should b e completed on jupyter python. Assignment to work on is attached(HW6). this is a follow up of hw5 which i have also attached. HW5 was done by expert Anuj by you guys and i got 70% which is not good: please look at the feedback i got for hw5 below so it can help you for hw6 assignment. Feedback for HW5:This is the feedback I got for the assignment - The features from buy sessions should not be the features to train a model to predict buy or not buy event. Because this information are not available when we have new data. The information from buy sessions will only be captured after buy event happens, therefore they cannot be used to predict whether a buy event will happen. You should not use the features from buy session for your HW6, otherwise it will cause information leak.
{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## HW6 Training Machine Learning Models\n", "\n", "#### This homework can not be dropped even it gets the lowest score in your homework, which means, the score you get from this homework will be counted towards your final grade. The lowest score from HW1 - HW5 will be dropped." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Load Python libraries that you will use :" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Load your Analytical Base Table from HW5 :" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Data Pre-Processing -- 20 points \n", "\n", " Examples: \n", " \n", " Categorical data encoding \n", " Missing data imputation \n", " Data normalization and standardization \n", " Split train and test datasets" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Develop two machine learning models to predict buy or not buy event, you can use any machine learning algorithms that we learned from class, or other ones not learning in class\n", "\n", "Each model training -- 15 points\\\n", "Model validation -- 15 points , you can use f1, plot roc curve or roc auc score for evaluation" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Explain pros and cons in each of your models; explain your evaluation results from training and test dataset and which model you would recommend.\n", "### This is not a coding task but use your writing skills.\n", "\n", "-- 20 points" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Put your writing in Markdown :" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.3" } }, "nbformat": 4, "nbformat_minor": 4 } SessionID,TimeStamp,ItemID,Price,Quantity 9641594,2014-09-01 09:09:25.575000+00:00,214853342,2093,2 9641594,2014-09-01 09:09:25.596000+00:00,214853340,837,2 9641594,2014-09-01 09:09:25.614000+00:00,214853420,1046,2 9431393,2014-09-01 13:38:48.351000+00:00,214846258,941,1 9431393,2014-09-01 13:38:48.414000+00:00,214853340,837,1 9431393,2014-09-01 13:38:48.479000+00:00,214853342,2093,6 9431411,2014-09-01 11:13:16.838000+00:00,214853992,627,1 9431411,2014-09-01 11:13:16.890000+00:00,214537220,10471,1 9431411,2014-09-01 11:13:16.891000+00:00,214853865,418,1 9725713,2014-09-01 14:28:22.593000+00:00,214677830,1465,1 9725713,2014-09-01 14:28:22.670000+00:00,214853169,1046,1 9725713,2014-09-01 14:28:22.755000+00:00,214846117,889,1 9725713,2014-09-01 14:28:22.821000+00:00,214678387,1046,1 9725713,2014-09-01 14:28:22.999000+00:00,214581611,1465,1 9725713,2014-09-01 14:28:23.018000+00:00,214853130,1674,1 9725713,2014-09-01 14:28:23.029000+00:00,214851740,1360,1 9293662,2014-09-01 07:11:38.046000+00:00,214677615,1151,1 9293704,2014-09-01 18:38:10.349000+00:00,214846258,941,1 9293704,2014-09-01 18:38:10.358000+00:00,214846258,941,2 9517256,2014-09-01 16:48:23.501000+00:00,214580462,1046,1 9517256,2014-09-01 16:48:23.528000+00:00,214861057,3141,1 9517256,2014-09-01 16:48:23.528000+00:00,214858680,2093,3 9571744,2014-09-01 