Newer
Older
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<!-- <img src=\"../fidle/img/00-Fidle-header-01.svg\" style=\"width:800\" /> -->\n",
"\n",
"Deep Neural Network (DNN) - BHPD dataset\n",
"========================================\n",
"\n",
"A very simple and classic example of **regression** :\n",
"## Objectives :\n",
"Predicts **housing prices** from a set of house features. \n",
"\n",
"The **[Boston Housing Dataset](https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html)** consists of price of houses in various places in Boston. \n",
"Alongside with price, the dataset also provide information such as Crime, areas of non-retail business in the town, \n",
"age of people who own the house and many other attributes...\n",
"\n",
"What we're going to do:\n",
"\n",
" - Retrieve data\n",
" - Preparing the data\n",
" - Build a model\n",
" - Train the model\n",
" - Evaluate the result\n"
]
},
"outputs": [
{
"data": {
"image/svg+xml": [
"<svg viewBox=\"0 0 319.4819 36.2319\" xmlns=\"http://www.w3.org/2000/svg\"><title>00-header-01</title><g data-name=\"Calque 2\" id=\"Calque_2\"><g data-name=\"Calque 4\" id=\"Calque_4\"><path d=\"M19.6212,13.4825a5.49,5.49,0,0,0,2.2409-.7517,2.75,2.75,0,0,1,1.0037-.3925A6.2169,6.2169,0,0,0,20.4184,5.353a7.2454,7.2454,0,0,0-5.0435-.8518,10.436,10.436,0,0,0-4.3281,2.2353c-.4328.3626-5.581,5.2428-7.7283,4.27C1.8658,10.3486,4.46,7.9537,3.27,5.7652a.0949.0949,0,0,0-.1584-.0105c-.6056.817-1.1976,1.7975-2.0041,1.3573A3.7988,3.7988,0,0,1,.1729,5.89.0941.0941,0,0,0,0,5.9434a9.9185,9.9185,0,0,0,2.4932,6.0532,15.0278,15.0278,0,0,0,10.339,5.3173c2.27.2261,7.6543-.49,9.8054-4.36a5.4574,5.4574,0,0,0-.5189.2577,6.04,6.04,0,0,1-2.448.8142c-.0748.0069-.1491.01-.2234.01a4.3218,4.3218,0,0,1-2.44-.9782.4573.4573,0,1,1,.3495-.4436l-.0023.0218A3.5637,3.5637,0,0,0,19.6212,13.4825ZM12.76,15.5084a8.3323,8.3323,0,0,1-1.9609.3562c-.4428,0-.627-.1255-.7147-.314-.2306-.4961.6005-1.2133,1.3378-1.7279a.2726.2726,0,0,1,.312.4472,4.4932,4.4932,0,0,0-1.1262,1.0351,5.352,5.352,0,0,0,2.0105-.3235.2728.2728,0,0,1,.1415.5269ZM19.0763,8.863a1.0412,1.0412,0,0,1,1.0109,1.0032.68.68,0,1,0-.6023.9942.7023.7023,0,0,0,.1263-.0126.9691.9691,0,0,1-.5349.1646,1.0763,1.0763,0,0,1,0-2.1494ZM15.5649,1.8843a.5453.5453,0,0,0,.2143.7407c.2638.1453.82-.1708,1.1567.3.1751.2449-.3665-1.11-.63-1.2554A.5449.5449,0,0,0,15.5649,1.8843Zm2.7777.0584c-.68.3984-.8055,2.0455-.63,1.8007a3.1,3.1,0,0,1,1.1567-.8456.5453.5453,0,0,0-.5264-.9551ZM17.6534.1266c-.3475.402-.11,1.4443-.0473,1.2532a2.216,2.216,0,0,1,.5595-.7875.3573.3573,0,0,0-.0087-.505A.3538.3538,0,0,0,17.6534.1266Z\" style=\"fill:#e12229\"/><path d=\"M1.2153,20.5943H4.63v.41H1.6972v2.7481H4.3837v.41H1.6972v3.3428H1.2153Z\" style=\"fill:#808285\"/><path d=\"M6.4355,20.5943v6.9111H5.9536V20.5943Z\" style=\"fill:#808285\"/><path d=\"M8.1171,20.6865a11.3714,11.3714,0,0,1,1.7637-.1435,3.7468,3.7468,0,0,1,2.7891.9433,3.269,3.269,0,0,1,.8613,2.3892,3.8066,3.8066,0,0,1-.9024,2.625A3.97,3.97,0,0,1,9.645,27.5567a14.7357,14.7357,0,0,1-1.5279-.0616Zm.482,6.4087a8.7069,8.7069,0,0,0,1.1176.0513,2.96,2.96,0,0,0,3.312-3.24c.01-1.7535-.9638-2.9532-3.1787-2.9532a7.3291,7.3291,0,0,0-1.2509.1026Z\" style=\"fill:#808285\"/><path d=\"M14.7524,20.5943h.4819v6.5009h3.0864v.41H14.7524Z\" style=\"fill:#808285\"/><path d=\"M22.5976,24.07H19.829v3.0249h3.0967v.41H19.3471V20.5943h3.4146v.41H19.829V23.66h2.7686Z\" style=\"fill:#808285\"/><path d=\"M39.1845,4.6616h5.874v1.26H40.6752V9.9678h4.064V11.21h-4.064v5.4126H39.1845Z\"/><path d=\"M53.5209,12.2749c0,3.2119-2.0053,4.5249-3.8506,4.5249-2.0942,0-3.727-1.6147-3.727-4.4184,0-2.9458,1.7568-4.5254,3.8511-4.5254C51.977,7.856,53.5209,9.542,53.5209,12.2749Zm-6.0512.0708c0,1.7393.8339,3.3184,2.2714,3.3184,1.4019,0,2.254-1.5972,2.254-3.354,0-1.42-.586-3.3-2.254-3.3C48.1083,9.01,47.47,10.8018,47.47,12.3457Z\"/><path d=\"M55.3456,10.5713c0-.9229-.0356-1.7749-.0708-2.5376h1.3306l.0532,1.5791h.0537A2.4529,2.4529,0,0,1,58.93,7.856a2.6759,2.6759,0,0,1,.3906.0356V9.3467a1.864,1.864,0,0,0-.4614-.0357,2.0646,2.0646,0,0,0-1.9521,1.9346,3.2178,3.2178,0,0,0-.0708.7451v4.6319H55.3456Z\"/><path d=\"M60.7211,10.3228c0-.9229-.0356-1.58-.0708-2.2891h1.313l.0889,1.2954h.0351A2.6985,2.6985,0,0,1,64.5541,7.856a2.3122,2.3122,0,0,1,2.2364,1.5971h.0351a3.1057,3.1057,0,0,1,.9405-1.0649,2.577,2.577,0,0,1,1.6684-.5322c1.1533,0,2.6084.7807,2.6084,3.5136v5.253H70.57V11.6182c0-1.5083-.4791-2.52-1.6685-2.52a1.8267,1.8267,0,0,0-1.668,1.3667,2.683,2.683,0,0,0-.1064.7807v5.377H65.6547V11.3345c0-1.2422-.48-2.2363-1.6152-2.2363a1.917,1.917,0,0,0-1.7388,1.5083,2.6343,2.6343,0,0,0-.1064.7631v5.253H60.7211Z\"/><path d=\"M78.747,16.6226l-.1245-1.0293h-.0532a2.7825,2.7825,0,0,1-2.36,1.2065A2.36,2.36,0,0,1,73.76,14.3335c0-2.0942,1.81-3.1767,4.72-3.1592v-.2129c0-.8339-.2305-1.9873-1.792-1.97a3.6276,3.6276,0,0,0-1.9878.5859l-.3369-1.0292a5.0217,5.0217,0,0,1,2.5908-.6924c2.36,0,3.0166,1.5971,3.0166,3.39V14.6a14.2132,14.2132,0,0,0,.1245,2.023Zm-.2485-4.4009c-1.3843-.0181-3.23.23-3.23,1.9521a1.314,1.314,0,0,0,1.331,1.49A1.8735,1.8735,0,0,0,78.4453,14.28a1.5848,1.5848,0,0,0,.0532-.4971Z\"/><path d=\"M84.0322,5.62V8.0337h2.0586V9.187H84.0322v4.7559c0,1.0825.32,1.5972,1.0825,1.5972a3.0043,3.0043,0,0,0,.7988-.0889l.0708,1.1357a3.3086,3.3086,0,0,1-1.2778.1953,2.044,2.044,0,0,1-1.5791-.6211,3.1748,3.1748,0,0,1-.5855-2.2006V9.187H81.2993V8.0337h1.2426V6.0283Z\"/><path d=\"M89.3369,5.6734a.894.894,0,0,1-.9405.94.8716.8716,0,0,1-.8872-.94.9142.9142,0,1,1,1.8277,0Zm-1.668,10.9492V8.0337h1.5083v8.5889Z\"/><path d=\"M98.581,12.2749c0,3.2119-2.0054,4.5249-3.8506,4.5249-2.0942,0-3.727-1.6147-3.727-4.4184,0-2.9458,1.7568-4.5254,3.851-4.5254C97.037,7.856,98.581,9.542,98.581,12.2749Zm-6.0513.0708c0,1.7393.834,3.3184,2.2715,3.3184,1.4019,0,2.2539-1.5972,2.2539-3.354,0-1.42-.5859-3.3-2.2539-3.3C93.1684,9.01,92.53,10.8018,92.53,12.3457Z\"/><path d=\"M100.4062,10.3228c0-.9229-.0357-1.58-.0708-2.2891h1.3306l.0712,1.2954h.0533a2.8836,2.8836,0,0,1,2.5732-1.4731c1.189,0,2.7329.7632,2.7329,3.46v5.3062h-1.4907V11.4942c0-1.2779-.4258-2.396-1.7393-2.396a1.9932,1.9932,0,0,0-1.8632,1.5439,2.9542,2.9542,0,0,0-.0889.7456v5.2349h-1.5083Z\"/><path d=\"M114.4921,4.6616v11.961h-1.4907V4.6616Z\"/><path d=\"M117.0815,10.3228c0-.9229-.0357-1.58-.0708-2.2891h1.3305l.0713,1.2954h.0533A2.8835,2.8835,0,0,1,121.039,7.856c1.189,0,2.7329.7632,2.7329,3.46v5.3062h-1.4907V11.4942c0-1.2779-.4263-2.396-1.7393-2.396a1.9934,1.9934,0,0,0-1.8633,1.5439,2.9592,2.9592,0,0,0-.0888.7456v5.2349h-1.5083Z\"/><path d=\"M127.8857,5.62V8.0337h2.0586V9.187h-2.0586v4.7559c0,1.0825.32,1.5972,1.0825,1.5972a3.0043,3.0043,0,0,0,.7988-.0889l.0708,1.1357a3.3083,3.3083,0,0,1-1.2778.1953,2.044,2.044,0,0,1-1.5791-.6211,3.1748,3.1748,0,0,1-.5855-2.2006V9.187h-1.2426V8.0337h1.2426V6.0283Z\"/><path d=\"M131.5224,10.5713c0-.9229-.0356-1.7749-.0708-2.5376h1.3306l.0532,1.5791h.0537a2.4529,2.4529,0,0,1,2.2178-1.7568,2.6759,2.6759,0,0,1,.3906.0356V9.3467a1.864,1.864,0,0,0-.4614-.0357,2.0648,2.0648,0,0,0-1.9522,1.9346,3.2233,3.2233,0,0,0-.0708.7451v4.6319h-1.4907Z\"/><path d=\"M143.73,12.2749c0,3.2119-2.0054,4.5249-3.8506,4.5249-2.0942,0-3.727-1.6147-3.727-4.4184,0-2.9458,1.7568-4.5254,3.8511-4.5254C142.186,7.856,143.73,9.542,143.73,12.2749Zm-6.0513.0708c0,1.7393.834,3.3184,2.2715,3.3184,1.4019,0,2.2539-1.5972,2.2539-3.354,0-1.42-.5859-3.3-2.2539-3.3C138.3173,9.01,137.6786,10.8018,137.6786,12.3457Z\"/><path