Crate sklears_utils 

Utility functions and helpers for sklears

This crate provides common utilities used across the sklears ecosystem, including data validation, array manipulation, random number generation, and dataset creation utilities.

Examples

use sklears_utils::validation::check_consistent_length;
use sklears_utils::random::set_random_state;
use scirs2_core::ndarray::array;

// Validation
let x = array![1, 2, 3];
let y = array![4, 5, 6];
assert!(check_consistent_length(&[&x, &y]).is_ok());

// Random state
set_random_state(42);

Re-exports

pub use api_integration::ApiClient;

pub use api_integration::ApiConfig;

pub use api_integration::ApiError;

pub use api_integration::ApiMetrics;

pub use api_integration::ApiRequest;

pub use api_integration::ApiResponse;

pub use api_integration::ApiService;

pub use api_integration::Authentication;

pub use api_integration::HttpMethod;

pub use api_integration::MLApiPatterns;

pub use api_integration::MethodStats;

pub use api_integration::MockApiClient;

pub use api_integration::RequestBuilder;

pub use array_utils::argmax;

pub use array_utils::argmin;

pub use array_utils::argsort;

pub use array_utils::array_add_constant_inplace;

pub use array_utils::array_apply_inplace;

pub use array_utils::array_concatenate;

pub use array_utils::array_cumsum;

pub use array_utils::array_describe;

pub use array_utils::array_max;

pub use array_utils::array_mean;

pub use array_utils::array_mean_f64;

pub use array_utils::array_median;

pub use array_utils::array_min;

pub use array_utils::array_min_max;

pub use array_utils::array_min_max_normalize;

pub use array_utils::array_min_max_normalize_inplace;

pub use array_utils::array_percentile;

pub use array_utils::array_quantiles;

pub use array_utils::array_resize;

pub use array_utils::array_reverse;

pub use array_utils::array_scale_inplace;

pub use array_utils::array_split;

pub use array_utils::array_standardize;

pub use array_utils::array_standardize_inplace;

pub use array_utils::array_std;

pub use array_utils::array_sum;

pub use array_utils::array_unique_counts;

pub use array_utils::array_var;

pub use array_utils::array_variance_f64;

pub use array_utils::boolean_indexing_1d;

pub use array_utils::boolean_indexing_2d;

pub use array_utils::broadcast_shape;

pub use array_utils::check_array_1d;

pub use array_utils::check_array_2d;

pub use array_utils::column_or_1d;

pub use array_utils::compatible_layout;

pub use array_utils::compress_1d;

pub use array_utils::concatenate_2d;

pub use array_utils::create_mask;

pub use array_utils::densify_threshold;

pub use array_utils::efficient_copy;

pub use array_utils::fancy_indexing_1d;

pub use array_utils::fancy_indexing_2d;

pub use array_utils::fast_dot_product_f32;

pub use array_utils::fast_dot_product_f64;

pub use array_utils::fast_sum_f32;

pub use array_utils::fast_sum_f64;

pub use array_utils::filter_array;

pub use array_utils::flatten_2d;

pub use array_utils::get_strides;

pub use array_utils::is_broadcastable;

pub use array_utils::is_contiguous;

pub use array_utils::label_counts;

pub use array_utils::make_contiguous;

pub use array_utils::normalize_array;

pub use array_utils::pad_2d;

pub use array_utils::put_1d;

pub use array_utils::reshape_1d_to_2d;

pub use array_utils::safe_indexing;

pub use array_utils::safe_indexing_2d;

pub use array_utils::safe_sparse_dot;

pub use array_utils::safe_sparse_dot_f32;

pub use array_utils::safe_sparse_dot_f64;

pub use array_utils::simd_add_arrays_f32;

pub use array_utils::simd_add_arrays_f64;

pub use array_utils::simd_multiply_arrays_f32;

pub use array_utils::simd_multiply_arrays_f64;

pub use array_utils::simd_scale_array_f32;

pub use array_utils::simd_scale_array_f64;

pub use array_utils::slice_with_step;

pub use array_utils::sparse_add;

pub use array_utils::sparse_diag;

pub use array_utils::sparse_transpose;

pub use array_utils::split_2d;

pub use array_utils::stack_1d;

pub use array_utils::take_1d;

pub use array_utils::tile_2d;

pub use array_utils::transpose;

pub use array_utils::unique_labels;

pub use array_utils::where_condition;

pub use array_utils::ArrayStatistics;

pub use cloud_storage::CloudProvider;

pub use cloud_storage::CloudStorageClient;

pub use cloud_storage::CloudStorageConfig;

