB1bSURBVPWxV
EE2Hp0sbPT3IjQjp1ipeuWtWCZTSzUnMZcDGNB8m7A6+k7RW1xkf3Bj7M7YQQ3gsh3BRCOBpYAwxtxvKamZUkB9HF1Ls33HZbnDf67LOhgOkG+/eHm2+G6dPjaoZmZgAhhNnAy8Douo4rOo841vmRlP1v4GvpeCfgeOCJtH9YWn0WSVsCmwHzW7IOZmalwEF0sY0YEafbuO02uOaagi4dPTouwjJmDDz8cMsUz8xK0i+BAbXyrpQ0A3gV+C9gVAhhdTr2XeArkqYDzwF/DyE8mY4dAsxK144nzvLxfovXwMysjfNiK21BdXVc0fCee+Dvf4djj23ypStXwt57w4IFMGNGHB1iZm2HF1sxMysdXmyl1LRrB7feCvvuC1/7Gkya1ORLO3aEO+6A5cvjpQXOmGdmZmZmG8BBdFvRqRPcfz9svTV86UsFTbux007w+9/D44/DBRe0YBnNzMzMDHAQ3
06QP
GfsmT7oIHj11SZfetppcP75cO21cOONLVhGMzMzM3MQ3eYMGRK7lKuq4JBD4I03mnzpFVfAoYfCOefAU0+1YBnNzMzMNnEOotuioUNjj/TSpbDXXnF5wiYoL4/jowcPhq98Jc6cZ2bW2nbp78VWzCz7HES3VXvuGZcF79MHDj44jpdugp49Ydy42JF95JHw0UctXE4zMzOzTZCD6LZsu+3g6adh111j1/If/9ikBVl22AHuvTeOBDniCFi2rBXKamZmZrYJcRDd1vXtG8dIH3oofOtbcPLJsGJFo5eNGgV33glTp8KXvxznkzYzMzOz5uEguhR06RLHaPziFzEyHjkS3m98wbCjj4a
oox+EkneQ5pMzMzs+biILpUlJfDj34UVzWcNQuGD4dnn230slNPjauJ33cffOMbcXFEMzMzM9s4DqJLzZe/HGfrqKiAAw6A3/ym0cj4vPPg0kvhL3+J80lXVbVOUc3MzMyyykF0KRo2DKZMgaOOggsvjLN3vP12g5dcckkcDfLXv8bvKDZhWLWZmZmZ1cNBdKnq1SsO7bjhBpg8GXbZJXY11zN7hxRHg1x/PTz0EBx2GCxZ0splNjMzM8sIB9GlTIoDnWfMgN12g9NPh2OOgQ8+qPeSs8+G226DSZPiDB4LF7Zecc3MzMyywkF0Fmy7LTzxBFx5ZVzpcMcd4Q9/gLVr6zz9xBPhgQdg9mwYMQJefbWVy2tmbYakYyRNr5WqJZ0tKUg6N+/c6ySdXsTimpm1GQ6is6KsLI6PnjEDdt89djnvs09c9bAOhx0G
oXfPxxXFn8oYdaubxm1iaEEO4NIQzLJeB64ClgPLAQ+K6kDkUtpJlZG+QgOmt23BEmTIhjNubPj4H0KafA3Lnrn
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
RhNepoju0ziqK6z6T95M
77nh+RUVcwSWXtt225nHgQOjZM85lbWZmZlaiHERbwfbeGx54uhePPDKaiy8ezdmT44x5Yy5/jwPKJ8WlxufOjenZZ+GTT9a9QUUFdO26burWre68/v1hyJA4v3XfvtC7d3EqbWZmZpbHQbRtEAkOPxwOOSTO3PHjH8OBJ23F/vsfx0UXHccRl0O73NwvH38Mb74Jr70G774b58y
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
wtlnx1k9PvoIpkyJ0+YNGRJXSjzttLho4WabxWEfl1wSe68
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
ZpuVqYmbURDqJtk9SuHQweHNMRR9TkhwAffFATVOcC7PHj42rW+crLYZttYkCdC6632Sam
eOqZRWA7dMeAk4bgOuOwkYIWle2t8MOAh4DCCE8CLwoqRbgTepI4gOIYwljp9m+PDhbX8pXDOzjeQg2iyPBFtuGdOoUeseW7Eirvo8b17sxZ43r2Z7/Hh4773177f55jGYHjAg9lzXlXr39vR81mweBy6TdFYKapG0K9CjvgskdQf2B7ZOY56R9HXgJEnPAsNDCBPT6cOAt1qw/GZmJcNBtFkTdeoU56feYYe6j69aBe++C++8E4Pt/DR3Ljz9dJymr7Z27eIUfX36QN++8bGutNlmMeDu1Qt69vRQEltfmlHjGOBqSRcDK4F5wPcauOwY4PFcAJ3cD1wBnA9cJOmPwAqgkjp6oc3MNkUOos2aSUVFHDc9ZEj956xaFYeFLFgQe67nz4dFi+K81rk0Zw4880zcXru2/nv16BED6lxgn
