File size: 3,924 Bytes
6cdce85 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 |
'use client';
import {
createContext,
useContext,
useState,
useEffect,
useCallback,
ReactNode,
} from 'react';
import { datasetLoader, FilterOptions, LoadExamplesResult } from './loader';
import type { DatasetExample, CodingProblem } from '@/types';
type Split = 'train' | 'validation' | 'test';
interface DatasetContextValue {
isLoading: boolean;
loadedSplits: Set<Split>;
splitCounts: Record<string, number>;
loadSplit: (split: Split) => Promise<void>;
filterExamples: (
split: Split,
filters: FilterOptions,
limit?: number,
offset?: number
) => LoadExamplesResult;
getCodingProblems: (split: Split) => CodingProblem[];
getAllExamples: (split: Split) => DatasetExample[];
}
const DatasetContext = createContext<DatasetContextValue | null>(null);
interface DatasetProviderProps {
children: ReactNode;
initialSplits?: Split[];
}
export function DatasetProvider({
children,
initialSplits = ['train', 'test', 'validation'],
}: DatasetProviderProps) {
const [isLoading, setIsLoading] = useState(true);
const [loadedSplits, setLoadedSplits] = useState<Set<Split>>(new Set());
const [splitCounts, setSplitCounts] = useState<Record<string, number>>({});
// Load initial splits on mount
useEffect(() => {
const loadInitialData = async () => {
setIsLoading(true);
try {
// Load split info first
const info = await datasetLoader.getSplitInfo();
setSplitCounts(info);
// Load initial splits in parallel
await Promise.all(
initialSplits.map(async (split) => {
await datasetLoader.preloadSplit(split);
setLoadedSplits((prev) => new Set([...prev, split]));
})
);
} catch (error) {
console.error('Failed to load dataset:', error);
} finally {
setIsLoading(false);
}
};
loadInitialData();
}, []);
const loadSplit = useCallback(async (split: Split) => {
if (datasetLoader.isLoaded(split)) {
setLoadedSplits((prev) => new Set([...prev, split]));
return;
}
await datasetLoader.preloadSplit(split);
setLoadedSplits((prev) => new Set([...prev, split]));
// Update counts after loading
const examples = datasetLoader.getAllExamples(split);
setSplitCounts((prev) => ({ ...prev, [split]: examples.length }));
}, []);
const filterExamples = useCallback(
(
split: Split,
filters: FilterOptions,
limit: number = 50,
offset: number = 0
): LoadExamplesResult => {
if (!datasetLoader.isLoaded(split)) {
return { examples: [], total: 0 };
}
return datasetLoader.filterExamples(split, filters, limit, offset);
},
[]
);
const getCodingProblems = useCallback((split: Split): CodingProblem[] => {
return datasetLoader.getCodingProblems(split);
}, []);
const getAllExamples = useCallback((split: Split): DatasetExample[] => {
return datasetLoader.getAllExamples(split);
}, []);
return (
<DatasetContext.Provider
value={{
isLoading,
loadedSplits,
splitCounts,
loadSplit,
filterExamples,
getCodingProblems,
getAllExamples,
}}
>
{children}
</DatasetContext.Provider>
);
}
export function useDataset() {
const context = useContext(DatasetContext);
if (!context) {
throw new Error('useDataset must be used within a DatasetProvider');
}
return context;
}
|