10 skills found
clohfink / RendezvousHashRendezvous or Highest Random Weight (HRW) hashing algorithm
Aastha2104 / Parkinson Disease PredictionIntroduction Parkinson’s Disease is the second most prevalent neurodegenerative disorder after Alzheimer’s, affecting more than 10 million people worldwide. Parkinson’s is characterized primarily by the deterioration of motor and cognitive ability. There is no single test which can be administered for diagnosis. Instead, doctors must perform a careful clinical analysis of the patient’s medical history. Unfortunately, this method of diagnosis is highly inaccurate. A study from the National Institute of Neurological Disorders finds that early diagnosis (having symptoms for 5 years or less) is only 53% accurate. This is not much better than random guessing, but an early diagnosis is critical to effective treatment. Because of these difficulties, I investigate a machine learning approach to accurately diagnose Parkinson’s, using a dataset of various speech features (a non-invasive yet characteristic tool) from the University of Oxford. Why speech features? Speech is very predictive and characteristic of Parkinson’s disease; almost every Parkinson’s patient experiences severe vocal degradation (inability to produce sustained phonations, tremor, hoarseness), so it makes sense to use voice to diagnose the disease. Voice analysis gives the added benefit of being non-invasive, inexpensive, and very easy to extract clinically. Background Parkinson's Disease Parkinson’s is a progressive neurodegenerative condition resulting from the death of the dopamine containing cells of the substantia nigra (which plays an important role in movement). Symptoms include: “frozen” facial features, bradykinesia (slowness of movement), akinesia (impairment of voluntary movement), tremor, and voice impairment. Typically, by the time the disease is diagnosed, 60% of nigrostriatal neurons have degenerated, and 80% of striatal dopamine have been depleted. Performance Metrics TP = true positive, FP = false positive, TN = true negative, FN = false negative Accuracy: (TP+TN)/(P+N) Matthews Correlation Coefficient: 1=perfect, 0=random, -1=completely inaccurate Algorithms Employed Logistic Regression (LR): Uses the sigmoid logistic equation with weights (coefficient values) and biases (constants) to model the probability of a certain class for binary classification. An output of 1 represents one class, and an output of 0 represents the other. Training the model will learn the optimal weights and biases. Linear Discriminant Analysis (LDA): Assumes that the data is Gaussian and each feature has the same variance. LDA estimates the mean and variance for each class from the training data, and then uses properties of statistics (Bayes theorem , Gaussian distribution, etc) to compute the probability of a particular instance belonging to a given class. The class with the largest probability is the prediction. k Nearest Neighbors (KNN): Makes predictions about the validation set using the entire training set. KNN makes a prediction about a new instance by searching through the entire set to find the k “closest” instances. “Closeness” is determined using a proximity measurement (Euclidean) across all features. The class that the majority of the k closest instances belong to is the class that the model predicts the new instance to be. Decision Tree (DT): Represented by a binary tree, where each root node represents an input variable and a split point, and each leaf node contains an output used to make a prediction. Neural Network (NN): Models the way the human brain makes decisions. Each neuron takes in 1+ inputs, and then uses an activation function to process the input with weights and biases to produce an output. Neurons can be arranged into layers, and multiple layers can form a network to model complex decisions. Training the network involves using the training instances to optimize the weights and biases. Naive Bayes (NB): Simplifies the calculation of probabilities by assuming that all features are independent of one another (a strong but effective assumption). Employs Bayes Theorem to calculate the probabilities that the instance to be predicted is in each class, then finds the class with the highest probability. Gradient Boost (GB): Generally used when seeking a model with very high predictive performance. Used to reduce bias and variance (“error”) by combining multiple “weak learners” (not very good models) to create a “strong learner” (high performance model). Involves 3 elements: a loss function (error function) to be optimized, a weak learner (decision tree) to make predictions, and an additive model to add trees to minimize the loss function. Gradient descent is used to minimize error after adding each tree (one by one). Engineering Goal Produce a machine learning model to diagnose Parkinson’s disease given various features of a patient’s speech with at least 90% accuracy and/or a Matthews Correlation Coefficient of at least 0.9. Compare various algorithms and parameters to determine the best model for predicting Parkinson’s. Dataset Description Source: the University of Oxford 195 instances (147 subjects with Parkinson’s, 48 without Parkinson’s) 22 features (elements that are possibly characteristic of Parkinson’s, such as frequency, pitch, amplitude / period of the sound wave) 1 label (1 for Parkinson’s, 0 for no Parkinson’s) Project Pipeline pipeline Summary of Procedure Split the Oxford Parkinson’s Dataset into two parts: one for training, one for validation (evaluate how well the model performs) Train each of the following algorithms with the training set: Logistic Regression, Linear Discriminant Analysis, k Nearest Neighbors, Decision Tree, Neural Network, Naive Bayes, Gradient Boost Evaluate results using the validation set Repeat for the following training set to validation set splits: 80% training / 20% validation, 75% / 25%, and 70% / 30% Repeat for a rescaled version of the dataset (scale all the numbers in the dataset to a range from 0 to 1: this helps to reduce the effect of outliers) Conduct 5 trials and average the results Data a_o a_r m_o m_r Data Analysis In general, the models tended to perform the best (both in terms of accuracy and Matthews Correlation Coefficient) on the rescaled dataset with a 75-25 train-test split. The two highest performing algorithms, k Nearest Neighbors and the Neural Network, both achieved an accuracy of 98%. The NN achieved a MCC of 0.96, while KNN achieved a MCC of 0.94. These figures outperform most existing literature and significantly outperform current methods of diagnosis. Conclusion and Significance These robust results suggest that a machine learning approach can indeed be implemented to significantly improve diagnosis methods of Parkinson’s disease. Given the necessity of early diagnosis for effective treatment, my machine learning models provide a very promising alternative to the current, rather ineffective method of diagnosis. Current methods of early diagnosis are only 53% accurate, while my machine learning model produces 98% accuracy. This 45% increase is critical because an accurate, early diagnosis is needed to effectively treat the disease. Typically, by the time the disease is diagnosed, 60% of nigrostriatal neurons have degenerated, and 80% of striatal dopamine have been depleted. With an earlier diagnosis, much of this degradation could have been slowed or treated. My results are very significant because Parkinson’s affects over 10 million people worldwide who could benefit greatly from an early, accurate diagnosis. Not only is my machine learning approach more accurate in terms of diagnostic accuracy, it is also more scalable, less expensive, and therefore more accessible to people who might not have access to established medical facilities and professionals. The diagnosis is also much simpler, requiring only a 10-15 second voice recording and producing an immediate diagnosis. Future Research Given more time and resources, I would investigate the following: Create a mobile application which would allow the user to record his/her voice, extract the necessary vocal features, and feed it into my machine learning model to diagnose Parkinson’s. Use larger datasets in conjunction with the University of Oxford dataset. Tune and improve my models even further to achieve even better results. Investigate different structures and types of neural networks. Construct a novel algorithm specifically suited for the prediction of Parkinson’s. Generalize my findings and algorithms for all types of dementia disorders, such as Alzheimer’s. References Bind, Shubham. "A Survey of Machine Learning Based Approaches for Parkinson Disease Prediction." International Journal of Computer Science and Information Technologies 6 (2015): n. pag. International Journal of Computer Science and Information Technologies. 2015. Web. 8 Mar. 2017. Brooks, Megan. "Diagnosing Parkinson's Disease Still Challenging." Medscape Medical News. National Institute of Neurological Disorders, 31 July 2014. Web. 20 Mar. 2017. Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection', Little MA, McSharry PE, Roberts SJ, Costello DAE, Moroz IM. BioMedical Engineering OnLine 2007, 6:23 (26 June 2007) Hashmi, Sumaiya F. "A Machine Learning Approach to Diagnosis of Parkinson’s Disease."Claremont Colleges Scholarship. Claremont College, 2013. Web. 10 Mar. 2017. Karplus, Abraham. "Machine Learning Algorithms for Cancer Diagnosis." Machine Learning Algorithms for Cancer Diagnosis (n.d.): n. pag. Mar. 2012. Web. 20 Mar. 2017. Little, Max. "Parkinsons Data Set." UCI Machine Learning Repository. University of Oxford, 26 June 2008. Web. 20 Feb. 2017. Ozcift, Akin, and Arif Gulten. "Classifier Ensemble Construction with Rotation Forest to Improve Medical Diagnosis Performance of Machine Learning Algorithms." Computer Methods and Programs in Biomedicine 104.3 (2011): 443-51. Semantic Scholar. 2011. Web. 15 Mar. 2017. "Parkinson’s Disease Dementia." UCI MIND. N.p., 19 Oct. 2015. Web. 17 Feb. 2017. Salvatore, C., A. Cerasa, I. Castiglioni, F. Gallivanone, A. Augimeri, M. Lopez, G. Arabia, M. Morelli, M.c. Gilardi, and A. Quattrone. "Machine Learning on Brain MRI Data for Differential Diagnosis of Parkinson's Disease and Progressive Supranuclear Palsy."Journal of Neuroscience Methods 222 (2014): 230-37. 2014. Web. 18 Mar. 2017. Shahbakhi, Mohammad, Danial Taheri Far, and Ehsan Tahami. "Speech Analysis for Diagnosis of Parkinson’s Disease Using Genetic Algorithm and Support Vector Machine."Journal of Biomedical Science and Engineering 07.04 (2014): 147-56. Scientific Research. July 2014. Web. 2 Mar. 2017. "Speech and Communication." Speech and Communication. Parkinson's Disease Foundation, n.d. Web. 22 Mar. 2017. Sriram, Tarigoppula V. S., M. Venkateswara Rao, G. V. Satya Narayana, and D. S. V. G. K. Kaladhar. "Diagnosis of Parkinson Disease Using Machine Learning and Data Mining Systems from Voice Dataset." SpringerLink. Springer, Cham, 01 Jan. 1970. Web. 17 Mar. 2017.
