/usr/lib/python3/dist-packages/xarray/tests/test_backends.py is in python3-xarray 0.10.2-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 | from __future__ import absolute_import, division, print_function
import contextlib
import itertools
import os.path
import pickle
import shutil
import sys
import tempfile
import unittest
import warnings
from io import BytesIO
import numpy as np
import pandas as pd
import pytest
import xarray as xr
from xarray import (
DataArray, Dataset, backends, open_dataarray, open_dataset, open_mfdataset,
save_mfdataset)
from xarray.backends.common import robust_getitem
from xarray.backends.netCDF4_ import _extract_nc4_variable_encoding
from xarray.backends.pydap_ import PydapDataStore
from xarray.core import indexing
from xarray.core.pycompat import (
PY2, ExitStack, basestring, dask_array_type, iteritems)
from xarray.tests import mock
from . import (
TestCase, assert_allclose, assert_array_equal, assert_equal,
assert_identical, flaky, has_netCDF4, has_scipy, network, raises_regex,
requires_dask, requires_h5netcdf, requires_netCDF4, requires_pathlib,
requires_pydap, requires_pynio, requires_rasterio, requires_scipy,
requires_scipy_or_netCDF4, requires_zarr)
from .test_dataset import create_test_data
try:
import netCDF4 as nc4
except ImportError:
pass
try:
import dask.array as da
except ImportError:
pass
try:
from pathlib import Path
except ImportError:
try:
from pathlib2 import Path
except ImportError:
pass
ON_WINDOWS = sys.platform == 'win32'
def open_example_dataset(name, *args, **kwargs):
return open_dataset(os.path.join(os.path.dirname(__file__), 'data', name),
*args, **kwargs)
def create_masked_and_scaled_data():
x = np.array([np.nan, np.nan, 10, 10.1, 10.2], dtype=np.float32)
encoding = {'_FillValue': -1, 'add_offset': 10,
'scale_factor': np.float32(0.1), 'dtype': 'i2'}
return Dataset({'x': ('t', x, {}, encoding)})
def create_encoded_masked_and_scaled_data():
attributes = {'_FillValue': -1, 'add_offset': 10,
'scale_factor': np.float32(0.1)}
return Dataset({'x': ('t', [-1, -1, 0, 1, 2], attributes)})
def create_unsigned_masked_scaled_data():
encoding = {'_FillValue': 255, '_Unsigned': 'true', 'dtype': 'i1',
'add_offset': 10, 'scale_factor': np.float32(0.1)}
x = np.array([10.0, 10.1, 22.7, 22.8, np.nan], dtype=np.float32)
return Dataset({'x': ('t', x, {}, encoding)})
def create_encoded_unsigned_masked_scaled_data():
# These are values as written to the file: the _FillValue will
# be represented in the signed form.
attributes = {'_FillValue': -1, '_Unsigned': 'true',
'add_offset': 10, 'scale_factor': np.float32(0.1)}
# Create signed data corresponding to [0, 1, 127, 128, 255] unsigned
sb = np.asarray([0, 1, 127, -128, -1], dtype='i1')
return Dataset({'x': ('t', sb, attributes)})
def create_boolean_data():
attributes = {'units': '-'}
return Dataset({'x': ('t', [True, False, False, True], attributes)})
class TestCommon(TestCase):
def test_robust_getitem(self):
class UnreliableArrayFailure(Exception):
pass
class UnreliableArray(object):
def __init__(self, array, failures=1):
self.array = array
self.failures = failures
def __getitem__(self, key):
if self.failures > 0:
self.failures -= 1
raise UnreliableArrayFailure
return self.array[key]
array = UnreliableArray([0])
with pytest.raises(UnreliableArrayFailure):
array[0]
self.assertEqual(array[0], 0)
actual = robust_getitem(array, 0, catch=UnreliableArrayFailure,
initial_delay=0)
self.assertEqual(actual, 0)
class NetCDF3Only(object):
pass
class DatasetIOTestCases(object):
autoclose = False
engine = None
file_format = None
def create_store(self):
raise NotImplementedError
@contextlib.contextmanager
def roundtrip(self, data, save_kwargs={}, open_kwargs={},
allow_cleanup_failure=False):
with create_tmp_file(
allow_cleanup_failure=allow_cleanup_failure) as path:
self.save(data, path, **save_kwargs)
with self.open(path, **open_kwargs) as ds:
yield ds
@contextlib.contextmanager
def roundtrip_append(self, data, save_kwargs={}, open_kwargs={},
allow_cleanup_failure=False):
with create_tmp_file(
allow_cleanup_failure=allow_cleanup_failure) as path:
for i, key in enumerate(data.variables):
mode = 'a' if i > 0 else 'w'
self.save(data[[key]], path, mode=mode, **save_kwargs)
with self.open(path, **open_kwargs) as ds:
yield ds
# The save/open methods may be overwritten below
def save(self, dataset, path, **kwargs):
dataset.to_netcdf(path, engine=self.engine, format=self.file_format,
**kwargs)
@contextlib.contextmanager
def open(self, path, **kwargs):
with open_dataset(path, engine=self.engine, autoclose=self.autoclose,
**kwargs) as ds:
yield ds
def test_zero_dimensional_variable(self):
expected = create_test_data()
expected['float_var'] = ([], 1.0e9, {'units': 'units of awesome'})
expected['bytes_var'] = ([], b'foobar')
expected['string_var'] = ([], u'foobar')
with self.roundtrip(expected) as actual:
assert_identical(expected, actual)
def test_write_store(self):
expected = create_test_data()
with self.create_store() as store:
expected.dump_to_store(store)
# we need to cf decode the store because it has time and
# non-dimension coordinates
with xr.decode_cf(store) as actual:
assert_allclose(expected, actual)
def check_dtypes_roundtripped(self, expected, actual):
for k in expected.variables:
expected_dtype = expected.variables[k].dtype
if (isinstance(self, NetCDF3Only) and expected_dtype == 'int64'):
# downcast
expected_dtype = np.dtype('int32')
actual_dtype = actual.variables[k].dtype
# TODO: check expected behavior for string dtypes more carefully
string_kinds = {'O', 'S', 'U'}
assert (expected_dtype == actual_dtype or
(expected_dtype.kind in string_kinds and
actual_dtype.kind in string_kinds))
def test_roundtrip_test_data(self):
expected = create_test_data()
with self.roundtrip(expected) as actual:
self.check_dtypes_roundtripped(expected, actual)
assert_identical(expected, actual)
def test_load(self):
expected = create_test_data()
@contextlib.contextmanager
def assert_loads(vars=None):
if vars is None:
vars = expected
with self.roundtrip(expected) as actual:
for k, v in actual.variables.items():
# IndexVariables are eagerly loaded into memory
self.assertEqual(v._in_memory, k in actual.dims)
yield actual
for k, v in actual.variables.items():
if k in vars:
self.assertTrue(v._in_memory)
assert_identical(expected, actual)
with pytest.raises(AssertionError):
# make sure the contextmanager works!
with assert_loads() as ds:
pass
with assert_loads() as ds:
ds.load()
with assert_loads(['var1', 'dim1', 'dim2']) as ds:
ds['var1'].load()
# verify we can read data even after closing the file
with self.roundtrip(expected) as ds:
actual = ds.load()
assert_identical(expected, actual)
def test_dataset_compute(self):
expected = create_test_data()
with self.roundtrip(expected) as actual:
# Test Dataset.compute()
for k, v in actual.variables.items():
# IndexVariables are eagerly cached
self.assertEqual(v._in_memory, k in actual.dims)
computed = actual.compute()
for k, v in actual.variables.items():
self.assertEqual(v._in_memory, k in actual.dims)
for v in computed.variables.values():
self.assertTrue(v._in_memory)
assert_identical(expected, actual)
assert_identical(expected, computed)
def test_pickle(self):
expected = Dataset({'foo': ('x', [42])})
with self.roundtrip(
expected, allow_cleanup_failure=ON_WINDOWS) as roundtripped:
raw_pickle = pickle.dumps(roundtripped)
# windows doesn't like opening the same file twice
roundtripped.close()
unpickled_ds = pickle.loads(raw_pickle)
assert_identical(expected, unpickled_ds)
def test_pickle_dataarray(self):
expected = Dataset({'foo': ('x', [42])})
with self.roundtrip(
expected, allow_cleanup_failure=ON_WINDOWS) as roundtripped:
unpickled_array = pickle.loads(pickle.dumps(roundtripped['foo']))
assert_identical(expected['foo'], unpickled_array)
def test_dataset_caching(self):
expected = Dataset({'foo': ('x', [5, 6, 7])})
with self.roundtrip(expected) as actual:
assert isinstance(actual.foo.variable._data,
indexing.MemoryCachedArray)
assert not actual.foo.variable._in_memory
actual.foo.values # cache
assert actual.foo.variable._in_memory
with self.roundtrip(expected, open_kwargs={'cache': False}) as actual:
assert isinstance(actual.foo.variable._data,
indexing.CopyOnWriteArray)
assert not actual.foo.variable._in_memory
actual.foo.values # no caching
assert not actual.foo.variable._in_memory
def test_roundtrip_None_variable(self):
expected = Dataset({None: (('x', 'y'), [[0, 1], [2, 3]])})
with self.roundtrip(expected) as actual:
assert_identical(expected, actual)
def test_roundtrip_object_dtype(self):
floats = np.array([0.0, 0.0, 1.0, 2.0, 3.0], dtype=object)
floats_nans = np.array([np.nan, np.nan, 1.0, 2.0, 3.0], dtype=object)
bytes_ = np.array([b'ab', b'cdef', b'g'], dtype=object)
bytes_nans = np.array([b'ab', b'cdef', np.nan], dtype=object)
strings = np.array([u'ab', u'cdef', u'g'], dtype=object)
strings_nans = np.array([u'ab', u'cdef', np.nan], dtype=object)
all_nans = np.array([np.nan, np.nan], dtype=object)
original = Dataset({'floats': ('a', floats),
'floats_nans': ('a', floats_nans),
'bytes': ('b', bytes_),
'bytes_nans': ('b', bytes_nans),
'strings': ('b', strings),
'strings_nans': ('b', strings_nans),
'all_nans': ('c', all_nans),
'nan': ([], np.nan)})
expected = original.copy(deep=True)
with self.roundtrip(original) as actual:
try:
assert_identical(expected, actual)
except AssertionError:
