[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"me":3,"catalog:en:ml-engineer\u002Ffe-categorical-encoding-mechanics":4,"config":191},null,{"field_key":5,"field_name":6,"seniority":7,"topic_key":8,"topic_name":9,"spec_key":7,"spec_name":7,"locale":10,"cell_total":11,"field_total":12,"seniorities":13,"topics":17,"specs":94,"samples":105},"ml-engineer","ML Engineer","","fe-categorical-encoding-mechanics","Fe Categorical Encoding Mechanics","en",75,1950,[14,15,16],"junior","mid","senior",[18,21,24,27,30,33,36,39,42,45,48,51,54,57,58,61,64,67,70,73,76,79,82,85,88,91],{"key":19,"name":20,"count":11},"cml-distance-clustering-dimreduction","Cml Distance Clustering Dimreduction",{"key":22,"name":23,"count":11},"cml-gradient-boosting-mechanics","Cml Gradient Boosting Mechanics",{"key":25,"name":26,"count":11},"cml-linear-logistic-internals","Cml Linear Logistic Internals",{"key":28,"name":29,"count":11},"cml-probabilistic-models-calibration","Cml Probabilistic Models Calibration",{"key":31,"name":32,"count":11},"cml-svm-kernels-margins","Cml Svm Kernels Margins",{"key":34,"name":35,"count":11},"cml-trees-randomforest-internals","Cml Trees Randomforest Internals",{"key":37,"name":38,"count":11},"dl-architecture-layers","Dl Architecture Layers",{"key":40,"name":41,"count":11},"dl-initialization-optimizers","Dl Initialization Optimizers",{"key":43,"name":44,"count":11},"dl-losses-output-layers","Dl Losses Output Layers",{"key":46,"name":47,"count":11},"dl-normalization-regularization","Dl Normalization Regularization",{"key":49,"name":50,"count":11},"dl-sequence-attention","Dl Sequence Attention",{"key":52,"name":53,"count":11},"dl-training-dynamics-backprop","Dl Training Dynamics Backprop",{"key":55,"name":56,"count":11},"fe-binning-discretization","Fe Binning Discretization",{"key":8,"name":9,"count":11},{"key":59,"name":60,"count":11},"fe-interactions-basis-expansion","Fe Interactions Basis Expansion",{"key":62,"name":63,"count":11},"fe-numeric-transforms-distributions","Fe Numeric Transforms Distributions",{"key":65,"name":66,"count":11},"fe-temporal-cyclical-features","Fe Temporal Cyclical Features",{"key":68,"name":69,"count":11},"fe-text-highcardinality-features","Fe Text Highcardinality Features",{"key":71,"name":72,"count":11},"ml-data-preparation","Ml Data Preparation",{"key":74,"name":75,"count":11},"ml-deployment-serving","Ml Deployment Serving",{"key":77,"name":78,"count":11},"ml-experimentation-reproducibility","Ml Experimentation Reproducibility",{"key":80,"name":81,"count":11},"ml-model-selection-tuning","Ml Model Selection Tuning",{"key":83,"name":84,"count":11},"ml-model-training-evaluation","Ml Model Training Evaluation",{"key":86,"name":87,"count":11},"ml-monitoring-drift","Ml Monitoring Drift",{"key":89,"name":90,"count":11},"ml-problem-framing","Ml Problem Framing",{"key":92,"name":93,"count":11},"ml-scaling-performance","Ml Scaling Performance",[95,99,102],{"key":96,"name":97,"count":98},"classical-ml","Classical ML",450,{"key":100,"name":101,"count":98},"deep-learning","Deep Learning",{"key":103,"name":104,"count":98},"feature-engineering","Feature Engineering",[106,124,138,152,165,178],{"id":107,"topic":9,"difficulty":108,"body":109,"options":110,"correct_key":115,"explanation":123},"01a04b40-ddd5-7b01-bdc4-61be8105285d",1,"A single categorical column holds exactly three distinct values. A one-hot encoder is fitted on it with default settings (scikit-learn 1.6). How many output columns does that one input column produce?",[111,114,117,120],{"key":112,"text":113},"a","Two, with the third level implied once the other two are known",{"key":115,"text":116},"b","Three, one indicator column per distinct level observed during