{"schema_version":1,"url":"https://uwcourses.com/courses/COMPSCI_774","title":"COMPSCI 774: Data Exploration, Cleaning, and Integration for Data Science | UW–Madison","dataset":{"revision":"e243353dcb7d79b7247ced91d69443ef4c2a6349","repository":"twangodev/uwcourses","schema_version":6,"importer_version":"7","projection_id":"52a78527ff09011d88cb04c7d43867d9fbfec2930bf1dd2ec359ebd2844e0b07","observed_at":"2026-09-07T15:55:43.033547+00:00","built_at":"2026-09-10T19:50:42.743001+00:00","courses":8951,"current_instructors":5754,"limited":false,"terms":["1272","1264","1262","1254","1252","1244","1242","1234","1232","1224","1222","1212","1204","1202","1194","1192","1184","1182","1174","1172","1164","1162","1154","1152","1144","1142","1134","1132","1124","1122","1114","1112","1104","1102","1094","1092","1084","1082","1074","1072"],"term":"1272","departments":[{"subject":"AAE","count":90},{"subject":"ABT","count":20},{"subject":"ACCTIS","count":36},{"subject":"ACTSCI","count":14},{"subject":"AFAERO","count":10},{"subject":"AFRICAN","count":87},{"subject":"AFROAMER","count":71},{"subject":"AGROECOL","count":21},{"subject":"AMERIND","count":53},{"subject":"ANAT&PHY","count":7},{"subject":"ANATOMY","count":2},{"subject":"ANESTHES","count":8},{"subject":"ANSCI","count":57},{"subject":"ANTHRO","count":95},{"subject":"ART","count":125},{"subject":"ARTED","count":10},{"subject":"ARTHIST","count":121},{"subject":"ASIALANG","count":129},{"subject":"ASIAN","count":109},{"subject":"ASIANAM","count":28},{"subject":"ASTRON","count":38},{"subject":"ATMOCN","count":69},{"subject":"BIOCHEM","count":51},{"subject":"BIOCORE","count":10},{"subject":"BIOLOGY","count":14},{"subject":"BIOMDSCI","count":18},{"subject":"BME","count":66},{"subject":"BMI","count":41},{"subject":"BMOLCHEM","count":10},{"subject":"BOTANY","count":69},{"subject":"BSE","count":44},{"subject":"C&ESOC","count":73},{"subject":"CBE","count":48},{"subject":"CHEM","count":101},{"subject":"CHICLA","count":52},{"subject":"CIVENGR","count":133},{"subject":"CLASSICS","count":47},{"subject":"CNP","count":10},{"subject":"CNSRSCI","count":50},{"subject":"COMARTS","count":137},{"subject":"COMPBIO","count":15},{"subject":"COMPLIT","count":11},{"subject":"COMPSCI","count":138},{"subject":"COUNPSY","count":78},{"subject":"CRB","count":19},{"subject":"CS&D","count":71},{"subject":"CSCS","count":40},{"subject":"CURRIC","count":193},{"subject":"DANCE","count":93},{"subject":"DERM","count":8},{"subject":"DS","count":88},{"subject":"DYSCI","count":35},{"subject":"ECE","count":155},{"subject":"ECON","count":145},{"subject":"EDPOL","count":114},{"subject":"EDPSYCH","count":97},{"subject":"ELPA","count":70},{"subject":"EMA","count":53},{"subject":"EMERMED","count":17},{"subject":"ENGL","count":206},{"subject":"ENTOM","count":40},{"subject":"ENVIRST","count":148},{"subject":"EP","count":15},{"subject":"EPD","count":67},{"subject":"ESL","count":16},{"subject":"F&WECOL","count":60},{"subject":"FAMMED","count":22},{"subject":"FINANCE","count":50},{"subject":"FOLKLORE","count":40},{"subject":"FOODSCI","count":43},{"subject":"FRENCH","count":63},{"subject":"GEN&WS","count":145},{"subject":"GENBUS","count":72},{"subject":"GENECSLR","count":17},{"subject":"GENETICS","count":60},{"subject":"GEOG","count":113},{"subject":"GEOSCI","count":83},{"subject":"GERMAN","count":82},{"subject":"GLE","count":48},{"subject":"GNS","count":38},{"subject":"GREEK","count":27},{"subject":"HDFS","count":41},{"subject":"HEBR-BIB","count":13},{"subject":"HEBR-MOD","count":10},{"subject":"HISTORY","count":233},{"subject":"HISTSCI","count":56},{"subject":"HONCOL","count":13},{"subject":"ILS","count":43},{"subject":"INFOSYS","count":9},{"subject":"INTEGART","count":7},{"subject":"INTEGSCI","count":22},{"subject":"INTER-AG","count":18},{"subject":"INTER-HE","count":11},{"subject":"INTER-LS","count":22},{"subject":"INTEREGR","count":16},{"subject":"INTLBUS","count":21},{"subject":"INTLST","count":50},{"subject":"ISYE","count":83},{"subject":"ITALIAN","count":53},{"subject":"JEWISH","count":56},{"subject":"JOURN","count":88},{"subject":"KINES","count":128},{"subject":"LACIS","count":26},{"subject":"LANDARC","count":61},{"subject":"LATIN","count":24},{"subject":"LAW","count":120},{"subject":"LEGALST","count":48},{"subject":"LINGUIS","count":35},{"subject":"LIS","count":89},{"subject":"LITTRANS","count":78},{"subject":"LSC","count":52},{"subject":"M&ENVTOX","count":7},{"subject":"MARKETNG","count":62},{"subject":"MATH","count":153},{"subject":"MDGENET","count":8},{"subject":"ME","count":130},{"subject":"MEDHIST","count":43},{"subject":"MEDICINE","count":60},{"subject":"MEDIEVAL","count":32},{"subject":"MEDPHYS","count":39},{"subject":"MEDSC-M","count":29},{"subject":"MEDSC-V","count":41},{"subject":"MHR","count":68},{"subject":"MICROBIO","count":45},{"subject":"MILSCI","count":16},{"subject":"MM&I","count":22},{"subject":"MOLBIOL","count":6},{"subject":"MS&E","count":59},{"subject":"MUSIC","count":165},{"subject":"MUSPERF","count":126},{"subject":"NAVSCI","count":20},{"subject":"NE","count":44},{"subject":"NEURODPT","count":11},{"subject":"NEUROL","count":7},{"subject":"NEURSURG","count":4},{"subject":"NTP","count":11},{"subject":"NURSING","count":111},{"subject":"NUTRSCI","count":65},{"subject":"OBS&GYN","count":18},{"subject":"OCCTHER","count":39},{"subject":"ONCOLOGY","count":14},{"subject":"OPHTHALM","count":5},{"subject":"OTM","count":43},{"subject":"PATH","count":34},{"subject":"PATH-BIO","count":29},{"subject":"PEDIAT","count":26},{"subject":"PHARMACY","count":31},{"subject":"PHILOS","count":77},{"subject":"PHMCOL-M","count":11},{"subject":"PHMPRAC","count":45},{"subject":"PHMSCI","count":60},{"subject":"PHYASST","count":37},{"subject":"PHYSICS","count":88},{"subject":"PHYSIOL","count":3},{"subject":"PHYTHER","count":37},{"subject":"PLANTSCI","count":52},{"subject":"PLPATH","count":35},{"subject":"POLISCI","count":192},{"subject":"POPHLTH","count":58},{"subject":"PORTUG","count":33},{"subject":"PSYCH","count":101},{"subject":"PSYCHIAT","count":22},{"subject":"PUBAFFR","count":54},{"subject":"PUBLHLTH","count":23},{"subject":"RADIOL","count":11},{"subject":"REALEST","count":41},{"subject":"RELIGST","count":90},{"subject":"RHABMED","count":9},{"subject":"RMI","count":24},{"subject":"RP&SE","count":102},{"subject":"S&APHM","count":17},{"subject":"SCANDST","count":73},{"subject":"SLAVIC","count":89},{"subject":"SOC","count":149},{"subject":"SOCWORK","count":87},{"subject":"SOILSCI","count":46},{"subject":"SPANISH","count":83},{"subject":"SRMED","count":21},{"subject":"STAT","count":94},{"subject":"STDYABRD","count":52},{"subject":"STS","count":8},{"subject":"SURGERY","count":25},{"subject":"SURGSCI","count":33},{"subject":"THEATRE","count":91},{"subject":"URBRPL","count":60},{"subject":"UROLOGY","count":5},{"subject":"ZOOLOGY","count":89}],"deployed_at":null},"data":{"course":{"run_id":"20260907T155543-ce3781c4","semester":"1272","observed_at":"2026-09-07 15:55:43.033547+00:00","record_version_id":"eb268fdc467307ea0c137ea3860f5d99f24b181a6db75d82789383649711347c","course_id":"COMPSCI 774","course_uid":"course_5ab2d4759486b00da0bb13b5","catalog_version_id":"e85f05ffd2d4f4c4902d449fe531a33d9165f7a5e3e29cb93fc655ca4b14f4b9","course_number":774,"subjects":["COMPSCI"],"title":"DATA EXPLORATION, CLEANING, AND INTEGRATION FOR