datapilot-cli
Version:
Enterprise-grade streaming multi-format data analysis with comprehensive statistical insights and intelligent relationship detection - supports CSV, JSON, Excel, TSV, Parquet - memory-efficient, cross-platform
92 lines • 2.58 kB
TypeScript
/**
* Streaming Analyzer Types
* Type definitions for streaming data analysis components
*/
import { DataType } from '../../core/types';
import type { Section3Config } from '../eda/types';
export interface StreamingConfig {
chunkSize: number;
memoryThreshold: number;
enableAdaptiveChunking?: boolean;
maxChunkSize?: number;
minChunkSize?: number;
}
export interface StreamingAnalyzerConfig extends Section3Config {
chunkSize: number;
memoryThresholdMB: number;
maxRowsAnalyzed: number;
adaptiveChunkSizing: boolean;
enableMemoryOptimization: boolean;
enableAdaptiveStreaming: boolean;
enableParallelProcessing: boolean;
}
export interface StreamingAnalyzerInput {
data: string[][];
headers: string[];
columnTypes: DataType[];
config?: StreamingConfig;
}
export interface BivariateConfig {
significanceLevel: number;
maxComparisons: number;
enableAdvancedTests?: boolean;
correlationThreshold?: number;
}
export interface BivariateAnalyzerInput {
data: string[][];
headers: string[];
columnTypes: DataType[];
numericalColumns: string[];
categoricalColumns: string[];
config?: BivariateConfig;
}
export interface ProcessingSummary {
totalRowsProcessed: number;
chunksProcessed: number;
memoryUsage: {
peakUsage: number;
averageUsage: number;
};
processingTime: number;
}
export interface StreamingColumnAnalysis {
columnName: string;
dataType: DataType;
statistics: {
count: number;
uniqueValues?: number;
nullCount?: number;
mean?: number;
standardDeviation?: number;
min?: number;
max?: number;
};
}
export interface StreamingAnalyzerResult {
columnAnalyses: StreamingColumnAnalysis[];
processingSummary: ProcessingSummary;
metadata: {
analysisStartTime: Date;
analysisEndTime: Date;
version: string;
};
}
export interface BivariateRelationship {
column1: string;
column2: string;
relationshipType: 'numerical-numerical' | 'numerical-categorical' | 'categorical-categorical';
strength: number;
significance: number;
method: string;
}
export interface BivariateAnalyzerResult {
numericalRelationships: BivariateRelationship[];
categoricalRelationships: BivariateRelationship[];
mixedRelationships: BivariateRelationship[];
metadata: {
totalComparisons: number;
significantRelationships: number;
analysisTime: number;
};
}
//# sourceMappingURL=types.d.ts.map