d=\"M152.2988,4.1118V14.4575c0,.71.0351,1.5972.0708,2.1651h-1.3311l-.0708-1.3662h-.0532A2.7766,2.7766,0,0,1,148.3412,16.8c-1.8989,0-3.3364-1.7036-3.3364-4.3652,0-2.9282,1.6328-4.5786,3.4785-4.5786a2.4975,2.4975,0,0,1,2.2891,1.2246h.0356V4.1118Zm-1.4908,7.3467a4.0769,4.0769,0,0,0-.0532-.6387,2.0659,2.0659,0,0,0-1.97-1.7568c-1.4732,0-2.2539,1.4727-2.2539,3.3008,0,1.7744.7451,3.2119,2.2182,3.2119a2.0694,2.0694,0,0,0,1.9874-1.7393,2.4325,2.4325,0,0,0,.0712-.6386Z\"/><path d=\"M161.24,14.28c0,.9048.0356,1.668.0713,2.3423h-1.3135l-.0889-1.26h-.0351a2.896,2.896,0,0,1-2.5376,1.437c-1.4024,0-2.6978-.8691-2.6978-3.62V8.0337h1.4907v4.8975c0,1.5439.4258,2.6264,1.6861,2.6264a1.9727,1.9727,0,0,0,1.81-1.3486,2.6964,2.6964,0,0,0,.1241-.7983V8.0337H161.24Z\"/><path d=\"M169.1869,16.3384a5.0911,5.0911,0,0,1-2.165.4438c-2.36,0-3.94-1.686-3.94-4.3652a4.2057,4.2057,0,0,1,4.2592-4.543,4.4515,4.4515,0,0,1,1.8809.39l-.3369,1.1714a3.42,3.42,0,0,0-1.5615-.355c-1.7925,0-2.7154,1.5259-2.7154,3.2651,0,2.0054,1.1182,3.2119,2.6973,3.2119a3.8408,3.8408,0,0,0,1.6328-.355Z\"/><path d=\"M172.8754,5.62V8.0337h2.0586V9.187h-2.0586v4.7559c0,1.0825.32,1.5972,1.0825,1.5972a3.0052,3.0052,0,0,0,.7989-.0889l.0708,1.1357a3.31,3.31,0,0,1-1.2774.1953,2.0446,2.0446,0,0,1-1.58-.6211,3.1748,3.1748,0,0,1-.5854-2.2006V9.187H170.143V8.0337h1.2422V6.0283Z\"/><path d=\"M178.18,5.6734a.894.894,0,0,1-.94.94.8716.8716,0,0,1-.8872-.94.9142.9142,0,1,1,1.8276,0Zm-1.6679,10.9492V8.0337H178.02v8.5889Z\"/><path d=\"M187.4238,12.2749c0,3.2119-2.0054,4.5249-3.8506,4.5249-2.0943,0-3.7271-1.6147-3.7271-4.4184,0-2.9458,1.7569-4.5254,3.8511-4.5254C185.88,7.856,187.4238,9.542,187.4238,12.2749Zm-6.0513.0708c0,1.7393.834,3.3184,2.2715,3.3184,1.4018,0,2.2539-1.5972,2.2539-3.354,0-1.42-.586-3.3-2.2539-3.3C182.0112,9.01,181.3725,10.8018,181.3725,12.3457Z\"/><path d=\"M189.249,10.3228c0-.9229-.0357-1.58-.0708-2.2891h1.3305l.0713,1.2954h.0532a2.8837,2.8837,0,0,1,2.5733-1.4731c1.1889,0,2.7329.7632,2.7329,3.46v5.3062h-1.4907V11.4942c0-1.2779-.4258-2.396-1.7393-2.396a1.9934,1.9934,0,0,0-1.8633,1.5439,2.9592,2.9592,0,0,0-.0888.7456v5.2349H189.249Z\"/><path d=\"M206.14,16.6226l-.1245-1.0293h-.0532a2.7825,2.7825,0,0,1-2.36,1.2065,2.36,2.36,0,0,1-2.4487-2.4663c0-2.0942,1.81-3.1767,4.72-3.1592v-.2129c0-.8339-.23-1.9873-1.792-1.97a3.6273,3.6273,0,0,0-1.9878.5859l-.3369-1.0292a5.0217,5.0217,0,0,1,2.5908-.6924c2.36,0,3.0166,1.5971,3.0166,3.39V14.6a14.2132,14.2132,0,0,0,.1245,2.023Zm-.2485-4.4009c-1.3843-.0181-3.23.23-3.23,1.9521a1.314,1.314,0,0,0,1.331,1.49,1.8733,1.8733,0,0,0,1.8457-1.3838,1.5819,1.5819,0,0,0,.0533-.4971Z\"/><path d=\"M216.27,14.28c0,.9048.0356,1.668.0713,2.3423h-1.3135l-.0889-1.26h-.0351a2.896,2.896,0,0,1-2.5376,1.437c-1.4024,0-2.6978-.8691-2.6978-3.62V8.0337h1.4907v4.8975c0,1.5439.4258,2.6264,1.6861,2.6264a1.9728,1.9728,0,0,0,1.81-1.3486,2.6966,2.6966,0,0,0,.124-.7983V8.0337H216.27Z\"/><path d=\"M222.21,4.8213a16.8353,16.8353,0,0,1,2.8574-.248,5.9357,5.9357,0,0,1,4.2236,1.3305,5.6509,5.6509,0,0,1,1.668,4.4546,6.55,6.55,0,0,1-1.6328,4.7734,6.464,6.464,0,0,1-4.6846,1.58,19.1885,19.1885,0,0,1-2.4316-.1245Zm1.4907,10.6123a8.7023,8.7023,0,0,0,1.2422.0708c2.7686,0,4.4546-1.6147,4.4546-5.0928.0176-2.8925-1.3843-4.6318-4.2417-4.6318a7.5156,7.5156,0,0,0-1.4551.124Z\"/><path d=\"M233.76,12.5586c.0352,2.2715,1.2773,3.0523,2.6616,3.0523a5.0482,5.0482,0,0,0,2.0943-.4083l.2661,1.0826a6.2362,6.2362,0,0,1-2.5733.497c-2.4668,0-3.9043-1.7392-3.9043-4.33,0-2.6441,1.4375-4.5962,3.709-4.5962,2.4844,0,3.1944,2.2715,3.1944,3.9575a7.0326,7.0326,0,0,1-.0357.7451Zm4.01-1.0825c.018-1.2066-.479-2.52-1.899-2.52-1.3838,0-1.9873,1.4018-2.0937,2.52Z\"/><path d=\"M241.92,12.5586c.0352,2.2715,1.2774,3.0523,2.6617,3.0523a5.0477,5.0477,0,0,0,2.0942-.4083l.2661,1.0826a6.2357,6.2357,0,0,1-2.5732.497c-2.4668,0-3.9043-1.7392-3.9043-4.33,0-2.6441,1.4375-4.5962,3.709-4.5962,2.4843,0,3.1943,2.2715,3.1943,3.9575a7.0657,7.0657,0,0,1-.0356.7451Zm4.01-1.0825c.0181-1.2066-.479-2.52-1.8989-2.52-1.3838,0-1.9873,1.4018-2.0938,2.52Z\"/><path d=\"M249.1752,10.8018c0-1.1709-.0356-2.023-.0708-2.7681h1.3487l.0708,1.3486h.0356a2.9639,2.9639,0,0,1,2.68-1.5263c1.8989,0,3.3008,1.7036,3.3008,4.3833,0,3.1235-1.7217,4.5605-3.5318,4.5605a2.5779,2.5779,0,0,1-2.3066-1.2422h-.0356v4.543h-1.4908Zm1.4908,2.4311a2.5684,2.5684,0,0,0,.0708.6568,2.0816,2.0816,0,0,0,2.0053,1.7212c1.5083,0,2.2715-1.42,2.2715-3.3184,0-1.7393-.7451-3.2119-2.2358-3.2119a2.2068,2.2068,0,0,0-2.023,1.81,2.64,2.64,0,0,0-.0888.6387Z\"/><path d=\"M261.9125,4.6616h1.4908V15.3628h4.5961v1.26h-6.0869Z\"/><path d=\"M270.1806,12.5586c.0352,2.2715,1.2773,3.0523,2.6616,3.0523a5.0482,5.0482,0,0,0,2.0943-.4083l.2661,1.0826a6.2362,6.2362,0,0,1-2.5733.497c-2.4668,0-3.9043-1.7392-3.9043-4.33,0-2.6441,1.4375-4.5962,3.709-4.5962,2.4844,0,3.1944,2.2715,3.1944,3.9575a7.0326,7.0326,0,0,1-.0357.7451Zm4.01-1.0825c.018-1.2066-.479-2.52-1.899-2.52-1.3838,0-1.9873,1.4018-2.0937,2.52Z\"/><path d=\"M281.8012,16.6226l-.1245-1.0293h-.0532a2.7825,2.7825,0,0,1-2.36,1.2065,2.36,2.36,0,0,1-2.4487-2.4663c0-2.0942,1.81-3.1767,4.72-3.1592v-.2129c0-.8339-.2305-1.9873-1.792-1.97a3.6276,3.6276,0,0,0-1.9878.5859l-.3369-1.0292a5.0217,5.0217,0,0,1,2.5908-.6924c2.36,0,3.0166,1.5971,3.0166,3.39V14.6a14.2132,14.2132,0,0,0,.1245,2.023Zm-.2485-4.4009c-1.3843-.0181-3.23.23-3.23,1.9521a1.314,1.314,0,0,0,1.331,1.49,1.8733,1.8733,0,0,0,1.8457-1.3838,1.5819,1.5819,0,0,0,.0533-.4971Z\"/><path d=\"M285.3652,10.5713c0-.9229-.0357-1.7749-.0708-2.5376h1.3305l.0533,1.5791h.0537A2.4527,2.4527,0,0,1,288.95,7.856a2.6786,2.6786,0,0,1,.3907.0356V9.3467a1.8644,1.8644,0,0,0-.4615-.0357,2.0646,2.0646,0,0,0-1.9521,1.9346,3.2233,3.2233,0,0,0-.0708.7451v4.6319h-1.4907Z\"/><path d=\"M290.7407,10.3228c0-.9229-.0357-1.58-.0708-2.2891H292l.0713,1.2954h.0532a2.8837,2.8837,0,0,1,2.5733-1.4731c1.1889,0,2.7329.7632,2.7329,3.46v5.3062H295.94V11.4942c0-1.2779-.4263-2.396-1.7393-2.396a1.9934,1.9934,0,0,0-1.8633,1.5439,2.9592,2.9592,0,0,0-.0888.7456v5.2349h-1.5083Z\"/><path d=\"M301.456,5.6734a.894.894,0,0,1-.94.94.8716.8716,0,0,1-.8872-.94.9142.9142,0,1,1,1.8276,0Zm-1.668,10.9492V8.0337h1.5083v8.5889Z\"/><path d=\"M303.6733,10.3228c0-.9229-.0357-1.58-.0708-2.2891h1.33l.0713,1.2954h.0533a2.8835,2.8835,0,0,1,2.5732-1.4731c1.189,0,2.7329.7632,2.7329,3.46v5.3062H308.873V11.4942c0-1.2779-.4263-2.396-1.7393-2.396a1.9934,1.9934,0,0,0-1.8633,1.5439,2.9592,2.9592,0,0,0-.0888.7456v5.2349h-1.5083Z\"/><path d=\"M319.4819,8.0337c-.0357.603-.0708,1.3306-.0708,2.4487V15.416c0,2.0762-.3731,3.1587-1.1006,3.8687a4.0969,4.0969,0,0,1-2.8745.9936,4.9764,4.9764,0,0,1-2.5733-.6211l.355-1.1538a4.4965,4.4965,0,0,0,2.2534.586c1.4375,0,2.4668-.7808,2.4668-2.8926v-.9229h-.0356a2.65,2.65,0,0,1-2.4131,1.313c-1.9522,0-3.3189-1.7744-3.3189-4.2055,0-2.9815,1.7569-4.5254,3.5318-4.5254a2.5523,2.5523,0,0,1,2.36,1.3667h.0357l.0532-1.189ZM317.92,11.2813a2.8123,2.8123,0,0,0-.0712-.6748,2.0058,2.0058,0,0,0-1.9165-1.5435c-1.3311,0-2.2359,1.2773-2.2359,3.2471,0,1.8281.7984,3.1235,2.2183,3.1235a1.9791,1.9791,0,0,0,1.8989-1.5083,3.0974,3.0974,0,0,0,.1064-.7988Z\"/><line style=\"fill:#58595b\" x1=\"30.9665\" x2=\"30.9665\" y1=\"4.4557\" y2=\"27.3725\"/><path d=\"M39.5317,26.3086a1.7032,1.7032,0,0,0,.9038.273A.9567.9567,0,0,0,41.5,25.6084c0-.5254-.28-.8408-.8613-1.1069-.5884-.2451-1.1138-.6372-1.1138-1.3028a1.1968,1.1968,0,0,1,1.2886-1.1836,1.5059,1.5059,0,0,1,.84.21l-.1259.2729a1.3163,1.3163,0,0,0-.7422-.21.846.846,0,0,0-.9385.84c0,.5391.3008.7915.8965,1.0713.707.3506,1.0786.7217,1.0786,1.3731a1.2716,1.2716,0,0,1-1.4009,1.2885,1.85,1.85,0,0,1-1.0088-.2871Z\"/><path d=\"M45.2382,25.0967c0,1.2471-.7495,1.772-1.4287,1.772-.7495,0-1.373-.6231-1.373-1.73,0-1.1768.68-1.772,1.4218-1.772C44.65,23.3672,45.2382,24.0044,45.2382,25.0967Zm-2.4721.0283c0,.75.4062,1.4707,1.0644,1.4707s1.0786-.7212,1.0786-1.4917c0-.5884-.2734-1.4639-1.0649-1.4639C43.0742,23.64,42.7661,24.4526,42.7661,25.125Z\"/><path