# Most stores use '' for nans in strings, but some don't.
# First try the ideal case (where the store returns exactly)
# the original Dataset), then try a more realistic case.
# This currently includes all netCDF files when encoding is not
# explicitly set.
# https://github.com/pydata/xarray/issues/1647
expected['bytes_nans'][-1] = b''
expected['strings_nans'][-1] = u''
assert_identical(expected, actual)
def test_roundtrip_string_data(self):
expected = Dataset({'x': ('t', ['ab', 'cdef'])})
with self.roundtrip(expected) as actual:
assert_identical(expected, actual)
def test_roundtrip_string_encoded_characters(self):
expected = Dataset({'x': ('t', [u'ab', u'cdef'])})
expected['x'].encoding['dtype'] = 'S1'
with self.roundtrip(expected) as actual:
assert_identical(expected, actual)
self.assertEqual(actual['x'].encoding['_Encoding'], 'utf-8')
expected['x'].encoding['_Encoding'] = 'ascii'
with self.roundtrip(expected) as actual:
assert_identical(expected, actual)
self.assertEqual(actual['x'].encoding['_Encoding'], 'ascii')
def test_roundtrip_datetime_data(self):
times = pd.to_datetime(['2000-01-01', '2000-01-02', 'NaT'])
expected = Dataset({'t': ('t', times), 't0': times[0]})
kwds = {'encoding': {'t0': {'units': 'days since 1950-01-01'}}}
with self.roundtrip(expected, save_kwargs=kwds) as actual:
assert_identical(expected, actual)
assert actual.t0.encoding['units'] == 'days since 1950-01-01'
def test_roundtrip_timedelta_data(self):
time_deltas = pd.to_timedelta(['1h', '2h', 'NaT'])
expected = Dataset({'td': ('td', time_deltas), 'td0': time_deltas[0]})
with self.roundtrip(expected) as actual:
assert_identical(expected, actual)
def test_roundtrip_float64_data(self):
expected = Dataset({'x': ('y', np.array([1.0, 2.0, np.pi],
dtype='float64'))})
with self.roundtrip(expected) as actual:
assert_identical(expected, actual)
def test_roundtrip_example_1_netcdf(self):
expected = open_example_dataset('example_1.nc')
with self.roundtrip(expected) as actual:
# we allow the attributes to differ since that
# will depend on the encoding used. For example,
# without CF encoding 'actual' will end up with
# a dtype attribute.
assert_equal(expected, actual)
def test_roundtrip_coordinates(self):
original = Dataset({'foo': ('x', [0, 1])},
{'x': [2, 3], 'y': ('a', [42]), 'z': ('x', [4, 5])})
with self.roundtrip(original) as actual:
assert_identical(original, actual)
def test_roundtrip_global_coordinates(self):
original = Dataset({'x': [2, 3], 'y': ('a', [42]), 'z': ('x', [4, 5])})
with self.roundtrip(original) as actual:
assert_identical(original, actual)
def test_roundtrip_coordinates_with_space(self):
original = Dataset(coords={'x': 0, 'y z': 1})
expected = Dataset({'y z': 1}, {'x': 0})
with pytest.warns(xr.SerializationWarning):
with self.roundtrip(original) as actual:
assert_identical(expected, actual)
def test_roundtrip_boolean_dtype(self):
original = create_boolean_data()
self.assertEqual(original['x'].dtype, 'bool')
with self.roundtrip(original) as actual:
assert_identical(original, actual)
self.assertEqual(actual['x'].dtype, 'bool')
def test_orthogonal_indexing(self):
in_memory = create_test_data()
with self.roundtrip(in_memory) as on_disk:
indexers = {'dim1': [1, 2, 0], 'dim2': [3, 2, 0, 3],
'dim3': np.arange(5)}
expected = in_memory.isel(**indexers)
actual = on_disk.isel(**indexers)
# make sure the array is not yet loaded into memory
assert not actual['var1'].variable._in_memory
assert_identical(expected, actual)
# do it twice, to make sure we're switched from orthogonal -> numpy
# when we cached the values
actual = on_disk.isel(**indexers)
assert_identical(expected, actual)
def test_vectorized_indexing(self):
in_memory = create_test_data()
with self.roundtrip(in_memory) as on_disk:
indexers = {'dim1': DataArray([0, 2, 0], dims='a'),
'dim2': DataArray([0, 2, 3], dims='a')}
expected = in_memory.isel(**indexers)
actual = on_disk.isel(**indexers)
# make sure the array is not yet loaded into memory
assert not actual['var1'].variable._in_memory
assert_identical(expected, actual.load())
# do it twice, to make sure we're switched from
# vectorized -> numpy when we cached the values
actual = on_disk.isel(**indexers)
assert_identical(expected, actual)
def multiple_indexing(indexers):
# make sure a sequence of lazy indexings certainly works.
with self.roundtrip(in_memory) as on_disk:
actual = on_disk['var3']
expected = in_memory['var3']
for ind in indexers:
actual = actual.isel(**ind)
expected = expected.isel(**ind)
# make sure the array is not yet loaded into memory
assert not actual.variable._in_memory
assert_identical(expected, actual.load())
# two-staged vectorized-indexing
indexers = [
{'dim1': DataArray([[0, 7], [2, 6], [3, 5]], dims=['a', 'b']),
'dim3': DataArray([[0, 4], [1, 3], [2, 2]], dims=['a', 'b'])},
{'a': DataArray([0, 1], dims=['c']),
'b': DataArray([0, 1], dims=['c'])}
]
multiple_indexing(indexers)
# vectorized-slice mixed
indexers = [
{'dim1': DataArray([[0, 7], [2, 6], [3, 5]], dims=['a', 'b']),
'dim3': slice(None, 10)}
]
multiple_indexing(indexers)
# vectorized-integer mixed
indexers = [
{'dim3': 0},
{'dim1': DataArray([[0, 7], [2, 6], [3, 5]], dims=['a', 'b'])},
{'a': slice(None, None, 2)}
]
multiple_indexing(indexers)
# vectorized-integer mixed
indexers = [
{'dim3': 0},
{'dim1': DataArray([[0, 7], [2, 6], [3, 5]], dims=['a', 'b'])},
{'a': 1, 'b': 0}
]
multiple_indexing(indexers)
# with negative step slice.
indexers = [
{'dim1': DataArray([[0, 7], [2, 6], [3, 5]], dims=['a', 'b']),
'dim3': slice(-1, 1, -1)},
]
multiple_indexing(indexers)
# with negative step slice.
indexers = [
{'dim1': DataArray([[0, 7], [2, 6], [3, 5]], dims=['a', 'b']),
'dim3': slice(-1, 1, -2)},
]
multiple_indexing(indexers)
def test_isel_dataarray(self):
# Make sure isel works lazily. GH:issue:1688
in_memory = create_test_data()
with self.roundtrip(in_memory) as on_disk:
expected = in_memory.isel(dim2=in_memory['dim2'] < 3)
actual = on_disk.isel(dim2=on_disk['dim2'] < 3)
assert_identical(expected, actual)
def validate_array_type(self, ds):
# Make sure that only NumpyIndexingAdapter stores a bare np.ndarray.
def find_and_validate_array(obj):
# recursively called function. obj: array or array wrapper.
if hasattr(obj, 'array'):
if isinstance(obj.array, indexing.ExplicitlyIndexed):
find_and_validate_array(obj.array)
else:
if isinstance(obj.array, np.ndarray):
assert isinstance(obj, indexing.NumpyIndexingAdapter)
elif isinstance(obj.array, dask_array_type):
assert isinstance(obj, indexing.DaskIndexingAdapter)
elif isinstance(obj.array, pd.Index):
assert isinstance(obj, indexing.PandasIndexAdapter)
else:
raise TypeError('{} is wrapped by {}'.format(
type(obj.array), type(obj)))
for k, v in ds.variables.items():
find_and_validate_array(v._data)
def test_array_type_after_indexing(self):
in_memory = create_test_data()
with self.roundtrip(in_memory) as on_disk:
self.validate_array_type(on_disk)
indexers = {'dim1': [1, 2, 0], 'dim2': [3, 2, 0, 3],
'dim3': np.arange(5)}
expected = in_memory.isel(**indexers)
actual = on_disk.isel(**indexers)
assert_identical(expected, actual)
self.validate_array_type(actual)
# do it twice, to make sure we're switched from orthogonal -> numpy
# when we cached the values
actual = on_disk.isel(**indexers)
assert_identical(expected, actual)
self.validate_array_type(actual)
def test_dropna(self):
# regression test for GH:issue:1694
a = np.random.randn(4, 3)
a[1, 1] = np.NaN
in_memory = xr.Dataset({'a': (('y', 'x'), a)},
coords={'y': np.arange(4), 'x': np.arange(3)})
assert_identical(in_memory.dropna(dim='x'),
in_memory.isel(x=slice(None, None, 2)))
with self.roundtrip(in_memory) as on_disk:
self.validate_array_type(on_disk)
expected = in_memory.dropna(dim='x')
actual = on_disk.dropna(dim='x')
assert_identical(expected, actual)
def test_ondisk_after_print(self):
""" Make sure print does not load file into memory """
in_memory = create_test_data()
with self.roundtrip(in_memory) as on_disk:
repr(on_disk)
assert not on_disk['var1']._in_memory
class CFEncodedDataTest(DatasetIOTestCases):
def test_roundtrip_bytes_with_fill_value(self):
values = np.array([b'ab', b'cdef', np.nan], dtype=object)
encoding = {'_FillValue': b'X', 'dtype': 'S1'}
original = Dataset({'x': ('t', values, {}, encoding)})
expected = original.copy(deep=True)
with self.roundtrip(original) as actual:
assert_identical(expected, actual)
original = Dataset({'x': ('t', values, {}, {'_FillValue': b''})})
with self.roundtrip(original) as actual:
assert_identical(expected, actual)
def test_roundtrip_string_with_fill_value_nchar(self):
values = np.array([u'ab', u'cdef', np.nan], dtype=object)
expected = Dataset({'x': ('t', values)})
encoding = {'dtype': 'S1', '_FillValue': b'X'}
original = Dataset({'x': ('t', values, {}, encoding)})
