or run

tessl search
Log in

Version

Workspace
tessl
Visibility
Public
Created
Last updated
Describes
pypipkg:pypi/scikit-learn@1.7.x

evals

scenario-5

rubric.jsontask.md
tile.json

tessl/pypi-scikit-learn

tessl install tessl/pypi-scikit-learn@1.7.0

A comprehensive machine learning library providing supervised and unsupervised learning algorithms with consistent APIs and extensive tools for data preprocessing, model evaluation, and deployment.

Agent Success

Agent success rate when using this tile

87%

Improvement

Agent success rate improvement when using this tile compared to baseline

0.99x

Baseline

Agent success rate without this tile

88%

task.mdevals/scenario-5/

Anomaly Analysis Toolkit

Build a module that learns unsupervised detectors for global and local anomalies, estimates robust covariance distances, and discovers biclusters in a rectangular dataset.

Capabilities

Global anomaly scoring

  • Fitting on 2D numeric data that mixes a tight cluster with two faraway points produces boolean predictions that flag the distant points and keep the cluster points as normal @test

Local neighborhood detection

  • After training on points that mostly share similar nearest neighbors plus a single remote point, the local anomaly score for the remote point is strictly higher than every inlier score @test

Robust covariance distances

  • Computing robust Mahalanobis-style distances from a fitted covariance model yields a markedly larger distance for an outlier point than for a typical cluster point @test

Bicluster segmentation

  • Fitting biclusters on a matrix containing a high-valued block distinct from its surroundings returns row and column labels that separate that block from the remaining rows and columns @test

Implementation

@generates

API

import numpy as np
from typing import Tuple

class AnomalySuite:
    def fit_global(self, samples: np.ndarray, contamination: float = 0.1) -> "AnomalySuite":
        """Fit a global anomaly detector on 2D numeric samples."""

    def predict_global(self, samples: np.ndarray) -> np.ndarray:
        """Return a boolean array marking anomalies in the provided samples."""

    def fit_local(self, samples: np.ndarray, neighbors: int = 20) -> "AnomalySuite":
        """Fit a neighborhood-sensitive anomaly detector."""

    def score_local(self, samples: np.ndarray) -> np.ndarray:
        """Return anomaly scores where higher values indicate stronger outlierness."""

    def fit_covariance(self, samples: np.ndarray) -> "AnomalySuite":
        """Estimate a robust covariance model from the samples."""

    def mahalanobis_distance(self, samples: np.ndarray) -> np.ndarray:
        """Compute robust Mahalanobis-style distances for each sample."""

    def fit_biclusters(self, matrix: np.ndarray, n_clusters: int) -> "AnomalySuite":
        """Fit biclusters on a 2D matrix representing feature-by-sample signals."""

    def bicluster_assignments(self) -> Tuple[np.ndarray, np.ndarray]:
        """Return row and column cluster labels from the last biclustering fit."""

Dependencies { .dependencies }

scikit-learn { .dependency }

Provides unsupervised anomaly detection, covariance estimation, and biclustering utilities.