d=\"M46.0273,24.3755c0-.3081-.0137-.6445-.0279-.9385h.3013l.0142.6446h.0137a.9865.9865,0,0,1,.89-.7144.5785.5785,0,0,1,.1118.0068v.3223a.6493.6493,0,0,0-.126-.0073c-.455,0-.7631.4136-.8335.9106a2.2678,2.2678,0,0,0-.021.3081v1.8911h-.3222Z\"/><path d=\"M49.5566,26.7988l-.0425-.4482h-.021a1.08,1.08,0,0,1-.9385.5181.88.88,0,0,1-.9175-.9244c0-.7841.6656-1.2255,1.8492-1.2187v-.0981c0-.4063-.07-.9874-.7774-.9874a1.3173,1.3173,0,0,0-.7353.2242l-.0982-.2383a1.6034,1.6034,0,0,1,.8824-.2588c.8125,0,1.0507.5879,1.0507,1.2534v1.3936a5.7536,5.7536,0,0,0,.042.7846Zm-.07-1.8c-.5884-.0141-1.5059.07-1.5059.9034a.6064.6064,0,0,0,.6094.6933.8715.8715,0,0,0,.8686-.6655.7406.7406,0,0,0,.0279-.2031Z\"/><path d=\"M50.6894,23.437l.77,2.15c.0913.2588.168.5249.2241.7422h.0142c.063-.21.147-.4761.2309-.7563l.7217-2.1363h.3428l-.8472,2.3184a5.9218,5.9218,0,0,1-1.0576,2.1782,2.1343,2.1343,0,0,1-.56.3921l-.126-.273a1.7412,1.7412,0,0,0,.5605-.4135,2.848,2.848,0,0,0,.49-.7915.5422.5422,0,0,0,.042-.1607.501.501,0,0,0-.0352-.14l-1.1138-3.11Z\"/><path d=\"M55.22,26.7988l-.0425-.4482h-.021a1.08,1.08,0,0,1-.9385.5181.88.88,0,0,1-.9175-.9244c0-.7841.6656-1.2255,1.8492-1.2187v-.0981c0-.4063-.07-.9874-.7774-.9874a1.3173,1.3173,0,0,0-.7353.2242l-.0982-.2383a1.6033,1.6033,0,0,1,.8823-.2588c.8125,0,1.0508.5879,1.0508,1.2534v1.3936a5.7536,5.7536,0,0,0,.042.7846Zm-.07-1.8c-.5884-.0141-1.5059.07-1.5059.9034a.6064.6064,0,0,0,.6094.6933.8715.8715,0,0,0,.8686-.6655.7406.7406,0,0,0,.0279-.2031Z\"/><path d=\"M58.4179,25.1528l-.5185,1.646H57.57l1.5268-4.7207h.3154l1.5269,4.7207h-.33l-.5322-1.646Zm1.5689-.2729-.49-1.499a7.9831,7.9831,0,0,1-.2383-.91h-.021c-.0629.3081-.14.5879-.2309.9033L58.5087,24.88Z\"/><path d=\"M61.63,24.3755c0-.3081-.0137-.6445-.0278-.9385h.3012l.0142.6446h.0137a.9865.9865,0,0,1,.89-.7144.578.578,0,0,1,.1118.0068v.3223a.6482.6482,0,0,0-.1259-.0073c-.4551,0-.7632.4136-.8335.9106a2.2518,2.2518,0,0,0-.021.3081v1.8911H61.63Z\"/><path d=\"M63.9824,22.5054a.2576.2576,0,0,1-.2662.28.2536.2536,0,0,1-.2451-.28.2624.2624,0,0,1,.252-.28A.26.26,0,0,1,63.9824,22.5054Zm-.42,4.2934V23.437h.3223v3.3618Z\"/><path d=\"M66.5805,26.7988l-.042-.4482H66.517a1.08,1.08,0,0,1-.9384.5181.88.88,0,0,1-.9175-.9244c0-.7841.6655-1.2255,1.8491-1.2187v-.0981c0-.4063-.07-.9874-.7774-.9874a1.3175,1.3175,0,0,0-.7353.2242l-.0981-.2383a1.6028,1.6028,0,0,1,.8823-.2588c.8125,0,1.0508.5879,1.0508,1.2534v1.3936a5.7538,5.7538,0,0,0,.0419.7846Zm-.07-1.8c-.5884-.0141-1.5059.07-1.5059.9034a.6064.6064,0,0,0,.6094.6933.8712.8712,0,0,0,.8687-.6655.74.74,0,0,0,.0278-.2031Z\"/><path d=\"M67.706,26.3716a1.321,1.321,0,0,0,.6792.2173.6363.6363,0,0,0,.7217-.6377c0-.3428-.1822-.5532-.63-.7632-.4976-.231-.8057-.5112-.8057-.9316a.9042.9042,0,0,1,.9737-.8892,1.1913,1.1913,0,0,1,.6865.2031l-.1333.2661a.96.96,0,0,0-.5952-.1963.5632.5632,0,0,0-.6094.5674c0,.3291.1963.4761.6162.6866.4766.2168.8193.49.8193,1.0083a.9566.9566,0,0,1-1.0644.9594,1.3761,1.3761,0,0,1-.7773-.2241Z\"/><path d=\"M69.7993,27.6812a9.6153,9.6153,0,0,0,.3637-1.4849l.4273-.07a8.7994,8.7994,0,0,1-.5391,1.52Z\"/><path d=\"M74.7841,24.4526H73.0893v2.066h1.9048v.28H72.767V22.0781h2.1221v.28h-1.8v1.814h1.6948Z\"/><path d=\"M75.707,24.3755c0-.3081-.0137-.6445-.0279-.9385H75.98l.0142.6446h.0136a.9865.9865,0,0,1,.89-.7144.5785.5785,0,0,1,.1118.0068v.3223a.65.65,0,0,0-.126-.0073c-.4551,0-.7632.4136-.8335.9106a2.2678,2.2678,0,0,0-.021.3081v1.8911H75.707Z\"/><path d=\"M78.059,22.5054a.2576.2576,0,0,1-.2661.28.2535.2535,0,0,1-.2451-.28.2624.2624,0,0,1,.2519-.28A.26.26,0,0,1,78.059,22.5054Zm-.42,4.2934V23.437h.3223v3.3618Z\"/><path d=\"M81.0771,26.6655a1.81,1.81,0,0,1-.8472.1963,1.5145,1.5145,0,0,1-1.4712-1.7158,1.6208,1.6208,0,0,1,1.5762-1.7788,1.5149,1.5149,0,0,1,.7563.1821l-.1123.273a1.3787,1.3787,0,0,0-.686-.1753c-.8125,0-1.2046.7217-1.2046,1.4848,0,.89.49,1.45,1.19,1.45a1.5933,1.5933,0,0,0,.7144-.168Z\"/><path d=\"M86.8461,24.5508c-.0425-.7144-.0981-1.541-.0844-2.0732h-.0279c-.1469.5253-.3222,1.0717-.5674,1.7651l-.9033,2.5561H85.06l-.8477-2.48c-.2519-.7353-.434-1.3027-.56-1.8417h-.021c-.0073.5673-.042,1.3515-.0913,2.1362l-.126,2.185h-.3223l.3155-4.7207h.3711l.9106,2.6338c.2031.6162.3569,1.0713.4829,1.5547h.021c.1123-.4692.2661-.9106.4834-1.5478l.9248-2.6407H87l.2945,4.7207h-.3223Z\"/><path d=\"M89.9037,26.7988l-.0419-.4482H89.84a1.08,1.08,0,0,1-.9385.5181.88.88,0,0,1-.9175-.9244c0-.7841.6655-1.2255,1.8491-1.2187v-.0981c0-.4063-.07-.9874-.7773-.9874a1.3176,1.3176,0,0,0-.7354.2242l-.0981-.2383a1.6031,1.6031,0,0,1,.8823-.2588c.8125,0,1.0508.5879,1.0508,1.2534v1.3936a5.7376,5.7376,0,0,0,.042.7846Zm-.07-1.8c-.5883-.0141-1.5058.07-1.5058.9034a.6064.6064,0,0,0,.6093.6933.8712.8712,0,0,0,.8687-.6655.74.74,0,0,0,.0278-.2031Z\"/><path d=\"M91.162,21.8613h.3223v4.9375H91.162Z\"/><path d=\"M94.9648,21.8613v4.188c0,.2173.0137.5464.0278.75h-.2939l-.021-.5815h-.021a1.1046,1.1046,0,0,1-1.0508.6514c-.7212,0-1.2959-.6372-1.2959-1.7017,0-1.1484.63-1.8,1.352-1.8a1.0329,1.0329,0,0,1,.9595.5459h.0142V21.8613Zm-.3291,2.8853a2.1051,2.1051,0,0,0-.021-.2871A.9719.9719,0,0,0,93.69,23.64c-.6724,0-1.05.6656-1.05,1.4991,0,.7563.3218,1.4565,1.0224,1.4565a.9824.9824,0,0,0,.9454-.84,1.07,1.07,0,0,0,.0283-.2661Z\"/><path d=\"M98.5488,25.0967c0,1.2471-.7495,1.772-1.4287,1.772-.75,0-1.3731-.6231-1.3731-1.73,0-1.1768.68-1.772,1.4219-1.772C97.96,23.3672,98.5488,24.0044,98.5488,25.0967Zm-2.4722.0283c0,.75.4062,1.4707,1.0645,1.4707S98.22,25.8745,98.22,25.104c0-.5884-.2735-1.4639-1.065-1.4639C96.3847,23.64,96.0766,24.4526,96.0766,25.125Z\"/><path d=\"M99.3383,24.2354c0-.3433-.0137-.5391-.0278-.7984h.3013l.021.5464h.0141a1.1256,1.1256,0,0,1,1.0293-.6162c.3364,0,1.0508.189,1.0508,1.3237v2.1079h-.3223V24.7466c0-.5742-.1889-1.1-.8193-1.1a.9326.9326,0,0,0-.8828.75.966.966,0,0,0-.042.2944v2.1079h-.3223Z\"/><path d=\"M104.4,26.7988l-.0425-.4482h-.0209a1.08,1.08,0,0,1-.9385.5181.88.88,0,0,1-.9175-.9244c0-.7841.6655-1.2255,1.8491-1.2187v-.0981c0-.4063-.07-.9874-.7773-.9874a1.3176,1.3176,0,0,0-.7354.2242l-.0981-.2383a1.6031,1.6031,0,0,1,.8823-.2588c.8125,0,1.0508.5879,1.0508,1.2534v1.3936a5.7376,5.7376,0,0,0,.042.7846Zm-.07-1.8c-.5884-.0141-1.5058.07-1.5058.9034a.6064.6064,0,0,0,.6093.6933.8717.8717,0,0,0,.8687-.6655.74.74,0,0,0,.0278-.2031Z\"/><path d=\"M108.0688,21.8613v4.188c0,.2173.0137.5464.0278.75h-.2939l-.021-.5815h-.021a1.1046,1.1046,0,0,1-1.0508.6514c-.7212,0-1.2959-.6372-1.2959-1.7017,0-1.1484.63-1.8,1.3521-1.8a1.0329,1.0329,0,0,1,.9594.5459h.0142V21.8613Zm-.3291,2.8853a2.0309,2.0309,0,0,0-.0215-.2871.9713.9713,0,0,0-.9243-.8194c-.6724,0-1.05.6656-1.05,1.4991,0,.7563.3218,1.4565,1.0225,1.4565a.9824.9824,0,0,0,.9453-.84,1.07,1.07,0,0,0,.0283-.2661Z\"/><path d=\"M111.6528,25.0967c0,1.2471-.7495,1.772-1.4287,1.772-.75,0-1.3731-.6231-1.3731-1.73,0-1.1768.68-1.772,1.4219-1.772C111.0644,23.3672,111.6528,24.0044,111.6528,25.0967Zm-2.4722.0283c0,.75.4058,1.4707,1.0645,1.4707s1.0786-.7212,1.0786-1.4917c0-.5884-.2735-1.4639-1.0645-1.4639C109.4887,23.64,109.1806,24.4526,109.1806,25.125Z\"/><path d=\"M111.9316,27.6812a9.6038,9.6038,0,0,0,.3637-1.4849l.4273-.07a8.7994,8.7994,0,0,1-.5391,1.52Z\"/><path d=\"M115.768,22.0781h.3223v3.334c0,1.1-.5044,1.4566-1.1768,1.4566a1.5443,1.5443,0,0,1-.49-.084l.063-.273a1.0852,1.0852,0,0,0,.4131.0772c.5605,0,.8686-.2525.8686-1.2329Z\"/><path d=\"M117.1879,25.0547c0,1.1626.5532,1.5269,1.149,1.5269a1.5524,1.5524,0,0,0,.8051-.1748l.084.2519a1.8851,1.8851,0,0,1-.9311.2031c-.8965,0-1.4292-.7-1.4292-1.6948,0-1.1064.5673-1.8,1.3588-1.8.9737,0,1.1695.9663,1.1695,1.4844a1.7348,1.7348,0,0,1-.0069.2031Zm1.87-.2588c.0069-.5747-.2309-1.1558-.8754-1.1558-.6373,0-.9244.63-.98,1.1558Z\"/><path