pub use cloud_storage::CloudStorageFactory;

pub use cloud_storage::CloudStorageUtils;

pub use cloud_storage::MockCloudStorageClient;

pub use cloud_storage::ObjectMetadata;

pub use cloud_storage::StorageMetrics;

pub use cloud_storage::SyncMode;

pub use cloud_storage::SyncResult;

pub use config::ArgParser;

pub use config::Config;

pub use config::ConfigBuilder;

pub use config::ConfigSource;

pub use config::ConfigValidator;

pub use config::ConfigValue;

pub use config::HotReloadConfig;

pub use cross_validation::CVSplit;

pub use cross_validation::GroupKFold;

pub use cross_validation::LeaveOneGroupOut;

pub use cross_validation::StratifiedKFold;

pub use cross_validation::TimeSeriesSplit;

pub use data_pipeline::DataPipeline;

pub use data_pipeline::MLPipelineBuilder;

pub use data_pipeline::PipelineContext;

pub use data_pipeline::PipelineMetrics;

pub use data_pipeline::PipelineMonitor;

pub use data_pipeline::PipelineResult;

pub use data_pipeline::PipelineStep;

pub use data_pipeline::StepMetrics;

pub use data_pipeline::TransformStep;

pub use data_structures::AtomicCounter;

pub use data_structures::BinarySearchTree;

pub use data_structures::BlockMatrix;

pub use data_structures::ConcurrentHashMap;

pub use data_structures::ConcurrentQueue;

pub use data_structures::ConcurrentRingBuffer;

pub use data_structures::Graph;

pub use data_structures::RingBuffer;

pub use data_structures::TreeNode;

pub use data_structures::TreeStatistics;

pub use data_structures::Trie;

pub use data_structures::TrieStatistics;

pub use data_structures::WeightedGraph;

pub use data_structures::WorkQueue;

pub use database::Connection;

pub use database::DatabaseConfig;

pub use database::DatabaseError;

pub use database::DatabasePool;

pub use database::Query;

pub use database::QueryBuilder;

pub use database::QueryResult;

pub use database::ResultSet;

pub use database::Transaction;

pub use debug::ArrayDebugger;

pub use debug::DebugContext;

pub use debug::DiagnosticTools;

pub use debug::MemoryDebugger;

pub use debug::PerformanceDebugger;

pub use debug::TestDataGenerator;

pub use debug::TimingStats;

pub use distributed_computing::ClusterConfig;

pub use distributed_computing::ClusterNode;

pub use distributed_computing::ClusterStats;

pub use distributed_computing::DistributedCluster;

pub use distributed_computing::DistributedError;

pub use distributed_computing::DistributedJob;

pub use distributed_computing::FaultDetector;

pub use distributed_computing::JobExecution;

pub use distributed_computing::JobPriority;

pub use distributed_computing::JobScheduler;

pub use distributed_computing::JobStatus;

pub use distributed_computing::JobType;

pub use distributed_computing::LoadBalancer;

pub use distributed_computing::LoadMetrics;

pub use distributed_computing::NodeCapabilities;

pub use distributed_computing::NodeStatus;

pub use distributed_computing::ResourceRequirements;

pub use distributed_computing::ResourceUsage;

pub use distributed_computing::SchedulingStrategy;

pub use ensemble::AggregationStrategy;

pub use ensemble::BaggingPredictor;

pub use ensemble::Bootstrap;

pub use ensemble::OOBScoreEstimator;

pub use ensemble::StackingHelper;

pub use environment::CacheInfo;

pub use environment::CpuInfo;

pub use environment::EnvironmentInfo;

pub use environment::FeatureChecker;

pub use environment::HardwareDetector;

pub use environment::MemoryInfo;

pub use environment::OSInfo;

pub use environment::PerformanceCharacteristics;

pub use environment::RuntimeInfo;

pub use error_handling::create_error;

pub use error_handling::create_error_at;

pub use error_handling::EnhancedError;

pub use error_handling::ErrorAggregator;

pub use error_handling::ErrorContext;

pub use error_handling::ErrorRecovery;

pub use error_handling::ErrorReporter;

pub use error_handling::ErrorStatistics;

pub use error_handling::ErrorSummary;

pub use error_handling::RecoveryStrategy;

pub use external_integration::ArrayTransfer;

pub use external_integration::CFunctionSignature;

pub use external_integration::CParameter;

pub use external_integration::CType;

pub use external_integration::FFIUtils;

pub use external_integration::PyArrayBuffer;

pub use external_integration::PythonInterop;

