{"paragraphs":[{"text":"import matplotlib.pyplot as plt\nfrom sklearn import linear_model\nimport numpy as np\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn import preprocessing\n\ndef newsample(xTest, ytest, model):\n ar = np.array([[[1],[2],[3]], [[2],[4],[6]]])\n y = ar[1,:]\n x = ar[0,:]\n\n if model == 1:\n reg = linear_model.LinearRegression()\n reg.fit(x,y)\n print('least square Coefficients: \\n', reg.coef_)\n if model == 2:\n reg = linear_model.Ridge (alpha = 1)\n reg.fit(x,y)\n print('ridged Coefficients: \\n', ridge.coef_)\n \n preds = reg.predict(xTest)\n\n er = []\n for i in range(len(ytest)):\n print( \"actual=\", ytest[i], \" preds=\", preds[i])\n x = (ytest[i] - preds[i]) **2\n er.append(x)\n\n v = np.var(er)\n print (\"variance\", v)\n \n print(\"Mean squared error (bias): %.2f\" % mean_squared_error(ytest,preds))\n\n tst = preprocessing.scale(ytest)\n prd = preprocessing.scale(preds)\n plt.plot(tst, prd, 'g^')\n \n x1 = preprocessing.scale(xTest)\n fx = preprocessing.scale(xTest * reg.coef_)\n\n plt.plot(x1,fx )\n plt.show()\n\n\na = np.array([[4],[5],[6]])\nb = np.array([[8.8],[14],[17]])\nnewsample(a,b, 1)\n\n","user":"admin","dateUpdated":"2018-07-05T13:10:44+0100","config":{"colWidth":12,"enabled":true,"results":{},"editorSetting":{"language":"python","editOnDblClick":false},"editorMode":"ace/mode/python"},"settings":{"params":{},"forms":{}},"apps":[],"jobName":"paragraph_1529322457628_-1366321680","id":"20180618-124737_619813385","dateCreated":"2018-06-18T12:47:37+0100","dateStarted":"2018-07-05T13:10:44+0100","dateFinished":"2018-07-05T13:10:45+0100","status":"FINISHED","progressUpdateIntervalMs":500,"focus":true,"$$hashKey":"object:635","results":{"code":"SUCCESS","msg":[{"type":"TEXT","data":"least square Coefficients: \n [[2.]]\nactual= [8.8] preds= [8.]\nactual= [14.] preds= [10.]\nactual= [17.] preds= [12.]\nvariance 101.14880000000011\nMean squared error (bias): 13.88\n"},{"type":"HTML","data":"