16:03:12.806000+00:00,214853325,4188,1 9370351,2014-09-01 16:09:07.369000+00:00,214826987,6282,1 9370351,2014-09-01 16:09:07.372000+00:00,214853325,4188,1 9293797,2014-09-01 16:57:57.697000+00:00,214822082,1042,1 9431511,2014-09-01 10:12:08.851000+00:00,214846408,1570,1 9571447,2014-09-01 18:42:18.799000+00:00,214678376,1046,1 9571447,2014-09-01 18:42:18.801000+00:00,214846119,889,1 9571447,2014-09-01 18:42:18.803000+00:00,214851313,2093,1 9571447,2014-09-01 18:42:18.804000+00:00,214853379,313,2 9571447,2014-09-01 18:42:18.806000+00:00,214845954,889,1 9641852,2014-09-01 11:23:06.804000+00:00,214820214,4397,1 9641852,2014-09-01 11:23:06.807000+00:00,214859062,6701,1 9641852,2014-09-01 11:23:06.809000+00:00,214834871,2093,1 9641852,2014-09-01 11:23:06.820000+00:00,214558192,554,1 9641852,2014-09-01 11:23:06.825000+00:00,214851080,627,1 9641852,2014-09-01 11:23:06.832000+00:00,214851575,418,1 9641852,2014-09-01 11:23:06.844000+00:00,214851234,941,1 9517423,2014-09-01 16:48:13.958000+00:00,214850949,1360,4 9571394,2014-09-01 10:59:25.747000+00:00,214850743,1989,1 9571394,2014-09-01 10:59:25.747000+00:00,214575125,1151,1 9571394,2014-09-01 10:59:25.749000+00:00,214853767,1046,1 9571394,2014-09-01 10:59:25.769000+00:00,214717397,1151,1 9571394,2014-09-01 10:59:25.771000+00:00,214687847,627,1 9571394,2014-09-01 10:59:25.808000+00:00,214851122,837,1 9571394,2014-09-01 10:59:25.838000+00:00,214705078,889,1 9571394,2014-09-01 10:59:25.978000+00:00,214718173,1151,1 9517361,2014-09-01 04:21:34.950000+00:00,214700002,6806,2 9447988,2014-09-01 14:34:27.153000+00:00,214846378,7643,1 9641787,2014-09-01 06:24:40.604000+00:00,214853282,4188,1 9370452,2014-09-01 15:14:36.012000+00:00,214853698,837,1 9370452,2014-09-01 15:14:36.024000+00:00,214853702,523,1 9725664,2014-09-01 10:59:24.023000+00:00,214851155,3350,1 9448172,2014-09-01 14:52:07.532000+00:00,214850947,523,2 9448172,2014-09-01 14:52:07.549000+00:00,214850949,1360,1 9448172,2014-09-01 14:52:07.560000+00:00,214850949,1360,2 9641949,2014-09-01 08:50:28.060000+00:00,214717777,3664,1 9641949,2014-09-01 08:50:28.137000+00:00,214853420,1046,2 9293442,2014-09-01 12:11:19.050000+00:00,214854125,1360,1 9293442,2014-09-01 12:11:19.073000+00:00,214854148,418,1 9431292,2014-09-01 19:08:11.529000+00:00,214846378,7643,1 9517499,2014-09-01 17:11:53.999000+00:00,214774685,2722,1 9571502,2014-09-01 14:13:59.241000+00:00,214853992,627,1 9571502,2014-09-01 14:13:59.318000+00:00,214853707,2093,1 9571502,2014-09-01 14:13:59.391000+00:00,214853709,837,1 9571502,2014-09-01 14:13:59.578000+00:00,214853767,1046,1 9725616,2014-09-01 08:37:31.309000+00:00,214853342,2093,3 9571483,2014-09-01 16:26:42.022000+00:00,214684093,1046,1 9725586,2014-09-01 20:00:52.263000+00:00,214826987,6282,2 9293112,2014-09-01 07:01:48.710000+00:00,214827022,5549,1 9447704,2014-09-01 18:50:03.490000+00:00,214853992,627,1 9447704,2014-09-01 18:50:03.494000+00:00,214854165,418,1 9447704,2014-09-01 18:50:03.499000+00:00,214854017,627,1 9447702,2014-09-01 13:08:18.721000+00:00,214541660,5968,1 9231987,2014-09-01 08:36:52.738000+00:00,214851281,418,1 9231987,2014-09-01 08:36:52.905000+00:00,214853709,837,1 9231987,2014-09-01 08:36:53.037000+00:00,214853698,837,1 9231987,2014-09-01 08:36:53.049000+00:00,214853722,418,2 9231987,2014-09-01 08:36:53.078000+00:00,214853702,523,1 9231987,2014-09-01 08:36:53.108000+00:00,214853700,837,2 9231987,2014-09-01 08:36:53.112000+00:00,214853707,2093,1 9431924,2014-09-01 08:46:35.184000+00:00,214826987,6282,1 9447877,2014-09-01 20:35:11.194000+00:00,214850396,1465,3 9641183,2014-09-01 07:52:21.364000+00:00,214839913,3141,1 9293209,2014-09-01 17:08:42.103000+00:00,214850949,1360,2 9447819,2014-09-01 19:40:18.427000+00:00,214853340,837,3 9641093,2014-09-01 11:48:34.249000+00:00,214701778,6596,1 