tysonmote / RendezvousGolang implementation of rendezvous hashing (highest random weight hashing)
Rogerio111 / Rogerio<!DOCTYPE html> <html> <head> <meta charset="utf-8"> <meta http-equiv="X-UA-Compatible" content="IE=edge"> <meta name="description" content="Eat cells smaller than you and don't get eaten by the bigger ones, as an MMO"> <meta name="keywords" content="agario, agar, io, cell, cells, virus, bacteria, blob, game, games, web game, html5, fun, flash"> <meta name="robots" content="index, follow"> <meta name="viewport" content="minimal-ui, width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no"> <meta name="apple-mobile-web-app-capable" content="yes"> <meta property="fb:app_id" content="677505792353827"/> <meta property="og:title" content="Agar.io"/> <meta property="og:description" content="Eat cells smaller than you and don't get eaten by the bigger ones, as an MMO"/> <meta property="og:url" content="http://agar.io"/> <meta property="og:image" content="http://agar.io/img/1200x630.png"/> <meta property="og:image:width" content="1200"/> <meta property="og:image:height" content="630"/> <meta property="og:type" content="website"/> <title>Agar.io</title> <link id="favicon" rel="icon" type="image/png" href="favicon-32x32.png"/> <!-- Área de anuncio --> <link href='https://fonts.googleapis.com/css?family=Ubuntu:700' rel='stylesheet' type='text/css'> <link href="css/bootstrap.min.css" rel="stylesheet"> <link href="css/glyphicons-social.css" rel="stylesheet"> <link href="css/animate.css" rel="stylesheet"> <style>body{padding:0;margin:0;overflow:hidden;}#canvas{position:absolute;left:0;right:0;top:0;bottom:0;width:100%;height:100%;}form{margin-bottom:0px;}.btn-play,.btn-settings,.btn-spectate,.btn-play-guest,.btn-login,.btn-logout{display:block;float:left;height:35px;}.btn-spectate,.btn-logout{height:35px;display:block;width:110px;margin-left:10px;margin-bottom:5px;}#helloContainer[data-logged-in="0"] .btn-play-guest{margin-left:5px;width:125px;}#helloContainer[data-logged-in="0"] .btn-login{margin-left:5px;width:145px;}#helloContainer[data-logged-in="0"] .agario-exp-bar,#helloContainer[data-logged-in="0"] .progress-bar-star,#helloContainer[data-logged-in="0"] #agario-main-buttons .agario-profile,#helloContainer[data-logged-in="0"] .btn-play{display:none;}#helloContainer[data-logged-in="0"] .btn-logout{display:none;}#helloContainer[data-logged-in="1"] .btn-play{margin-left:5px;width:275px;}#helloContainer[data-logged-in="1"] .btn-play-guest{display:none;}#helloContainer[data-logged-in="1"] .btn-login{display:none;}.btn-settings{width:40px;}.btn-spectate{display:block;float:right;}#adsBottom{position:absolute;left:0;right:0;bottom:0;}#adsBottomInner{margin:0px auto;width:728px;height:90px;border:5px solid white;border-radius:5px 5px 0px 0px;background-color:#FFFFFF;box-sizing:content-box;}.region-message{display:none;margin-bottom:12px;margin-left:6px;margin-right:6px;text-align:center;}#preview {width: 30px;height: 30px;border-radius: 400px;border: 3px solid #17c834;margin: 1px 0;float: left; position: absolute;left: 52.7%; top:42.5%;}#nicks {width: 10%;float: left; position: absolute; left: 46%; top: 42.5%;}#nick{width:10%;padding: 0px; left: 46%; top: -12px;position: relative;}#locationKnown #region{width:100%;}#locationUnknown #region{margin-bottom:15px;}#gamemode{width:10%;float:right;top: -42.5%;right: 44%;position: relative;}.agario-panel{display:inline-block;width:350px;background-color:rgba(25, 28, 29, 0.72);margin:2px;border-radius:10px;padding:5px 15px 5px 15px;vertical-align:top;}.agario-side-panel{display:inline-block;width:220px;}#helloContainer,.connecting-panel{position:absolute;top:50%;left:50%;margin-right:-50%;-webkit-transform:translate(-50%,-50%);-ms-transform:translate(-50%,-50%);transform:translate(-50%,-50%);}#a300x250{width:300px;height:250px;background-repeat:no-repeat;background-size:contain;background-position:center center;}.agario-exp-bar{height:30px;position:relative;border:2px solid #01612B;}.agario-exp-bar .progress-bar{background-color:#338833;border-radius:0px 4px 4px 0px;-webkit-transition:none;transition:none;}.agario-exp-bar .progress-bar-text{font-size:12pt;cursor:default;opacity:0.75;color:#FFF;text-align:center;line-height:26px;text-shadow:0px 0px 3px #000000,-1px 0px 0px #000000,1px 0px 0px #000000,0px 1px 0px #000000,0px -1px 0px #000000,-1px -1px 0px #000000,1px 1px 0px #000000,-1px 1px 0px #000000,1px -1px 0px #000000;position:absolute;top:0;bottom:0;left:0;right:0;font-family:'Ubuntu',sans-serif;}#agario-results-table{width:100%;}#agario-results-table th{text-align:center;font-size:8pt;}#agario-results-table td{text-align:center;color:#999;font-size:11pt;padding-bottom:15px;}.progress-bar-star{position:absolute;top:-13px;right:-16px;width:50px;height:50px;background-image:url("img/star.png");background-size:cover;-webkit-transform:rotate3d(0,0,1,10deg);transform:rotate3d(0,0,1,10deg);-webkit-animation-duration:1s;animation-duration:1s;-webkit-animation-delay:0s;animation-delay:0s;-webkit-animation-iteration-count:1;animation-iteration-count:1;cursor:default;color:#FFF;text-align:center;line-height:55px;font-size:12pt;text-shadow:0px 0px 3px #000000,-1px 0px 0px #000000,1px 0px 0px #000000,0px 1px 0px #000000,0px -1px 0px #000000,-1px -1px 0px #000000,1px 1px 0px #000000,-1px 1px 0px #000000,1px -1px 0px #000000;font-family:'Ubuntu',sans-serif;}.tooltip-inner{max-width:300px;}.agario-profile-panel{padding:15px 15px 15px 15px;}.agario-profile-panel .agario-profile-picture{float:left;display:block;width:64px;height:64px;border-radius:5px;border:2px solid #CCC;margin-right:6px;}.agario-profile-panel .agario-profile-name-container{float:left;display:table;width:120px;height:64px;position:relative;}.agario-profile-panel .agario-profile-name-container .agario-profile-name{display:table-cell;vertical-align:middle;text-align:center;font-weight:bold;}#helloContainer[data-has-account-data="0"] .agario-profile-panel{display:none;}.agario-party,.agario-party-0,.agario-party-1,.agario-party-2,.agario-party-3,.agario-party-4,.agario-party-5,.agario-party-6{display:none;}#helloContainer[data-gamemode=":party"] .agario-party{display:block;position:relative;}#helloContainer[data-gamemode=":party"] .agario-promo{display:none;}#helloContainer[data-party-state="0"] .agario-party-0{display:block;}#helloContainer[data-party-state="1"] .agario-party-1{display:block;}#helloContainer[data-party-state="2"] .agario-party-2{display:block;}#helloContainer[data-party-state="3"] .agario-party-3{display:block;}#helloContainer[data-party-state="4"] .agario-party-4{display:block;}#helloContainer[data-party-state="5"] .agario-party-5{display:block;}#helloContainer[data-party-state="6"] .agario-party-6{display:block;}.partyToken{margin-bottom:10px;}.side-container{vertical-align:top;display:inline-block;width:224px;}.cell-spinner{display:block;margin:0;}.creating-party-text{position:absolute;cursor:default;top:0;bottom:0;left:0;right:0;width:100%;height:100%;text-align:center;color:#FFF;font-size:24px;line-height:100px;text-shadow:0px 0px 3px #000000,-1px 0px 0px #000000,1px 0px 0px #000000,0px 1px 0px #000000,0px -1px 0px #000000,-1px -1px 0px #000000,1px 1px 0px #000000,-1px 1px 0px #000000,1px -1px 0px #000000;}.agario-results-0,.agario-results-1,.agario-results-2{display:none;}#helloContainer[data-results-state="0"] .agario-results-0{display:block;}#helloContainer[data-results-state="1"] .agario-results-1{display:block;}#helloContainer[data-results-state="2"] .agario-results-2{display:block;}#options>label{display:block;width:94px;float:left;}#stats{position:relative;width:350px;height:581px;padding:0px 0px 300px 0px;overflow:hidden;}#statsPelletsContainer,#statsTimeAliveContainer,#statsHighestMassContainer,#statsTimeLeaderboardContainer,#statsPlayerCellsEatenContainer,#statsTopPositionContainer{position:absolute;width:100px;height:100px;}#statsPelletsContainer{top:30px;left:50px;}#statsHighestMassContainer{top:30px;right:50px;}#statsTimeAliveContainer{top:85px;left:50px;}#statsTimeLeaderboardContainer{top:85px;right:50px;}#statsPlayerCellsEatenContainer{top:140px;left:50px;}#statsTopPositionContainer{top:140px;right:50px;}#statsPellets{position:absolute;top:0;left:0;bottom:0;right:0;margin:auto;}#statsText{position:absolute;top:0;bottom:0;left:0;right:0;line-height:100px;font-size:23px;}#statsSubtext{position:absolute;bottom:0;left:0;right:0;line-height:60px;font-size:12px;color:#000;text-align:center;}#statsChartText{position:absolute;left:20px;bottom:250px;line-height:40px;font-size:40px;}#statsChartText,#statsText{cursor:default;color:#444;text-align:center;font-weight:bold;}#statsContinue{position:absolute;left:25px;right:25px;width:300px;bottom:295px;}#statsGraph{position:absolute;bottom:350px;left:0px;right:0px;opacity:0.4;}#s300x250{position:absolute;bottom:10px;left:25px;right:25px;width:300px;height:250px;}.tosBox{z-index:1000;position:absolute;bottom:0;right:0;background-color:#FFF;border-radius:5px 