d=\"M121.83,26.7988l-.0425-.4482h-.021a1.08,1.08,0,0,1-.9384.5181.88.88,0,0,1-.9175-.9244c0-.7841.6655-1.2255,1.8491-1.2187v-.0981c0-.4063-.07-.9874-.7773-.9874a1.3176,1.3176,0,0,0-.7354.2242l-.0981-.2383a1.6028,1.6028,0,0,1,.8823-.2588c.8125,0,1.0508.5879,1.0508,1.2534v1.3936a5.7376,5.7376,0,0,0,.042.7846Zm-.07-1.8c-.5884-.0141-1.5059.07-1.5059.9034a.6064.6064,0,0,0,.6094.6933.8717.8717,0,0,0,.8687-.6655.74.74,0,0,0,.0278-.2031Z\"/><path d=\"M123.0888,24.2354c0-.3433-.0137-.5391-.0278-.7984h.3012l.021.5464h.0142a1.1256,1.1256,0,0,1,1.0293-.6162c.3364,0,1.0508.189,1.0508,1.3237v2.1079h-.3223V24.7466c0-.5742-.189-1.1-.8193-1.1a.9326.9326,0,0,0-.8828.75.966.966,0,0,0-.042.2944v2.1079h-.3223Z\"/><path d=\"M127.8422,24.7818v.28h-1.6528v-.28Z\"/><path d=\"M128.5839,22.0781h.3223v4.4478h1.8911v.2729h-2.2134Z\"/><path d=\"M133.6391,25.9722c0,.3222.0142.5815.0278.8266h-.2939l-.0283-.5254h-.0137a1.1574,1.1574,0,0,1-1.0156.5953c-.4624,0-1.03-.28-1.03-1.4078V23.437h.3222v1.9541c0,.6934.1822,1.1978.7847,1.1978a.9653.9653,0,0,0,.8755-.6514,1.4313,1.4313,0,0,0,.0488-.3574V23.437h.3223Z\"/><path d=\"M136.7465,26.6655a1.81,1.81,0,0,1-.8471.1963,1.5145,1.5145,0,0,1-1.4712-1.7158,1.6208,1.6208,0,0,1,1.5761-1.7788,1.5153,1.5153,0,0,1,.7564.1821l-.1123.273a1.3794,1.3794,0,0,0-.6861-.1753c-.8125,0-1.2045.7217-1.2045,1.4848,0,.89.49,1.45,1.19,1.45a1.5925,1.5925,0,0,0,.7143-.168Z\"/><path d=\"M138.88,22.1343a4.5191,4.5191,0,0,1,.9033-.0908,1.567,1.567,0,0,1,1.1416.3847,1.24,1.24,0,0,1,.3506.9317,1.3833,1.3833,0,0,1-.2944.9175,1.6368,1.6368,0,0,1-1.2954.54,2.0535,2.0535,0,0,1-.4834-.042v2.0239H138.88Zm.3223,2.3535a1.6865,1.6865,0,0,0,.49.0557,1.1055,1.1055,0,0,0,1.2539-1.1626c0-.6792-.4414-1.0576-1.1767-1.0576a2.5523,2.5523,0,0,0-.5674.0493Z\"/><path d=\"M143.5229,26.7988l-.042-.4482h-.0215a1.08,1.08,0,0,1-.9385.5181.88.88,0,0,1-.9174-.9244c0-.7841.6655-1.2255,1.8491-1.2187v-.0981c0-.4063-.07-.9874-.7774-.9874a1.3173,1.3173,0,0,0-.7353.2242l-.0982-.2383a1.6034,1.6034,0,0,1,.8824-.2588c.8125,0,1.0507.5879,1.0507,1.2534v1.3936a5.7536,5.7536,0,0,0,.042.7846Zm-.07-1.8c-.5884-.0141-1.5059.07-1.5059.9034a.6064.6064,0,0,0,.6094.6933.871.871,0,0,0,.8686-.6655.7406.7406,0,0,0,.0279-.2031Z\"/><path d=\"M144.7812,24.3755c0-.3081-.0137-.6445-.0278-.9385h.3012l.0142.6446h.0137a.9865.9865,0,0,1,.89-.7144.578.578,0,0,1,.1118.0068v.3223a.6488.6488,0,0,0-.126-.0073c-.455,0-.7631.4136-.8335.9106a2.268,2.268,0,0,0-.0209.3081v1.8911h-.3223Z\"/><path d=\"M149.144,25.0967c0,1.2471-.75,1.772-1.4287,1.772-.75,0-1.3731-.6231-1.3731-1.73,0-1.1768.68-1.772,1.4219-1.772C148.5556,23.3672,149.144,24.0044,149.144,25.0967Zm-2.4722.0283c0,.75.4058,1.4707,1.0645,1.4707s1.0786-.7212,1.0786-1.4917c0-.5884-.2735-1.4639-1.0645-1.4639C146.98,23.64,146.6718,24.4526,146.6718,25.125Z\"/><path d=\"M152.2656,25.9722c0,.3222.0141.5815.0278.8266h-.294l-.0283-.5254h-.0136a1.1575,1.1575,0,0,1-1.0157.5953c-.4624,0-1.03-.28-1.03-1.4078V23.437h.3223v1.9541c0,.6934.1821,1.1978.7847,1.1978a.9654.9654,0,0,0,.8755-.6514,1.4313,1.4313,0,0,0,.0488-.3574V23.437h.3223Z\"/><path d=\"M153.7485,22.4917v.9453h.8618v.2661h-.8618v2.22c0,.434.1333.6655.4482.6655a.9507.9507,0,0,0,.33-.0493l.042.2524a1.0879,1.0879,0,0,1-.42.07.6636.6636,0,0,1-.5391-.2241,1.2232,1.2232,0,0,1-.1894-.7915V23.7031h-.5181V23.437h.5181v-.8335Z\"/><path d=\"M155.2739,23.437l.77,2.15c.0913.2588.1679.5249.2241.7422h.0142c.0629-.21.1469-.4761.2309-.7563l.7217-2.1363h.3428l-.8472,2.3184a5.9218,5.9218,0,0,1-1.0576,2.1782,2.1326,2.1326,0,0,1-.5606.3921l-.1259-.273a1.7423,1.7423,0,0,0,.5605-.4135,2.85,2.85,0,0,0,.49-.7915.539.539,0,0,0,.042-.1607.5.5,0,0,0-.0351-.14l-1.1138-3.11Z\"/><path d=\"M160.9238,24.7818v.28h-1.6529v-.28Z\"/><path d=\"M165.88,26.6587a2.5779,2.5779,0,0,1-1.0854.2031c-1.0225,0-2.003-.6865-2.003-2.3882a2.1666,2.1666,0,0,1,2.1363-2.4585,2.0588,2.0588,0,0,1,.9311.1753l-.105.28a1.9019,1.9019,0,0,0-.84-.1753c-1.0366,0-1.7861.7354-1.7861,2.1641,0,1.394.6933,2.1221,1.7583,2.1221a2.1036,2.1036,0,0,0,.9033-.189Z\"/><path d=\"M166.6142,26.7988V22.0781h.3081l1.5762,2.6827c.3359.5952.602,1.0927.8193,1.583l.0137-.0074c-.0488-.7143-.0557-1.2324-.0557-1.9887v-2.27h.315v4.7207h-.3081l-1.5621-2.6894a14.8094,14.8094,0,0,1-.8261-1.583l-.0142.0073c.042.6231.042,1.1343.042,1.9961v2.269Z\"/><path d=\"M170.6528,22.1411a4.1559,4.1559,0,0,1,.9033-.0976,1.572,1.572,0,0,1,1.17.3779,1.216,1.216,0,0,1,.3223.8545,1.2421,1.2421,0,0,1-.8828,1.2329v.0137c.3784.1123.6025.4692.7143,1.0434a6.0279,6.0279,0,0,0,.3223,1.2329h-.336a6.8731,6.8731,0,0,1-.2871-1.1626c-.1333-.6792-.4135-.98-1.0087-1.0014h-.5953v2.164h-.3222Zm.3222,2.2344h.6026a1.0323,1.0323,0,0,0,1.1416-1.0435c0-.6933-.4483-1.0156-1.1768-1.0156a2.4091,2.4091,0,0,0-.5674.0562Z\"/><path d=\"M173.7607,26.3086a1.7032,1.7032,0,0,0,.9038.273.9567.9567,0,0,0,1.0644-.9732c0-.5254-.28-.8408-.8613-1.1069-.5884-.2451-1.1138-.6372-1.1138-1.3028a1.1968,1.1968,0,0,1,1.2886-1.1836,1.5066,1.5066,0,0,1,.84.21l-.126.2729a1.3163,1.3163,0,0,0-.7422-.21.846.846,0,0,0-.9385.84c0,.5391.3013.7915.8965,1.0713.707.3506,1.0786.7217,1.0786,1.3731a1.2716,1.2716,0,0,1-1.4009,1.2885,1.85,1.85,0,0,1-1.0088-.2871Z\"/><path d=\"M176.3574,27.0791l1.9892-5.0708h.3218l-2.0029,5.0708Z\"/><path d=\"M179.06,26.3086a1.7035,1.7035,0,0,0,.9038.273.9568.9568,0,0,0,1.0645-.9732c0-.5254-.28-.8408-.8614-1.1069-.5883-.2451-1.1137-.6372-1.1137-1.3028a1.1968,1.1968,0,0,1,1.2885-1.1836,1.5066,1.5066,0,0,1,.84.21l-.126.2729a1.3163,1.3163,0,0,0-.7422-.21.846.846,0,0,0-.9385.84c0,.5391.3013.7915.8965,1.0713.7071.3506,1.0786.7217,1.0786,1.3731a1.2715,1.2715,0,0,1-1.4008,1.2885,1.85,1.85,0,0,1-1.0088-.2871Z\"/><path d=\"M182.7138,25.1528l-.5185,1.646h-.3292l1.5269-4.7207h.3154l1.5269,4.7207h-.33l-.5322-1.646Zm1.5689-.2729-.49-1.499a7.9831,7.9831,0,0,1-.2383-.91h-.021c-.0629.3081-.14.5879-.2309.9033l-.4976,1.5059Z\"/><path d=\"M185.94,22.1411a4.1559,4.1559,0,0,1,.9033-.0976,1.5728,1.5728,0,0,1,1.17.3779,1.216,1.216,0,0,1,.3223.8545,1.2421,1.2421,0,0,1-.8828,1.2329v.0137c.3784.1123.6025.4692.7143,1.0434a6.0279,6.0279,0,0,0,.3223,1.2329h-.336a6.9252,6.9252,0,0,1-.2871-1.1626c-.1333-.6792-.4135-.98-1.0088-1.0014h-.5952v2.164H185.94Zm.3222,2.2344h.6021a1.0324,1.0324,0,0,0,1.1421-1.0435c0-.6933-.4483-1.0156-1.1768-1.0156a2.4091,2.4091,0,0,0-.5674.0562Z\"/><path d=\"M189.5107,22.0781v4.7207h-.3223V22.0781Z\"/><path d=\"M190.0424,27.0791l1.9893-5.0708h.3218l-2.003,5.0708Z\"/><path d=\"M192.8842,22.1411a5.6723,5.6723,0,0,1,1.0225-.0976,2.2048,2.2048,0,0,1,1.625.5459,2.3036,2.3036,0,0,1,.6094,1.7231,2.6818,2.6818,0,0,1-.5884,1.8491,2.3064,2.3064,0,0,1-1.7862.6724,7.2309,7.2309,0,0,1-.8823-.042Zm.3223,4.3848a5.0466,5.0466,0,0,0,.6025.0278c1.2676,0,1.9956-.7212,1.9956-2.2134a1.7565,1.7565,0,0,0-1.9116-2.017,4.1658,4.1658,0,0,0-.6865.0561Z\"/><path d=\"M198.9472,24.4526h-1.6948v2.066h1.9048v.28H196.93V22.0781h2.1221v.28h-1.8v1.814h1.6948Z\"/><path d=\"M200.9282,26.7988l-1.4219-4.7207h.3359l.7427,2.4654c.1958.6445.3853,1.289.5039,1.8423h.021a18.4779,18.4779,0,0,1,.5327-1.8423l.8052-2.4654h.3364l-1.5552,4.7207Z\"/><path d=\"M203.3212,22.0781h.3223v4.4478h1.8911v.2729h-2.2134Z\"/><path d=\"M209.28,24.4033c0,1.6953-.8891,2.4654-1.8628,2.4654-.9946,0-1.8-.833-1.8-2.3951,0-1.604.8335-2.4653,1.87-2.4653C208.4955,22.0083,209.28,22.8486,209.28,24.4033Zm-3.3266.0635c0,1.0151.49,2.1289,1.4917,2.1289,1.0088,0,1.499-1.0854,1.499-2.1782,0-.9663-.4414-2.1362-1.4917-2.1362C206.3945,22.2813,205.9531,23.416,205.9531,24.4668Z\"/><path