9517716,2014-09-01 09:55:15.067000+00:00,214853282,4188,1 9517716,2014-09-01 09:55:15.079000+00:00,214854022,4188,1 9447828,2014-09-01 11:29:15.668000+00:00,214853454,1884,1 9572258,2014-09-01 17:20:19.303000+00:00,214716930,3664,1 9572282,2014-09-01 12:10:23.951000+00:00,214821373,3141,2 9724999,2014-09-01 15:55:59.427000+00:00,214850949,1360,1 9641304,2014-09-01 18:03:44.606000+00:00,214853707,2093,1 9641304,2014-09-01 18:03:44.622000+00:00,214821373,3141,1 9641304,2014-09-01 18:03:44.635000+00:00,214853702,523,1 9641304,2014-09-01 18:03:44.681000+00:00,214853700,837,1 9641281,2014-09-01 21:35:18.455000+00:00,214851167,837,5 9517943,2014-09-01 15:24:58.443000+00:00,214774685,2722,1 9369932,2014-09-01 06:47:04.670000+00:00,214853420,1046,2 9369932,2014-09-01 06:47:04.723000+00:00,214850945,732,1 9369933,2014-09-01 08:34:47.858000+00:00,214551607,627,4 9232284,2014-09-01 17:17:45.908000+00:00,214853342,2093,1 9232284,2014-09-01 17:17:45.918000+00:00,214711307,523,1 9232284,2014-09-01 17:17:45.935000+00:00,214850947,523,1 9232284,2014-09-01 17:17:45.944000+00:00,214848185,313,1 9572044,2014-09-01 08:14:54.222000+00:00,214700002,6806,1 9725152,2014-09-01 13:57:52.550000+00:00,214853402,2617,1 9518063,2014-09-01 18:59:37.706000+00:00,214821373,3141,1 9518063,2014-09-01 18:59:37.768000+00:00,214839913,3141,1 9370078,2014-09-01 08:22:23.331000+00:00,214567333,837,1 9370078,2014-09-01 08:22:23.358000+00:00,214853726,1046,1 9370078,2014-09-01 08:22:23.362000+00:00,214854176,627,1 9370078,2014-09-01 08:22:23.374000+00:00,214716671,449,1 9447581,2014-09-01 13:25:58.443000+00:00,214849132,9947,1 9293054,2014-09-01 15:15:45.455000+00:00,214853460,1046,1 9293054,2014-09-01 15:15:45.549000+00:00,214853428,418,2 9293054,2014-09-01 15:15:45.974000+00:00,214680371,9424,1 9293054,2014-09-01 15:15:45.983000+00:00,214826662,6596,1 9293054,2014-09-01 15:15:45.996000+00:00,214826666,6596,1 9641376,2014-09-01 13:30:15.890000+00:00,214846382,4397,1 9292619,2014-09-01 08:33:56.272000+00:00,214853420,1046,2 9432386,2014-09-01 20:20:25.776000+00:00,214829878,889,2 9432386,2014-09-01 20:21:05.022000+00:00,214829878,889,2 9449239,2014-09-01 15:05:23.926000+00:00,214840740,3664,1 9449239,2014-09-01 15:05:23.952000+00:00,214829878,889,1 9449239,2014-09-01 15:05:23.979000+00:00,214850947,523,1 9449239,2014-09-01 15:05:23.991000+00:00,214643036,2093,1 9292558,2014-09-01 20:40:07.288000+00:00,214853424,3141,1 9292558,2014-09-01 20:40:07.338000+00:00,214853454,1884,1 9292558,2014-09-01 20:40:07.355000+00:00,214853340,837,2 9640512,2014-09-01 12:25:58.976000+00:00,214853398,1779,1 9640512,2014-09-01 12:25:59.011000+00:00,214853381,313,1 9640512,2014-09-01 12:25:59.045000+00:00,214853154,313,1 9640512,2014-09-01 12:25:59.169000+00:00,214844396,680,1 9292568,2014-09-01 14:26:10.669000+00:00,214844439,2093,3 9230571,2014-09-01 16:03:12.495000+00:00,214680371,9424,1 9570702,2014-09-01 09:32:48.668000+00:00,214850949,1360,1 9570702,2014-09-01 09:32:48.685000+00:00,214853420,1046,1 9518334,2014-09-01 08:37:49.537000+00:00,214774685,2722,1 9432181,2014-09-01 18:48:12.819000+00:00,214853420,1046,2 9432186,2014-09-01 13:34:55.732000+00:00,214717063,1674,1 9432186,2014-09-01 13:34:55.740000+00:00,214845971,994,1 9432186,2014-09-01 13:34:55.742000+00:00,214851742,1360,1 9432186,2014-09-01 13:34:55.752000+00:00,214853128,1674,1 9432186,2014-09-01 13:34:55.760000+00:00,214677830,1465,1 9230703,2014-09-01 15:26:46.663000+00:00,214850949,1360,2 9432171,2014-09-01 11:26:32.086000+00:00,214854262,837,3 9432171,2014-09-01 11:26:32.093000+00:00,214850621,784,1 9432171,2014-09-01 11:26:32.102000+00:00,214567333,837,3 9292377,2014-09-01 11:42:16.486000+00:00,214853852,313,1 9292377,2014-09-01 11:42:16.556000+00:00,214567329,837,1 9292377