pub use external_integration::PythonParameter;

pub use external_integration::PythonValue;

pub use external_integration::WasmBuildConfig;

pub use external_integration::WasmOptimization;

pub use external_integration::WasmParameter;

pub use external_integration::WasmType;

pub use external_integration::WasmUtils;

pub use feature_engineering::BinningStrategy;

pub use feature_engineering::FeatureBinner;

pub use feature_engineering::InteractionFeatures;

pub use feature_engineering::PolynomialFeatures;

pub use file_io::CompressionUtils;

pub use file_io::EfficientFileReader;

pub use file_io::EfficientFileWriter;

pub use file_io::FormatConverter;

pub use file_io::SerializationUtils;

pub use file_io::StreamProcessor;

pub use gpu_computing::ActivationFunction;

pub use gpu_computing::GpuArrayOps;

pub use gpu_computing::GpuDevice;

pub use gpu_computing::GpuError;

pub use gpu_computing::GpuKernelExecution;

pub use gpu_computing::GpuKernelInfo;

pub use gpu_computing::GpuMemoryAllocation;

pub use gpu_computing::GpuProfiler;

pub use gpu_computing::GpuUtils;

pub use gpu_computing::KernelStats;

pub use gpu_computing::MemoryStats;

pub use gpu_computing::MemoryTransferStats;

pub use linear_algebra::ConditionNumber;

pub use linear_algebra::EigenDecomposition;

pub use linear_algebra::MatrixDecomposition;

pub use linear_algebra::MatrixNorms;

pub use linear_algebra::MatrixRank;

pub use linear_algebra::MatrixUtils;

pub use linear_algebra::Pseudoinverse;

pub use logging::flush_global_logger;

pub use logging::get_global_logger;

pub use logging::set_global_level;

pub use logging::ConsoleOutput;

pub use logging::DistributedLogger;

pub use logging::FileOutput;

pub use logging::JsonFormatter;

pub use logging::LogAnalysis;

pub use logging::LogAnalyzer;

pub use logging::LogEntry;

pub use logging::LogLevel;

pub use logging::LogStats;

pub use logging::Logger;

pub use logging::LoggerConfig;

pub use logging::OperationStats;

pub use logging::PerformanceLogger;

pub use logging::TextFormatter;

pub use math_utils::constants;

pub use math_utils::NumericalPrecision;

pub use math_utils::OverflowDetection;

pub use math_utils::RobustArrayOps;

pub use math_utils::SpecialFunctions;

pub use memory::AllocationStats;

pub use memory::GcHelper;

pub use memory::LeakDetector;

pub use memory::MemoryAlignment;

pub use memory::MemoryMappedFile;

pub use memory::MemoryMonitor;

pub use memory::MemoryPool;

pub use memory::MemoryValidator;

pub use memory::SafeBuffer;

pub use memory::SafePtr;

pub use memory::SafeVec;

pub use memory::StackGuard;

pub use memory::TrackingAllocator;

pub use metrics::bhattacharyya_distance;

pub use metrics::braycurtis_distance;

pub use metrics::canberra_distance;

pub use metrics::chebyshev_distance;

pub use metrics::cosine_distance;

pub use metrics::cosine_distance_f32;

pub use metrics::cosine_similarity;

pub use metrics::cosine_similarity_f32;

pub use metrics::euclidean_distance;

pub use metrics::euclidean_distance_f32;

pub use metrics::hamming_distance;

pub use metrics::hamming_distance_normalized;

pub use metrics::hellinger_distance;

pub use metrics::jaccard_distance;

pub use metrics::jaccard_similarity;

pub use metrics::jensen_shannon_divergence;

pub use metrics::kl_divergence;

pub use metrics::mahalanobis_distance;

pub use metrics::manhattan_distance;

pub use metrics::manhattan_distance_f32;

pub use metrics::minkowski_distance;

pub use metrics::wasserstein_1d;

pub use optimization::ConstraintHandler;

pub use optimization::ConstraintViolation;

pub use optimization::ConvergenceCriteria;

pub use optimization::ConvergenceStatus;

pub use optimization::GradientComputer;

pub use optimization::GradientMethod;

pub use optimization::LineSearch;

pub use optimization::LineSearchMethod;

pub use optimization::OptimizationHistory;

pub use parallel::ParallelIterator;

pub use parallel::ParallelReducer;

pub use parallel::ThreadPool;

pub use parallel::WorkStealingQueue;

pub use performance::BaselineMetrics;

pub use performance::Benchmark;

pub use performance::BenchmarkResult;