# Not supported yet.
with pytest.raises(NotImplementedError):
with self.roundtrip(original) as actual:
assert_identical(expected, actual)
def test_unsigned_roundtrip_mask_and_scale(self):
decoded = create_unsigned_masked_scaled_data()
encoded = create_encoded_unsigned_masked_scaled_data()
with self.roundtrip(decoded) as actual:
for k in decoded.variables:
self.assertEqual(decoded.variables[k].dtype,
actual.variables[k].dtype)
assert_allclose(decoded, actual, decode_bytes=False)
with self.roundtrip(decoded,
open_kwargs=dict(decode_cf=False)) as actual:
for k in encoded.variables:
self.assertEqual(encoded.variables[k].dtype,
actual.variables[k].dtype)
assert_allclose(encoded, actual, decode_bytes=False)
with self.roundtrip(encoded,
open_kwargs=dict(decode_cf=False)) as actual:
for k in encoded.variables:
self.assertEqual(encoded.variables[k].dtype,
actual.variables[k].dtype)
assert_allclose(encoded, actual, decode_bytes=False)
# make sure roundtrip encoding didn't change the
# original dataset.
assert_allclose(
encoded, create_encoded_unsigned_masked_scaled_data())
with self.roundtrip(encoded) as actual:
for k in decoded.variables:
self.assertEqual(decoded.variables[k].dtype,
actual.variables[k].dtype)
assert_allclose(decoded, actual, decode_bytes=False)
with self.roundtrip(encoded,
open_kwargs=dict(decode_cf=False)) as actual:
for k in encoded.variables:
self.assertEqual(encoded.variables[k].dtype,
actual.variables[k].dtype)
assert_allclose(encoded, actual, decode_bytes=False)
def test_roundtrip_mask_and_scale(self):
decoded = create_masked_and_scaled_data()
encoded = create_encoded_masked_and_scaled_data()
with self.roundtrip(decoded) as actual:
assert_allclose(decoded, actual, decode_bytes=False)
with self.roundtrip(decoded,
open_kwargs=dict(decode_cf=False)) as actual:
# TODO: this assumes that all roundtrips will first
# encode. Is that something we want to test for?
assert_allclose(encoded, actual, decode_bytes=False)
with self.roundtrip(encoded,
open_kwargs=dict(decode_cf=False)) as actual:
assert_allclose(encoded, actual, decode_bytes=False)
# make sure roundtrip encoding didn't change the
# original dataset.
assert_allclose(encoded,
create_encoded_masked_and_scaled_data(),
decode_bytes=False)
with self.roundtrip(encoded) as actual:
assert_allclose(decoded, actual, decode_bytes=False)
with self.roundtrip(encoded,
open_kwargs=dict(decode_cf=False)) as actual:
assert_allclose(encoded, actual, decode_bytes=False)
def test_coordinates_encoding(self):
def equals_latlon(obj):
return obj == 'lat lon' or obj == 'lon lat'
original = Dataset({'temp': ('x', [0, 1]), 'precip': ('x', [0, -1])},
{'lat': ('x', [2, 3]), 'lon': ('x', [4, 5])})
with self.roundtrip(original) as actual:
assert_identical(actual, original)
with create_tmp_file() as tmp_file:
original.to_netcdf(tmp_file)
with open_dataset(tmp_file, decode_coords=False) as ds:
self.assertTrue(equals_latlon(ds['temp'].attrs['coordinates']))
self.assertTrue(
equals_latlon(ds['precip'].attrs['coordinates']))
self.assertNotIn('coordinates', ds.attrs)
self.assertNotIn('coordinates', ds['lat'].attrs)
self.assertNotIn('coordinates', ds['lon'].attrs)
modified = original.drop(['temp', 'precip'])
with self.roundtrip(modified) as actual:
assert_identical(actual, modified)
with create_tmp_file() as tmp_file:
modified.to_netcdf(tmp_file)
with open_dataset(tmp_file, decode_coords=False) as ds:
self.assertTrue(equals_latlon(ds.attrs['coordinates']))
self.assertNotIn('coordinates', ds['lat'].attrs)
self.assertNotIn('coordinates', ds['lon'].attrs)
def test_roundtrip_endian(self):
ds = Dataset({'x': np.arange(3, 10, dtype='>i2'),
'y': np.arange(3, 20, dtype='<i4'),
'z': np.arange(3, 30, dtype='=i8'),
'w': ('x', np.arange(3, 10, dtype=np.float))})
with self.roundtrip(ds) as actual:
# technically these datasets are slightly different,
# one hold mixed endian data (ds) the other should be
# all big endian (actual). assertDatasetIdentical
# should still pass though.
assert_identical(ds, actual)
if isinstance(self, NetCDF4DataTest):
ds['z'].encoding['endian'] = 'big'
with pytest.raises(NotImplementedError):
with self.roundtrip(ds) as actual:
pass
def test_invalid_dataarray_names_raise(self):
te = (TypeError, 'string or None')
ve = (ValueError, 'string must be length 1 or')
data = np.random.random((2, 2))
da = xr.DataArray(data)
for name, e in zip([0, (4, 5), True, ''], [te, te, te, ve]):
ds = Dataset({name: da})
with raises_regex(*e):
with self.roundtrip(ds):
pass
def test_encoding_kwarg(self):
ds = Dataset({'x': ('y', np.arange(10.0))})
kwargs = dict(encoding={'x': {'dtype': 'f4'}})
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
self.assertEqual(actual.x.encoding['dtype'], 'f4')
self.assertEqual(ds.x.encoding, {})
kwargs = dict(encoding={'x': {'foo': 'bar'}})
with raises_regex(ValueError, 'unexpected encoding'):
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
pass
kwargs = dict(encoding={'x': 'foo'})
with raises_regex(ValueError, 'must be castable'):
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
pass
kwargs = dict(encoding={'invalid': {}})
with pytest.raises(KeyError):
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
pass
ds = Dataset({'t': pd.date_range('2000-01-01', periods=3)})
units = 'days since 1900-01-01'
kwargs = dict(encoding={'t': {'units': units}})
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
self.assertEqual(actual.t.encoding['units'], units)
assert_identical(actual, ds)
def test_default_fill_value(self):
# Test default encoding for float:
ds = Dataset({'x': ('y', np.arange(10.0))})
kwargs = dict(encoding={'x': {'dtype': 'f4'}})
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
self.assertEqual(actual.x.encoding['_FillValue'],
np.nan)
self.assertEqual(ds.x.encoding, {})
# Test default encoding for int:
ds = Dataset({'x': ('y', np.arange(10.0))})
kwargs = dict(encoding={'x': {'dtype': 'int16'}})
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
self.assertTrue('_FillValue' not in actual.x.encoding)
self.assertEqual(ds.x.encoding, {})
# Test default encoding for implicit int:
ds = Dataset({'x': ('y', np.arange(10, dtype='int16'))})
with self.roundtrip(ds) as actual:
self.assertTrue('_FillValue' not in actual.x.encoding)
self.assertEqual(ds.x.encoding, {})
def test_explicitly_omit_fill_value(self):
ds = Dataset({'x': ('y', [np.pi, -np.pi])})
ds.x.encoding['_FillValue'] = None
with self.roundtrip(ds) as actual:
assert '_FillValue' not in actual.x.encoding
def test_explicitly_omit_fill_value_via_encoding_kwarg(self):
ds = Dataset({'x': ('y', [np.pi, -np.pi])})
kwargs = dict(encoding={'x': {'_FillValue': None}})
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
assert '_FillValue' not in actual.x.encoding
self.assertEqual(ds.y.encoding, {})
def test_explicitly_omit_fill_value_in_coord(self):
ds = Dataset({'x': ('y', [np.pi, -np.pi])}, coords={'y': [0.0, 1.0]})
ds.y.encoding['_FillValue'] = None
with self.roundtrip(ds) as actual:
assert '_FillValue' not in actual.y.encoding
def test_explicitly_omit_fill_value_in_coord_via_encoding_kwarg(self):
ds = Dataset({'x': ('y', [np.pi, -np.pi])}, coords={'y': [0.0, 1.0]})
kwargs = dict(encoding={'y': {'_FillValue': None}})
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
assert '_FillValue' not in actual.y.encoding
self.assertEqual(ds.y.encoding, {})
def test_encoding_same_dtype(self):
ds = Dataset({'x': ('y', np.arange(10.0, dtype='f4'))})
kwargs = dict(encoding={'x': {'dtype': 'f4'}})
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
self.assertEqual(actual.x.encoding['dtype'], 'f4')
self.assertEqual(ds.x.encoding, {})
def test_append_write(self):
# regression for GH1215
data = create_test_data()
with self.roundtrip_append(data) as actual:
assert_identical(data, actual)
def test_append_overwrite_values(self):
# regression for GH1215
data = create_test_data()
with create_tmp_file(allow_cleanup_failure=False) as tmp_file:
self.save(data, tmp_file, mode='w')
data['var2'][:] = -999
data['var9'] = data['var2'] * 3
self.save(data[['var2', 'var9']], tmp_file, mode='a')
with self.open(tmp_file) as actual:
assert_identical(data, actual)
def test_append_with_invalid_dim_raises(self):
data = create_test_data()
with create_tmp_file(allow_cleanup_failure=False) as tmp_file:
self.save(data, tmp_file, mode='w')
data['var9'] = data['var2'] * 3
data = data.isel(dim1=slice(2, 6)) # modify one dimension
with raises_regex(ValueError,
'Unable to update size for existing dimension'):
self.save(data, tmp_file, mode='a')
def test_multiindex_not_implemented(self):
ds = (Dataset(coords={'y': ('x', [1, 2]), 'z': ('x', ['a', 'b'])})
.set_index(x=['y', 'z']))
with raises_regex(NotImplementedError, 'MultiIndex'):
with self.roundtrip(ds):
pass
_counter = itertools.count()
@contextlib.contextmanager
def create_tmp_file(suffix='.nc', allow_cleanup_failure=False):
temp_dir = tempfile.mkdtemp()
path = os.path.join(temp_dir, 'temp-%s%s' % (next(_counter), suffix))
try:
yield path
finally:
try:
shutil.rmtree(temp_dir)
except OSError:
if not allow_cleanup_failure:
raise
@contextlib.contextmanager
def create_tmp_files(nfiles, suffix='.nc', allow_cleanup_failure=False):
with ExitStack() as stack:
files = [stack.enter_context(create_tmp_file(suffix,
allow_cleanup_failure))
for apath in np.arange(nfiles)]
yield files
@requires_netCDF4
class BaseNetCDF4Test(CFEncodedDataTest):
engine = 'netcdf4'
def test_open_group(self):
# Create a netCDF file with a dataset stored within a group
with create_tmp_file() as tmp_file:
with nc4.Dataset(tmp_file, 'w') as rootgrp:
foogrp = rootgrp.createGroup('foo')
ds = foogrp
ds.createDimension('time', size=10)