0px 0px 0px;padding:5px 10px;}</style> <script src="js/jquery.js"></script> <script src="js/bootstrap.min.js"></script> <script> i18n_lang = 'en'; i18n_dict = { 'en': { 'connecting': 'Connecting', 'connect_help': 'If you cannot connect to the servers, check if you have some anti virus or firewall blocking the connection.', 'play': 'Jogar', 'spectate': 'Observar O Jogo', 'login_and_play': 'Logar No Facebook', 'play_as_guest': 'Play as guest', 'share': 'Share', 'advertisement': 'Advertisement', 'privacy_policy': 'Privacy Policy', 'terms_of_service': 'Terms of Service', 'changelog': 'Changelog', 'instructions_mouse': 'Move your mouse to control your cell', 'instructions_space': 'Pressiona <b>Space</b> Para Duplica', 'instructions_w': 'Pressiona <b>W</b> Para Da Massa', 'gamemode_ffa': 'FFA', 'gamemode_teams': 'Time', 'gamemode_experimental': 'Experimental', 'region_select': ' -- Select a Region -- ', 'region_us_east': 'US East', 'region_us_west': 'US West', 'region_north_america': 'North America', 'region_south_america': 'South America', 'region_europe': 'Europe', 'region_turkey': 'Turkey', 'region_poland': 'Poland', 'region_east_asia': 'East Asia', 'region_russia': 'Russia', 'region_china': 'China', 'region_oceania': 'Oceania', 'region_australia': 'Australia', 'region_players': 'players', 'option_no_skins': 'Remover skins', 'option_no_names': 'Sem Nome', 'option_dark_theme': 'Tema Escuro', 'option_no_colors': 'Sem Cores', 'option_show_mass': 'Most. Massa', 'leaderboard': 'Leaderboard', 'unnamed_cell': 'Célula sem nome !"', 'last_match_results': 'Last match results', 'score': 'Pontos', 'leaderboard_time': '', 'mass_eaten': 'Mass Eaten', 'top_position': 'Top Position', 'position_1': 'Primeiro', 'position_2': 'Segundo', 'position_3': 'Terceiro', 'position_4': 'Quarto', 'position_5': 'Quinto', 'position_6': 'Sexto', 'position_7': 'Setimo', 'position_8': 'Oitavo', 'position_9': 'Nono', 'position_10': 'Decimo', 'player_cells_eaten': 'Player Cells Eaten', 'survival_time': 'Survival Time', 'games_played': 'Games played', 'highest_mass': 'Massa Total', 'total_cells_eaten': 'Total cells eaten', 'total_mass_eaten': 'Total mass eaten', 'longest_survival': 'Longest survival', 'logout': 'Sair', 'stats': 'Stats', 'shop': 'Shop', 'party': 'Jogar Com Os Amigos', 'party_description': 'Play with your friends in the same map', 'create_party': 'Create', 'creating_party': 'Criando Ah partida...', 'join_party': 'Criar Partoda', 'back_button': 'Sair', 'joining_party': 'Connectando Na Sala ...', 'joined_party_instructions': 'You are now playing with this Sala:', 'party_join_error': 'There was a problem joining that party, please make sure the code is correct, or try creating another party', 'login_tooltip': 'Login with Facebook and get:<br\xA0/><br /><br />Jogar the game with more mass!<br />Level up to get even more starting mass!', 'create_party_instructions': 'Give this link to your friends:', 'join_party_instructions': 'Your friend should have given you a code, type it here:', 'continue': 'Continuar', 'option_skip_stats': 'Pular Estatísticas', 'stats_food_eaten': 'Alim. ingeridos', 'stats_highest_mass': 'highest mass', 'stats_time_alive': 'Tempo Vivo', 'stats_leaderboard_time': 'Tempo no Rank', 'stats_cells_eaten': 'Células Ingeridas', 'stats_top_position': 'Posição Rankeada?', '': '' }, '?': {} }; i18n_lang = (window.navigator.userLanguage || window.navigator.language || 'en').split('-')[0]; if (!i18n_dict.hasOwnProperty(i18n_lang)) { i18n_lang = 'en'; } i18n = i18n_dict[i18n_lang]; (function(window, $) { function Init() { g_drawLines = true; PlayerStats(); setInterval(PlayerStats, 180000); g_canvas = g_canvas_ = document.getElementById('canvas'); g_context = g_canvas.getContext('2d'); g_canvas.onmousedown = function(event) { if (g_touchCapable) { var deltaX = event.clientX - (5 + g_protocol / 5 / 2); var deltaY = event.clientY - (5 + g_protocol / 5 / 2); if (Math.sqrt(deltaX * deltaX + deltaY * deltaY) <= g_protocol / 5 / 2) { SendPos(); SendCmd(17); return; } } g_mouseX = event.clientX; g_mouseY = event.clientY; UpdatePos(); SendPos(); }; g_canvas.onmousemove = function(event) { g_mouseX = event.clientX; g_mouseY = event.clientY; UpdatePos(); }; g_canvas.onmouseup = function() {}; if (/firefox/i.test(navigator.userAgent)) { document.addEventListener('DOMMouseScroll', WheelHandler, false); } else { document.body.onmousewheel = WheelHandler; } var spaceDown = false; var cachedSkin = false; var wkeyDown = false; var keyEPressed = false; //EDITED window.onkeydown = function(event) { if (!(32 != event.keyCode || spaceDown)) { SendPos(); SendCmd(17); spaceDown = true; } if (!(81 != event.keyCode || cachedSkin)) { SendCmd(18); cachedSkin = true; } if (!(87 != event.keyCode || wkeyDown)) { SendPos(); SendCmd(21); wkeyDown = true; } if (69 == event.keyCode) { //EDITED if (!keyEPressed) { keyEPressed = true; timerE(); } } if (27 == event.keyCode) { __unmatched_10(300); } }; window.onkeyup = function(event) { if (32 == event.keyCode) { spaceDown = false; } if (87 == event.keyCode) { wkeyDown = false; } if (81 == event.keyCode && cachedSkin) { SendCmd(19); cachedSkin = false; } if (69 == event.keyCode) { //EDITED if (keyEPressed) { keyEPressed = false; } } }; window.onblur = function() { SendCmd(19); wkeyDown = cachedSkin = spaceDown = keyEPressed = false; //EDITED }; function timerE () { //EDITED if (keyEPressed) { SendPos(); SendCmd(21); setInterval(timerE, 200); } } window.onresize = ResizeHandler; window.requestAnimationFrame(__unmatched_130); setInterval(SendPos, 40); if (g_region) { $('#region').val(g_region); } SyncRegion(); SetRegion($('#region').val()); $.each(g_skinNamesA, function(v, node) { //EDITED $("#nicks").append($("<option></option>").attr("value", v).text(node)); }); if (0 == __unmatched_112 && g_region) { Start(); } __unmatched_10(0); ResizeHandler(); if (window.location.hash && 6 <= window.location.hash.length) { RenderLoop(window.location.hash); } } function WheelHandler(event) { g_zoom *= Math.pow(0.9, event.wheelDelta / -120 || event.detail || 0); if(!isUnlimitedZoom) { if (1 > g_zoom) { g_zoom = 1; } if (g_zoom > 4 / g_scale) { g_zoom = 4 / g_scale; } } } function UpdateTree() { if (0.4 > g_scale) { g_pointTree = null; } else { for (var minX = Number.POSITIVE_INFINITY, minY = Number.POSITIVE_INFINITY, maxX = Number.NEGATIVE_INFINITY, maxY = Number.NEGATIVE_INFINITY, maxSize = 0, i = 0; i < g_cells.length; i++) { var cell = g_cells[i]; if (!(!cell.N() || cell.R || 20 >= cell.size * g_scale)) { maxSize = Math.max(cell.size, maxSize); minX = Math.min(cell.x, minX); minY = Math.min(cell.y, minY); maxX = Math.max(cell.x, maxX); maxY = Math.max(cell.y, maxY); } } g_pointTree = QTreeFactory.la({ ca: minX - (maxSize + 100), da: minY - (maxSize + 100), oa: maxX + (maxSize + 100), pa: maxY + (maxSize + 100), ma: 2, na: 4 }); for (i = 0; i < g_cells.length; i++) { if (cell = g_cells[i], cell.N() && !(20 >= cell.size * g_scale)) { for (minX = 0; minX < cell.a.length; ++minX) { minY = cell.a[minX].x; maxX = cell.a[minX].y; if (!(minY < g_viewX - g_protocol / 2 / g_scale || maxX < g_viewY - __unmatched_60 / 2 / g_scale || minY > g_viewX + g_protocol / 2 / g_scale || maxX > g_viewY + __unmatched_60 / 2 / g_scale)) { g_pointTree.m(cell.a[minX]); } } } } } } function UpdatePos() { g_moveX = (g_mouseX - g_protocol / 2) / g_scale + g_viewX; g_moveY = (g_mouseY - __unmatched_60 / 2) / g_scale + g_viewY; } function PlayerStats() { if (null == g_regionLabels) { g_regionLabels = {}; $('#region').children().each(function() { var $this = $(this); var val = $this.val(); if (val) { g_regionLabels[val] = $this.text(); } }); } $.get('https://m.agar.io/info', function(data) { var regionNumPlayers = {}; var region; for (region in data.regions) { var region_ = region.split(':')[0]; regionNumPlayers[region_] = regionNumPlayers[region_] || 0; regionNumPlayers[region_] += data.regions[region].numPlayers; } for (region in regionNumPlayers) { $('#region option[value="' + region + '"]').text(g_regionLabels[region] + ' (' + regionNumPlayers[region] + ' players)'); } }, 'json'); } function HideOverlay() { $('#adsBottom').hide(); $('#overlays').hide(); $('#stats').hide(); $('#mainPanel').hide(); __unmatched_141 = g_playerCellDestroyed = false; SyncRegion(); if (window.googletag && window.googletag.pubads && window.googletag.pubads().clear) { window.googletag.pubads().clear(window.aa.concat(window.ab)); } } function SetRegion(val) { if (val && val != g_region) { if ($('#region').val() != val) { $('#region').val(val); } g_region = window.localStorage.location = val; $('.region-message').hide(); $('.region-message.' + val).show(); $('.btn-needs-server').prop('disabled', false); if (g_drawLines) { Start(); } } } function __unmatched_10(char) { if (!