pub use performance::MemoryTracker;

pub use performance::ProfileReport;

pub use performance::ProfileResult;

pub use performance::Profiler;

pub use performance::RegressionDetector;

pub use performance::RegressionResult;

pub use performance::Timer;

pub use performance::TimerSummary;

pub use performance_regression::PerformanceRegressionTester;

pub use performance_regression::RegressionTestResult;

pub use performance_regression::RegressionThresholds;

pub use preprocessing::DataCleaner;

pub use preprocessing::DataQualityAssessor;

pub use preprocessing::FeatureScaler;

pub use preprocessing::OutlierDetector;

pub use probabilistic::BloomFilter;

pub use probabilistic::BloomFilterStats;

pub use probabilistic::CountMinSketch;

pub use probabilistic::CountMinSketchStats;

pub use probabilistic::HyperLogLog;

pub use probabilistic::HyperLogLogStats;

pub use probabilistic::LSHash;

pub use probabilistic::LSHashStats;

pub use probabilistic::MinHash;

pub use probabilistic::MinHashStats;

pub use profile_guided_optimization::BranchProfile;

pub use profile_guided_optimization::BranchType;

pub use profile_guided_optimization::CacheStatistics;

pub use profile_guided_optimization::DependencyChain;

pub use profile_guided_optimization::FunctionProfile;

pub use profile_guided_optimization::ImplementationEffort;

pub use profile_guided_optimization::InstructionMix;

pub use profile_guided_optimization::LoopProfile;

pub use profile_guided_optimization::MemoryAccessPattern;

pub use profile_guided_optimization::MemoryAccessType;

pub use profile_guided_optimization::OptimizationApplication;

pub use profile_guided_optimization::OptimizationOpportunity;

pub use profile_guided_optimization::OptimizationRecommendation;

pub use profile_guided_optimization::OptimizationReport;

pub use profile_guided_optimization::OptimizationRule;

pub use profile_guided_optimization::OptimizationType;

pub use profile_guided_optimization::PerformanceProfile;

pub use profile_guided_optimization::PerformanceTargets;

pub use profile_guided_optimization::ProfileError;

pub use profile_guided_optimization::ProfileGuidedOptimizer;

pub use profile_guided_optimization::ProfileSummary;

pub use profile_guided_optimization::ProfilerConfig;

pub use profile_guided_optimization::RiskLevel;

pub use profile_guided_optimization::StridePattern;

pub use profile_guided_optimization::TriggerCondition;

pub use r_integration::RDataFrame;

pub use r_integration::RError;

pub use r_integration::RIntegration;

pub use r_integration::RMatrix;

pub use r_integration::RPackageManager;

pub use r_integration::RScriptBuilder;

pub use r_integration::RStatisticalFunctions;

pub use r_integration::RValue;

pub use random::bootstrap_indices;

pub use random::get_rng;

pub use random::importance_sampling;

pub use random::k_fold_indices;

pub use random::random_indices;

pub use random::random_permutation;

pub use random::random_weights;

pub use random::reservoir_sampling;

pub use random::set_random_state;

pub use random::shuffle_indices;

pub use random::stratified_split_indices;

pub use random::train_test_split_indices;

pub use random::weighted_sampling_without_replacement;

pub use random::DistributionSampler;

pub use random::ThreadSafeRng;

pub use simd::SimdCapabilities;

pub use simd::SimdDistanceOps;

pub use simd::SimdF32Ops;

pub use simd::SimdF64Ops;

pub use simd::SimdMatrixOps;

pub use simd::SimdStatsOps;

pub use spatial::geographic::CoordinateSystem;

pub use spatial::geographic::GeoBounds;

pub use spatial::geographic::GeoPoint;

pub use spatial::geographic::GeoUtils;

pub use spatial::geographic::Hemisphere;

pub use spatial::KdTree;

pub use spatial::OctTree;

pub use spatial::Point;

pub use spatial::QuadTree;

pub use spatial::RTree;

pub use spatial::Rectangle;

pub use spatial::SpatialHash;

pub use spatial::SpatialHashStats;

pub use statistical::ConfidenceInterval;

pub use statistical::ConfidenceIntervals;

pub use statistical::CorrelationAnalysis;

pub use statistical::DistributionFitting;

pub use statistical::StatisticalTests;

pub use statistical::TestResult;

pub use text_processing::RegexUtils;

pub use text_processing::StringSimilarity;

pub use text_processing::TextAnalysis;

pub use text_processing::TextNormalizer;

pub use text_processing::TextParser;

pub use text_processing::UnicodeUtils;