x = np.arange(10)
ds.createVariable('x', np.int32, dimensions=('time',))
ds.variables['x'][:] = x
expected = Dataset()
expected['x'] = ('time', x)
# check equivalent ways to specify group
for group in 'foo', '/foo', 'foo/', '/foo/':
with open_dataset(tmp_file, group=group) as actual:
assert_equal(actual['x'], expected['x'])
# check that missing group raises appropriate exception
with pytest.raises(IOError):
open_dataset(tmp_file, group='bar')
with raises_regex(ValueError, 'must be a string'):
open_dataset(tmp_file, group=(1, 2, 3))
def test_open_subgroup(self):
# Create a netCDF file with a dataset within a group within a group
with create_tmp_file() as tmp_file:
rootgrp = nc4.Dataset(tmp_file, 'w')
foogrp = rootgrp.createGroup('foo')
bargrp = foogrp.createGroup('bar')
ds = bargrp
ds.createDimension('time', size=10)
x = np.arange(10)
ds.createVariable('x', np.int32, dimensions=('time',))
ds.variables['x'][:] = x
rootgrp.close()
expected = Dataset()
expected['x'] = ('time', x)
# check equivalent ways to specify group
for group in 'foo/bar', '/foo/bar', 'foo/bar/', '/foo/bar/':
with open_dataset(tmp_file, group=group) as actual:
assert_equal(actual['x'], expected['x'])
def test_write_groups(self):
data1 = create_test_data()
data2 = data1 * 2
with create_tmp_file() as tmp_file:
data1.to_netcdf(tmp_file, group='data/1')
data2.to_netcdf(tmp_file, group='data/2', mode='a')
with open_dataset(tmp_file, group='data/1') as actual1:
assert_identical(data1, actual1)
with open_dataset(tmp_file, group='data/2') as actual2:
assert_identical(data2, actual2)
def test_roundtrip_string_with_fill_value_vlen(self):
values = np.array([u'ab', u'cdef', np.nan], dtype=object)
expected = Dataset({'x': ('t', values)})
# netCDF4-based backends don't support an explicit fillvalue
# for variable length strings yet.
# https://github.com/Unidata/netcdf4-python/issues/730
# https://github.com/shoyer/h5netcdf/issues/37
original = Dataset({'x': ('t', values, {}, {'_FillValue': u'XXX'})})
with pytest.raises(NotImplementedError):
with self.roundtrip(original) as actual:
assert_identical(expected, actual)
original = Dataset({'x': ('t', values, {}, {'_FillValue': u''})})
with pytest.raises(NotImplementedError):
with self.roundtrip(original) as actual:
assert_identical(expected, actual)
def test_roundtrip_character_array(self):
with create_tmp_file() as tmp_file:
values = np.array([['a', 'b', 'c'], ['d', 'e', 'f']], dtype='S')
with nc4.Dataset(tmp_file, mode='w') as nc:
nc.createDimension('x', 2)
nc.createDimension('string3', 3)
v = nc.createVariable('x', np.dtype('S1'), ('x', 'string3'))
v[:] = values
values = np.array(['abc', 'def'], dtype='S')
expected = Dataset({'x': ('x', values)})
with open_dataset(tmp_file) as actual:
assert_identical(expected, actual)
# regression test for #157
with self.roundtrip(actual) as roundtripped:
assert_identical(expected, roundtripped)
def test_default_to_char_arrays(self):
data = Dataset({'x': np.array(['foo', 'zzzz'], dtype='S')})
with self.roundtrip(data) as actual:
assert_identical(data, actual)
self.assertEqual(actual['x'].dtype, np.dtype('S4'))
def test_open_encodings(self):
# Create a netCDF file with explicit time units
# and make sure it makes it into the encodings
# and survives a round trip
with create_tmp_file() as tmp_file:
with nc4.Dataset(tmp_file, 'w') as ds:
ds.createDimension('time', size=10)
ds.createVariable('time', np.int32, dimensions=('time',))
units = 'days since 1999-01-01'
ds.variables['time'].setncattr('units', units)
ds.variables['time'][:] = np.arange(10) + 4
expected = Dataset()
time = pd.date_range('1999-01-05', periods=10)
encoding = {'units': units, 'dtype': np.dtype('int32')}
expected['time'] = ('time', time, {}, encoding)
with open_dataset(tmp_file) as actual:
assert_equal(actual['time'], expected['time'])
actual_encoding = dict((k, v) for k, v in
iteritems(actual['time'].encoding)
if k in expected['time'].encoding)
self.assertDictEqual(actual_encoding,
expected['time'].encoding)
def test_dump_encodings(self):
# regression test for #709
ds = Dataset({'x': ('y', np.arange(10.0))})
kwargs = dict(encoding={'x': {'zlib': True}})
with self.roundtrip(ds, save_kwargs=kwargs) as actual:
self.assertTrue(actual.x.encoding['zlib'])
def test_dump_and_open_encodings(self):
# Create a netCDF file with explicit time units
# and make sure it makes it into the encodings
# and survives a round trip
with create_tmp_file() as tmp_file:
with nc4.Dataset(tmp_file, 'w') as ds:
ds.createDimension('time', size=10)
ds.createVariable('time', np.int32, dimensions=('time',))
units = 'days since 1999-01-01'
ds.variables['time'].setncattr('units', units)
ds.variables['time'][:] = np.arange(10) + 4
with open_dataset(tmp_file) as xarray_dataset:
with create_tmp_file() as tmp_file2:
xarray_dataset.to_netcdf(tmp_file2)
with nc4.Dataset(tmp_file2, 'r') as ds:
self.assertEqual(
ds.variables['time'].getncattr('units'), units)
assert_array_equal(
ds.variables['time'], np.arange(10) + 4)
def test_compression_encoding(self):
data = create_test_data()
data['var2'].encoding.update({'zlib': True,
'chunksizes': (5, 5),
'fletcher32': True,
'shuffle': True,
'original_shape': data.var2.shape})
with self.roundtrip(data) as actual:
for k, v in iteritems(data['var2'].encoding):
self.assertEqual(v, actual['var2'].encoding[k])
# regression test for #156
expected = data.isel(dim1=0)
with self.roundtrip(expected) as actual:
assert_equal(expected, actual)
def test_encoding_chunksizes_unlimited(self):
# regression test for GH1225
ds = Dataset({'x': [1, 2, 3], 'y': ('x', [2, 3, 4])})
ds.variables['x'].encoding = {
'zlib': False,
'shuffle': False,
'complevel': 0,
'fletcher32': False,
'contiguous': False,
'chunksizes': (2 ** 20,),
'original_shape': (3,),
}
with self.roundtrip(ds) as actual:
assert_equal(ds, actual)
def test_mask_and_scale(self):
with create_tmp_file() as tmp_file:
with nc4.Dataset(tmp_file, mode='w') as nc:
nc.createDimension('t', 5)
nc.createVariable('x', 'int16', ('t',), fill_value=-1)
v = nc.variables['x']
v.set_auto_maskandscale(False)
v.add_offset = 10
v.scale_factor = 0.1
v[:] = np.array([-1, -1, 0, 1, 2])
# first make sure netCDF4 reads the masked and scaled data
# correctly
with nc4.Dataset(tmp_file, mode='r') as nc:
expected = np.ma.array([-1, -1, 10, 10.1, 10.2],
mask=[True, True, False, False, False])
actual = nc.variables['x'][:]
assert_array_equal(expected, actual)
# now check xarray
with open_dataset(tmp_file) as ds:
expected = create_masked_and_scaled_data()
assert_identical(expected, ds)
def test_0dimensional_variable(self):
# This fix verifies our work-around to this netCDF4-python bug:
# https://github.com/Unidata/netcdf4-python/pull/220
with create_tmp_file() as tmp_file:
with nc4.Dataset(tmp_file, mode='w') as nc:
v = nc.createVariable('x', 'int16')
v[...] = 123
with open_dataset(tmp_file) as ds:
expected = Dataset({'x': ((), 123)})
assert_identical(expected, ds)
def test_already_open_dataset(self):
with create_tmp_file() as tmp_file:
with nc4.Dataset(tmp_file, mode='w') as nc:
v = nc.createVariable('x', 'int')
v[...] = 42
nc = nc4.Dataset(tmp_file, mode='r')
with backends.NetCDF4DataStore(nc, autoclose=False) as store:
with open_dataset(store) as ds:
expected = Dataset({'x': ((), 42)})
assert_identical(expected, ds)
def test_variable_len_strings(self):
with create_tmp_file() as tmp_file:
values = np.array(['foo', 'bar', 'baz'], dtype=object)
with nc4.Dataset(tmp_file, mode='w') as nc:
nc.createDimension('x', 3)
v = nc.createVariable('x', str, ('x',))
v[:] = values
expected = Dataset({'x': ('x', values)})
for kwargs in [{}, {'decode_cf': True}]:
with open_dataset(tmp_file, **kwargs) as actual:
assert_identical(expected, actual)
@requires_netCDF4
class NetCDF4DataTest(BaseNetCDF4Test, TestCase):
autoclose = False
@contextlib.contextmanager
def create_store(self):
with create_tmp_file() as tmp_file:
with backends.NetCDF4DataStore.open(tmp_file, mode='w') as store:
yield store
def test_variable_order(self):
# doesn't work with scipy or h5py :(
ds = Dataset()
ds['a'] = 1
ds['z'] = 2
ds['b'] = 3
ds.coords['c'] = 4
with self.roundtrip(ds) as actual:
self.assertEqual(list(ds.variables), list(actual.variables))
def test_unsorted_index_raises(self):
# should be fixed in netcdf4 v1.2.1
random_data = np.random.random(size=(4, 6))
dim0 = [0, 1, 2, 3]
dim1 = [0, 2, 1, 3, 5, 4] # We will sort this in a later step
da = xr.DataArray(data=random_data, dims=('dim0', 'dim1'),
coords={'dim0': dim0, 'dim1': dim1}, name='randovar')
ds = da.to_dataset()
with self.roundtrip(ds) as ondisk:
inds = np.argsort(dim1)
ds2 = ondisk.isel(dim1=inds)
# Older versions of NetCDF4 raise an exception here, and if so we
# want to ensure we improve (that is, replace) the error message
try:
ds2.randovar.values
except IndexError as err:
self.assertIn('first by calling .load', str(err))
def test_88_character_filename_segmentation_fault(self):
# should be fixed in netcdf4 v1.3.1
with mock.patch('netCDF4.__version__', '1.2.4'):
with warnings.catch_warnings():
warnings.simplefilter("error")
with raises_regex(Warning, 'segmentation fault'):
# Need to construct 88 character filepath
xr.Dataset().to_netcdf('a' * (88 - len(os.getcwd()) - 1))
class NetCDF4DataStoreAutocloseTrue(NetCDF4DataTest):
autoclose = True
@requires_netCDF4
@requires_dask
class NetCDF4ViaDaskDataTest(NetCDF4DataTest):
@contextlib.contextmanager
def roundtrip(self, data, save_kwargs={}, open_kwargs={},
allow_cleanup_failure=False):
with NetCDF4DataTest.roundtrip(
self, data, save_kwargs, open_kwargs,
allow_cleanup_failure) as ds:
yield ds.chunk()
def test_unsorted_index_raises(self):