fit",{"key":118,"text":119},"c","One, holding the integer position of the level inside the sorted level list",{"key":121,"text":122},"d","Four: three level indicators plus a reserved column for values not seen during fit","A plain one-hot expansion allocates exactly one indicator column per category recorded at fit time, so three levels give three columns. Neither a compressed integer code nor an extra reserved slot appears under the default settings; those come from other options entirely.",{"id":125,"topic":9,"difficulty":126,"body":127,"options":128,"correct_key":112,"explanation":137},"01a04b40-dddd-784b-bafe-82a4a0620286",2,"A column with five levels is one-hot encoded with drop='first' (scikit-learn 1.6). How wide is the output block for that column, and how does a row belonging to the dropped level look?",[129,131,133,135],{"key":112,"text":130},"Four columns; a row of the dropped level has zero in all four indicators",{"key":115,"text":132},"Four columns; a row of the dropped level carries minus one in the first indicator",{"key":118,"text":134},"Five columns; the first level keeps its column but it is filled with zeros everywhere",{"key":121,"text":136},"Four columns; rows belonging to the dropped level are removed from the output entirely","Dropping one level removes its indicator column, leaving k-1 columns for k levels. That level is still representable: it is the unique pattern where every remaining indicator is zero, which is why the encoding stays lossless.",{"id":139,"topic":9,"difficulty":140,"body":141,"options":142,"correct_key":118,"explanation":151},"01a04b40-dde3-7aae-b544-3ed3faf93bb5",3,"A table has three categorical columns: color (4 levels), is_member (2 levels), plan (3 levels). It is encoded with OneHotEncoder(drop='if_binary') in scikit-learn 1.6. How many output columns result?",[143,145,147,149],{"key":112,"text":144},"6, because one level is dropped from every column",{"key":115,"text":146},"9, because the setting only changes the column names, not the width",{"key":118,"text":148},"8, because only the two-level column loses one of its indicators",{"key":121,"text":150},"7, because the two-level column collapses to zero columns after the drop","The 'if_binary' rule fires only on columns that have exactly two levels, so color contributes 4 and plan contributes 3 unchanged, while is_member contributes 1 instead of 2. That gives 4+1+3 = 8 columns; dropping from every column would give 6.",{"id":153,"topic":9,"difficulty":126,"body":154,"options":155,"correct_key":121,"explanation":164},"01a04b40-dde5-75e1-ab2f-78a9a0090b45","A one-hot encoder is fitted on a city column containing Ankara, Istanbul and Izmir, with handle_unknown='ignore'. At transform time a row arrives with city='Bursa'. What does that row's three-column block contain?",[156,158,160,162],{"key":112,"text":157},"The transform stops with an error naming the unrecognised city value",{"key":115,"text":159},"The indicator of the alphabetically closest known city is set to one",{"key":118,"text":161},"All three indicators are set to the average value each takes in the training data",{"key":121,"text":163},"All three indicators are zero, so the row carries no city information at all","With unknown values ignored, the encoder simply fails to match any known level and emits an all-zero block for that feature. The row still flows through the pipeline with the right width, but every downstream model reads it as 'none of the known cities'.",{"id":166,"topic":9,"difficulty":126,"body":167,"options":168,"correct_key":118,"explanation":177},"01a04b40-ddea-7a8b-ba21-e0e8baf12f02","A size column holds the values S, M, L and XL. An engineer applies OrdinalEncoder() with no extra arguments (scikit-learn 1.6). Which integer codes come out?",[169,171,173,175],{"key":112,"text":170},"S=0, M=1, L=2, XL=3, because the encoder keeps the order of first appearance in the data",{"key":115,"text":172},"S=0, M=1, L=2, XL=3, because the encoder recognises standard clothing size names",{"key":118,"text":174},"L=0, M=1, S=2, XL=3, because the levels are sorted as plain strings before numbering",{"key":121,"text":176},"S=3, M=2, L=1, XL=0, because frequency ranking assigns the smallest code to the commonest level","By default the encoder collects the distinct values and sorts them, and for text that sort is lexicographic, which puts L before M before S before XL. The resulting codes therefore carry an ordering that has nothing to do with garment size.",{"id":179,"topic":9,"difficulty":126,"body":180,"options":181,"correct_key":112,"explanation":190},"01a04b40-ddee-7e82-9e36-bfd5e9958260","An engineer wants the codes for a size column to follow S \u003C M \u003C L \u003C XL rather than the default ordering. In scikit-learn 1.6 they construct OrdinalEncoder(categories=[['S','M','L','XL']]). What does this argument change?",[182,184,186,188],{"key":112,"text":183},"It fixes the level list and its position order, so each level's code is its index in that list",{"key":115,"text":185},"It only validates that those four levels exist, while the codes still follow the sorted order",{"key":118,"text":187},"It makes the encoder learn the ordering from how strongly each level correlates with the target",{"key":121,"text":189},"It rescales the codes to the 0-1 range, equalising the gap between the sizes' codes","Passing an explicit category list replaces the automatic sorted vocabulary with the given sequence, and the code assigned to a level is simply its position there. That is the only supervision the encoder has about ordering, since it never looks at the target.",{"fields":192,"seniorities":414,"interview_shapes":415,"locales":420,"oauth":422,"question_count":425,"coach_enabled":426,"jd_match_enabled":426},[193,218,238,254,278,291,310,329,351,370,385,407],{"key":194,"name_tr":195,"name_en":195,"sort":108,"specializations":196},"backend","Backend",[197,200,203,206,209,212,215],{"key":198,"name":199,"field":194},"general","Genel",{"key":201,"name":202,"field":194},"go","Go",{"key":204,"name":205,"field":194},"python","Python",{"key":207,"name":208,"field":194},"java","Java",{"key":210,"name":211,"field":194},"csharp","C#\u002F.NET",{"key":213,"name":214,"field":194},"nodejs","Node.js",{"key":216,"name":217,"field":194},"php","PHP",{"key":219,"name_tr":220,"name_en":220,"sort":126,"specializations":221},"frontend","Frontend",[222,223,226,229,232,235],{"key":198,"name":199,"field":219},{"key":224,"name":225,"field":219},"javascript","JavaScript",{"key":227,"name":228,"field":219},"typescript","TypeScript",{"key":230,"name":231,"field":219},"react","React",{"key":233,"name":234,"field":219},"vue","Vue",{"key":236,"name":237,"field":219},"angular","Angular",{"key":239,"name_tr":240,"name_en":240,"sort":140,"specializations":241},"fullstack","Fullstack",[242,243,244,245,246,247,248,249,250,251,252,253],{"key":198,"name":199,"field":239},{"key":201,"name":202,"field":194},{"key":204,"name":205,"field":194},{"key":207,"name":208,"field":194},{"key":210,"name":211,"field":194},{"key":213,"name":214,"field":194},{"key":216,"name":217,"field":194},{"key":224,"name":225,"field":219},{"key":227,"name":228,"field":219},{"key":230,"name":231,"field":219},{"key":233,"name":234,"field":219},{"key":236,"name":237,"field":219},{"key":255,"name_tr":256,"name_en":256,"sort":257,"specializations":258},"devops-cloud","DevOps \u002F