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
mS2uZ8Oa3GaXRBC9ISRNCSEML3Y5WkqW6+e6la4s1y/LdWtum8rPyvXMFtczW1qjnh7OYWZmZmZWIAfRZmZmZmYFynIQP
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
o7AXsWOQiNQtJRwELQwhTi12WFjQihLAH8aO
0s6IP9gqf9u2sbJcrsFm8zfOMRe2T2A34cQdgcqqTV0IyOvZy/gaOKbhq2ALqw
CGzWuM1zGIQPR/YOm9/QMordR9I6geQHhem/JK
6T2xH9Efwsh3JOyM1O/nBDCJ8ATxI/LekoqT4fy6/BZ/dLxHsBHrVzUpvoC8CVJ84A7iB/3XkM26gZ81nNDCGEhcC/xTVDmfjdbUGZ/JgW2W6Wq0L/xUvUu8G4I4fm0fzcxqM7a63kw8GYIYVEIoQq4h/gaZ+31zNeq7XUWg+jJwPbp26cdiIPoxxW5TM1hHHBa2j6NOCYvl39q+ubpPsCSvI8y2hxJAv4EvBJC+G3eoazUr6+knmm7E3Hc5CvEYPq4dFrt+uXqfRzweHr33OaEEH4YQhgQQhhE/Lt6PITw32SgbgCSukjqltsGDgFmkZHfzVaSyfZ3A9qtkrQBf+MlKYTwPvCOpB1S1v8BXiZjrydxGMc+kjqn3+FcPTP1etbSuu11sQeFt0QCjgBeJY5F/VGxy7MB5b+dOH6piviO+UziuLQJwGvAv4De6VwRvw3/BvAi8Vu4Ra9DA3UbQfx4ZSYwPaUjMlS/XYFpqX6zgEtS
AC8DrwN+BipTfMe2/no5vW+w6NLGeI4EHs1S3VI8ZKb2Uazuy8rvZij/Hkm5/66lTQe1WFlJT/sZLORFnT5qSXtP7gF5ZfD2BnwKz0/+jW4GKrLyetIFYySsWmpmZmZkVKIvDOczMzMzMWpSDaDMzMzOzAjmINjMzMzMrkINoMzMzM7MCOYg2MzMzMyuQg2hrNpLWSpouaYak/0jar5nv/39r7U9qpvuOlPRg3nazlVvSIEkn5+0Pl3Rtc93fzKwQee30LEkP5Oa1b+Sa5Y0c7ynpnLz9rSTd3QxlHSRp1sbep8DnHCbpiNZ8TitdDqKtOa0IIQwLIewG/BD4VTPff50gOoTQrEF6MhIo6L55Kz/VZRDwWRAdQpgSQjhvg0pmZ
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
xvy7tWj2K+5k5NTaaW8drOMuFrdYWn/EGAscWW3dsCDwAG1rikHuqftPsQV70T8xG1W3nN8tg+cD/w0bfcD5qTty4Cvpe2exFUuu9Qqa/59Tk/P1w3om9r8b6VjY4Dvpe2JuXYSOCDv+oba2/y2/HTgurwydAfK0
BwD/yzpsL9CD+r3kL2DqVLf
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\n",
"text/plain": [
"
"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"MSE for Random Forest: 10.2649\n",
"MSE for Ridge Regression: 16.3246\n"
]
}
],
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
...
SOLUTION.PDF

Answer To This Question Is Available To Download

Related Questions & Answers

More Questions »

Submit New Assignment

Copy and Paste Your Assignment Here