All authors
Claude Skills by wenmin-wu
github.com/wenmin-wu535 skills0 installs688 views
- Successive Groupby AggregatesBuild hierarchical features for transaction panels by aggregating twice — first groupby (entity, sub-key) to get a per-(entity, sub-key) summary, then groupby (entity) on those summaries to compute mean/min/max/std across the sub-keys, capturing the *distribution* of per-customer behavior rather than a single flat meanVotes: 0GitHub stars: 61
- Svd Target ReconstructionCompresses high-dimensional targets with TruncatedSVD, trains on the reduced space, then reconstructs full predictions via the components matrix.Votes: 0GitHub stars: 61
- Synthetic Sample DetectionDetects synthetic/fake test samples by checking whether each row has at least one unique value across all features — real samples do, synthetic ones don't.Votes: 0GitHub stars: 61
- Tabnet Sklearn WrapperWrap PyTorch TabNet in a scikit-learn BaseEstimator with built-in imputation and early stopping for use in VotingRegressor ensemblesVotes: 0GitHub stars: 61
- Tabpfn Small Dataset EnsembleEnsembles TabPFN (a prior-fitted Bayesian transformer for small tabular data) with XGBoost, averaging probabilities for stronger predictions on datasets under 1000 rows.Votes: 0GitHub stars: 61
- Tabular To Image CnnReshapes tabular features into 2D pseudo-images via random feature permutation, enabling CNN-based feature interaction learning.Votes: 0GitHub stars: 61
- Temporal Session AggregationBuilds user-level features by accumulating statistics across sequential event sessions before each assessment point.Votes: 0GitHub stars: 61
- Tfidf Svd Dense Text FeaturesCompress TF-IDF sparse text vectors into a handful of dense TruncatedSVD components so GBDTs can consume free-text fields as plain tabular columnsVotes: 0GitHub stars: 61
- Tfidf Weighted Category CountsConvert per-group categorical event counts into TF-IDF-style features using log(1+tf/total) * log(N/df)Votes: 0GitHub stars: 61
- Threaded Parquet Describe FeaturesParallel-load per-subject parquet time-series files with ThreadPoolExecutor and flatten describe() statistics into tabular feature vectorsVotes: 0GitHub stars: 61
- Time Varying Reward ShapingShape RL rewards with time-decaying asset weights and time-increasing resource weights so the agent transitions from expansion to accumulation as the game progressesVotes: 0GitHub stars: 61
- Toroidal Manhattan DistanceCompute shortest Manhattan distance on a toroidal (wrapping) grid by comparing normal vs wrap-around routes in each axisVotes: 0GitHub stars: 61
- Transductive Train Test TransformFit unsupervised transforms (scaler, PCA, variance filter) on combined train+test data for more stable statistics, especially on small datasetsVotes: 0GitHub stars: 61
- Transitive Match ClosurePost-processes entity match predictions to enforce symmetry (A→B implies B→A) and transitivity (A→B, B→C implies A→C) via graph closure.Votes: 0GitHub stars: 61
- Two Level Hierarchical AggregationAggregates deeply nested relational tables through two groupby levels (child → intermediate → parent) to build features from multi-hop relationships.Votes: 0GitHub stars: 61
- Type Weighted Covisitation MatrixBuild item co-visitation matrix from session pairs within a time window, weighting by interaction type (click/cart/order) via GPU self-joinVotes: 0GitHub stars: 61
- Typed Panel AggregationAggregate panel/sequential data with type-appropriate statistics — numeric (mean/std/min/max/last) and categorical (count/last/nunique) — then concat into flat featuresVotes: 0GitHub stars: 61
- Vote Ensemble Outer JoinEnsemble ranked recommendation lists by outer-joining exploded candidates and re-ranking by weighted vote sumVotes: 0GitHub stars: 61
- Weather Ordinal EncodingMap free-text categorical descriptions to ordinal numeric scores via keyword matching — captures ordered severity in a single dense featureVotes: 0GitHub stars: 61
- Weighted Gini Top Recall MetricCustom ranking metric combining normalized weighted Gini coefficient with top-K% capture rate for imbalanced classification with class-weighted evaluationVotes: 0GitHub stars: 61
- Weighted Position Decay EnsembleEnsembles multiple ranked recommendation lists by scoring items as model_weight / position_rank, then re-ranking.Votes: 0GitHub stars: 61
- Weighted Recall Multi Objective MetricEvaluate recommendation quality with recall@K per action type, combined via business-importance weightsVotes: 0GitHub stars: 61
- Xgb Gpu Batch IteratorUse XGBoost DeviceQuantileDMatrix with a custom batch iterator to train on large datasets without exhausting GPU memoryVotes: 0GitHub stars: 61
- Yearly Partitioned GroupbySplit a multi-year table into per-year partitions, run the same groupby aggregation on each, then concat and gc — a pure-pandas map-reduce that survives 100M+ rows on a 16GB kernelVotes: 0GitHub stars: 61