d=\"M213.0805,26.6167a3.1243,3.1243,0,0,1-1.19.231,1.9629,1.9629,0,0,1-1.4781-.5743,2.5344,2.5344,0,0,1-.6162-1.8,2.1931,2.1931,0,0,1,2.2129-2.4443,2.35,2.35,0,0,1,.9595.189l-.105.2734a1.9674,1.9674,0,0,0-.8681-.1753c-1.086,0-1.8633.7354-1.8633,2.1153,0,1.4287.7353,2.1289,1.8071,2.1289a1.8881,1.8881,0,0,0,.8125-.1329V24.7256h-.98V24.46h1.31Z\"/><path d=\"M299.4156,24.5166a2.34,2.34,0,0,1-.3314,1.1954,2.3729,2.3729,0,0,1-.8906.8814,2.5139,2.5139,0,0,1-1.2323.3241,2.4774,2.4774,0,0,1-2.1333-1.2055,2.4051,2.4051,0,0,1,0-2.4009,2.4778,2.4778,0,0,1,2.1333-1.2056,2.514,2.514,0,0,1,1.2323.3242,2.4238,2.4238,0,0,1,1.222,2.0869Z\" style=\"fill:#fff;fill-rule:evenodd\"/><path d=\"M296.93,21.8421a2.7039,2.7039,0,0,1,1.9469.78,2.5739,2.5739,0,0,1,.59.8611,2.8679,2.8679,0,0,1,.1968,1.0333,2.5113,2.5113,0,0,1-.7767,1.864,2.7866,2.7866,0,0,1-1.9572.8,2.7706,2.7706,0,0,1-1.0356-.2026,2.8242,2.8242,0,0,1-.8906-.5875,2.6813,2.6813,0,0,1-.59-.8611,2.6075,2.6075,0,0,1-.2071-1.0131,2.62,2.62,0,0,1,.8077-1.8944,2.6158,2.6158,0,0,1,1.9158-.78Zm.01.4863a2.1413,2.1413,0,0,0-1.5741.6382,2.2164,2.2164,0,0,0-.4971.7092,2.1379,2.1379,0,0,0-.1657.8408,2.0414,2.0414,0,0,0,.1657.8206,2.11,2.11,0,0,0,.4971.7091,2.2379,2.2379,0,0,0,.7249.4762,2.1827,2.1827,0,0,0,.8492.162,2.22,2.22,0,0,0,.8491-.162,2.5124,2.5124,0,0,0,.7456-.4762,2.0468,2.0468,0,0,0,.6317-1.53,2.0674,2.0674,0,0,0-.1657-.8408,2.151,2.151,0,0,0-.4763-.7092,2.1985,2.1985,0,0,0-1.5844-.6382Zm-.0311,1.7425-.3728.1823a.3138.3138,0,0,0-.1346-.1621.3867.3867,0,0,0-.1657-.0506c-.2382,0-.3625.1519-.3625.4761a.5374.5374,0,0,0,.0932.3343.3058.3058,0,0,0,.2693.1317.3447.3447,0,0,0,.3417-.2229l.3314.1621a.7164.7164,0,0,1-.3.3039.7261.7261,0,0,1-.4142.1115.8075.8075,0,0,1-.59-.2128.85.85,0,0,1-.2278-.6078.8329.8329,0,0,1,.2278-.6078.7813.7813,0,0,1,.58-.2229.7608.7608,0,0,1,.7249.385Zm1.5741,0-.3625.1823a.3634.3634,0,0,0-.3107-.2127c-.2381,0-.3624.1519-.3624.4761a.5374.5374,0,0,0,.0932.3343.3055.3055,0,0,0,.2692.1317.3538.3538,0,0,0,.3418-.2229l.3417.1621a.8043.8043,0,0,1-.3107.3039.7257.7257,0,0,1-.4142.1115.7462.7462,0,0,1-.8077-.8206.7933.7933,0,0,1,.2278-.6078.86.86,0,0,1,1.2945.1621Z\" style=\"fill-rule:evenodd\"/><path d=\"M305.7222,24.5369a2.2338,2.2338,0,0,1-.321,1.1751,2.394,2.394,0,0,1-.88.8712,2.5353,2.5353,0,0,1-1.2116.3141,2.4653,2.4653,0,0,1-1.2012-.3141,2.4207,2.4207,0,0,1-.8906-.8712,2.3109,2.3109,0,0,1,0-2.35,2.4207,2.4207,0,0,1,.8906-.8712,2.4664,2.4664,0,0,1,1.2012-.3141,2.5364,2.5364,0,0,1,1.2116.3141,2.394,2.394,0,0,1,.88.8712,2.2339,2.2339,0,0,1,.321,1.1752Z\" style=\"fill:#fff;fill-rule:evenodd\"/><path d=\"M303.299,21.8421a2.6954,2.6954,0,0,1,1.9365.77,2.57,2.57,0,0,1,.7974,1.9045,2.4417,2.4417,0,0,1-.7871,1.864,2.6916,2.6916,0,0,1-1.9468.8,2.6591,2.6591,0,0,1-1.9262-.79,2.5074,2.5074,0,0,1-.8077-1.8742,2.5891,2.5891,0,0,1,.8077-1.9045,2.6884,2.6884,0,0,1,1.9262-.77Zm0,.4863a2.1579,2.1579,0,0,0-1.5741.6382,2.1228,2.1228,0,0,0-.6628,1.55,2.0626,2.0626,0,0,0,.6628,1.53,2.1609,2.1609,0,0,0,1.5741.6484,2.2346,2.2346,0,0,0,1.5947-.6585,1.9734,1.9734,0,0,0,.6421-1.53,2.0814,2.0814,0,0,0-.6524-1.54,2.1817,2.1817,0,0,0-1.5844-.6382Zm.7352,1.52v1.0941h-.3107v1.2967h-.8491V24.9421h-.3107V23.848a.1659.1659,0,0,1,.0518-.1216.1732.1732,0,0,1,.1242-.0506h1.1185a.1732.1732,0,0,1,.1242.0506.1659.1659,0,0,1,.0518.1216Zm-1.1184-.6889a.3832.3832,0,1,1,.3832.3748.3364.3364,0,0,1-.3832-.3748Z\" style=\"fill-rule:evenodd\"/><path d=\"M312.0909,24.5065a2.4053,2.4053,0,0,1-.3313,1.2055,2.43,2.43,0,0,1-.9113.8814,2.4875,2.4875,0,0,1-3.3656-.8814,2.4044,2.4044,0,0,1-.3314-1.2055,2.35,2.35,0,0,1,.3314-1.2056,2.4947,2.4947,0,0,1,3.3656-.8813,2.4294,2.4294,0,0,1,.9113.8813,2.3506,2.3506,0,0,1,.3313,1.2056Z\" style=\"fill:#fff;fill-rule:evenodd\"/><path d=\"M311.6042,22.6121a2.8071,2.8071,0,0,0-3.8627,0,2.59,2.59,0,0,0-.8077,1.9045,2.54,2.54,0,0,0,.8077,1.8742,2.6593,2.6593,0,0,0,1.9262.79,2.7648,2.7648,0,0,0,1.9572-.79,2.5238,2.5238,0,0,0,.7767-1.8742,2.57,2.57,0,0,0-.7974-1.9045Zm-.3417,3.4241a2.2174,2.2174,0,0,1-1.5948.6585,2.1844,2.1844,0,0,1-1.5741-.6484,2.0684,2.0684,0,0,1-.6627-1.54,2.313,2.313,0,0,1,.1139-.7092l.7249.3141h-.0518v.3242h.2589c0,.04-.01.081-.01.1317v.0709h-.2485v.3242h.3a1.2447,1.2447,0,0,0,.2589.5774,1.3542,1.3542,0,0,0,1.1081.5065,1.6053,1.6053,0,0,0,.7145-.1621l-.1035-.4964a1.5167,1.5167,0,0,1-.5282.1115.8223.8223,0,0,1-.59-.2229.8116.8116,0,0,1-.1449-.314h.9941l1.4084.6078a1.7712,1.7712,0,0,1-.3728.466Zm-1.7708-1.398h0Zm.8491-.2026h.0414v-.3242h-.7766l-.3107-.1317a.38.38,0,0,1,.0932-.152.6984.6984,0,0,1,.5592-.2431,1.5282,1.5282,0,0,1,.5074.1013l.1347-.5065a1.8267,1.8267,0,0,0-.6939-.1317,1.4134,1.4134,0,0,0-1.0563.4558c-.0517.0608-.1035.1419-.1553.2128l-.8906-.385a2.03,2.03,0,0,1,.3-.3647,2.1673,2.1673,0,0,1,1.5741-.6483,2.1905,2.1905,0,0,1,1.5844.6483,2.0557,2.0557,0,0,1,.6524,1.55,2.5764,2.5764,0,0,1-.0621.5673l-1.5016-.6483Z\" style=\"fill-rule:evenodd\"/><path d=\"M318.5115,24.4963a2.3507,2.3507,0,0,1-.3314,1.2056,2.4563,2.4563,0,0,1-.9113.8915,2.505,2.505,0,0,1-2.4647,0,2.4563,2.4563,0,0,1-.9113-.8915,2.3507,2.3507,0,0,1-.3314-1.2056,2.3868,2.3868,0,0,1,1.2427-2.097,2.5043,2.5043,0,0,1,2.4647,0,2.3868,2.3868,0,0,1,1.2427,2.097Z\" style=\"fill:#fff;fill-rule:evenodd\"/><path d=\"M316.0261,21.8421a2.6629,2.6629,0,0,1,1.9365.78,2.6493,2.6493,0,0,1,.0207,3.7686,2.73,2.73,0,0,1-1.9572.79,2.6527,2.6527,0,0,1-1.9158-.79,2.5074,2.5074,0,0,1-.8077-1.8742,2.567,2.567,0,0,1,.8077-1.8944,2.6494,2.6494,0,0,1,1.9158-.78Zm.01.4863A2.2213,2.2213,0,0,0,313.8,24.5166a2.0469,2.0469,0,0,0,.6628,1.53,2.1443,2.1443,0,0,0,1.5741.6484,2.194,2.194,0,0,0,1.5844-.6585,1.9817,1.9817,0,0,0,.642-1.52,2.0712,2.0712,0,0,0-.6524-1.55,2.1413,2.1413,0,0,0-1.574-.6382Zm1.0252,1.55v.466h-1.978v-.466Zm0,.8611v.4559h-1.978V24.74Z\" style=\"fill-rule:evenodd\"/><line style=\"fill:none;stroke:#e6e7e8;stroke-miterlimit:10;stroke-width:0.25px\" x1=\"0.9591\" x2=\"318.4111\" y1=\"36.1069\" y2=\"36.1069\"/></g></g></svg>"
],
"text/plain": [
"<IPython.core.display.SVG object>"
]
},
"metadata": {},
"output_type": "display_data"
"from IPython.display import Image, SVG\n",
"display(SVG(filename='../fidle/img/00-Fidle-header-01.svg'))"
{
"cell_type": "markdown",
"metadata": {},
"source": [
]
},
{
"cell_type": "code",
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
{
"data": {
"text/html": [
"<style>\n",
"\n",
"div.warn { \n",
" background-color: #fcf2f2;\n",
" border-color: #dFb5b4;\n",
" border-left: 5px solid #dfb5b4;\n",
" padding: 0.5em;\n",
" font-weight: bold;\n",
" font-size: 1.1em;;\n",
" }\n",
"\n",
"\n",
"\n",
"div.nota { \n",
" background-color: #DAFFDE;\n",
" border-left: 5px solid #92CC99;\n",
" padding: 0.5em;\n",
" }\n",
"\n",
"\n",
"\n",
"</style>\n",
"\n"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"FIDLE 2020 - Practical Work Module\n",
"Version : 0.2.9\n",
"Run time : Monday 17 February 2020, 22:08:38\n",
"TensorFlow version : 2.0.0\n",
"Keras version : 2.2.4-tf\n"
"source": [
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import pandas as pd\n",
"\n",
"from IPython.display import display, Markdown\n",
"from importlib import reload\n",
"\n",
"sys.path.append('..')\n",
"import fidle.pwk as ooo\n",
"\n",
"ooo.init()\n",
"os.makedirs('./run/models', mode=0o750, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Boston housing is a famous historic dataset, so we can get it directly from [Keras datasets](https://www.tensorflow.org/api_docs/python/tf/keras/datasets) "
]
},
{
"metadata": {},
"source": [
"(x_train, y_train), (x_test, y_test) = keras.datasets.boston_housing.load_data(test_split=0.2, seed=113)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2.2 - Option 2 : From a csv file\n",
"More fun !"