(g_playerCellDestroyed || __unmatched_141)) { $('#adsBottom').show(); g_nick = null; __unmatched_13(window.aa); if (1000 > char) { qkeyDown = 1; } g_playerCellDestroyed = true; $('#mainPanel').show(); if (0 < char) { $('#overlays').fadeIn(char); } else { $('#overlays').show(); } } } function Render(__unmatched_174) { $('#helloContainer').attr('data-gamemode', __unmatched_174); __unmatched_95 = __unmatched_174; $('#gamemode').val(__unmatched_174); } function SyncRegion() { if ($('#region').val()) { window.localStorage.location = $('#region').val(); } else if (window.localStorage.location) { $('#region').val(window.localStorage.location); } if ($('#region').val()) { $('#locationKnown').append($('#region')); } else { $('#locationUnknown').append($('#region')); } } function __unmatched_13(__unmatched_175) { if (window.googletag) { window.googletag.cmd.push(function() { if (g_canRefreshAds) { g_canRefreshAds = false; setTimeout(function() { g_canRefreshAds = true; }, 60000 * g_refreshAdsCooldown); if (window.googletag && window.googletag.pubads && window.googletag.pubads().refresh) { window.googletag.pubads().refresh(__unmatched_175); } } }); } } function __unmatched_14(i_) { return window.i18n[i_] || window.i18n_dict.en[i_] || i_; } function FindGame() { var __unmatched_177 = ++__unmatched_112; console.log('Find ' + g_region + __unmatched_95); $.ajax('https://m.agar.io/', { error: function() { setTimeout(FindGame, 1000); }, success: function(__unmatched_178) { __unmatched_178 = __unmatched_178.split('\n'); Connect('ws://' + __unmatched_178[0], __unmatched_178[1]); }, dataType: 'text', method: 'POST', cache: false, crossDomain: true, data: (g_region + __unmatched_95 || '?') + '\n154669603' }); } function Start() { if (g_drawLines && g_region) { $('#connecting').show(); FindGame(); } } function Connect(address, ticket) { if (points) { points.onopen = null; points.onmessage = null; points.onclose = null; try { points.close(); } catch (exception) {} points = null; } if (__unmatched_113.ip) { address = 'ws://' + __unmatched_113.ip; } if (null != __unmatched_121) { var __unmatched_181 = __unmatched_121; __unmatched_121 = function() { __unmatched_181(ticket); }; } if (g_secure) { var parts = address.split(':'); address = parts[0] + 's://ip-' + parts[1].replace(/\./g, '-').replace(/\//g, '') + '.tech.agar.io:' + (+parts[2] + 2000); } g_playerCellIds = []; g_playerCells = []; g_cellsById = {}; g_cells = []; g_destroyedCells = []; g_scoreEntries = []; g_leaderboardCanvas = g_scorePartitions = null; g_maxScore = 0; g_connectSuccessful = false; console.log('Connecting to ' + address); points = new WebSocket(address); points.binaryType = 'arraybuffer'; points.onopen = function() { var data; console.log('socket open'); data = GetBuffer(5); data.setUint8(0, 254); data.setUint32(1, 5, true); SendBuffer(data); data = GetBuffer(5); data.setUint8(0, 255); data.setUint32(1, 154669603, true); SendBuffer(data); data = GetBuffer(1 + ticket.length); data.setUint8(0, 80); for (var i = 0; i < ticket.length; ++i) { data.setUint8(i + 1, ticket.charCodeAt(i)); } SendBuffer(data); RefreshAds(); }; points.onmessage = MessageHandler; points.onclose = CloseHandler; points.onerror = function() { console.log('socket error'); }; } function GetBuffer(size) { return new DataView(new ArrayBuffer(size)); } function SendBuffer(data) { points.send(data.buffer); } function CloseHandler() { if (g_connectSuccessful) { g_retryTimeout = 500; } console.log('socket close'); setTimeout(Start, g_retryTimeout); g_retryTimeout *= 2; } function MessageHandler(data) { Receive(new DataView(data.data)); } function Receive(data) { function __unmatched_190() { for (var string = '';;) { var char = data.getUint16(pos, true); pos += 2; if (0 == char) { break; } string += String.fromCharCode(char); } return string; } var pos = 0; if (240 == data.getUint8(pos)) { pos += 5; } switch (data.getUint8(pos++)) { case 16: ParseCellUpdates(data, pos); break; case 17: g_viewX_ = data.getFloat32(pos, true); pos += 4; g_viewY_ = data.getFloat32(pos, true); pos += 4; g_scale_ = data.getFloat32(pos, true); pos += 4; break; case 20: g_playerCells = []; g_playerCellIds = []; break; case 21: g_linesY_ = data.getInt16(pos, true); pos += 2; g_linesX_ = data.getInt16(pos, true); pos += 2; if (!g_ready) { g_ready = true; g_linesX = g_linesY_; g_linesY = g_linesX_; } break; case 32: g_playerCellIds.push(data.getUint32(pos, true)); pos += 4; break; case 49: if (null != g_scorePartitions) { break; } var num = data.getUint32(pos, true); var pos = pos + 4; g_scoreEntries = []; for (var i = 0; i < num; ++i) { var id = data.getUint32(pos, true); var pos = pos + 4; g_scoreEntries.push({ id: id, name: __unmatched_190() }); } UpdateLeaderboard(); break; case 50: g_scorePartitions = []; num = data.getUint32(pos, true); pos += 4; for (i = 0; i < num; ++i) { g_scorePartitions.push(data.getFloat32(pos, true)); pos += 4; } UpdateLeaderboard(); break; case 64: g_minX = data.getFloat64(pos, true); pos += 8; g_minY = data.getFloat64(pos, true); pos += 8; g_maxX = data.getFloat64(pos, true); pos += 8; g_maxY = data.getFloat64(pos, true); pos += 8; g_viewX_ = (g_maxX + g_minX) / 2; g_viewY_ = (g_maxY + g_minY) / 2; g_scale_ = 1; if (0 == g_playerCells.length) { g_viewX = g_viewX_; g_viewY = g_viewY_; g_scale = g_scale_; } break; case 81: var x = data.getUint32(pos, true); var pos = pos + 4; var __unmatched_196 = data.getUint32(pos, true); var pos = pos + 4; var __unmatched_197 = data.getUint32(pos, true); var pos = pos + 4; setTimeout(function() { __unmatched_43({ e: x, f: __unmatched_196, d: __unmatched_197 }); }, 1200); } } function ParseCellUpdates(data, pos) { function __unmatched_202() { for (var string = '';;) { var id = data.getUint16(pos, true); pos += 2; if (0 == id) { break; } string += String.fromCharCode(id); } return string; } function __unmatched_203() { for (var __unmatched_218 = '';;) { var r = data.getUint8(pos++); if (0 == r) { break; } __unmatched_218 += String.fromCharCode(r); } return __unmatched_218; } __unmatched_107 = g_time = Date.now(); if (!g_connectSuccessful) { g_connectSuccessful = true; __unmatched_24(); } __unmatched_88 = false; var num = data.getUint16(pos, true); pos += 2; for (var i = 0; i < num; ++i) { var cellA = g_cellsById[data.getUint32(pos, true)]; var cellB = g_cellsById[data.getUint32(pos + 4, true)]; pos += 8; if (cellA && cellB) { cellB.X(); cellB.s = cellB.x; cellB.t = cellB.y; cellB.r = cellB.size; cellB.J = cellA.x; cellB.K = cellA.y; cellB.q = cellB.size; cellB.Q = g_time; __unmatched_49(cellA, cellB); } } for (i = 0;;) { num = data.getUint32(pos, true); pos += 4; if (0 == num) { break; } ++i; var size; var cellA = data.getInt32(pos, true); pos += 4; cellB = data.getInt32(pos, true); pos += 4; size = data.getInt16(pos, true); pos += 2; var flags = data.getUint8(pos++); var y = data.getUint8(pos++); var b = data.getUint8(pos++); var y = __unmatched_40(flags << 16 | y << 8 | b); var b = data.getUint8(pos++); var isVirus = !!(b & 1); var isAgitated = !!(b & 16); var __unmatched_214 = null; if (b & 2) { pos += 4 + data.getUint32(pos, true); } if (b & 4) { __unmatched_214 = __unmatched_203(); } var name = __unmatched_202(); var flags = null; if (g_cellsById.hasOwnProperty(num)) { flags = g_cellsById[num]; flags.P(); flags.s = flags.x; flags.t = flags.y; flags.r = flags.size; flags.color = y; } else { flags = new Cell(num, cellA, cellB, size, y, name); g_cells.push(flags); g_cellsById[num] = flags; flags.ta = cellA; flags.ua = cellB; } flags.h = isVirus; flags.n = isAgitated; flags.J = cellA; flags.K = cellB; flags.q = size; flags.Q = g_time; flags.ba = b; flags.fa = __unmatched_214; if (name) { flags.B(name); } if (-1 != g_playerCellIds.indexOf(num) && -1 == g_playerCells.indexOf(flags)) { g_playerCells.push(flags); if (1 == g_playerCells.length) { g_viewX = flags.x; g_viewY = flags.y; __unmatched_136(); document.getElementById('overlays').style.display = 'none'; cached = []; __unmatched_139 = 0; __unmatched_140 = g_playerCells[0].color; __unmatched_142 = true; __unmatched_143 = Date.now(); g_mode = __unmatched_146 = __unmatched_145 = 0; } } } cellA = data.getUint32(pos, true); pos += 4; for (i = 0; i < cellA; i++) { num = data.getUint32(pos, true); pos += 4; flags = g_cellsById[num]; if (null != flags) { flags.X(); } } if (__unmatched_88 && 0 == g_playerCells.length) { __unmatched_144 = Date.now(); __unmatched_142 = false; if (!