# Skip when using dask because dask rewrites indexers to getitem,
# dask first pulls items by block.
pass
def test_dataset_caching(self):
# caching behavior differs for dask
pass
class NetCDF4ViaDaskDataTestAutocloseTrue(NetCDF4ViaDaskDataTest):
autoclose = True
@requires_zarr
class BaseZarrTest(CFEncodedDataTest):
DIMENSION_KEY = '_ARRAY_DIMENSIONS'
@contextlib.contextmanager
def create_store(self):
with self.create_zarr_target() as store_target:
yield backends.ZarrStore.open_group(store_target, mode='w')
def save(self, dataset, store_target, **kwargs):
dataset.to_zarr(store=store_target, **kwargs)
@contextlib.contextmanager
def open(self, store_target, **kwargs):
with xr.open_zarr(store_target, **kwargs) as ds:
yield ds
@contextlib.contextmanager
def roundtrip(self, data, save_kwargs={}, open_kwargs={},
allow_cleanup_failure=False):
with self.create_zarr_target() as store_target:
self.save(data, store_target, **save_kwargs)
with self.open(store_target, **open_kwargs) as ds:
yield ds
@contextlib.contextmanager
def roundtrip_append(self, data, save_kwargs={}, open_kwargs={},
allow_cleanup_failure=False):
pytest.skip("zarr backend does not support appending")
def test_auto_chunk(self):
original = create_test_data().chunk()
with self.roundtrip(
original, open_kwargs={'auto_chunk': False}) as actual:
for k, v in actual.variables.items():
# only index variables should be in memory
self.assertEqual(v._in_memory, k in actual.dims)
# there should be no chunks
self.assertEqual(v.chunks, None)
with self.roundtrip(
original, open_kwargs={'auto_chunk': True}) as actual:
for k, v in actual.variables.items():
# only index variables should be in memory
self.assertEqual(v._in_memory, k in actual.dims)
# chunk size should be the same as original
self.assertEqual(v.chunks, original[k].chunks)
def test_chunk_encoding(self):
# These datasets have no dask chunks. All chunking specified in
# encoding
data = create_test_data()
chunks = (5, 5)
data['var2'].encoding.update({'chunks': chunks})
with self.roundtrip(data) as actual:
self.assertEqual(chunks, actual['var2'].encoding['chunks'])
# expect an error with non-integer chunks
data['var2'].encoding.update({'chunks': (5, 4.5)})
with pytest.raises(TypeError):
with self.roundtrip(data) as actual:
pass
def test_chunk_encoding_with_dask(self):
# These datasets DO have dask chunks. Need to check for various
# interactions between dask and zarr chunks
ds = xr.DataArray((np.arange(12)), dims='x', name='var1').to_dataset()
# - no encoding specified -
# zarr automatically gets chunk information from dask chunks
ds_chunk4 = ds.chunk({'x': 4})
with self.roundtrip(ds_chunk4) as actual:
self.assertEqual((4,), actual['var1'].encoding['chunks'])
# should fail if dask_chunks are irregular...
ds_chunk_irreg = ds.chunk({'x': (5, 4, 3)})
with pytest.raises(ValueError) as e_info:
with self.roundtrip(ds_chunk_irreg) as actual:
pass
# make sure this error message is correct and not some other error
assert e_info.match('chunks')
# ... except if the last chunk is smaller than the first
ds_chunk_irreg = ds.chunk({'x': (5, 5, 2)})
with self.roundtrip(ds_chunk_irreg) as actual:
self.assertEqual((5,), actual['var1'].encoding['chunks'])
# - encoding specified -
# specify compatible encodings
for chunk_enc in 4, (4, ):
ds_chunk4['var1'].encoding.update({'chunks': chunk_enc})
with self.roundtrip(ds_chunk4) as actual:
self.assertEqual((4,), actual['var1'].encoding['chunks'])
# specify incompatible encoding
ds_chunk4['var1'].encoding.update({'chunks': (5, 5)})
with pytest.raises(ValueError) as e_info:
with self.roundtrip(ds_chunk4) as actual:
pass
assert e_info.match('chunks')
# TODO: remove this failure once syncronized overlapping writes are
# supported by xarray
ds_chunk4['var1'].encoding.update({'chunks': 5})
with pytest.raises(NotImplementedError):
with self.roundtrip(ds_chunk4) as actual:
pass
def test_hidden_zarr_keys(self):
expected = create_test_data()
with self.create_store() as store:
expected.dump_to_store(store)
zarr_group = store.ds
# check that a variable hidden attribute is present and correct
# JSON only has a single array type, which maps to list in Python.
# In contrast, dims in xarray is always a tuple.
for var in expected.variables.keys():
dims = zarr_group[var].attrs[self.DIMENSION_KEY]
assert dims == list(expected[var].dims)
with xr.decode_cf(store):
# make sure it is hidden
for var in expected.variables.keys():
assert self.DIMENSION_KEY not in expected[var].attrs
# put it back and try removing from a variable
del zarr_group.var2.attrs[self.DIMENSION_KEY]
with pytest.raises(KeyError):
with xr.decode_cf(store):
pass
def test_write_persistence_modes(self):
original = create_test_data()
# overwrite mode
with self.roundtrip(original, save_kwargs={'mode': 'w'}) as actual:
assert_identical(original, actual)
# don't overwrite mode
with self.roundtrip(original, save_kwargs={'mode': 'w-'}) as actual:
assert_identical(original, actual)
# make sure overwriting works as expected
with self.create_zarr_target() as store:
self.save(original, store)
# should overwrite with no error
self.save(original, store, mode='w')
with self.open(store) as actual:
assert_identical(original, actual)
with pytest.raises(ValueError):
self.save(original, store, mode='w-')
# check that we can't use other persistence modes
# TODO: reconsider whether other persistence modes should be supported
with pytest.raises(ValueError):
with self.roundtrip(original, save_kwargs={'mode': 'a'}) as actual:
pass
def test_compressor_encoding(self):
original = create_test_data()
# specify a custom compressor
import zarr
blosc_comp = zarr.Blosc(cname='zstd', clevel=3, shuffle=2)
save_kwargs = dict(encoding={'var1': {'compressor': blosc_comp}})
with self.roundtrip(original, save_kwargs=save_kwargs) as ds:
actual = ds['var1'].encoding['compressor']
# get_config returns a dictionary of compressor attributes
assert actual.get_config() == blosc_comp.get_config()
def test_group(self):
original = create_test_data()
group = 'some/random/path'
with self.roundtrip(original, save_kwargs={'group': group},
open_kwargs={'group': group}) as actual:
assert_identical(original, actual)
# TODO: implement zarr object encoding and make these tests pass
@pytest.mark.xfail(reason="Zarr object encoding not implemented")
def test_multiindex_not_implemented(self):
super(CFEncodedDataTest, self).test_multiindex_not_implemented()
@pytest.mark.xfail(reason="Zarr object encoding not implemented")
def test_roundtrip_bytes_with_fill_value(self):
super(CFEncodedDataTest, self).test_roundtrip_bytes_with_fill_value()
@pytest.mark.xfail(reason="Zarr object encoding not implemented")
def test_roundtrip_object_dtype(self):
super(CFEncodedDataTest, self).test_roundtrip_object_dtype()
@pytest.mark.xfail(reason="Zarr object encoding not implemented")
def test_roundtrip_string_encoded_characters(self):
super(CFEncodedDataTest,
self).test_roundtrip_string_encoded_characters()
# TODO: someone who understand caching figure out whether chaching
# makes sense for Zarr backend
@pytest.mark.xfail(reason="Zarr caching not implemented")
def test_dataset_caching(self):
super(CFEncodedDataTest, self).test_dataset_caching()
@pytest.mark.xfail(reason="Zarr stores can not be appended to")
def test_append_write(self):
super(CFEncodedDataTest, self).test_append_write()
@pytest.mark.xfail(reason="Zarr stores can not be appended to")
def test_append_overwrite_values(self):
super(CFEncodedDataTest, self).test_append_overwrite_values()
@pytest.mark.xfail(reason="Zarr stores can not be appended to")
def test_append_with_invalid_dim_raises(self):
super(CFEncodedDataTest, self).test_append_with_invalid_dim_raises()
@requires_zarr
class ZarrDictStoreTest(BaseZarrTest, TestCase):
@contextlib.contextmanager
def create_zarr_target(self):
yield {}
@requires_zarr
class ZarrDirectoryStoreTest(BaseZarrTest, TestCase):
@contextlib.contextmanager
def create_zarr_target(self):
with create_tmp_file(suffix='.zarr') as tmp:
yield tmp
@requires_scipy
class ScipyInMemoryDataTest(CFEncodedDataTest, NetCDF3Only, TestCase):
engine = 'scipy'
@contextlib.contextmanager
def create_store(self):
fobj = BytesIO()
yield backends.ScipyDataStore(fobj, 'w')
def test_to_netcdf_explicit_engine(self):
# regression test for GH1321
Dataset({'foo': 42}).to_netcdf(engine='scipy')
@pytest.mark.skipif(PY2, reason='cannot pickle BytesIO on Python 2')
def test_bytesio_pickle(self):
data = Dataset({'foo': ('x', [1, 2, 3])})