]
},
{
"cell_type": "code",
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >crim</th> <th class=\"col_heading level0 col1\" >zn</th> <th class=\"col_heading level0 col2\" >indus</th> <th class=\"col_heading level0 col3\" >chas</th> <th class=\"col_heading level0 col4\" >nox</th> <th class=\"col_heading level0 col5\" >rm</th> <th class=\"col_heading level0 col6\" >age</th> <th class=\"col_heading level0 col7\" >dis</th> <th class=\"col_heading level0 col8\" >rad</th> <th class=\"col_heading level0 col9\" >tax</th> <th class=\"col_heading level0 col10\" >ptratio</th> <th class=\"col_heading level0 col11\" >b</th> <th class=\"col_heading level0 col12\" >lstat</th> <th class=\"col_heading level0 col13\" >medv</th> </tr></thead><tbody>\n",
" <th id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col0\" class=\"data row0 col0\" >0.01</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col1\" class=\"data row0 col1\" >18.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col2\" class=\"data row0 col2\" >2.31</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col4\" class=\"data row0 col4\" >0.54</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col5\" class=\"data row0 col5\" >6.58</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col6\" class=\"data row0 col6\" >65.20</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col7\" class=\"data row0 col7\" >4.09</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col8\" class=\"data row0 col8\" >1.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col9\" class=\"data row0 col9\" >296.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col10\" class=\"data row0 col10\" >15.30</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col11\" class=\"data row0 col11\" >396.90</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col12\" class=\"data row0 col12\" >4.98</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row0_col13\" class=\"data row0 col13\" >24.00</td>\n",
" <th id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col0\" class=\"data row1 col0\" >0.03</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col2\" class=\"data row1 col2\" >7.07</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col4\" class=\"data row1 col4\" >0.47</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col5\" class=\"data row1 col5\" >6.42</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col6\" class=\"data row1 col6\" >78.90</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col7\" class=\"data row1 col7\" >4.97</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col8\" class=\"data row1 col8\" >2.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col9\" class=\"data row1 col9\" >242.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col10\" class=\"data row1 col10\" >17.80</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col11\" class=\"data row1 col11\" >396.90</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col12\" class=\"data row1 col12\" >9.14</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row1_col13\" class=\"data row1 col13\" >21.60</td>\n",
" <th id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col0\" class=\"data row2 col0\" >0.03</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col1\" class=\"data row2 col1\" >0.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col2\" class=\"data row2 col2\" >7.07</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col3\" class=\"data row2 col3\" >0.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col4\" class=\"data row2 col4\" >0.47</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col5\" class=\"data row2 col5\" >7.18</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col6\" class=\"data row2 col6\" >61.10</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col7\" class=\"data row2 col7\" >4.97</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col8\" class=\"data row2 col8\" >2.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col9\" class=\"data row2 col9\" >242.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col10\" class=\"data row2 col10\" >17.80</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col11\" class=\"data row2 col11\" >392.83</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col12\" class=\"data row2 col12\" >4.03</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row2_col13\" class=\"data row2 col13\" >34.70</td>\n",
" <th id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col0\" class=\"data row3 col0\" >0.03</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col2\" class=\"data row3 col2\" >2.18</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col4\" class=\"data row3 col4\" >0.46</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col5\" class=\"data row3 col5\" >7.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col6\" class=\"data row3 col6\" >45.80</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col7\" class=\"data row3 col7\" >6.06</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col8\" class=\"data row3 col8\" >3.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col9\" class=\"data row3 col9\" >222.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col10\" class=\"data row3 col10\" >18.70</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col11\" class=\"data row3 col11\" >394.63</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col12\" class=\"data row3 col12\" >2.94</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row3_col13\" class=\"data row3 col13\" >33.40</td>\n",
" <th id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col2\" class=\"data row4 col2\" >2.18</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col4\" class=\"data row4 col4\" >0.46</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col5\" class=\"data row4 col5\" >7.15</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col6\" class=\"data row4 col6\" >54.20</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col7\" class=\"data row4 col7\" >6.06</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col8\" class=\"data row4 col8\" >3.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col9\" class=\"data row4 col9\" >222.00</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col10\" class=\"data row4 col10\" >18.70</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col11\" class=\"data row4 col11\" >396.90</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col12\" class=\"data row4 col12\" >5.33</td>\n",
" <td id=\"T_aac3e7e8_51c9_11ea_b50a_1f46721d93b7row4_col13\" class=\"data row4 col13\" >36.20</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f953611fb50>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Données manquantes : 0 Shape is : (506, 14)\n"
]
}
],
"source": [
"data = pd.read_csv('./data/BostonHousing.csv', header=0)\n",
"\n",
"display(data.head(5).style.format(\"{0:.2f}\"))\n",
"print('Données manquantes : ',data.isna().sum().sum(), ' Shape is : ', data.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 3 - Preparing the data\n",
"### 3.1 - Split data\n",
"We will use 70% of the data for training and 30% for validation. \n",
"x will be input data and y the expected output"
]
},
{
"cell_type": "code",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Original data shape was : (506, 14)\n",
"x_train : (354, 13) y_train : (354,)\n",
"x_test : (152, 13) y_test : (152,)\n"
]
}
],
"source": [
"# ---- Split => train, test\n",
"#\n",
"data_train = data.sample(frac=0.7, axis=0)\n",
"data_test = data.drop(data_train.index)\n",
"\n",
"# ---- Split => x,y (medv is price)\n",
"#\n",
"x_train = data_train.drop('medv', axis=1)\n",
"y_train = data_train['medv']\n",
"x_test = data_test.drop('medv', axis=1)\n",
"y_test = data_test['medv']\n",
"\n",
"print('Original data shape was : ',data.shape)\n",
"print('x_train : ',x_train.shape, 'y_train : ',y_train.shape)\n",
"print('x_test : ',x_test.shape, 'y_test : ',y_test.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Note :** \n",
" - All input data must be normalized, train and test. \n",
" - To do this we will **subtract the mean** and **divide by the standard deviation**. \n",
" - But test data should not be used in any way, even for normalization. \n",
" - The mean and the standard deviation will therefore only be calculated with the train data."
]
},
{
"cell_type": "code",
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7\" ><caption>Before normalization :</caption><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >crim</th> <th class=\"col_heading level0 col1\" >zn</th> <th class=\"col_heading level0 col2\" >indus</th> <th class=\"col_heading level0 col3\" >chas</th> <th class=\"col_heading level0 col4\" >nox</th> <th class=\"col_heading level0 col5\" >rm</th> <th class=\"col_heading level0 col6\" >age</th> <th class=\"col_heading level0 col7\" >dis</th> <th class=\"col_heading level0 col8\" >rad</th> <th class=\"col_heading level0 col9\" >tax</th> <th class=\"col_heading level0 col10\" >ptratio</th> <th class=\"col_heading level0 col11\" >b</th> <th class=\"col_heading level0 col12\" >lstat</th> </tr></thead><tbody>\n",
" <th id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" <th id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col0\" class=\"data row1 col0\" >3.72</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col1\" class=\"data row1 col1\" >11.78</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col2\" class=\"data row1 col2\" >11.07</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col3\" class=\"data row1 col3\" >0.06</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col4\" class=\"data row1 col4\" >0.55</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col5\" class=\"data row1 col5\" >6.30</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col6\" class=\"data row1 col6\" >69.19</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col7\" class=\"data row1 col7\" >3.78</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col8\" class=\"data row1 col8\" >9.85</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col9\" class=\"data row1 col9\" >412.77</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col10\" class=\"data row1 col10\" >18.47</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col11\" class=\"data row1 col11\" >357.65</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row1_col12\" class=\"data row1 col12\" >12.59</td>\n",
" <th id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col0\" class=\"data row2 col0\" >8.30</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col1\" class=\"data row2 col1\" >23.59</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col2\" class=\"data row2 col2\" >6.78</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col3\" class=\"data row2 col3\" >0.24</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col4\" class=\"data row2 col4\" >0.11</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col5\" class=\"data row2 col5\" >0.71</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col6\" class=\"data row2 col6\" >27.24</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col7\" class=\"data row2 col7\" >2.08</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col8\" class=\"data row2 col8\" >8.88</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col9\" class=\"data row2 col9\" >171.88</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col10\" class=\"data row2 col10\" >2.17</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col11\" class=\"data row2 col11\" >90.85</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row2_col12\" class=\"data row2 col12\" >6.82</td>\n",
" <th id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col0\" class=\"data row3 col0\" >0.01</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col2\" class=\"data row3 col2\" >0.74</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col4\" class=\"data row3 col4\" >0.39</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col5\" class=\"data row3 col5\" >3.86</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col6\" class=\"data row3 col6\" >6.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col7\" class=\"data row3 col7\" >1.14</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col8\" class=\"data row3 col8\" >1.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col9\" class=\"data row3 col9\" >188.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col10\" class=\"data row3 col10\" >12.60</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col11\" class=\"data row3 col11\" >0.32</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row3_col12\" class=\"data row3 col12\" >1.73</td>\n",
" <th id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col0\" class=\"data row4 col0\" >0.08</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col2\" class=\"data row4 col2\" >5.15</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col4\" class=\"data row4 col4\" >0.45</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col5\" class=\"data row4 col5\" >5.89</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col6\" class=\"data row4 col6\" >47.45</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col7\" class=\"data row4 col7\" >2.11</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col8\" class=\"data row4 col8\" >4.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col9\" class=\"data row4 col9\" >279.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col10\" class=\"data row4 col10\" >17.40</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col11\" class=\"data row4 col11\" >375.91</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row4_col12\" class=\"data row4 col12\" >7.28</td>\n",
" <th id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col0\" class=\"data row5 col0\" >0.25</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col1\" class=\"data row5 col1\" >0.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col2\" class=\"data row5 col2\" >9.79</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col3\" class=\"data row5 col3\" >0.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col4\" class=\"data row5 col4\" >0.54</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col5\" class=\"data row5 col5\" >6.23</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col6\" class=\"data row5 col6\" >77.95</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col7\" class=\"data row5 col7\" >3.13</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col8\" class=\"data row5 col8\" >5.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col9\" class=\"data row5 col9\" >332.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col10\" class=\"data row5 col10\" >18.90</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col11\" class=\"data row5 col11\" >392.22</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row5_col12\" class=\"data row5 col12\" >11.39</td>\n",