(g_playerCellDestroyed || __unmatched_141)) { if (__unmatched_148) { __unmatched_13(window.ab); ShowOverlay(); __unmatched_141 = true; $('#overlays').fadeIn(3000); $('#stats').show(); } else { __unmatched_10(3000); } } } } function __unmatched_24() { $('#connecting').hide(); SendNick(); if (__unmatched_121) { __unmatched_121(); __unmatched_121 = null; } if (null != __unmatched_123) { clearTimeout(__unmatched_123); } __unmatched_123 = setTimeout(function() { if (window.ga) { ++__unmatched_124; window.ga('set', 'dimension2', __unmatched_124); } }, 10000); } function SendPos() { if (IsConnected()) { var deltaY = g_mouseX - g_protocol / 2; var delta = g_mouseY - __unmatched_60 / 2; if (!(64 > deltaY * deltaY + delta * delta || 0.01 > Math.abs(g_lastMoveY - g_moveX) && 0.01 > Math.abs(g_lastMoveX - g_moveY))) { g_lastMoveY = g_moveX; g_lastMoveX = g_moveY; deltaY = GetBuffer(21); deltaY.setUint8(0, 16); deltaY.setFloat64(1, g_moveX, true); deltaY.setFloat64(9, g_moveY, true); deltaY.setUint32(17, 0, true); SendBuffer(deltaY); } } } function SendNick() { if (IsConnected() && g_connectSuccessful && null != g_nick) { var data = GetBuffer(1 + 2 * g_nick.length); data.setUint8(0, 0); for (var i = 0; i < g_nick.length; ++i) { data.setUint16(1 + 2 * i, g_nick.charCodeAt(i), true); } SendBuffer(data); g_nick = null; } } function IsConnected() { return null != points && points.readyState == points.OPEN; } function SendCmd(cmd) { if (IsConnected()) { var data = GetBuffer(1); data.setUint8(0, cmd); SendBuffer(data); } } function RefreshAds() { if (IsConnected() && null != __unmatched_108) { var __unmatched_226 = GetBuffer(1 + __unmatched_108.length); __unmatched_226.setUint8(0, 81); for (var y = 0; y < __unmatched_108.length; ++y) { __unmatched_226.setUint8(y + 1, __unmatched_108.charCodeAt(y)); } SendBuffer(__unmatched_226); } } function ResizeHandler() { g_protocol = window.innerWidth; __unmatched_60 = window.innerHeight; g_canvas_.width = g_canvas.width = g_protocol; g_canvas_.height = g_canvas.height = __unmatched_60; var $dialog = $('#helloContainer'); $dialog.css('transform', 'none'); var dialogHeight = $dialog.height(); var height = window.innerHeight; if (dialogHeight > height / 1.1) { $dialog.css('transform', 'translate(-50%, -50%) scale(' + height / dialogHeight / 1.1 + ')'); } else { $dialog.css('transform', 'translate(-50%, -50%)'); } GetScore(); } function ScaleModifier() { var scale; scale = 1 * Math.max(__unmatched_60 / 1080, g_protocol / 1920); return scale *= g_zoom; } function __unmatched_32() { if (0 != g_playerCells.length) { for (var scale = 0, i = 0; i < g_playerCells.length; i++) { scale += g_playerCells[i].size; } scale = Math.pow(Math.min(64 / scale, 1), 0.4) * ScaleModifier(); g_scale = (9 * g_scale + scale) / 10; } } function GetScore() { var x; var time = Date.now(); ++__unmatched_75; g_time = time; if (0 < g_playerCells.length) { __unmatched_32(); for (var y = x = 0, i = 0; i < g_playerCells.length; i++) { g_playerCells[i].P(); x += g_playerCells[i].x / g_playerCells.length; y += g_playerCells[i].y / g_playerCells.length; } g_viewX_ = x; g_viewY_ = y; g_scale_ = g_scale; g_viewX = (g_viewX + x) / 2; g_viewY = (g_viewY + y) / 2; } else { g_viewX = (29 * g_viewX + g_viewX_) / 30; g_viewY = (29 * g_viewY + g_viewY_) / 30; g_scale = (9 * g_scale + g_scale_ * ScaleModifier()) / 10; } UpdateTree(); UpdatePos(); if (!g_showTrails) { g_context.clearRect(0, 0, g_protocol, __unmatched_60); } if (g_showTrails) { g_context.fillStyle = g_showMass ? '#111111' : '#F2FBFF'; g_context.globalAlpha = 0.05; g_context.fillRect(0, 0, g_protocol, __unmatched_60); g_context.globalAlpha = 1; } else { DrawGrid(); } g_cells.sort(function(A, B) { return A.size == B.size ? A.id - B.id : A.size - B.size; }); g_context.save(); g_context.translate(g_protocol / 2, __unmatched_60 / 2); g_context.scale(g_scale, g_scale); g_context.translate(-g_viewX, -g_viewY); drawBorders(); drawLogo(); myMass = Math.min.apply(null, g_playerCells.map(function(r) { return r.N(); })) for (i = 0; i < g_destroyedCells.length; i++) { g_destroyedCells[i].w(g_context); } for (i = 0; i < g_cells.length; i++) { g_cells[i].w(g_context); } if (g_ready) { g_linesX = (3 * g_linesX + g_linesY_) / 4; g_linesY = (3 * g_linesY + g_linesX_) / 4; g_context.save(); g_context.strokeStyle = '#FFAAAA'; g_context.lineWidth = 10; g_context.lineCap = 'round'; g_context.lineJoin = 'round'; g_context.globalAlpha = 0.5; g_context.beginPath(); for (i = 0; i < g_playerCells.length; i++) { g_context.moveTo(g_playerCells[i].x, g_playerCells[i].y); g_context.lineTo(g_linesX, g_linesY); } g_context.stroke(); g_context.restore(); } g_context.restore(); if (g_leaderboardCanvas && g_leaderboardCanvas.width) { g_context.drawImage(g_leaderboardCanvas, g_protocol - g_leaderboardCanvas.width - 10, 10); } g_maxScore = Math.max(g_maxScore, __unmatched_36()); if (0 != g_maxScore) { if (null == g_cachedScore) { g_cachedScore = new CachedCanvas(24, '#FFFFFF'); } g_cachedScore.C(__unmatched_14('score') + ': ' + ~~(g_maxScore / 100)); y = g_cachedScore.L(); x = y.width; g_context.globalAlpha = 0.2; g_context.fillStyle = '#000000'; g_context.fillRect(10, __unmatched_60 - 10 - 24 - 10, x + 10, 34); g_context.globalAlpha = 1; g_context.drawImage(y, 15, __unmatched_60 - 10 - 24 - 5); } DrawSplitImage(); time = Date.now() - time; if (time > 1000 / 60) { g_pointNumScale -= 0.01; } else if (time < 1000 / 65) { g_pointNumScale += 0.01; } if (0.4 > g_pointNumScale) { g_pointNumScale = 0.4; } if (1 < g_pointNumScale) { g_pointNumScale = 1; } time = g_time - __unmatched_77; if (!IsConnected() || g_playerCellDestroyed || __unmatched_141) { qkeyDown += time / 2000; if (1 < qkeyDown) { qkeyDown = 1; } } else { qkeyDown -= time / 300; if (0 > qkeyDown) { qkeyDown = 0; } } if (0 < qkeyDown) { g_context.fillStyle = '#000000'; g_context.globalAlpha = 0.5 * qkeyDown; g_context.fillRect(0, 0, g_protocol, __unmatched_60); g_context.globalAlpha = 1; } __unmatched_77 = g_time; } function DrawGrid() { g_context.fillStyle = g_showMass ? '#111111' : '#F2FBFF'; g_context.fillRect(0, 0, g_protocol, __unmatched_60); g_context.save(); g_context.strokeStyle = g_showMass ? '#AAAAAA' : '#000000'; g_context.globalAlpha = 0.2 * g_scale; for (var width = g_protocol / g_scale, height = __unmatched_60 / g_scale, g_width = (-g_viewX + width / 2) % 50; g_width < width; g_width += 50) { g_context.beginPath(); g_context.moveTo(g_width * g_scale - 0.5, 0); g_context.lineTo(g_width * g_scale - 0.5, height * g_scale); g_context.stroke(); } for (g_width = (-g_viewY + height / 2) % 50; g_width < height; g_width += 50) { g_context.beginPath(); g_context.moveTo(0, g_width * g_scale - 0.5); g_context.lineTo(width * g_scale, g_width * g_scale - 0.5); g_context.stroke(); } g_context.restore(); } function DrawSplitImage() { if (g_touchCapable && g_splitImage.width) { var size = g_protocol / 5; g_context.drawImage(g_splitImage, 5, 5, size, size); } } function __unmatched_36() { for (var score = 0, i = 0; i < g_playerCells.length; i++) { score += g_playerCells[i].q * g_playerCells[i].q; } return score; } function UpdateLeaderboard() { g_leaderboardCanvas = null; if (null != g_scorePartitions || 0 != g_scoreEntries.length) { if (null != g_scorePartitions || g_showNames) { g_leaderboardCanvas = document.createElement('canvas'); var context = g_leaderboardCanvas.getContext('2d'); var height = 60; var height = null == g_scorePartitions ? height + 24 * g_scoreEntries.length : height + 180; var scale = Math.min(200, 0.3 * g_protocol) / 200; g_leaderboardCanvas.width = 200 * scale; g_leaderboardCanvas.height = height * scale; context.scale(scale, scale); context.globalAlpha = 0.4; context.fillStyle = '#000000'; context.fillRect(0, 0, 200, height); context.globalAlpha = 1; context.fillStyle = '#FFFFFF'; scale = null; scale = __unmatched_14('leaderboard'); context.font = '30px Ubuntu'; context.fillText(scale, 100 - context.measureText(scale).width / 2, 40); if (null == g_scorePartitions) { for (context.font = '20px Ubuntu', height = 0; height < g_scoreEntries.length; ++height) { scale = g_scoreEntries[height].name || __unmatched_14('unnamed_cell'); if (!g_showNames) { scale = __unmatched_14('unnamed_cell'); } if (-1 != g_playerCellIds.indexOf(g_scoreEntries[height].id)) { if (g_playerCells[0].name) { scale = g_playerCells[0].name; } context.fillStyle = '#FFAAAA'; } else { context.fillStyle = '#FFFFFF'; } scale = height + 1 + '. ' + scale; context.fillText(scale, 100 - context.measureText(scale).width / 2, 70 + 24 * height); } } else { for (height = scale = 0; height < g_scorePartitions.length; ++height) { var end = scale + g_scorePartitions[height] * Math.PI * 2; context.fillStyle = g_teamColors[height + 