DATA SCIENCE","description":"Big Data is often said to deal with four Vs: volume, velocity, variety, and veracity. The focus is on variety and veracity challenges, which often arise in data science projects. In many such projects, data is often incorrect, hard to understand, and come from a variety of sources. Data scientists often spend 80% of their effort to explore, clean, and integrate this data, before analysis can be carried out to extract insights. As a result, managing variety and veracity has received significant attention. Study these topics, understand their challenges, and discuss solutions. These solutions often require data management, machine learning, big data scaling, cloud, crowdsourcing, and user interaction techniques. Knowledge of machine learning/AI [COMP SCI 540], databases [COMP SCI 564] and Python [COMP SCI 320] recommended.","requirements_text":"Graduate/professional standing","credits_min":null,"credits_max":null,"credit_offering_ids":[],"llm_job_id":"enrich-8b774950c2b6adfdc46d1b82","llm_output_id":"3ec64fe09ace5b599429d3f424b0a433a43f0b35829af5d6fa841dc2b28b41aa","llm_model":"nvidia/Qwen3.6-35B-A3B-NVFP4","llm_model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","llm_task_version":"14","llm_search_status":"valid","llm_summary":"This course covers data exploration, cleaning, and integration for data science, focusing on variety and veracity challenges using data management, machine learning, and cloud techniques.","llm_topics":["Big Data variety and veracity challenges","Data exploration, cleaning, and integration","Data management, machine learning, big data scaling, cloud, crowdsourcing, and user interaction techniques"],"llm_skills":["Data management, machine learning, big data scaling, cloud, crowdsourcing, and user interaction techniques","Data exploration, cleaning, and integration"],"llm_assumed_background":["Machine learning, databases, and Python programming","Machine learning and probabilistic reasoning","Database management systems and data models","Intermediate Python programming and data structures"],"llm_search_phrases":["big data variety veracity","data cleaning integration","data science programming python","machine learning databases graduate"],"llm_requirements_status":"valid","llm_student_summary_status":"valid","llm_experience_status":"insufficient_evidence","catalog_variants":[],"student_summary":{"context_hash":"1608782ef9e92e5b74ff80ed987c381ff15c2b0d20c25f6a185aa004e9ad7f84","course_id":"COMPSCI 774","current_instructors":[],"difficulty_workload":[],"errors":[],"historical_context":[],"message":"No course-specific reviews available","offered":false,"profile_hash":"5cb4dabf887cdbcd8c00d5a1312e10828b95c63f30bc3ea76aea199565390d02","quick_take":[{"citations":[{"course_id":"COMPSCI 774","run_id":"20260907T155543-ce3781c4","source_record":{"entity_id":"777078ea-c43e-380d-9c7f-50d97ec7ddbb","file":"tables/observations.parquet","kind":"grades","source":"madgrades"},"table":"grades_latest","term_id":"1254","type":"grade"},{"course_id":"COMPSCI 774","run_id":"20260907T155543-ce3781c4","source_record":{"entity_id":"777078ea-c43e-380d-9c7f-50d97ec7ddbb","file":"tables/observations.parquet","kind":"grades","source":"madgrades"},"table":"grades_latest","term_id":"1264","type":"grade"}],"text":"Recent recorded grades — Spring 2025: 3.97 GPA, 100.0% A/AB (n=51 letter grades); Spring 2026: 3.77 GPA, 81.8% A/AB (n=66 letter grades)."