Cloud",4,[259,260,263,266,269,272,275],{"key":198,"name":199,"field":255},{"key":261,"name":262,"field":255},"aws","AWS",{"key":264,"name":265,"field":255},"gcp","GCP",{"key":267,"name":268,"field":255},"azure","Azure",{"key":270,"name":271,"field":255},"kubernetes","Kubernetes",{"key":273,"name":274,"field":255},"terraform","Terraform",{"key":276,"name":277,"field":255},"linux","Linux",{"key":279,"name_tr":280,"name_en":280,"sort":281,"specializations":282},"ai-engineer","AI Engineer",5,[283,284,285,288],{"key":198,"name":199,"field":279},{"key":204,"name":205,"field":279},{"key":286,"name":287,"field":279},"llm-rag","LLM\u002FRAG",{"key":289,"name":290,"field":279},"mlops","MLOps",{"key":292,"name_tr":293,"name_en":294,"sort":295,"specializations":296},"database","Veritabanı","Database",6,[297,298,301,304,307],{"key":198,"name":199,"field":292},{"key":299,"name":300,"field":292},"postgresql","PostgreSQL",{"key":302,"name":303,"field":292},"mysql","MySQL",{"key":305,"name":306,"field":292},"mongodb","MongoDB",{"key":308,"name":309,"field":292},"redis","Redis",{"key":311,"name_tr":312,"name_en":313,"sort":314,"specializations":315},"mobile","Mobil","Mobile",7,[316,317,320,323,326],{"key":198,"name":199,"field":311},{"key":318,"name":319,"field":311},"ios-swift","iOS (Swift)",{"key":321,"name":322,"field":311},"android-kotlin","Android (Kotlin)",{"key":324,"name":325,"field":311},"flutter","Flutter",{"key":327,"name":328,"field":311},"react-native","React Native",{"key":330,"name_tr":331,"name_en":332,"sort":333,"specializations":334},"security","Güvenlik","Security",8,[335,336,339,342,345,348],{"key":198,"name":199,"field":330},{"key":337,"name":338,"field":330},"appsec","AppSec",{"key":340,"name":341,"field":330},"offensive-pentest","Offensive \u002F Pentest",{"key":343,"name":344,"field":330},"cloud-security","Cloud Security",{"key":346,"name":347,"field":330},"devsecops","DevSecOps",{"key":349,"name":350,"field":330},"blue-team-incident","Blue Team \u002F Incident",{"key":352,"name_tr":353,"name_en":354,"sort":355,"specializations":356},"qa-test-automation","QA \u002F Test Otomasyonu","QA \u002F Test Automation",9,[357,358,361,364,367],{"key":198,"name":199,"field":352},{"key":359,"name":360,"field":352},"test-automation","Test Automation",{"key":362,"name":363,"field":352},"sdet","SDET",{"key":365,"name":366,"field":352},"performance-testing","Performance Testing",{"key":368,"name":369,"field":352},"mobile-qa","Mobile QA",{"key":371,"name_tr":372,"name_en":372,"sort":373,"specializations":374},"data-engineer","Data Engineer",10,[375,376,379,382],{"key":198,"name":199,"field":371},{"key":377,"name":378,"field":371},"pipelines-etl","Pipelines \u002F ETL",{"key":380,"name":381,"field":371},"streaming","Streaming",{"key":383,"name":384,"field":371},"warehousing","Warehousing",{"key":386,"name_tr":387,"name_en":388,"sort":389,"specializations":390},"game-dev","Oyun Geliştirme","Game Development",11,[391,392,395,398,401,404],{"key":198,"name":199,"field":386},{"key":393,"name":394,"field":386},"unity-csharp","Unity (C#)",{"key":396,"name":397,"field":386},"unreal-cpp","Unreal (C++)",{"key":399,"name":400,"field":386},"gameplay","Gameplay",{"key":402,"name":403,"field":386},"graphics-rendering","Graphics \u002F Rendering",{"key":405,"name":406,"field":386},"multiplayer-netcode","Multiplayer \u002F Netcode",{"key":5,"name_tr":6,"name_en":6,"sort":408,"specializations":409},12,[410,411,412,413],{"key":198,"name":199,"field":5},{"key":96,"name":97,"field":5},{"key":103,"name":104,"field":5},{"key":100,"name":101,"field":5},[14,15,16],{"junior":416,"mid":418,"senior":419},{"questions":417,"median_sec":3},20,{"questions":417,"median_sec":3},{"questions":417,"median_sec":3},[421,10],"tr",[423,424],"google","github",28500,true]