pub use time_series::AggregationMethod;

pub use time_series::LagFeatureGenerator;

pub use time_series::SlidingWindow;

pub use time_series::TemporalAggregator;

pub use time_series::TemporalIndex;

pub use time_series::TimeSeries;

pub use time_series::TimeSeriesPoint;

pub use time_series::TimeZoneUtils;

pub use time_series::Timestamp;

pub use time_series::TrendDirection;

pub use time_series::WindowStats;

pub use type_safety::DataState;

pub use type_safety::ExactSize;

pub use type_safety::Kilograms;

pub use type_safety::MatrixMul;

pub use type_safety::Measurement;

pub use type_safety::Meters;

pub use type_safety::MinSize;

pub use type_safety::ModelState;

pub use type_safety::NonNegative;

pub use type_safety::Normalized;

pub use type_safety::One;

pub use type_safety::Pixels;

pub use type_safety::Positive;

pub use type_safety::Seconds;

pub use type_safety::Three;

pub use type_safety::Trained;

pub use type_safety::Two;

pub use type_safety::TypedArray;

pub use type_safety::Untrained;

pub use type_safety::Unvalidated;

pub use type_safety::Validated;

pub use type_safety::ValidatedArray;

pub use type_safety::Zero;

pub use type_safety::D1;

pub use type_safety::D2;

pub use type_safety::D3;

pub use visualization::AxisConfig;

pub use visualization::BoxPlotData;

pub use visualization::ChartData;

pub use visualization::Color;

pub use visualization::HeatmapData;

pub use visualization::HistogramData;

pub use visualization::LinePlotData;

pub use visualization::MLVisualizationUtils;

pub use visualization::PlotData;

pub use visualization::PlotLayout;

pub use visualization::PlotMargin;

pub use visualization::PlotSummary;

pub use visualization::PlotUtils;

pub use visualization::Point2D;

pub use visualization::ScatterPlotData;

pub use data_generation::*;

pub use multiclass::*;

pub use validation::*;

Modules

api_integration

API integration utilities for ML workflows

array_utils

Array utilities module

cloud_storage

Cloud storage utilities for machine learning data processing

config

Configuration Management Utilities

cross_validation

Advanced cross-validation utilities for machine learning

data_generation

data_pipeline

Data pipeline utilities for ML workflows

data_structures

Auto-generated module structure

database

Database connectivity utilities for ML data processing

debug

Debug utilities for development and troubleshooting

distributed_computing

Auto-generated module structure

ensemble

Ensemble utilities for machine learning

environment

Environment detection utilities for hardware and runtime capabilities

error_handling

Enhanced error handling utilities for machine learning workflows

external_integration

External integration utilities for machine learning interoperability

feature_engineering

Feature engineering utilities for machine learning

file_io

File I/O utilities for efficient data handling in machine learning workflows

gpu_computing

GPU computing integration utilities

linear_algebra

Linear Algebra Utilities

logging

Comprehensive logging framework for sklears

math_utils

Mathematical utility functions for numerical computing

memory

Memory management utilities for high-performance ML workloads

metrics

Distance and similarity metrics

multiclass

optimization

Optimization utilities for numerical optimization algorithms

parallel

Parallel computing utilities for machine learning workloads

performance

Performance measurement and profiling utilities

performance_regression

Performance regression testing utilities

preprocessing

Data preprocessing utilities for machine learning

probabilistic

Probabilistic data structures for efficient approximate algorithms

profile_guided_optimization

Profile-guided optimization utilities

r_integration

R integration utilities

random

Random number generation utilities

simd

SIMD (Single Instruction, Multiple Data) optimizations for high-performance computing

spatial

Spatial data structures for efficient spatial queries and indexing

statistical

Statistical Utilities

stats

Statistical utility functions

text_processing

Text processing utilities for machine learning workflows

time_series

Time Series Utilities

type_safety

Type safety utilities for compile-time validation and zero-cost abstractions

validation

Input validation utilities

visualization

Visualization utilities for machine learning data preparation

Macros

assert_shape

Compile-time shape assertion

benchmark_regression

Macro to easily benchmark functions

const_assert

Compile-time assertion macro

debug_assert_msg

Enhanced assertion macro with debugging information

debug_context

Macro for creating debug contexts easily

debug_println

Macro for conditional debugging output

defer

Macro for creating stack guards

log_debug

log_error

Logging macros

log_info

log_trace

log_warn

time_it

Macro for quick performance timing

Enums

UtilsError

Common error type for utils

Type Aliases

UtilsResult

Type alias for utils results