}],"student_experience":[],"task_hash":"74fb0997943e888960bbc9e47db8c4fd12e4292d55c20509d8d89db6a9910f68","teaching_history":[],"term_id":"1272","term_name":"2026 Fall","version":2},"requirements":{"nodes":[{"children":[],"condition":"Graduate/professional standing","course":null,"evidence":"Graduate/professional standing","id":"n0","kind":"condition"}],"notes":[],"root":"n0","status":"parsed"},"instructors":[],"offerings":[],"sections":[],"grade_instructors":[{"instructor_uid":"instructor_8a8d069a7cfff58ad5a275b4","source":"madgrades","source_instructor_id":"4195805","identity_basis":"source_id","identity_status":"source_identified","name":"AN H DOAN","email":null,"first_observed_at":"2026-09-06 23:14:58.172943+00:00","last_observed_at":"2026-09-07 15:55:43.033547+00:00","grade_statistics":{"gpa":3.693,"graded":1832,"counts":[1122,428,196,66,10,6,4],"sections":152},"instructor_url":"/instructors/AN_H_DOAN"},{"instructor_uid":"instructor_e485342c7375f6ab43cf133d","source":"madgrades","source_instructor_id":"6657792","identity_basis":"source_id","identity_status":"source_identified","name":"DEV AHLUWALIA","email":null,"first_observed_at":"2026-09-06 23:14:58.172943+00:00","last_observed_at":"2026-09-07 15:55:43.033547+00:00","grade_statistics":{"gpa":3.304,"graded":441,"counts":[180,81,80,53,36,9,2],"sections":3},"instructor_url":"/instructors/DEV_AHLUWALIA--instructor_e485342c7375f6ab43cf133d"}],"grades":[{"run_id":"20260907T155543-ce3781c4","semester":"1272","observed_at":"2026-09-07 15:55:43.033547+00:00","course_id":"COMPSCI 774","course_uid":"course_5ab2d4759486b00da0bb13b5","term_id":"1254","term_name":"Spring 2025","instructors":["AN H DOAN"],"a":48,"ab":3,"b":0,"bc":0,"c":0,"d":0,"f":0,"satisfactory":0,"unsatisfactory":0,"credit":0,"no_credit":0,"passed":0,"incomplete":0,"no_work":0,"not_reported":0,"other":0,"total":51,"source_aliases":["COMPSCI 774"]},{"run_id":"20260907T155543-ce3781c4","semester":"1272","observed_at":"2026-09-07 15:55:43.033547+00:00","course_id":"COMPSCI 774","course_uid":"course_5ab2d4759486b00da0bb13b5","term_id":"1264","term_name":"Spring 2026","instructors":["AN H DOAN","DEV AHLUWALIA"],"a":48,"ab":6,"b":12,"bc":0,"c":0,"d":0,"f":0,"satisfactory":1,"unsatisfactory":0,"credit":0,"no_credit":0,"passed":0,"incomplete":0,"no_work":0,"not_reported":0,"other":0,"total":67,"source_aliases":["COMPSCI 774"]}],"statistics":{"gpa":3.859,"graded":117,"counts":[96,9,12,0,0,0,0]},"grade_conflicts":[],"evidence":{"history":["/data/e243353dcb7d79b7247ced91d69443ef4c2a6349/history/course_5ab2d4759486b00da0bb13b5-0.json"],"traces":["/data/e243353dcb7d79b7247ced91d69443ef4c2a6349/traces/course_5ab2d4759486b00da0bb13b5-0.json"],"results":["/data/e243353dcb7d79b7247ced91d69443ef4c2a6349/results/course_5ab2d4759486b00da0bb13b5-0.json"]},"revision":"e243353dcb7d79b7247ced91d69443ef4c2a6349"},"context":{"all":{"term":"","gpa":3.858974358974359,"count":117,"university":{"size":2021,"gpaPercentile":69,"countPercentile":65,"medianCount":77,"histogram":[{"range":"0.0–0.4","count":0,"current":false},{"range":"0.4–0.8","count":0,"current":false},{"range":"0.8–1.2","count":0,"current":false},{"range":"1.2–1.6","count":0,"current":false},{"range":"1.6–2.0","count":0,"current":false},{"range":"2.0–2.4","count":0,"current":false},{"range":"2.4–2.8","count":21,"current":false},{"range":"2.8–3.2","count":152,"current":false},{"range":"3.2–3.6","count":521,"current":false},{"range":"3.6–4.0","count":1327,"current":true}]},"departments":[{"subject":"COMPSCI","comparison":{"size":65,"gpaPercentile":83,"countPercentile":45,"medianCount":126,"histogram":[{"range":"0.0–0.4","count":0,"current":false},{"range":"0.4–0.8","count":0,"current":false},{"range":"0.8–1.2","count":0,"current":false},{"range":"1.2–1.6","count":0,"current":false},{"range":"1.6–2.0","count":0,"current":false},{"range":"2.0–2.4","count":0,"current":false},{"range":"2.4–2.8","count