" <th id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col0\" class=\"data row6 col0\" >3.85</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col1\" class=\"data row6 col1\" >19.50</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col2\" class=\"data row6 col2\" >18.10</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col3\" class=\"data row6 col3\" >0.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col4\" class=\"data row6 col4\" >0.62</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col5\" class=\"data row6 col5\" >6.64</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col6\" class=\"data row6 col6\" >93.97</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col7\" class=\"data row6 col7\" >5.08</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col8\" class=\"data row6 col8\" >24.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col9\" class=\"data row6 col9\" >666.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col10\" class=\"data row6 col10\" >20.20</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col11\" class=\"data row6 col11\" >396.90</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row6_col12\" class=\"data row6 col12\" >16.57</td>\n",
" <th id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col0\" class=\"data row7 col0\" >73.53</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col1\" class=\"data row7 col1\" >100.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col2\" class=\"data row7 col2\" >27.74</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col3\" class=\"data row7 col3\" >1.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col4\" class=\"data row7 col4\" >0.87</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col5\" class=\"data row7 col5\" >8.78</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col6\" class=\"data row7 col6\" >100.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col7\" class=\"data row7 col7\" >10.71</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col8\" class=\"data row7 col8\" >24.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col9\" class=\"data row7 col9\" >711.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col10\" class=\"data row7 col10\" >22.00</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col11\" class=\"data row7 col11\" >396.90</td>\n",
" <td id=\"T_aaccf306_51c9_11ea_b50a_1f46721d93b7row7_col12\" class=\"data row7 col12\" >37.97</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f953611f5d0>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7\" ><caption>After normalization :</caption><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >crim</th> <th class=\"col_heading level0 col1\" >zn</th> <th class=\"col_heading level0 col2\" >indus</th> <th class=\"col_heading level0 col3\" >chas</th> <th class=\"col_heading level0 col4\" >nox</th> <th class=\"col_heading level0 col5\" >rm</th> <th class=\"col_heading level0 col6\" >age</th> <th class=\"col_heading level0 col7\" >dis</th> <th class=\"col_heading level0 col8\" >rad</th> <th class=\"col_heading level0 col9\" >tax</th> <th class=\"col_heading level0 col10\" >ptratio</th> <th class=\"col_heading level0 col11\" >b</th> <th class=\"col_heading level0 col12\" >lstat</th> </tr></thead><tbody>\n",
" <th id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" <th id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col0\" class=\"data row1 col0\" >0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col1\" class=\"data row1 col1\" >-0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col2\" class=\"data row1 col2\" >0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col3\" class=\"data row1 col3\" >-0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col6\" class=\"data row1 col6\" >0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col7\" class=\"data row1 col7\" >0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col8\" class=\"data row1 col8\" >0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col10\" class=\"data row1 col10\" >0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col11\" class=\"data row1 col11\" >0.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row1_col12\" class=\"data row1 col12\" >-0.00</td>\n",
" <th id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col0\" class=\"data row2 col0\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col1\" class=\"data row2 col1\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col2\" class=\"data row2 col2\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col3\" class=\"data row2 col3\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col4\" class=\"data row2 col4\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col5\" class=\"data row2 col5\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col6\" class=\"data row2 col6\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col7\" class=\"data row2 col7\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col8\" class=\"data row2 col8\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col9\" class=\"data row2 col9\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col10\" class=\"data row2 col10\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col11\" class=\"data row2 col11\" >1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row2_col12\" class=\"data row2 col12\" >1.00</td>\n",
" <th id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col0\" class=\"data row3 col0\" >-0.45</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col1\" class=\"data row3 col1\" >-0.50</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col2\" class=\"data row3 col2\" >-1.52</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col3\" class=\"data row3 col3\" >-0.26</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col4\" class=\"data row3 col4\" >-1.49</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col5\" class=\"data row3 col5\" >-3.44</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col6\" class=\"data row3 col6\" >-2.32</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col7\" class=\"data row3 col7\" >-1.27</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col8\" class=\"data row3 col8\" >-1.00</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col9\" class=\"data row3 col9\" >-1.31</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col10\" class=\"data row3 col10\" >-2.70</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col11\" class=\"data row3 col11\" >-3.93</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row3_col12\" class=\"data row3 col12\" >-1.59</td>\n",
" <th id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col0\" class=\"data row4 col0\" >-0.44</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col1\" class=\"data row4 col1\" >-0.50</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col2\" class=\"data row4 col2\" >-0.87</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col3\" class=\"data row4 col3\" >-0.26</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col4\" class=\"data row4 col4\" >-0.88</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col5\" class=\"data row4 col5\" >-0.58</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col6\" class=\"data row4 col6\" >-0.80</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col7\" class=\"data row4 col7\" >-0.81</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col8\" class=\"data row4 col8\" >-0.66</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col9\" class=\"data row4 col9\" >-0.78</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col10\" class=\"data row4 col10\" >-0.49</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col11\" class=\"data row4 col11\" >0.20</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row4_col12\" class=\"data row4 col12\" >-0.78</td>\n",
" <th id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col0\" class=\"data row5 col0\" >-0.42</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col1\" class=\"data row5 col1\" >-0.50</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col2\" class=\"data row5 col2\" >-0.19</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col3\" class=\"data row5 col3\" >-0.26</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col4\" class=\"data row5 col4\" >-0.13</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col5\" class=\"data row5 col5\" >-0.10</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col6\" class=\"data row5 col6\" >0.32</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col7\" class=\"data row5 col7\" >-0.31</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col8\" class=\"data row5 col8\" >-0.55</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col9\" class=\"data row5 col9\" >-0.47</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col10\" class=\"data row5 col10\" >0.20</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col11\" class=\"data row5 col11\" >0.38</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row5_col12\" class=\"data row5 col12\" >-0.18</td>\n",
" <th id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col0\" class=\"data row6 col0\" >0.02</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col1\" class=\"data row6 col1\" >0.33</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col2\" class=\"data row6 col2\" >1.04</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col3\" class=\"data row6 col3\" >-0.26</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col4\" class=\"data row6 col4\" >0.63</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col5\" class=\"data row6 col5\" >0.48</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col6\" class=\"data row6 col6\" >0.91</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col7\" class=\"data row6 col7\" >0.63</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col8\" class=\"data row6 col8\" >1.59</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col9\" class=\"data row6 col9\" >1.47</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col10\" class=\"data row6 col10\" >0.80</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col11\" class=\"data row6 col11\" >0.43</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row6_col12\" class=\"data row6 col12\" >0.58</td>\n",
" <th id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col0\" class=\"data row7 col0\" >8.41</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col1\" class=\"data row7 col1\" >3.74</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col2\" class=\"data row7 col2\" >2.46</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col3\" class=\"data row7 col3\" >3.88</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col4\" class=\"data row7 col4\" >2.82</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col5\" class=\"data row7 col5\" >3.50</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col6\" class=\"data row7 col6\" >1.13</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col7\" class=\"data row7 col7\" >3.34</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col8\" class=\"data row7 col8\" >1.59</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col9\" class=\"data row7 col9\" >1.74</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col10\" class=\"data row7 col10\" >1.63</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col11\" class=\"data row7 col11\" >0.43</td>\n",
" <td id=\"T_aadc40b8_51c9_11ea_b50a_1f46721d93b7row7_col12\" class=\"data row7 col12\" >3.72</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f952e97ff50>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"Before normalization :\"))\n",
"\n",
"mean = x_train.mean()\n",
"std = x_train.std()\n",
"x_train = (x_train - mean) / std\n",
"x_test = (x_test - mean) / std\n",
"\n",
"display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"After normalization :\"))\n",
"\n",
"x_train, y_train = np.array(x_train), np.array(y_train)\n",
"x_test, y_test = np.array(x_test), np.array(y_test)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"About informations about : \n",
" - [Optimizer](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers)\n",
" - [Activation](https://www.tensorflow.org/api_docs/python/tf/keras/activations)\n",
" - [Loss](https://www.tensorflow.org/api_docs/python/tf/keras/losses)\n",
" - [Metrics](https://www.tensorflow.org/api_docs/python/tf/keras/metrics)"
]
},
{
"cell_type": "code",
"metadata": {},
"outputs": [],
"source": [
" def get_model_v1(shape):\n",
" \n",
" model = keras.models.Sequential()\n",
" model.add(keras.layers.Input(shape, name=\"InputLayer\"))\n",
" model.add(keras.layers.Dense(64, activation='relu', name='Dense_n1'))\n",
" model.add(keras.layers.Dense(64, activation='relu', name='Dense_n2'))\n",
" model.add(keras.layers.Dense(1, name='Output'))\n",
" \n",
" model.compile(optimizer = 'rmsprop',\n",
" loss = 'mse',\n",
" metrics = ['mae', 'mse'] )\n",
" return model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 5 - Train the model\n",
"### 5.1 - Get it"
]
},
{
"cell_type": "code",
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: \"sequential\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"Dense_n1 (Dense) (None, 64) 896 \n",
"_________________________________________________________________\n",
"Dense_n2 (Dense) (None, 64) 4160 \n",
"_________________________________________________________________\n",
"Output (Dense) (None, 1) 65 \n",
"=================================================================\n",
"Total params: 5,121\n",
"Trainable params: 5,121\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<IPython.core.display.Image object>"
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model=get_model_v1( (13,) )\n",
"\n",
"model.summary()\n",
"keras.utils.plot_model( model, to_file='./run/model.png', show_shapes=True, show_layer_names=True, dpi=96)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
]
},
{
"cell_type": "code",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train on 354 samples, validate on 152 samples\n",
"Epoch 1/100\n",
"354/354 [==============================] - 1s 2ms/sample - loss: 414.5603 - mae: 18.2577 - mse: 414.5602 - val_loss: 266.3728 - val_mae: 13.9913 - val_mse: 266.3728\n",
"354/354 [==============================] - 0s 190us/sample - loss: 165.4507 - mae: 10.4618 - mse: 165.4507 - val_loss: 74.4125 - val_mae: 6.0372 - val_mse: 74.4125\n",
"354/354 [==============================] - 0s 187us/sample - loss: 54.2313 - mae: 5.3763 - mse: 54.2313 - val_loss: 47.0203 - val_mae: 4.7399 - val_mse: 47.0203\n",
"354/354 [==============================] - 0s 166us/sample - loss: 32.3303 - mae: 4.2632 - mse: 32.3303 - val_loss: 38.0120 - val_mae: 4.2484 - val_mse: 38.0120\n",
"354/354 [==============================] - 0s 153us/sample - loss: 25.3763 - mae: 3.7745 - mse: 25.3763 - val_loss: 32.4707 - val_mae: 3.8465 - val_mse: 32.4707\n",
"354/354 [==============================] - 0s 153us/sample - loss: 22.2331 - mae: 3.4720 - mse: 22.2331 - val_loss: 29.6142 - val_mae: 3.4844 - val_mse: 29.6142\n",
"354/354 [==============================] - 0s 154us/sample - loss: 19.7834 - mae: 3.2245 - mse: 19.7834 - val_loss: 27.1649 - val_mae: 3.5465 - val_mse: 27.1649\n",
"354/354 [==============================] - 0s 155us/sample - loss: 18.0991 - mae: 3.0669 - mse: 18.0991 - val_loss: 26.0093 - val_mae: 3.5617 - val_mse: 26.0093\n",
"354/354 [==============================] - 0s 161us/sample - loss: 16.9247 - mae: 2.9184 - mse: 16.9247 - val_loss: 23.2549 - val_mae: 3.3243 - val_mse: 23.2549\n",
"354/354 [==============================] - 0s 150us/sample - loss: 16.0827 - mae: 2.8116 - mse: 16.0827 - val_loss: 21.1365 - val_mae: 3.0248 - val_mse: 21.1365\n",
"354/354 [==============================] - 0s 170us/sample - loss: 15.0334 - mae: 2.7214 - mse: 15.0334 - val_loss: 20.0163 - val_mae: 2.9800 - val_mse: 20.0163\n",
"354/354 [==============================] - 0s 180us/sample - loss: 14.4011 - mae: 2.6949 - mse: 14.4011 - val_loss: 19.8958 - val_mae: 2.9262 - val_mse: 19.8958\n",