fobj = BytesIO(data.to_netcdf())
with open_dataset(fobj, autoclose=self.autoclose) as ds:
unpickled = pickle.loads(pickle.dumps(ds))
assert_identical(unpickled, data)
class ScipyInMemoryDataTestAutocloseTrue(ScipyInMemoryDataTest):
autoclose = True
@requires_scipy
class ScipyFileObjectTest(CFEncodedDataTest, NetCDF3Only, TestCase):
engine = 'scipy'
@contextlib.contextmanager
def create_store(self):
fobj = BytesIO()
yield backends.ScipyDataStore(fobj, 'w')
@contextlib.contextmanager
def roundtrip(self, data, save_kwargs={}, open_kwargs={},
allow_cleanup_failure=False):
with create_tmp_file() as tmp_file:
with open(tmp_file, 'wb') as f:
self.save(data, f, **save_kwargs)
with open(tmp_file, 'rb') as f:
with self.open(f, **open_kwargs) as ds:
yield ds
@pytest.mark.skip(reason='cannot pickle file objects')
def test_pickle(self):
pass
@pytest.mark.skip(reason='cannot pickle file objects')
def test_pickle_dataarray(self):
pass
@requires_scipy
class ScipyFilePathTest(CFEncodedDataTest, NetCDF3Only, TestCase):
engine = 'scipy'
@contextlib.contextmanager
def create_store(self):
with create_tmp_file() as tmp_file:
with backends.ScipyDataStore(tmp_file, mode='w') as store:
yield store
def test_array_attrs(self):
ds = Dataset(attrs={'foo': [[1, 2], [3, 4]]})
with raises_regex(ValueError, 'must be 1-dimensional'):
with self.roundtrip(ds):
pass
def test_roundtrip_example_1_netcdf_gz(self):
with open_example_dataset('example_1.nc.gz') as expected:
with open_example_dataset('example_1.nc') as actual:
assert_identical(expected, actual)
def test_netcdf3_endianness(self):
# regression test for GH416
expected = open_example_dataset('bears.nc', engine='scipy')
for var in expected.variables.values():
self.assertTrue(var.dtype.isnative)
@requires_netCDF4
def test_nc4_scipy(self):
with create_tmp_file(allow_cleanup_failure=True) as tmp_file:
with nc4.Dataset(tmp_file, 'w', format='NETCDF4') as rootgrp:
rootgrp.createGroup('foo')
with raises_regex(TypeError, 'pip install netcdf4'):
open_dataset(tmp_file, engine='scipy')
class ScipyFilePathTestAutocloseTrue(ScipyFilePathTest):
autoclose = True
@requires_netCDF4
class NetCDF3ViaNetCDF4DataTest(CFEncodedDataTest, NetCDF3Only, TestCase):
engine = 'netcdf4'
file_format = 'NETCDF3_CLASSIC'
@contextlib.contextmanager
def create_store(self):
with create_tmp_file() as tmp_file:
with backends.NetCDF4DataStore.open(
tmp_file, mode='w', format='NETCDF3_CLASSIC') as store:
yield store
class NetCDF3ViaNetCDF4DataTestAutocloseTrue(NetCDF3ViaNetCDF4DataTest):
autoclose = True
@requires_netCDF4
class NetCDF4ClassicViaNetCDF4DataTest(CFEncodedDataTest, NetCDF3Only,
TestCase):
engine = 'netcdf4'
file_format = 'NETCDF4_CLASSIC'
@contextlib.contextmanager
def create_store(self):
with create_tmp_file() as tmp_file:
with backends.NetCDF4DataStore.open(
tmp_file, mode='w', format='NETCDF4_CLASSIC') as store:
yield store
class NetCDF4ClassicViaNetCDF4DataTestAutocloseTrue(
NetCDF4ClassicViaNetCDF4DataTest):
autoclose = True
@requires_scipy_or_netCDF4
class GenericNetCDFDataTest(CFEncodedDataTest, NetCDF3Only, TestCase):
# verify that we can read and write netCDF3 files as long as we have scipy
# or netCDF4-python installed
file_format = 'netcdf3_64bit'
def test_write_store(self):
# there's no specific store to test here
pass
def test_engine(self):
data = create_test_data()
with raises_regex(ValueError, 'unrecognized engine'):
data.to_netcdf('foo.nc', engine='foobar')
with raises_regex(ValueError, 'invalid engine'):
data.to_netcdf(engine='netcdf4')
with create_tmp_file() as tmp_file:
data.to_netcdf(tmp_file)
with raises_regex(ValueError, 'unrecognized engine'):
open_dataset(tmp_file, engine='foobar')
netcdf_bytes = data.to_netcdf()
with raises_regex(ValueError, 'can only read'):
open_dataset(BytesIO(netcdf_bytes), engine='foobar')
def test_cross_engine_read_write_netcdf3(self):
data = create_test_data()
valid_engines = set()
if has_netCDF4:
valid_engines.add('netcdf4')
if has_scipy:
valid_engines.add('scipy')
for write_engine in valid_engines:
for format in ['NETCDF3_CLASSIC', 'NETCDF3_64BIT']:
with create_tmp_file() as tmp_file:
data.to_netcdf(tmp_file, format=format,
engine=write_engine)
for read_engine in valid_engines:
with open_dataset(tmp_file,
engine=read_engine) as actual:
# hack to allow test to work:
# coord comes back as DataArray rather than coord,
# and so need to loop through here rather than in
# the test function (or we get recursion)
[assert_allclose(data[k].variable,
actual[k].variable)
for k in data.variables]
def test_encoding_unlimited_dims(self):
ds = Dataset({'x': ('y', np.arange(10.0))})
with self.roundtrip(ds,
save_kwargs=dict(unlimited_dims=['y'])) as actual:
self.assertEqual(actual.encoding['unlimited_dims'], set('y'))
assert_equal(ds, actual)
ds.encoding = {'unlimited_dims': ['y']}
with self.roundtrip(ds) as actual:
self.assertEqual(actual.encoding['unlimited_dims'], set('y'))
assert_equal(ds, actual)
class GenericNetCDFDataTestAutocloseTrue(GenericNetCDFDataTest):
autoclose = True
@requires_h5netcdf
@requires_netCDF4
class H5NetCDFDataTest(BaseNetCDF4Test, TestCase):
engine = 'h5netcdf'
@contextlib.contextmanager
def create_store(self):
with create_tmp_file() as tmp_file:
yield backends.H5NetCDFStore(tmp_file, 'w')
def test_complex(self):
expected = Dataset({'x': ('y', np.ones(5) + 1j * np.ones(5))})
with self.roundtrip(expected) as actual:
assert_equal(expected, actual)
@pytest.mark.xfail(reason='https://github.com/pydata/xarray/issues/535')
def test_cross_engine_read_write_netcdf4(self):
# Drop dim3, because its labels include strings. These appear to be
# not properly read with python-netCDF4, which converts them into
# unicode instead of leaving them as bytes.
data = create_test_data().drop('dim3')
data.attrs['foo'] = 'bar'
valid_engines = ['netcdf4', 'h5netcdf']
for write_engine in valid_engines:
with create_tmp_file() as tmp_file:
data.to_netcdf(tmp_file, engine=write_engine)
for read_engine in valid_engines:
with open_dataset(tmp_file, engine=read_engine) as actual:
assert_identical(data, actual)
def test_read_byte_attrs_as_unicode(self):
with create_tmp_file() as tmp_file:
with nc4.Dataset(tmp_file, 'w') as nc:
nc.foo = b'bar'
with open_dataset(tmp_file) as actual:
expected = Dataset(attrs={'foo': 'bar'})
assert_identical(expected, actual)
def test_encoding_unlimited_dims(self):
ds = Dataset({'x': ('y', np.arange(10.0))})
with self.roundtrip(ds,
save_kwargs=dict(unlimited_dims=['y'])) as actual:
self.assertEqual(actual.encoding['unlimited_dims'], set('y'))
assert_equal(ds, actual)
ds.encoding = {'unlimited_dims': ['y']}
with self.roundtrip(ds) as actual:
self.assertEqual(actual.encoding['unlimited_dims'], set('y'))
assert_equal(ds, actual)
# tests pending h5netcdf fix
@unittest.skip
class H5NetCDFDataTestAutocloseTrue(H5NetCDFDataTest):
autoclose = True
class OpenMFDatasetManyFilesTest(TestCase):
def validate_open_mfdataset_autoclose(self, engine, nfiles=10):
randdata = np.random.randn(nfiles)
original = Dataset({'foo': ('x', randdata)})
# test standard open_mfdataset approach with too many files
with create_tmp_files(nfiles) as tmpfiles:
for readengine in engine:
writeengine = (readengine if readengine != 'pynio'
else 'netcdf4')
# split into multiple sets of temp files
for ii in original.x.values:
subds = original.isel(x=slice(ii, ii + 1))
subds.to_netcdf(tmpfiles[ii], engine=writeengine)
# check that calculation on opened datasets works properly
ds = open_mfdataset(tmpfiles, engine=readengine,
autoclose=True)
self.assertAllClose(ds.x.sum().values,
(nfiles * (nfiles - 1)) / 2)
self.assertAllClose(ds.foo.sum().values, np.sum(randdata))
self.assertAllClose(ds.sum().foo.values, np.sum(randdata))
ds.close()
def validate_open_mfdataset_large_num_files(self, engine):
self.validate_open_mfdataset_autoclose(engine, nfiles=2000)
@requires_dask
@requires_netCDF4
def test_1_autoclose_netcdf4(self):
self.validate_open_mfdataset_autoclose(engine=['netcdf4'])
@requires_dask
@requires_scipy
def test_2_autoclose_scipy(self):
self.validate_open_mfdataset_autoclose(engine=['scipy'])
@requires_dask
@requires_pynio
def test_3_autoclose_pynio(self):
self.validate_open_mfdataset_autoclose(engine=['pynio'])
# use of autoclose=True with h5netcdf broken because of
# probable h5netcdf error
@requires_dask
@requires_h5netcdf
@pytest.mark.xfail
def test_4_autoclose_h5netcdf(self):
self.validate_open_mfdataset_autoclose(engine=['h5netcdf'])