":1,"current":false},{"range":"2.8–3.2","count":8,"current":false},{"range":"3.2–3.6","count":28,"current":false},{"range":"3.6–4.0","count":28,"current":true}]}}]},"terms":{"1254":{"term":"1254","gpa":3.9705882352941178,"count":51,"university":{"size":1289,"gpaPercentile":92,"countPercentile":37,"medianCount":66,"histogram":[{"range":"0.0–0.4","count":0,"current":false},{"range":"0.4–0.8","count":0,"current":false},{"range":"0.8–1.2","count":0,"current":false},{"range":"1.2–1.6","count":0,"current":false},{"range":"1.6–2.0","count":0,"current":false},{"range":"2.0–2.4","count":0,"current":false},{"range":"2.4–2.8","count":17,"current":false},{"range":"2.8–3.2","count":128,"current":false},{"range":"3.2–3.6","count":379,"current":false},{"range":"3.6–4.0","count":765,"current":true}]},"departments":[{"subject":"COMPSCI","comparison":{"size":52,"gpaPercentile":98,"countPercentile":20,"medianCount":105,"histogram":[{"range":"0.0–0.4","count":0,"current":false},{"range":"0.4–0.8","count":0,"current":false},{"range":"0.8–1.2","count":0,"current":false},{"range":"1.2–1.6","count":0,"current":false},{"range":"1.6–2.0","count":0,"current":false},{"range":"2.0–2.4","count":0,"current":false},{"range":"2.4–2.8","count":1,"current":false},{"range":"2.8–3.2","count":10,"current":false},{"range":"3.2–3.6","count":24,"current":false},{"range":"3.6–4.0","count":17,"current":true}]}}]},"1264":{"term":"1264","gpa":3.772727272727273,"count":66,"university":{"size":1283,"gpaPercentile":59,"countPercentile":49,"medianCount":66,"histogram":[{"range":"0.0–0.4","count":0,"current":false},{"range":"0.4–0.8","count":0,"current":false},{"range":"0.8–1.2","count":0,"current":false},{"range":"1.2–1.6","count":0,"current":false},{"range":"1.6–2.0","count":0,"current":false},{"range":"2.0–2.4","count":1,"current":false},{"range":"2.4–2.8","count":20,"current":false},{"range":"2.8–3.2","count":130,"current":false},{"range":"3.2–3.6","count":343,"current":false},{"range":"3.6–4.0","count":789,"current":true}]},"departments":[{"subject":"COMPSCI","comparison":{"size":48,"gpaPercentile":74,"countPercentile":32,"medianCount":105.5,"histogram":[{"range":"0.0–0.4","count":0,"current":false},{"range":"0.4–0.8","count":0,"current":false},{"range":"0.8–1.2","count":0,"current":false},{"range":"1.2–1.6","count":0,"current":false},{"range":"1.6–2.0","count":0,"current":false},{"range":"2.0–2.4","count":0,"current":false},{"range":"2.4–2.8","count":1,"current":false},{"range":"2.8–3.2","count":7,"current":false},{"range":"3.2–3.6","count":21,"current":false},{"range":"3.6–4.0","count":19,"current":true}]}}]}},"benchmarks":{"all":{"school":{"size":2021,"gpa":3.660373947354374,"topShare":82.25902967226666,"count":77},"COMPSCI":{"size":65,"gpa":3.54676671421842,"topShare":75.29768070134821,"count":126}},"terms":{"1254":{"school":{"size":1289,"gpa":3.6126423469389106,"topShare":79.48050408754871,"count":66},"COMPSCI":{"size":52,"gpa":3.482652727664103,"topShare":71.33786483648515,"count":105}},"1264":{"school":{"size":1283,"gpa":3.6229729166451925,"topShare":80.13669149396227,"count":66},"COMPSCI":{"size":48,"gpa":3.5022746140005943,"topShare":73.13318776233326,"count":105.5}}}}},"instructorTrends":[{"uid":"instructor_8a8d069a7cfff58ad5a275b4","name":"AN H DOAN","count":117,"terms":[{"term":"1254","count":51,"sections":1,"gpa":3.9705882352941178},{"term":"1264","count":66,"sections":1,"gpa":3.772727272727273}]},{"uid":"instructor_e485342c7375f6ab43cf133d","name":"DEV AHLUWALIA","count":66,"terms":[{"term":"1264","count":66,"sections":1,"gpa":3.772727272727273}]}],"following":[{"code":"COMPSCI 739","title":"DISTRIBUTED SYSTEMS"}],"projection":null}}