1]; context.beginPath(); context.moveTo(100, 140); context.arc(100, 140, 80, scale, end, false); context.fill(); scale = end; } } } } } function __unmatched_38(__unmatched_250, __unmatched_251, __unmatched_252, __unmatched_253, __unmatched_254) { this.V = __unmatched_250; this.x = __unmatched_251; this.y = __unmatched_252; this.i = __unmatched_253; this.b = __unmatched_254; } function Cell(id, x, y, size, color, name) { this.id = id; this.s = this.x = x; this.t = this.y = y; this.r = this.size = size; this.color = color; this.a = []; this.W(); this.B(name); } function __unmatched_40(__unmatched_261) { for (__unmatched_261 = __unmatched_261.toString(16); 6 > __unmatched_261.length;) { __unmatched_261 = '0' + __unmatched_261; } return '#' + __unmatched_261; } function drawBorders() { g_context.save() g_context.beginPath(); g_context.lineWidth = 1; g_context.strokeStyle = "#F87B32"; g_context.moveTo(getMapStartX(), getMapStartY()); g_context.lineTo(getMapStartX(), getMapEndY()); g_context.stroke(); g_context.moveTo(getMapStartX(), getMapStartY()); g_context.lineTo(getMapEndX(), getMapStartY()); g_context.stroke(); g_context.moveTo(getMapEndX(), getMapStartY()); g_context.lineTo(getMapEndX(), getMapEndY()); g_context.stroke(); g_context.moveTo(getMapStartX(), getMapEndY()); g_context.lineTo(getMapEndX(), getMapEndY()); g_context.stroke(); g_context.restore(); } function drawLogo(){ var logoimage = new Image(); logoimage.src = "img/split.png"; var width = this.j / 2; var dim = width / 2; g_context.save(); g_context.beginPath(); g_context.strokeStyle = "#F87B32"; g_context.moveTo(getMapStartX()/2, getMapStartX()/2); g_context.lineTo(getMapStartX()/2, getMapStartX()/2); g_context.stroke(); g_context.restore(); } function CachedCanvas(size, color, stroke, strokeColor) { if (size) { this.u = size; } if (color) { this.S = color; } this.U = !!stroke; if (strokeColor) { this.v = strokeColor; } } function __unmatched_42(__unmatched_266) { for (var size_ = __unmatched_266.length, __unmatched_268, __unmatched_269; 0 < size_;) { __unmatched_269 = Math.floor(Math.random() * size_); size_--; __unmatched_268 = __unmatched_266[size_]; __unmatched_266[size_] = __unmatched_266[__unmatched_269]; __unmatched_266[__unmatched_269] = __unmatched_268; } } function __unmatched_43(g_socket, __unmatched_271) { var noClip = '1' == $('#helloContainer').attr('data-has-account-data'); $('#helloContainer').attr('data-has-account-data', '1'); if (null == __unmatched_271 && window.localStorage.loginCache) { var rand = JSON.parse(window.localStorage.loginCache); rand.f = g_socket.f; rand.d = g_socket.d; rand.e = g_socket.e; window.localStorage.loginCache = JSON.stringify(rand); } if (noClip) { var __unmatched_274 = +$('.agario-exp-bar .progress-bar-text').first().text().split('/')[0]; var noClip = +$('.agario-exp-bar .progress-bar-text').first().text().split('/')[1].split(' ')[0]; var rand = $('.agario-profile-panel .progress-bar-star').first().text(); if (rand != g_socket.e) { __unmatched_43({ f: noClip, d: noClip, e: rand }, function() { $('.agario-profile-panel .progress-bar-star').text(g_socket.e); $('.agario-exp-bar .progress-bar').css('width', '100%'); $('.progress-bar-star').addClass('animated tada').one('webkitAnimationEnd mozAnimationEnd MSAnimationEnd oanimationend animationend', function() { $('.progress-bar-star').removeClass('animated tada'); }); setTimeout(function() { $('.agario-exp-bar .progress-bar-text').text(g_socket.d + '/' + g_socket.d + ' XP'); __unmatched_43({ f: 0, d: g_socket.d, e: g_socket.e }, function() { __unmatched_43(g_socket, __unmatched_271); }); }, 1000); }); } else { var __unmatched_275 = Date.now(); var name = function() { var deltaX; deltaX = (Date.now() - __unmatched_275) / 1000; deltaX = 0 > deltaX ? 0 : 1 < deltaX ? 1 : deltaX; deltaX = deltaX * deltaX * (3 - 2 * deltaX); $('.agario-exp-bar .progress-bar-text').text(~~(__unmatched_274 + (g_socket.f - __unmatched_274) * deltaX) + '/' + g_socket.d + ' XP'); $('.agario-exp-bar .progress-bar').css('width', (88 * (__unmatched_274 + (g_socket.f - __unmatched_274) * deltaX) / g_socket.d).toFixed(2) + '%'); if (1 > deltaX) { window.requestAnimationFrame(name); } else if (__unmatched_271) { __unmatched_271(); } }; window.requestAnimationFrame(name); } } else { $('.agario-profile-panel .progress-bar-star').text(g_socket.e); $('.agario-exp-bar .progress-bar-text').text(g_socket.f + '/' + g_socket.d + ' XP'); $('.agario-exp-bar .progress-bar').css('width', (88 * g_socket.f / g_socket.d).toFixed(2) + '%'); if (__unmatched_271) { __unmatched_271(); } } } function __unmatched_44(__unmatched_278) { if ('string' == typeof __unmatched_278) { __unmatched_278 = JSON.parse(__unmatched_278); } if (Date.now() + 1800000 > __unmatched_278.ka) { $('#helloContainer').attr('data-logged-in', '0'); } else { window.localStorage.loginCache = JSON.stringify(__unmatched_278); __unmatched_108 = __unmatched_278.ha; $('.agario-profile-name').text(__unmatched_278.name); RefreshAds(); __unmatched_43({ f: __unmatched_278.f, d: __unmatched_278.d, e: __unmatched_278.e }); $('#helloContainer').attr('data-logged-in', '1'); } } function __unmatched_45(data) { data = data.split('\n'); __unmatched_44({ name: data[0], sa: data[1], ha: data[2], ka: 1000 * +data[3], e: +data[4], f: +data[5], d: +data[6] }); } function UpdateScale(__unmatched_280) { if ('connected' == __unmatched_280.status) { var x = __unmatched_280.authResponse.accessToken; window.FB.api('/me/picture?width=180&height=180', function(__unmatched_282) { window.localStorage.fbPictureCache = __unmatched_282.data.url; $('.agario-profile-picture').attr('src', __unmatched_282.data.url); }); $('#helloContainer').attr('data-logged-in', '1'); if (null != __unmatched_108) { $.ajax('https://m.agar.io/checkToken', { error: function() { __unmatched_108 = null; UpdateScale(__unmatched_280); }, success: function(__unmatched_283) { __unmatched_283 = __unmatched_283.split('\n'); __unmatched_43({ e: +__unmatched_283[0], f: +__unmatched_283[1], d: +__unmatched_283[2] }); }, dataType: 'text', method: 'POST', cache: false, crossDomain: true, data: __unmatched_108 }); } else { $.ajax('https://m.agar.io/facebookLogin', { error: function() { __unmatched_108 = null; $('#helloContainer').attr('data-logged-in', '0'); }, success: __unmatched_45, dataType: 'text', method: 'POST', cache: false, crossDomain: true, data: x }); } } } function RenderLoop(x) { Render(':party'); $('#helloContainer').attr('data-party-state', '4'); x = decodeURIComponent(x).replace(/.*#/gim, ''); __unmatched_48('#' + window.encodeURIComponent(x)); $.ajax('https://m.agar.io/getToken', { error: function() { $('#helloContainer').attr('data-party-state', '6'); }, success: function(quick) { quick = quick.split('\n'); $('.partyToken').val('agar.io/#' + window.encodeURIComponent(x)); $('#helloContainer').attr('data-party-state', '5'); Render(':party'); Connect('ws://' + quick[0], x); }, dataType: 'text', method: 'POST', cache: false, crossDomain: true, data: x }); } function __unmatched_48(__unmatched_286) { if (window.history && window.history.replaceState) { window.history.replaceState({}, window.document.title, __unmatched_286); } } function __unmatched_49(__unmatched_287, __unmatched_288) { var playerOwned = -1 != g_playerCellIds.indexOf(__unmatched_287.id); var __unmatched_290 = -1 != g_playerCellIds.indexOf(__unmatched_288.id); var __unmatched_291 = 30 > __unmatched_288.size; if (playerOwned && __unmatched_291) { ++__unmatched_139; } if (!(__unmatched_291 || !playerOwned || __unmatched_290)) { ++__unmatched_146; } } function __unmatched_50(__unmatched_292) { __unmatched_292 = ~~__unmatched_292; var color = (__unmatched_292 % 60).toString(); __unmatched_292 = (~~(__unmatched_292 / 60)).toString(); if (2 > color.length) { color = '0' + color; } return __unmatched_292 + ':' + color; } function __unmatched_51() { if (null == g_scoreEntries) { return 0; } for (var i = 0; i < g_scoreEntries.length; ++i) { if (-1 != g_playerCellIds.indexOf(g_scoreEntries[i].id)) { return i + 1; } } return 0; } function ShowOverlay() { $('.stats-food-eaten').text(__unmatched_139); $('.stats-time-alive').text(__unmatched_50((__unmatched_144 - __unmatched_143) / 1000)); $('.stats-leaderboard-time').text(__unmatched_50(__unmatched_145)); $('.stats-highest-mass').text(~~(g_maxScore / 100)); $('.stats-cells-eaten').text(__unmatched_146); $('.stats-top-position').text(0 == g_mode ? ':(' : g_mode); var g_height = document.getElementById('statsGraph'); if (g_height) { var pointsAcc = g_height.getContext('2d'); var scale = g_height.width; var g_height = g_height.height; pointsAcc.clearRect(0, 0, scale, g_height); if (2 < cached.length) { for (var __unmatched_298 = 200, i = 0; i < cached.length; i++) { __unmatched_298 = Math.max(cached[i], __unmatched_298); } pointsAcc.lineWidth = 3; pointsAcc.lineCap = 'round'; pointsAcc.lineJoin = 'round'; pointsAcc.strokeStyle = __unmatched_140; pointsAcc.fillStyle = __unmatched_140; pointsAcc.beginPath(); pointsAcc.moveTo(0, g_height - cached[0] / __unmatched_298 * (g_height - 10) + 10); for (i = 1; i < cached.length; i += Math.max(~~(cached.length / scale), 1)) { for (var __unmatched_300 = i / (cached.length - 1) * scale, __unmatched_301 = [], __unmatched_302 = -20; 20 >= __unmatched_302; ++__unmatched_302) { if (!