# These tests below are marked as flaky (and skipped by default) because
# they fail sometimes on Travis-CI, for no clear reason.
@requires_dask
@requires_netCDF4
@flaky
@pytest.mark.slow
def test_1_open_large_num_files_netcdf4(self):
self.validate_open_mfdataset_large_num_files(engine=['netcdf4'])
@requires_dask
@requires_scipy
@flaky
@pytest.mark.slow
def test_2_open_large_num_files_scipy(self):
self.validate_open_mfdataset_large_num_files(engine=['scipy'])
@requires_dask
@requires_pynio
@flaky
@pytest.mark.slow
def test_3_open_large_num_files_pynio(self):
self.validate_open_mfdataset_large_num_files(engine=['pynio'])
# use of autoclose=True with h5netcdf broken because of
# probable h5netcdf error
@requires_dask
@requires_h5netcdf
@flaky
@pytest.mark.xfail
@pytest.mark.slow
def test_4_open_large_num_files_h5netcdf(self):
self.validate_open_mfdataset_large_num_files(engine=['h5netcdf'])
@requires_scipy_or_netCDF4
class OpenMFDatasetWithDataVarsAndCoordsKwTest(TestCase):
coord_name = 'lon'
var_name = 'v1'
@contextlib.contextmanager
def setup_files_and_datasets(self):
ds1, ds2 = self.gen_datasets_with_common_coord_and_time()
with create_tmp_file() as tmpfile1:
with create_tmp_file() as tmpfile2:
# save data to the temporary files
ds1.to_netcdf(tmpfile1)
ds2.to_netcdf(tmpfile2)
yield [tmpfile1, tmpfile2], [ds1, ds2]
def gen_datasets_with_common_coord_and_time(self):
# create coordinate data
nx = 10
nt = 10
x = np.arange(nx)
t1 = np.arange(nt)
t2 = np.arange(nt, 2 * nt, 1)
v1 = np.random.randn(nt, nx)
v2 = np.random.randn(nt, nx)
ds1 = Dataset(data_vars={self.var_name: (['t', 'x'], v1),
self.coord_name: ('x', 2 * x)},
coords={
't': (['t', ], t1),
'x': (['x', ], x)
})
ds2 = Dataset(data_vars={self.var_name: (['t', 'x'], v2),
self.coord_name: ('x', 2 * x)},
coords={
't': (['t', ], t2),
'x': (['x', ], x)
})
return ds1, ds2
def test_open_mfdataset_does_same_as_concat(self):
options = ['all', 'minimal', 'different', ]
with self.setup_files_and_datasets() as (files, [ds1, ds2]):
for opt in options:
with open_mfdataset(files, data_vars=opt) as ds:
kwargs = dict(data_vars=opt, dim='t')
ds_expect = xr.concat([ds1, ds2], **kwargs)
assert_identical(ds, ds_expect)
with open_mfdataset(files, coords=opt) as ds:
kwargs = dict(coords=opt, dim='t')
ds_expect = xr.concat([ds1, ds2], **kwargs)
assert_identical(ds, ds_expect)
def test_common_coord_when_datavars_all(self):
opt = 'all'
with self.setup_files_and_datasets() as (files, [ds1, ds2]):
# open the files with the data_var option
with open_mfdataset(files, data_vars=opt) as ds:
coord_shape = ds[self.coord_name].shape
coord_shape1 = ds1[self.coord_name].shape
coord_shape2 = ds2[self.coord_name].shape
var_shape = ds[self.var_name].shape
self.assertEqual(var_shape, coord_shape)
self.assertNotEqual(coord_shape1, coord_shape)
self.assertNotEqual(coord_shape2, coord_shape)
def test_common_coord_when_datavars_minimal(self):
opt = 'minimal'
with self.setup_files_and_datasets() as (files, [ds1, ds2]):
# open the files using data_vars option
with open_mfdataset(files, data_vars=opt) as ds:
coord_shape = ds[self.coord_name].shape
coord_shape1 = ds1[self.coord_name].shape
coord_shape2 = ds2[self.coord_name].shape
var_shape = ds[self.var_name].shape
self.assertNotEqual(var_shape, coord_shape)
self.assertEqual(coord_shape1, coord_shape)
self.assertEqual(coord_shape2, coord_shape)
def test_invalid_data_vars_value_should_fail(self):
with self.setup_files_and_datasets() as (files, _):
with pytest.raises(ValueError):
with open_mfdataset(files, data_vars='minimum'):
pass
# test invalid coord parameter
with pytest.raises(ValueError):
with open_mfdataset(files, coords='minimum'):
pass
@requires_dask
@requires_scipy
@requires_netCDF4
class DaskTest(TestCase, DatasetIOTestCases):
@contextlib.contextmanager
def create_store(self):
yield Dataset()
@contextlib.contextmanager
def roundtrip(self, data, save_kwargs={}, open_kwargs={},
allow_cleanup_failure=False):
yield data.chunk()
# Override methods in DatasetIOTestCases - not applicable to dask
def test_roundtrip_string_encoded_characters(self):
pass
def test_roundtrip_coordinates_with_space(self):
pass
def test_roundtrip_datetime_data(self):
# Override method in DatasetIOTestCases - remove not applicable
# save_kwds
times = pd.to_datetime(['2000-01-01', '2000-01-02', 'NaT'])
expected = Dataset({'t': ('t', times), 't0': times[0]})
with self.roundtrip(expected) as actual:
assert_identical(expected, actual)
def test_write_store(self):
# Override method in DatasetIOTestCases - not applicable to dask
pass
def test_dataset_caching(self):
expected = Dataset({'foo': ('x', [5, 6, 7])})
with self.roundtrip(expected) as actual:
assert not actual.foo.variable._in_memory
actual.foo.values # no caching
assert not actual.foo.variable._in_memory
def test_open_mfdataset(self):
original = Dataset({'foo': ('x', np.random.randn(10))})
with create_tmp_file() as tmp1:
with create_tmp_file() as tmp2:
original.isel(x=slice(5)).to_netcdf(tmp1)
original.isel(x=slice(5, 10)).to_netcdf(tmp2)
with open_mfdataset([tmp1, tmp2],
autoclose=self.autoclose) as actual:
self.assertIsInstance(actual.foo.variable.data, da.Array)
self.assertEqual(actual.foo.variable.data.chunks,
((5, 5),))
assert_identical(original, actual)
with open_mfdataset([tmp1, tmp2], chunks={'x': 3},
autoclose=self.autoclose) as actual:
self.assertEqual(actual.foo.variable.data.chunks,
((3, 2, 3, 2),))
with raises_regex(IOError, 'no files to open'):
open_mfdataset('foo-bar-baz-*.nc', autoclose=self.autoclose)
@requires_pathlib
def test_open_mfdataset_pathlib(self):
original = Dataset({'foo': ('x', np.random.randn(10))})
with create_tmp_file() as tmp1:
with create_tmp_file() as tmp2:
tmp1 = Path(tmp1)
tmp2 = Path(tmp2)
original.isel(x=slice(5)).to_netcdf(tmp1)
original.isel(x=slice(5, 10)).to_netcdf(tmp2)
with open_mfdataset([tmp1, tmp2],
autoclose=self.autoclose) as actual:
assert_identical(original, actual)
def test_attrs_mfdataset(self):
original = Dataset({'foo': ('x', np.random.randn(10))})
with create_tmp_file() as tmp1:
with create_tmp_file() as tmp2:
ds1 = original.isel(x=slice(5))
ds2 = original.isel(x=slice(5, 10))
ds1.attrs['test1'] = 'foo'
ds2.attrs['test2'] = 'bar'
ds1.to_netcdf(tmp1)
ds2.to_netcdf(tmp2)
with open_mfdataset([tmp1, tmp2]) as actual:
# presumes that attributes inherited from
# first dataset loaded
self.assertEqual(actual.test1, ds1.test1)
# attributes from ds2 are not retained, e.g.,
with raises_regex(AttributeError,
'no attribute'):
actual.test2
def test_preprocess_mfdataset(self):
original = Dataset({'foo': ('x', np.random.randn(10))})
with create_tmp_file() as tmp:
original.to_netcdf(tmp)
def preprocess(ds):
return ds.assign_coords(z=0)
expected = preprocess(original)
with open_mfdataset(tmp, preprocess=preprocess,
autoclose=self.autoclose) as actual:
assert_identical(expected, actual)
def test_save_mfdataset_roundtrip(self):
original = Dataset({'foo': ('x', np.random.randn(10))})
datasets = [original.isel(x=slice(5)),
original.isel(x=slice(5, 10))]
with create_tmp_file() as tmp1:
with create_tmp_file() as tmp2:
save_mfdataset(datasets, [tmp1, tmp2])
with open_mfdataset([tmp1, tmp2],
autoclose=self.autoclose) as actual:
assert_identical(actual, original)
def test_save_mfdataset_invalid(self):
ds = Dataset()
with raises_regex(ValueError, 'cannot use mode'):
save_mfdataset([ds, ds], ['same', 'same'])
with raises_regex(ValueError, 'same length'):
save_mfdataset([ds, ds], ['only one path'])
def test_save_mfdataset_invalid_dataarray(self):
# regression test for GH1555
da = DataArray([1, 2])
with raises_regex(TypeError, 'supports writing Dataset'):
save_mfdataset([da], ['dataarray'])
@requires_pathlib
def test_save_mfdataset_pathlib_roundtrip(self):
original = Dataset({'foo': ('x', np.random.randn(10))})
datasets = [original.isel(x=slice(5)),
original.isel(x=slice(5, 10))]
with create_tmp_file() as tmp1:
