Concatenate many bags together, unioning all elements. >>> import dask.bag as db >>> a = db.from_sequence([1, 2, 3]) >>> b = db.from_sequence([4, 5, 6]) >>> c = db.concat([a, b]) >>> list(c) [1, 2, 3, 4, 5, 6]
(bags)
| 1855 | |
| 1856 | |
| 1857 | def concat(bags): |
| 1858 | """Concatenate many bags together, unioning all elements. |
| 1859 | |
| 1860 | >>> import dask.bag as db |
| 1861 | >>> a = db.from_sequence([1, 2, 3]) |
| 1862 | >>> b = db.from_sequence([4, 5, 6]) |
| 1863 | >>> c = db.concat([a, b]) |
| 1864 | |
| 1865 | >>> list(c) |
| 1866 | [1, 2, 3, 4, 5, 6] |
| 1867 | """ |
| 1868 | token = tokenize(*bags) |
| 1869 | name = f"concat-{token}" |
| 1870 | counter = itertools.count(0) |
| 1871 | dsk = {(name, next(counter)): key for bag in bags for key in bag.__dask_keys__()} |
| 1872 | graph = HighLevelGraph.from_collections(name, dsk, dependencies=bags) |
| 1873 | return Bag(graph, name, len(dsk)) |
| 1874 | |
| 1875 | |
| 1876 | def reify(seq): |
searching dependent graphs…