"354/354 [==============================] - 0s 184us/sample - loss: 13.9168 - mae: 2.5674 - mse: 13.9168 - val_loss: 18.5729 - val_mae: 2.7302 - val_mse: 18.5729\n",
"354/354 [==============================] - 0s 161us/sample - loss: 13.5575 - mae: 2.5442 - mse: 13.5575 - val_loss: 17.8812 - val_mae: 2.6748 - val_mse: 17.8812\n",
"354/354 [==============================] - 0s 166us/sample - loss: 12.8689 - mae: 2.4779 - mse: 12.8689 - val_loss: 18.9649 - val_mae: 2.7560 - val_mse: 18.9649\n",
"354/354 [==============================] - 0s 159us/sample - loss: 12.6470 - mae: 2.4670 - mse: 12.6470 - val_loss: 16.5834 - val_mae: 2.6016 - val_mse: 16.5834\n",
"354/354 [==============================] - 0s 159us/sample - loss: 12.3566 - mae: 2.4280 - mse: 12.3566 - val_loss: 16.7371 - val_mae: 2.6670 - val_mse: 16.7371\n",
"354/354 [==============================] - 0s 158us/sample - loss: 12.3328 - mae: 2.4060 - mse: 12.3328 - val_loss: 16.3754 - val_mae: 2.6027 - val_mse: 16.3754\n",
"354/354 [==============================] - 0s 152us/sample - loss: 11.8357 - mae: 2.3106 - mse: 11.8357 - val_loss: 16.1015 - val_mae: 2.6255 - val_mse: 16.1015\n",
"354/354 [==============================] - 0s 163us/sample - loss: 11.6722 - mae: 2.3482 - mse: 11.6722 - val_loss: 16.1405 - val_mae: 2.6889 - val_mse: 16.1405\n",
"354/354 [==============================] - 0s 175us/sample - loss: 11.2774 - mae: 2.3344 - mse: 11.2774 - val_loss: 15.2110 - val_mae: 2.5038 - val_mse: 15.2110\n",
"354/354 [==============================] - 0s 180us/sample - loss: 11.2491 - mae: 2.3055 - mse: 11.2491 - val_loss: 15.4745 - val_mae: 2.4494 - val_mse: 15.4744\n",
"354/354 [==============================] - 0s 187us/sample - loss: 10.9102 - mae: 2.2171 - mse: 10.9102 - val_loss: 15.1145 - val_mae: 2.4282 - val_mse: 15.1145\n",
"354/354 [==============================] - 0s 168us/sample - loss: 10.7952 - mae: 2.2533 - mse: 10.7952 - val_loss: 14.3789 - val_mae: 2.3683 - val_mse: 14.3789\n",
"354/354 [==============================] - 0s 171us/sample - loss: 10.7250 - mae: 2.2489 - mse: 10.7250 - val_loss: 15.1102 - val_mae: 2.3422 - val_mse: 15.1102\n",
"354/354 [==============================] - 0s 158us/sample - loss: 10.4010 - mae: 2.1702 - mse: 10.4010 - val_loss: 14.3260 - val_mae: 2.3176 - val_mse: 14.3260\n",
"354/354 [==============================] - 0s 149us/sample - loss: 10.1442 - mae: 2.1797 - mse: 10.1442 - val_loss: 13.6694 - val_mae: 2.3864 - val_mse: 13.6694\n",
"354/354 [==============================] - 0s 168us/sample - loss: 10.1391 - mae: 2.1809 - mse: 10.1391 - val_loss: 14.0177 - val_mae: 2.3467 - val_mse: 14.0177\n",
"354/354 [==============================] - 0s 149us/sample - loss: 9.9119 - mae: 2.1267 - mse: 9.9119 - val_loss: 14.0739 - val_mae: 2.4617 - val_mse: 14.0739\n",
"354/354 [==============================] - 0s 164us/sample - loss: 10.0176 - mae: 2.1669 - mse: 10.0176 - val_loss: 13.5116 - val_mae: 2.3158 - val_mse: 13.5116\n",
"354/354 [==============================] - 0s 189us/sample - loss: 9.8259 - mae: 2.1407 - mse: 9.8259 - val_loss: 13.7364 - val_mae: 2.3531 - val_mse: 13.7364\n",
"354/354 [==============================] - 0s 178us/sample - loss: 9.4495 - mae: 2.0922 - mse: 9.4495 - val_loss: 14.1936 - val_mae: 2.3887 - val_mse: 14.1936\n",
"354/354 [==============================] - 0s 164us/sample - loss: 9.6721 - mae: 2.0870 - mse: 9.6721 - val_loss: 13.4267 - val_mae: 2.3508 - val_mse: 13.4267\n",
"354/354 [==============================] - 0s 167us/sample - loss: 9.1042 - mae: 2.0644 - mse: 9.1042 - val_loss: 13.3821 - val_mae: 2.4709 - val_mse: 13.3821\n",
"354/354 [==============================] - 0s 155us/sample - loss: 9.0129 - mae: 2.0482 - mse: 9.0129 - val_loss: 14.2184 - val_mae: 2.2754 - val_mse: 14.2184\n",
"354/354 [==============================] - 0s 160us/sample - loss: 9.2470 - mae: 2.0661 - mse: 9.2470 - val_loss: 14.3466 - val_mae: 2.5561 - val_mse: 14.3466\n",
"354/354 [==============================] - 0s 169us/sample - loss: 9.1695 - mae: 2.0766 - mse: 9.1695 - val_loss: 13.3818 - val_mae: 2.2373 - val_mse: 13.3818\n",
"354/354 [==============================] - 0s 165us/sample - loss: 9.1663 - mae: 2.0617 - mse: 9.1663 - val_loss: 14.7461 - val_mae: 2.5061 - val_mse: 14.7461\n",
"354/354 [==============================] - 0s 159us/sample - loss: 8.7273 - mae: 2.0208 - mse: 8.7273 - val_loss: 12.5890 - val_mae: 2.3037 - val_mse: 12.5890\n",
"354/354 [==============================] - 0s 166us/sample - loss: 8.9038 - mae: 2.0352 - mse: 8.9038 - val_loss: 12.9754 - val_mae: 2.2079 - val_mse: 12.9754\n",
"354/354 [==============================] - 0s 153us/sample - loss: 8.6155 - mae: 2.0267 - mse: 8.6155 - val_loss: 13.9239 - val_mae: 2.3525 - val_mse: 13.9239\n",
"354/354 [==============================] - 0s 163us/sample - loss: 8.5479 - mae: 2.0170 - mse: 8.5479 - val_loss: 13.6362 - val_mae: 2.2694 - val_mse: 13.6362\n",
"354/354 [==============================] - 0s 165us/sample - loss: 8.7087 - mae: 2.0062 - mse: 8.7087 - val_loss: 13.1138 - val_mae: 2.2386 - val_mse: 13.1138\n",
"354/354 [==============================] - 0s 160us/sample - loss: 8.3942 - mae: 1.9622 - mse: 8.3942 - val_loss: 12.3461 - val_mae: 2.2337 - val_mse: 12.3461\n",
"354/354 [==============================] - 0s 168us/sample - loss: 8.4101 - mae: 2.0098 - mse: 8.4101 - val_loss: 13.2116 - val_mae: 2.2682 - val_mse: 13.2116\n",
"354/354 [==============================] - 0s 156us/sample - loss: 8.3264 - mae: 1.9483 - mse: 8.3264 - val_loss: 12.5519 - val_mae: 2.4063 - val_mse: 12.5519\n",
"354/354 [==============================] - 0s 158us/sample - loss: 8.1445 - mae: 1.9549 - mse: 8.1445 - val_loss: 12.1838 - val_mae: 2.2591 - val_mse: 12.1838\n",
"354/354 [==============================] - 0s 156us/sample - loss: 8.0389 - mae: 1.9304 - mse: 8.0389 - val_loss: 12.6978 - val_mae: 2.1907 - val_mse: 12.6978\n",
"354/354 [==============================] - 0s 164us/sample - loss: 8.0705 - mae: 1.9493 - mse: 8.0705 - val_loss: 12.4833 - val_mae: 2.4720 - val_mse: 12.4833\n",
"354/354 [==============================] - 0s 158us/sample - loss: 8.1872 - mae: 1.9630 - mse: 8.1872 - val_loss: 12.0043 - val_mae: 2.2610 - val_mse: 12.0043\n",
"354/354 [==============================] - 0s 158us/sample - loss: 8.0357 - mae: 1.8946 - mse: 8.0357 - val_loss: 11.3982 - val_mae: 2.1770 - val_mse: 11.3982\n",
"354/354 [==============================] - 0s 162us/sample - loss: 7.6882 - mae: 1.8951 - mse: 7.6882 - val_loss: 13.0714 - val_mae: 2.4109 - val_mse: 13.0714\n",
"354/354 [==============================] - 0s 162us/sample - loss: 7.9639 - mae: 1.9103 - mse: 7.9639 - val_loss: 12.4297 - val_mae: 2.2996 - val_mse: 12.4297\n",
"354/354 [==============================] - 0s 183us/sample - loss: 7.7929 - mae: 1.8971 - mse: 7.7929 - val_loss: 11.9751 - val_mae: 2.2491 - val_mse: 11.9751\n",
"354/354 [==============================] - 0s 185us/sample - loss: 7.4411 - mae: 1.8631 - mse: 7.4411 - val_loss: 11.3761 - val_mae: 2.3416 - val_mse: 11.3761\n",
"354/354 [==============================] - 0s 186us/sample - loss: 7.6105 - mae: 1.9111 - mse: 7.6105 - val_loss: 12.4939 - val_mae: 2.4095 - val_mse: 12.4939\n",
"354/354 [==============================] - 0s 190us/sample - loss: 7.5013 - mae: 1.9146 - mse: 7.5013 - val_loss: 11.6668 - val_mae: 2.1468 - val_mse: 11.6668\n",
"354/354 [==============================] - 0s 195us/sample - loss: 7.4096 - mae: 1.8515 - mse: 7.4096 - val_loss: 13.8000 - val_mae: 2.5222 - val_mse: 13.8000\n",
"354/354 [==============================] - 0s 180us/sample - loss: 7.2263 - mae: 1.8241 - mse: 7.2263 - val_loss: 10.8964 - val_mae: 2.2130 - val_mse: 10.8964\n",
"354/354 [==============================] - 0s 161us/sample - loss: 7.1773 - mae: 1.8526 - mse: 7.1773 - val_loss: 10.7862 - val_mae: 2.1088 - val_mse: 10.7862\n",
"354/354 [==============================] - 0s 165us/sample - loss: 7.0812 - mae: 1.8308 - mse: 7.0812 - val_loss: 10.8147 - val_mae: 2.3209 - val_mse: 10.8147\n",
"354/354 [==============================] - 0s 155us/sample - loss: 7.2235 - mae: 1.8367 - mse: 7.2235 - val_loss: 11.0399 - val_mae: 2.2583 - val_mse: 11.0399\n",
"354/354 [==============================] - 0s 155us/sample - loss: 7.0341 - mae: 1.8172 - mse: 7.0341 - val_loss: 10.9894 - val_mae: 2.1429 - val_mse: 10.9894\n",
"354/354 [==============================] - 0s 157us/sample - loss: 6.8729 - mae: 1.7492 - mse: 6.8729 - val_loss: 10.5465 - val_mae: 2.1532 - val_mse: 10.5465\n",
"354/354 [==============================] - 0s 164us/sample - loss: 6.9345 - mae: 1.7837 - mse: 6.9345 - val_loss: 11.5379 - val_mae: 2.1963 - val_mse: 11.5379\n",
"354/354 [==============================] - 0s 166us/sample - loss: 6.8218 - mae: 1.7714 - mse: 6.8218 - val_loss: 10.1486 - val_mae: 2.1617 - val_mse: 10.1486\n",
"354/354 [==============================] - 0s 157us/sample - loss: 6.8711 - mae: 1.8045 - mse: 6.8711 - val_loss: 10.3196 - val_mae: 2.2297 - val_mse: 10.3196\n",
"354/354 [==============================] - 0s 162us/sample - loss: 6.7281 - mae: 1.7762 - mse: 6.7281 - val_loss: 11.2361 - val_mae: 2.2046 - val_mse: 11.2361\n",
"354/354 [==============================] - 0s 158us/sample - loss: 6.5518 - mae: 1.7292 - mse: 6.5518 - val_loss: 10.2378 - val_mae: 2.1494 - val_mse: 10.2378\n",
"354/354 [==============================] - 0s 161us/sample - loss: 6.6489 - mae: 1.7383 - mse: 6.6489 - val_loss: 11.1613 - val_mae: 2.2212 - val_mse: 11.1613\n",
"354/354 [==============================] - 0s 176us/sample - loss: 6.5827 - mae: 1.7564 - mse: 6.5827 - val_loss: 10.0177 - val_mae: 2.2440 - val_mse: 10.0177\n",
"354/354 [==============================] - 0s 168us/sample - loss: 6.3411 - mae: 1.7463 - mse: 6.3411 - val_loss: 10.7929 - val_mae: 2.1946 - val_mse: 10.7929\n",
"354/354 [==============================] - 0s 163us/sample - loss: 6.3621 - mae: 1.7466 - mse: 6.3621 - val_loss: 9.7344 - val_mae: 2.1441 - val_mse: 9.7344\n",
"354/354 [==============================] - 0s 158us/sample - loss: 6.2298 - mae: 1.7411 - mse: 6.2298 - val_loss: 11.2495 - val_mae: 2.1948 - val_mse: 11.2495\n",
"354/354 [==============================] - 0s 159us/sample - loss: 6.3037 - mae: 1.7169 - mse: 6.3037 - val_loss: 10.1339 - val_mae: 2.1716 - val_mse: 10.1339\n",
"354/354 [==============================] - 0s 158us/sample - loss: 6.0780 - mae: 1.6686 - mse: 6.0780 - val_loss: 11.9975 - val_mae: 2.3317 - val_mse: 11.9975\n",
"354/354 [==============================] - 0s 165us/sample - loss: 6.3311 - mae: 1.7082 - mse: 6.3311 - val_loss: 11.6433 - val_mae: 2.2756 - val_mse: 11.6433\n",
"354/354 [==============================] - 0s 155us/sample - loss: 6.0620 - mae: 1.6765 - mse: 6.0620 - val_loss: 13.0159 - val_mae: 2.5073 - val_mse: 13.0159\n",
"354/354 [==============================] - 0s 167us/sample - loss: 6.1819 - mae: 1.7157 - mse: 6.1819 - val_loss: 10.1000 - val_mae: 2.1462 - val_mse: 10.1000\n",
"354/354 [==============================] - 0s 158us/sample - loss: 5.9085 - mae: 1.6720 - mse: 5.9085 - val_loss: 11.7867 - val_mae: 2.5045 - val_mse: 11.7866\n",
"354/354 [==============================] - 0s 168us/sample - loss: 6.0201 - mae: 1.6678 - mse: 6.0201 - val_loss: 10.8789 - val_mae: 2.3031 - val_mse: 10.8789\n",
"354/354 [==============================] - 0s 159us/sample - loss: 6.1278 - mae: 1.6799 - mse: 6.1278 - val_loss: 9.8114 - val_mae: 2.1048 - val_mse: 9.8114\n",
"354/354 [==============================] - 0s 150us/sample - loss: 5.6372 - mae: 1.6280 - mse: 5.6372 - val_loss: 10.0971 - val_mae: 2.1464 - val_mse: 10.0971\n",
"354/354 [==============================] - 0s 153us/sample - loss: 5.9587 - mae: 1.6421 - mse: 5.9587 - val_loss: 9.4731 - val_mae: 2.1915 - val_mse: 9.4731\n",
"354/354 [==============================] - 0s 158us/sample - loss: 5.6189 - mae: 1.6223 - mse: 5.6189 - val_loss: 9.9788 - val_mae: 2.3332 - val_mse: 9.9788\n",
"354/354 [==============================] - 0s 158us/sample - loss: 5.8193 - mae: 1.6930 - mse: 5.8193 - val_loss: 10.4070 - val_mae: 2.1490 - val_mse: 10.4070\n",
"354/354 [==============================] - 0s 155us/sample - loss: 5.5919 - mae: 1.6152 - mse: 5.5919 - val_loss: 9.9985 - val_mae: 2.2546 - val_mse: 9.9985\n",
"354/354 [==============================] - 0s 160us/sample - loss: 5.6652 - mae: 1.6246 - mse: 5.6652 - val_loss: 9.1506 - val_mae: 2.0642 - val_mse: 9.1506\n",
"354/354 [==============================] - 0s 157us/sample - loss: 5.6349 - mae: 1.6108 - mse: 5.6349 - val_loss: 9.8522 - val_mae: 2.0813 - val_mse: 9.8522\n",
"354/354 [==============================] - 0s 159us/sample - loss: 5.6165 - mae: 1.6449 - mse: 5.6165 - val_loss: 9.1553 - val_mae: 2.0421 - val_mse: 9.1553\n",
"354/354 [==============================] - 0s 161us/sample - loss: 5.5416 - mae: 1.6153 - mse: 5.5416 - val_loss: 10.4231 - val_mae: 2.2880 - val_mse: 10.4231\n",
"354/354 [==============================] - 0s 158us/sample - loss: 5.3909 - mae: 1.5863 - mse: 5.3909 - val_loss: 8.8087 - val_mae: 2.1022 - val_mse: 8.8087\n",
"354/354 [==============================] - 0s 155us/sample - loss: 5.3540 - mae: 1.5986 - mse: 5.3540 - val_loss: 9.6963 - val_mae: 2.1931 - val_mse: 9.6963\n",
"354/354 [==============================] - 0s 161us/sample - loss: 5.3198 - mae: 1.6074 - mse: 5.3198 - val_loss: 9.1875 - val_mae: 2.1917 - val_mse: 9.1875\n",
"354/354 [==============================] - 0s 165us/sample - loss: 5.2299 - mae: 1.5638 - mse: 5.2299 - val_loss: 8.8746 - val_mae: 2.1273 - val_mse: 8.8746\n",
"354/354 [==============================] - 0s 163us/sample - loss: 5.2789 - mae: 1.5651 - mse: 5.2789 - val_loss: 9.7351 - val_mae: 2.2359 - val_mse: 9.7351\n",
"354/354 [==============================] - 0s 153us/sample - loss: 5.3399 - mae: 1.6002 - mse: 5.3399 - val_loss: 9.7185 - val_mae: 2.1080 - val_mse: 9.7185\n",
"354/354 [==============================] - 0s 159us/sample - loss: 5.0072 - mae: 1.5055 - mse: 5.0072 - val_loss: 8.3621 - val_mae: 2.0586 - val_mse: 8.3621\n",
"354/354 [==============================] - 0s 156us/sample - loss: 5.2596 - mae: 1.5557 - mse: 5.2596 - val_loss: 8.6406 - val_mae: 2.0527 - val_mse: 8.6406\n",
"354/354 [==============================] - 0s 159us/sample - loss: 5.0983 - mae: 1.5543 - mse: 5.0983 - val_loss: 8.4836 - val_mae: 2.0234 - val_mse: 8.4836\n"
"source": [
"history = model.fit(x_train,\n",
" y_train,\n",
" epochs = 100,\n",
" batch_size = 10,\n",
" validation_data = (x_test, y_test))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 6 - Evaluate\n",
"### 6.1 - Model evaluation\n",
"MAE = Mean Absolute Error (between the labels and predictions) \n",
"A mae equal to 3 represents an average error in prediction of $3k."
]
},
{
"cell_type": "code",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"x_test / loss : 8.4836\n",
"x_test / mae : 2.0234\n",
"x_test / mse : 8.4836\n"
"source": [
"score = model.evaluate(x_test, y_test, verbose=0)\n",
"\n",
"print('x_test / loss : {:5.4f}'.format(score[0]))\n",
"print('x_test / mae : {:5.4f}'.format(score[1]))\n",
"print('x_test / mse : {:5.4f}'.format(score[2]))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"What was the best result during our training ?"
]
},
{
"cell_type": "code",
"outputs": [
{
"data": {
"text/html": [
"<div>\n",