(0 > i + __unmatched_302 || i + __unmatched_302 >= cached.length)) { __unmatched_301.push(cached[i + __unmatched_302]); } } __unmatched_301 = __unmatched_301.reduce(function(__unmatched_303, __unmatched_304) { return __unmatched_303 + __unmatched_304; }) / __unmatched_301.length / __unmatched_298; pointsAcc.lineTo(__unmatched_300, g_height - __unmatched_301 * (g_height - 10) + 10); } pointsAcc.stroke(); pointsAcc.globalAlpha = 0.5; pointsAcc.lineTo(scale, g_height); pointsAcc.lineTo(0, g_height); pointsAcc.fill(); pointsAcc.globalAlpha = 1; } } } if (!window.agarioNoInit) { var __unmatched_53 = window.location.protocol; var g_secure = 'https:' == __unmatched_53; if (g_secure && -1 == window.location.search.indexOf('fb')) { window.location.href = 'http://agar.io/'; } else { var items = window.navigator.userAgent; if (-1 != items.indexOf('Android')) { if (window.ga) { window.ga('send', 'event', 'MobileRedirect', 'PlayStore'); } setTimeout(function() { window.location.href = 'https://play.google.com/store/apps/details?id=com.miniclip.agar.io'; }, 1000); } else if (-1 != items.indexOf('iPhone') || -1 != items.indexOf('iPad') || -1 != items.indexOf('iPod')) { if (window.ga) { window.ga('send', 'event', 'MobileRedirect', 'AppStore'); } setTimeout(function() { window.location.href = 'https://itunes.apple.com/app/agar.io/id995999703?mt=8&at=1l3vajp'; }, 1000); } else { var g_canvas_; var g_context; var g_canvas; var g_protocol; var __unmatched_60; var g_pointTree = null; var points = null; var g_viewX = 0; var g_viewY = 0; var g_playerCellIds = []; var g_playerCells = []; var g_cellsById = {}; var g_cells = []; var g_destroyedCells = []; var g_scoreEntries = []; var g_mouseX = 0; var g_mouseY = 0; var g_moveX = -1; var g_moveY = -1; var __unmatched_75 = 0; var g_time = 0; var __unmatched_77 = 0; var g_nick = null; var g_minX = 0; var g_minY = 0; var g_maxX = 10000; var g_maxY = 10000; var g_scale = 1; var g_region = null; var g_showSkins = true; var g_showNames = true; var g_noColors = false; var __unmatched_88 = false; var g_maxScore = 0; var g_showMass = false; var g_darkTheme = true; var g_viewX_ = g_viewX = ~~((g_minX + g_maxX) / 2); var g_viewY_ = g_viewY = ~~((g_minY + g_maxY) / 2); var g_scale_ = 1; var __unmatched_95 = ''; var g_scorePartitions = null; var g_drawLines = false; var g_ready = false; var g_linesY_ = 0; var g_linesX_ = 0; var g_linesX = 0; var g_linesY = 0; var g_ABGroup = 0; var g_teamColors = [ '#333333', '#FF3333', '#33FF33', '#3333FF' ]; var g_showTrails = false; var g_connectSuccessful = false; var __unmatched_107 = 0; var __unmatched_108 = null; var g_zoom = 1; var qkeyDown = 1; var g_playerCellDestroyed = false; var __unmatched_112 = 0; var __unmatched_113 = {}; (function() { var point = window.location.search; if ('?' == point.charAt(0)) { point = point.slice(1); } for (var point = point.split('&'), __unmatched_306 = 0; __unmatched_306 < point.length; __unmatched_306++) { var parts = point[__unmatched_306].split('='); __unmatched_113[parts[0]] = parts[1]; } }()); var g_touchCapable = 'ontouchstart' in window && /Android|webOS|iPhone|iPad|iPod|BlackBerry|IEMobile|Opera Mini/i.test(window.navigator.userAgent); var g_splitImage = new Image(); g_splitImage.src = 'img/split.png'; var canvasTest = document.createElement('canvas'); if ('undefined' == typeof console || 'undefined' == typeof DataView || 'undefined' == typeof WebSocket || null == canvasTest || null == canvasTest.getContext || null == window.localStorage) { alert('You browser does not support this game, we recommend you to use Firefox to play this'); } else { var g_regionLabels = null; window.setNick = function(val) { HideOverlay(); g_nick = val; SendNick(); g_maxScore = 0; }; window.setRegion = SetRegion; window.setSkins = function(val) { g_showSkins = val; }; window.setUnlimitedZoom = function(val) { isUnlimitedZoom = val; }; window.setNames = function(val) { g_showNames = val; }; window.setDarkTheme = function(val) { g_showMass = val; }; window.setColors = function(val) { g_noColors = val; }; window.setShowMass = function(val) { g_darkTheme = val; }; window.spectate = function(val) { isSpectating = val g_nick = null; SendCmd(1); HideOverlay(); }; window.setLargeBlobBorders = function(val) { isLargeBlobBorders = val; } window.setLargeNames = function(val) { isLargeNames = val; } window.setVirusTransparent = function(val){ isVirusTransparent = val; } window.nicksChange = function() { var name = $("#nicks").children("option").filter(":selected").text(); $("#nick").val(name); if (-1 != g_skinNamesA.indexOf(name)) { $("#preview").attr("src", "skins/" + name + ".png"); } }; window.getMapStartX = function() { return g_minX; } window.getMapStartY = function() { return g_minY; } window.getMapEndX = function() { return g_maxX; } window.getMapEndY = function() { return g_maxY; } window.setGameMode = function(val) { if (val != __unmatched_95) { if (':party' == __unmatched_95) { $('#helloContainer').attr('data-party-state', '0'); } Render(val); if (':party' != val) { Start(); } } }; window.setAcid = function(val) { g_showTrails = val; }; if (null != window.localStorage) { if (null == window.localStorage.AB9) { window.localStorage.AB9 = 0 + ~~(100 * Math.random()); } g_ABGroup = +window.localStorage.AB9; window.ABGroup = g_ABGroup; } $.get(__unmatched_53 + '//gc.agar.io', function(code) { var __unmatched_317 = code.split(' '); code = __unmatched_317[0]; __unmatched_317 = __unmatched_317[1] || ''; if (-1 == ['UA'].indexOf(code)) { g_skinNamesA.push('ussr'); } if (g_regionsByCC.hasOwnProperty(code)) { if ('string' == typeof g_regionsByCC[code]) { if (!g_region) { SetRegion(g_regionsByCC[code]); } else if (g_regionsByCC[code].hasOwnProperty(__unmatched_317)) { if (!g_region) { SetRegion(g_regionsByCC[code][__unmatched_317]); } } } } }, 'text'); if (window.ga) { window.ga('send', 'event', 'User-Agent', window.navigator.userAgent, { nonInteraction: 1 }); } var g_canRefreshAds = true; var g_refreshAdsCooldown = 0; var g_regionsByCC = { AF: 'JP-Tokyo', AX: 'EU-London', AL: 'EU-London', DZ: 'EU-London', AS: 'SG-Singapore', AD: 'EU-London', AO: 'EU-London', AI: 'US-Atlanta', AG: 'US-Atlanta', AR: 'BR-Brazil', AM: 'JP-Tokyo', AW: 'US-Atlanta', AU: 'SG-Singapore', AT: 'EU-London', AZ: 'JP-Tokyo', BS: 'US-Atlanta', BH: 'JP-Tokyo', BD: 'JP-Tokyo', BB: 'US-Atlanta', BY: 'EU-London', BE: 'EU-London', BZ: 'US-Atlanta', BJ: 'EU-London', BM: 'US-Atlanta', BT: 'JP-Tokyo', BO: 'BR-Brazil', BQ: 'US-Atlanta', BA: 'EU-London', BW: 'EU-London', BR: 'BR-Brazil', IO: 'JP-Tokyo', VG: 'US-Atlanta', BN: 'JP-Tokyo', BG: 'EU-London', BF: 'EU-London', BI: 'EU-London', KH: 'JP-Tokyo', CM: 'EU-London', CA: 'US-Atlanta', CV: 'EU-London', KY: 'US-Atlanta', CF: 'EU-London', TD: 'EU-London', CL: 'BR-Brazil', CN: 'CN-China', CX: 'JP-Tokyo', CC: 'JP-Tokyo', CO: 'BR-Brazil', KM: 'EU-London', CD: 'EU-London', CG: 'EU-London', CK: 'SG-Singapore', CR: 'US-Atlanta', CI: 'EU-London', HR: 'EU-London', CU: 'US-Atlanta', CW: 'US-Atlanta', CY: 'JP-Tokyo', CZ: 'EU-London', DK: 'EU-London', DJ: 'EU-London', DM: 'US-Atlanta', DO: 'US-Atlanta', EC: 'BR-Brazil', EG: 'EU-London', SV: 'US-Atlanta', GQ: 'EU-London', ER: 'EU-London', EE: 'EU-London', ET: 'EU-London', FO: 'EU-London', FK: 'BR-Brazil', FJ: 'SG-Singapore', FI: 'EU-London', FR: 'EU-London', GF: 'BR-Brazil', PF: 'SG-Singapore', GA: 'EU-London', GM: 'EU-London', GE: 'JP-Tokyo', DE: 'EU-London', GH: 'EU-London', GI: 'EU-London', GR: 'EU-London', GL: 'US-Atlanta', GD: 'US-Atlanta', GP: 'US-Atlanta', GU: 'SG-Singapore', GT: 'US-Atlanta', GG: 'EU-London', GN: 'EU-London', GW: 'EU-London', GY: 'BR-Brazil', HT: 'US-Atlanta', VA: 'EU-London', HN: 'US-Atlanta', HK: 'JP-Tokyo', HU: 'EU-London', IS: 'EU-London', IN: 'JP-Tokyo', ID: 'JP-Tokyo', IR: 'JP-Tokyo', IQ: 'JP-Tokyo', IE: 'EU-London', IM: 'EU-London', IL: 'JP-Tokyo', IT: 'EU-London', JM: 'US-Atlanta', JP: 'JP-Tokyo', JE: 'EU-London', JO: 'JP-Tokyo', KZ: 'JP-Tokyo', KE: 'EU-London', KI: 'SG-Singapore', KP: 'JP-Tokyo', KR: 'JP-Tokyo', KW: 'JP-Tokyo', KG: 'JP-Tokyo', LA: 'JP-Tokyo', LV: 'EU-London', LB: 'JP-Tokyo', LS: 'EU-London', LR: 'EU-London', LY: 'EU-London', LI: 'EU-London', LT: 'EU-London', LU: 'EU-London', MO: 'JP-Tokyo', MK: 'EU-London', MG: 'EU-London', MW: 'EU-London', MY: 'JP-Tokyo', MV: 'JP-Tokyo', ML: 'EU-London', MT: 'EU-London', MH: 'SG-Singapore', MQ: 'US-Atlanta', MR: 'EU-London', MU: 'EU-London', YT: 'EU-London', MX: 'US-Atlanta', FM: 'SG-Singapore', MD: 'EU-London', MC: 'EU-London', MN: 'JP-Tokyo', ME: 'EU-London', MS: 'US-Atlanta', MA: 'EU-London', MZ: 'EU-London', MM: 'JP-Tokyo', NA: 'EU-London', NR: 'SG-Singapore', NP: 'JP-Tokyo', NL: 'EU-London', NC: 'SG-Singapore', NZ: 'SG-Singapore', NI: 'US-Atlanta', NE: 'EU-London', NG: 'EU-London', NU: 'SG-Singapore', NF: 'SG-Singapore', MP: 'SG-Singapore', NO: 'EU-London', OM: 'JP-Tokyo', PK: 'JP-Tokyo', PW: 'SG-Singapore', PS: 'JP-Tokyo', PA: 'US-Atlanta', PG: 'SG-Singapore', PY: 'BR-Brazil', PE: 'BR-Brazil', PH: 'JP-Tokyo', PN: 'SG-Singapore', PL: 'EU-London', PT: 'EU-London', PR: 'US-Atlanta', QA: 'JP-Tokyo', RE: 'EU-London', RO: 'EU-London', RU: 'RU-Russia', RW: 'EU-London', BL: 'US-Atlanta', SH:
