All authors
Claude Skills by wenmin-wu
github.com/wenmin-wu535 skills0 installs779 views
- Yes No Answer Type RoutingRoutes QA predictions through an answer-type classifier to emit boolean answers, extractive spans, or null based on type logits.Votes: 0GitHub stars: 61
- Adversarial ValidationTrains a classifier to distinguish train from test data, detecting distribution shift and identifying leaked features.Votes: 0GitHub stars: 61
- Anomaly Flag ImputationDetects sentinel anomaly values in numeric columns, creates a boolean flag feature, then replaces the sentinel with NaN for proper imputation.Votes: 0GitHub stars: 61
- Anonymized Target Reverse EngineeringProbe an anonymized regression target by testing whether simple invertible transforms (2**y, exp(y), log(y), affine rescale) produce a distribution with recognizable structure — round numbers, integer histograms, or a familiar finance/retail range — and use the recovered semantics to motivate features and loss choices the host's bland description would never suggestVotes: 0GitHub stars: 61
- Authorized Flag Table SplitSplit a transaction table by a binary status flag (authorized vs. declined, paid vs. refunded) into two parallel sub-tables, then build the same aggregate feature pipeline on each — the declined-transaction features are usually as predictive as the authorized ones because they encode risk and friction the authorized stream alone hidesVotes: 0GitHub stars: 61
- Autoencoder Timeseries EmbeddingTrain a PyTorch autoencoder on time-series summary statistics to produce dense encoded features for downstream GBDT modelsVotes: 0GitHub stars: 61
- Balanced Log LossClass-balanced log loss that weights each class by the inverse of its sample count, equalizing the contribution of minority and majority classes.Votes: 0GitHub stars: 61
- Ball Landing PredictionPredict where a projectile will land using kinematic equations with estimated gravity to intercept aerial passes in game AI simulationsVotes: 0GitHub stars: 61
- Brand Name Recovery From TitleRecover missing categorical values by matching words in a related text field against a known vocabulary built from the full datasetVotes: 0GitHub stars: 61
- Catboost MultirmseCatBoostRegressor with MultiRMSE loss for native multi-output regression, predicting all targets in a single model without per-target loops.Votes: 0GitHub stars: 61
- Chained Target PredictionPredict correlated targets sequentially, using earlier target predictions as input features for subsequent targets to exploit inter-target dependenciesVotes: 0GitHub stars: 61
- Chunked Hdf5 StreamingStreams large HDF5 files in fixed-size row chunks to compute summary statistics without loading the full dataset into memory.Votes: 0GitHub stars: 61
- Co Purchase Item PairingRecommends items frequently purchased together with a customer's recent items using pre-computed pair dictionaries.Votes: 0GitHub stars: 61
- Collinear Feature RemovalRemoves redundant features by iterating pairwise Pearson correlations and dropping one member of each pair exceeding a threshold.Votes: 0GitHub stars: 61
- Column Shuffle AugmentationAugments imbalanced tabular data by independently shuffling each feature column within a class, creating synthetic samples that preserve per-column marginal distributions.Votes: 0GitHub stars: 61
- Confidence Probability ClippingHard-clips predicted probabilities to 0 or 1 when they exceed high-confidence thresholds, reducing log loss on near-certain predictions.Votes: 0GitHub stars: 61
- Confidence Weighted Rate EncodingEncodes categorical groups by their target rate scaled by a log-confidence factor, smoothing unreliable rates from low-frequency groups toward zero.Votes: 0GitHub stars: 61
- Content Difficulty FeaturesPrecomputes item/content difficulty as historical mean accuracy, merged as a static feature for user-item prediction tasks.Votes: 0GitHub stars: 61
- Convex Hull Bbox RotationMinimize axis-aligned bounding box side length by finding the optimal rotation angle over convex hull vertices using bounded scalar optimizationVotes: 0GitHub stars: 61
- Cross Dataset User AggregationBuild user-level behavioral features (avg listing duration, relisting frequency, total items) by joining auxiliary activity tables that share user_id but not item_id with train/testVotes: 0GitHub stars: 61
- Crps Cdf LossModel cumulative distribution via softmax output layer and CRPS loss — for probabilistic regression over discrete binsVotes: 0GitHub stars: 61
- Cyclical Feature EncodingEncodes cyclical features (hour, month, day-of-week) using sine/cosine transforms to preserve circular distance.Votes: 0GitHub stars: 61
- Declarative Groupby AggregationConfig-driven feature factory that generates groupby aggregation features from a declarative spec list, supporting count, mean, var, nunique, cumcount, and custom lambdas.Votes: 0GitHub stars: 61
- Distribution Matching PostprocessReshapes model predictions to match the known label distribution from training data using rank-based mapping.Votes: 0GitHub stars: 61