- Activity Threshold Lastval FallbackOverride model predictions with last known value for low-activity or low-density entities where learned trends are unreliableVotes: 0GitHub stars: 61
- Availability Masked Regression LossMultiply per-timestep regression loss by a 0/1 availability mask so missing future steps contribute zero gradientVotes: 0GitHub stars: 61
- Bootstrapped Residual Prediction IntervalsGenerate prediction intervals by repeatedly sampling from model residuals, adding to point forecasts, and taking quantiles across synthetic futuresVotes: 0GitHub stars: 61
- Burst Rle DetectionDetect P-bursts (fast-typing runs) and R-bursts (consecutive revisions) via polars run-length encoding over boolean event conditionsVotes: 0GitHub stars: 61
- Class Weighted Multiclass LoglossCustom multiclass log-loss that weights per-class contributions by class frequency and domain importance, usable as both training loss and eval metricVotes: 0GitHub stars: 61
- Cnn Transformer Multimodal FusionProcess multiple sensor modalities through separate CNN branches then fuse via a transformer with CLS token for classificationVotes: 0GitHub stars: 61
- Correlated Double SamplingSubtract paired reference frames from signal frames to cancel readout noise and common-mode biasVotes: 0GitHub stars: 61
- Density To Count RoundtripConvert a density metric back to integer counts using known population, round to nearest integer, then recompute density to exploit the discrete nature of the targetVotes: 0GitHub stars: 61
- Detector Calibration PipelineMulti-step detector calibration pipeline — ADC inversion, hot/dead pixel masking, nonlinearity correction, dark subtraction, flat-field normalizationVotes: 0GitHub stars: 61
- Dilated Conv Residual GruCombines dilated 1D convolutions for multi-scale receptive fields with residual bidirectional GRU layers for sequence classification.Votes: 0GitHub stars: 61
- Event Anchored Frame SyncAlign low-Hz sensor data to high-fps video by anchoring a named event (e.g. ball_snap) to a known frame index and converting time offsets via fpsVotes: 0GitHub stars: 61
- Event Peak DetectionDetects discrete events (state transitions) from continuous predictions using local maxima with minimum-interval constraints.Votes: 0GitHub stars: 61
- Expanding Window StackingWalk-forward stacking ensemble that trains base models on expanding windows and a meta-learner on their out-of-fold predictions across timeVotes: 0GitHub stars: 61
- Flux Snr Weighted FeaturesEngineer SNR-derived features from irregular time series — flux ratio squared, error-weighted mean flux, and normalized amplitude/range featuresVotes: 0GitHub stars: 61
- Gaussian Log Likelihood MetricEvaluate probabilistic forecasts using normalized Gaussian log-likelihood relative to naive and oracle baselines, scoring both mean accuracy and uncertainty calibrationVotes: 0GitHub stars: 61
- Gradient Event Boundary DetectionDetect event start/end boundaries in time series by finding extrema of the first derivative (steepest gradient points)Votes: 0GitHub stars: 61
- Gradient Transit Phase DetectionDetect event ingress/egress boundaries by finding steepest gradient on each side of the signal minimum in a smoothed time seriesVotes: 0GitHub stars: 61
- Hierarchy Level Confidence CoefficientsAssign different uncertainty spread coefficients per aggregation level in hierarchical forecasts, reflecting that higher aggregation yields narrower intervalsVotes: 0GitHub stars: 61
- Imu Gravity RemovalRemove gravity component from raw accelerometer data using quaternion rotation to yield linear accelerationVotes: 0GitHub stars: 61
- Inverse Variance Channel WeightingWeight multi-channel signals by inverse per-channel variance with percentile clipping, emphasizing low-noise channels in aggregationVotes: 0GitHub stars: 61
- K Mode Gaussian Nll LossNegative log-likelihood loss over K isotropic-Gaussian trajectory modes with per-mode confidences and logsumexp stabilityVotes: 0GitHub stars: 61
- Kaggle Api Streaming InferencePredict day-by-day via Kaggle's iter_test API while maintaining a rolling history buffer for computing lag features onlineVotes: 0GitHub stars: 61
- Keras Multi Quantile LossSingle neural network outputting all quantiles simultaneously via pinball loss over a quantile vector for joint probabilistic forecastingVotes: 0GitHub stars: 61
- Keystroke Pause Bucket FeaturesBucket inter-keystroke latencies into pause-duration ranges (0.5-1s, 1-1.5s, 1.5-2s, 2-3s, >3s) and count per session as hesitation featuresVotes: 0GitHub stars: 61
- Learnable Fir FilterInitialize a depthwise Conv1d with FIR filter coefficients as a trainable high-pass/low-pass filter for sensor signal preprocessingVotes: 0GitHub stars: 61
- Locale Scoped Holiday FlagBuild a single per-row "day off" boolean from a holidays table with National/Regional/Local locale hierarchy and Work Day overrides that flip make-up working weekends back to working daysVotes: 0GitHub stars: 61