Aayushi-2808 / Cervical Cancer Detection Using ML# Cervical_cancer_detection_using_ML # Introduction According to World Health Organisation (WHO), when detected at an early stage, cervical cancer is one of the most curable cancers. Hence, the main motive behind this project is to detect the cancer in its early stages so that it can be treated and managed in the patients effectively. # Flow of project is as explained below: This project is divided into 5 parts: 1. Data Cleaning 2. Exploratory Data Analysis 3. Baseline model: Logistic Regression 4. Ensemble Models: Bagging with Decision Trees, Random forest and Boosting 5. Model Comparison and results # Refer below for References: Link to basic information regarding cervical cancer : https://www.cdc.gov/cancer/cervical/basic_info/index.htm The dataset for tackling the problem is supplied by the UCI repository for Machine Learning. Link to Dataset : https://archive.ics.uci.edu/ml/datasets/Cervical+cancer+%28Risk+Factors%29 The dataset contains a list of risk factors that lead up to the Biopsy examination. The generation of the predictor variable is taken care of in part 2 (Exploratory data analysis) of this report. We will try to predict the 'biopsy' variable from the dataset using Logistic Regression, Random Forest, Bagging with Decision Trees and Boosting with XGBoost Classifier. # Results: Based on our Base model and The Ensemble Models we used, we observed - 1. After the entire process of training, hyperparameter tuning and tackling class imbalance was complete , we obtained the results as depicted through the graphics. 2. We observe that Bagging and Random Forest gives the highest accuracy and precision of 97.09 and 80% resp. 3. Plotting the Confusion matrix showed us that Random Forest using upsampling and class weights gives us 2 false positives and 3 false negatives with auc of 0.87 # Why random forest is the best model?? 1. So as we see, while comparing all of our models,RF has maximum f1_score and accuracy along with Bagging i.e. 76.2 n 97.09% resp. 2. And it also produces the same amount of false negatives with a recall of 72.73% just like all the other models. 3. But we still consider RF better coz of its added advantage that, the decision trees are decorrelated as compared to bagging leading to lesser variance and greater ability to generalize. # Conclusion: On observing the feature importance of the best model i.e random forest, we can see that the most important features are Schiller, Hinselmann, HPV, Citology, etc. This also makes sense because Schiller and Hinselmann are actually the tests used to detect cervical cancer. # Problems Faced: A major problem encountered while training the model was that it had too little data to train. On collaborating with all the hospitals in India, we can have enough data points to train a model with a higher recall, thus making the model better. # Scope of Improvement As next steps I would want to do exactly that, to deploy the model and refine it. We may also modify the number of the predictor variables, as it may well turn out that there are other predictors which may not be present in our current dataset. This can only be found by practical implementation of our predictions.
Bribak / SURFY2This repository constitutes SURFY2 and corresponds to the bioRxiv preprint 'Updating the in silico human surfaceome with meta-ensemble learning and feature engineering' by Daniel Bojar. SURFY2 is a machine learning classifier to predict whether a human transmembrane protein is located at the surface of a cell (the plasma membrane) or in one of the intracellular membranes based on the sequence characteristics of the protein. Making use of the data described in the recent publication from Bausch-Fluck et al. (https://doi.org/10.1073/pnas.1808790115), SURFY2 considerably improves on their reported classifier SURFY in terms of accuracy (95.5%), precision (94.3%), recall (97.6%) and area under ROC curve (0.954) when using a test set never seen by the classifier before. SURFY2 consists of a layer of 12 base estimators generating 24 new engineered features (class probabilities for both classes) which are appended to the original 253 features. Then, a soft voting classifier with three optimized base estimators (Random Forest, Gradient Boosting and Logistic Regression) and optimized voting weights is trained on this expanded dataset, resulting in the final prediction. The motivation of SURFY2 is to provide an updated and better version of the in silico human surfaceome to facilitate research and drug development on human surface-exposed transmembrane proteins. Additionally, SURFY2 enabled insights into biological properties of these proteins and generated several new hypotheses / ideas for experiments. The workflow is as following: 1) dataPrep Gets training data from data.xlsx, labels it according to surface class and outputs 'train_data.csv' 2) split Gets train_data.csv, splits it into training, validation and test data and outputs 'train.csv', 'val.csv', 'test.csv'. 3) main_val Was used for optimizing hyperparameters of base estimators and estimators & weights of voting classifier. Stores all estimators. Evaluates meta-ensemble classifier SURFY2 on validation set. 4) classifier_selection All base estimators and meta-ensemble approaches are tested on the initial dataset as well as the expanded dataset including the engineered features and compared in terms of their cross-validation score. 5) main_test Evaluates SURFY2 on the separate test set (trained on training + validation set). 6) testing_SURFY Evaluates the original SURFY through cross-validation and on validation as well as test set. 7) pred_unlabeled Uses SURFY2 to predict the surface label (+ prediction score) for unlabeled proteins in data.xlsx. Also gets the feature importances of the voting classifier estimators. 8) getting_discrepancies Compare predictions with those made by SURFY ('surfy.xlsx') and store mismatches. Also store the 10 most confident mismatches (by SURFY2 classification score) from each class. 9) feature_importances Plot the 10 most important features for the voting classifier estimators (Random Forest, Gradient Boosting, Logistic Regression) to interpret predictions. 10) base_estimator_importances Plot the 10 most important features for the two most important base estimators (XGBClassifier and Gradient Boosting). 11) comparing_mismatches Separate datasets into shared & discrepant predictions (between SURFY and SURFY2). Compare feature means and select features with the highest class feature mean differences between prediction datasets. Statistically analyze differences in features means between classes in both prediction datasets. Plot 9 representative features with their means grouped according to class and prediction dataset to rationalize discrepant predictions. 12) tSNE_surfy2 Perform nonlinear dimensionality reduction using t-SNE on proteins with predictions from both SURFY and SURFY2. Plot the two t-SNE dimensions and label the proteins according to their prediction class in order to see where discrepant predictions reside in the landscape. Plot surface proteins with most prevalent annotated functional subclasses and label them according to their subclass to enable comparison to class predictions. Functional annotations came from 'surfy.xlsx'.
timdeputter / RendezvousImplementation of the Rendezvous or Highest Random Weight (HRW) hashing algorithm in the Elixir Programming Language
SenseUnit / AhrwAggregated Highest Random Weight Hashing / Aggregated Rendezvous Hashing
codahale / HrwA Go implementation of Highest Random Weight hashing.
motmaytinh / WeightedRendezvousHashWeighted Rendezvous or Weighted Highest Random Weight (WHRW) hashing algorithm