- Dtype Preset Csv LoadPredefines minimal unsigned integer dtypes before CSV loading to cut DataFrame memory usage by 2-4x without any data loss.Votes: 0GitHub stars: 61
- Featureunion Field DispatchUse sklearn FeatureUnion with closure-based preprocessors to apply different vectorizers to different DataFrame columns in a single fit_transform callVotes: 0GitHub stars: 61
- Frequency EncodingAdds each feature's value-count frequency as a new column, enabling tree models to split on how common or rare a value is.Votes: 0GitHub stars: 61
- Game State Grid EncodingEncode a 2D game board into a normalized multi-channel feature tensor with log-scaled resources, signed unit counts, and directional features for RL agentsVotes: 0GitHub stars: 61
- Gmm Feature AugmentationFits a Gaussian Mixture Model on the joint feature-target space and samples synthetic data pairs to augment small tabular datasets.Votes: 0GitHub stars: 61
- Gnn On Knn GraphConstructs a customer similarity graph via KNN on mixed features, then trains a GraphSAGE GNN for node classification. Captures relational patterns that tree and linear models miss, adding ensemble diversity.Votes: 0GitHub stars: 61
- Group Kfold Leak PreventionUses GroupKFold to prevent data leakage when multiple rows share a common entity (e.g., same user, question, or document).Votes: 0GitHub stars: 61
- Group Mean Log Mae MetricCustom evaluation metric that computes log of per-group MAE then averages, penalizing uniformly bad groups.Votes: 0GitHub stars: 61
- Group Shuffle SplitSplits train/validation using GroupShuffleSplit so that related samples (forks, families, sessions) never span both sets.Votes: 0GitHub stars: 61
- Haversine Knn Candidate GenerationGenerates geographically proximate candidate pairs for entity matching using KNN with haversine distance, optionally partitioned by country.Votes: 0GitHub stars: 61
- Hierarchical Collision CascadeThree-level polygon overlap test — AABB early exit, then point-in-polygon ray casting, then segment intersection — for fast non-convex collision detectionVotes: 0GitHub stars: 61
- Hierarchical Rule EngineTwo-level group-then-pattern dispatch for game AI agents where groups filter by game state and ordered patterns within a group fire the first matching actionVotes: 0GitHub stars: 61
- Implicit Als Collaborative FilteringAlternating Least Squares matrix factorization on sparse user-item interaction matrices for implicit feedback recommendations.Votes: 0GitHub stars: 61
- Inner Kfold Target EncodingComputes leak-free target encoding statistics (mean, std, min, max) using nested inner KFold within each outer CV fold, preventing target leakage that occurs with naive groupby-based encoding.Votes: 0GitHub stars: 61
- Iterative Pseudo Label RefinementMulti-round pseudo labeling with progressively confident test predictions merged into training plus OOF-based train label correctionVotes: 0GitHub stars: 61
- L1 Coefficient Interaction MapExtract and visualize per-subgroup feature coefficient signs from L1-regularized models as an interaction heatmap for EDAVotes: 0GitHub stars: 61
- Last Diff Lag FeaturesCompute first-order difference between last and second-to-last rows per entity in panel data to capture recent trend direction and magnitudeVotes: 0GitHub stars: 61
- Leak Free Loop FeaturesIterates through rows chronologically to accumulate user statistics, fetching current state before updating to prevent future data leakage.Votes: 0GitHub stars: 61
- Lgbm Dart BoostingUse LightGBM DART boosting (dropout on trees) with aggressive feature and bagging fractions to reduce overfitting on high-dimensional tabular dataVotes: 0GitHub stars: 61
- Log Odds Fold AveragingAverage model predictions across CV folds in log-odds space rather than probability space for better-calibrated ensemble outputsVotes: 0GitHub stars: 61
- Logit Transform StackingApplies logit transformation to base model probabilities before fitting a logistic regression meta-learner, enabling principled linear combination in log-odds space.Votes: 0GitHub stars: 61
- Logspace Recency RerankingRerank session candidates using log-spaced recency weights multiplied by interaction-type multipliersVotes: 0GitHub stars: 61
- Majority Vote Submission BlendBlend multiple submission CSVs by row-wise majority voting on discrete predictions to produce a more robust final outputVotes: 0GitHub stars: 61
- Morgan Fingerprint FeaturesConverts molecular SMILES strings to fixed-length Morgan fingerprint bit vectors using RDKit for use as tabular ML features.Votes: 0GitHub stars: 61
- Multi Input Embedding NnKeras multi-input model with separate embedding layers for categoricals, GRU for text sequences, and dense layers for numerics, all concatenated into a shared regression trunkVotes: 0GitHub stars: 61
- Multi Output Auxiliary TargetsNeural network with multiple output heads for main target plus auxiliary targets, improving representation learning via shared layers.Votes: 0GitHub stars: 61