with create_tmp_file() as tmp2:
tmp1 = Path(tmp1)
tmp2 = Path(tmp2)
save_mfdataset(datasets, [tmp1, tmp2])
with open_mfdataset([tmp1, tmp2],
autoclose=self.autoclose) as actual:
assert_identical(actual, original)
def test_open_and_do_math(self):
original = Dataset({'foo': ('x', np.random.randn(10))})
with create_tmp_file() as tmp:
original.to_netcdf(tmp)
with open_mfdataset(tmp, autoclose=self.autoclose) as ds:
actual = 1.0 * ds
assert_allclose(original, actual, decode_bytes=False)
def test_open_mfdataset_concat_dim_none(self):
with create_tmp_file() as tmp1:
with create_tmp_file() as tmp2:
data = Dataset({'x': 0})
data.to_netcdf(tmp1)
Dataset({'x': np.nan}).to_netcdf(tmp2)
with open_mfdataset([tmp1, tmp2], concat_dim=None,
autoclose=self.autoclose) as actual:
assert_identical(data, actual)
def test_open_dataset(self):
original = Dataset({'foo': ('x', np.random.randn(10))})
with create_tmp_file() as tmp:
original.to_netcdf(tmp)
with open_dataset(tmp, chunks={'x': 5}) as actual:
self.assertIsInstance(actual.foo.variable.data, da.Array)
self.assertEqual(actual.foo.variable.data.chunks, ((5, 5),))
assert_identical(original, actual)
with open_dataset(tmp, chunks=5) as actual:
assert_identical(original, actual)
with open_dataset(tmp) as actual:
self.assertIsInstance(actual.foo.variable.data, np.ndarray)
assert_identical(original, actual)
def test_dask_roundtrip(self):
with create_tmp_file() as tmp:
data = create_test_data()
data.to_netcdf(tmp)
chunks = {'dim1': 4, 'dim2': 4, 'dim3': 4, 'time': 10}
with open_dataset(tmp, chunks=chunks) as dask_ds:
assert_identical(data, dask_ds)
with create_tmp_file() as tmp2:
dask_ds.to_netcdf(tmp2)
with open_dataset(tmp2) as on_disk:
assert_identical(data, on_disk)
def test_deterministic_names(self):
with create_tmp_file() as tmp:
data = create_test_data()
data.to_netcdf(tmp)
with open_mfdataset(tmp, autoclose=self.autoclose) as ds:
original_names = dict((k, v.data.name)
for k, v in ds.data_vars.items())
with open_mfdataset(tmp, autoclose=self.autoclose) as ds:
repeat_names = dict((k, v.data.name)
for k, v in ds.data_vars.items())
for var_name, dask_name in original_names.items():
self.assertIn(var_name, dask_name)
self.assertEqual(dask_name[:13], 'open_dataset-')
self.assertEqual(original_names, repeat_names)
def test_dataarray_compute(self):
# Test DataArray.compute() on dask backend.
# The test for Dataset.compute() is already in DatasetIOTestCases;
# however dask is the only tested backend which supports DataArrays
actual = DataArray([1, 2]).chunk()
computed = actual.compute()
self.assertFalse(actual._in_memory)
self.assertTrue(computed._in_memory)
assert_allclose(actual, computed, decode_bytes=False)
class DaskTestAutocloseTrue(DaskTest):
autoclose = True
@requires_scipy_or_netCDF4
@requires_pydap
class PydapTest(TestCase):
def convert_to_pydap_dataset(self, original):
from pydap.model import GridType, BaseType, DatasetType
ds = DatasetType('bears', **original.attrs)
for key, var in original.data_vars.items():
v = GridType(key)
v[key] = BaseType(key, var.values, dimensions=var.dims,
**var.attrs)
for d in var.dims:
v[d] = BaseType(d, var[d].values)
ds[key] = v
# check all dims are stored in ds
for d in original.coords:
ds[d] = BaseType(d, original[d].values, dimensions=(d, ),
**original[d].attrs)
return ds
@contextlib.contextmanager
def create_datasets(self, **kwargs):
with open_example_dataset('bears.nc') as expected:
pydap_ds = self.convert_to_pydap_dataset(expected)
actual = open_dataset(PydapDataStore(pydap_ds))
# TODO solve this workaround:
# netcdf converts string to byte not unicode
expected['bears'] = expected['bears'].astype(str)
yield actual, expected
def test_cmp_local_file(self):
with self.create_datasets() as (actual, expected):
assert_equal(actual, expected)
# global attributes should be global attributes on the dataset
self.assertNotIn('NC_GLOBAL', actual.attrs)
self.assertIn('history', actual.attrs)
# we don't check attributes exactly with assertDatasetIdentical()
# because the test DAP server seems to insert some extra
# attributes not found in the netCDF file.
assert actual.attrs.keys() == expected.attrs.keys()
with self.create_datasets() as (actual, expected):
assert_equal(
actual.isel(l=2), expected.isel(l=2)) # noqa: E741
with self.create_datasets() as (actual, expected):
assert_equal(actual.isel(i=0, j=-1),
expected.isel(i=0, j=-1))
with self.create_datasets() as (actual, expected):
assert_equal(actual.isel(j=slice(1, 2)),
expected.isel(j=slice(1, 2)))
with self.create_datasets() as (actual, expected):
indexers = {'i': [1, 0, 0], 'j': [1, 2, 0, 1]}
assert_equal(actual.isel(**indexers),
expected.isel(**indexers))
with self.create_datasets() as (actual, expected):
indexers = {'i': DataArray([0, 1, 0], dims='a'),
'j': DataArray([0, 2, 1], dims='a')}
assert_equal(actual.isel(**indexers),
expected.isel(**indexers))
def test_compatible_to_netcdf(self):
# make sure it can be saved as a netcdf
with self.create_datasets() as (actual, expected):
with create_tmp_file() as tmp_file:
actual.to_netcdf(tmp_file)
actual = open_dataset(tmp_file)
actual['bears'] = actual['bears'].astype(str)
assert_equal(actual, expected)
@requires_dask
def test_dask(self):
with self.create_datasets(chunks={'j': 2}) as (actual, expected):
assert_equal(actual, expected)
@network
@requires_scipy_or_netCDF4
@requires_pydap
class PydapOnlineTest(PydapTest):
@contextlib.contextmanager
def create_datasets(self, **kwargs):
url = 'http://test.opendap.org/opendap/hyrax/data/nc/bears.nc'
actual = open_dataset(url, engine='pydap', **kwargs)
with open_example_dataset('bears.nc') as expected:
# workaround to restore string which is converted to byte
expected['bears'] = expected['bears'].astype(str)
yield actual, expected
def test_session(self):
from pydap.cas.urs import setup_session
session = setup_session('XarrayTestUser', 'Xarray2017')
with mock.patch('pydap.client.open_url') as mock_func:
xr.backends.PydapDataStore.open('http://test.url', session=session)
mock_func.assert_called_with('http://test.url', session=session)
@requires_scipy
@requires_pynio
class TestPyNio(CFEncodedDataTest, NetCDF3Only, TestCase):
def test_write_store(self):
# pynio is read-only for now
pass
@contextlib.contextmanager
def open(self, path, **kwargs):
with open_dataset(path, engine='pynio', autoclose=self.autoclose,
**kwargs) as ds:
yield ds
def save(self, dataset, path, **kwargs):
dataset.to_netcdf(path, engine='scipy', **kwargs)
def test_weakrefs(self):
example = Dataset({'foo': ('x', np.arange(5.0))})
expected = example.rename({'foo': 'bar', 'x': 'y'})
with create_tmp_file() as tmp_file:
example.to_netcdf(tmp_file, engine='scipy')
on_disk = open_dataset(tmp_file, engine='pynio')
actual = on_disk.rename({'foo': 'bar', 'x': 'y'})
del on_disk # trigger garbage collection
assert_identical(actual, expected)
class TestPyNioAutocloseTrue(TestPyNio):
autoclose = True
@requires_rasterio
@contextlib.contextmanager
def create_tmp_geotiff(nx=4, ny=3, nz=3,
transform=None,
transform_args=[5000, 80000, 1000, 2000.],
crs={'units': 'm', 'no_defs': True, 'ellps': 'WGS84',
'proj': 'utm', 'zone': 18},
open_kwargs={}):
# yields a temporary geotiff file and a corresponding expected DataArray
import rasterio
from rasterio.transform import from_origin
with create_tmp_file(suffix='.tif') as tmp_file:
# allow 2d or 3d shapes
if nz == 1:
data_shape = ny, nx
write_kwargs = {'indexes': 1}
else:
data_shape = nz, ny, nx
write_kwargs = {}
data = np.arange(
nz * ny * nx,
dtype=rasterio.float32).reshape(
*data_shape)
if transform is None:
transform = from_origin(*transform_args)
with rasterio.open(
tmp_file, 'w',
driver='GTiff', height=ny, width=nx, count=nz,
crs=crs,
transform=transform,
dtype=rasterio.float32,
**open_kwargs) as s:
s.write(data, **write_kwargs)
dx, dy = s.res[0], -s.res[1]
a, b, c, d = transform_args
data = data[np.newaxis, ...] if nz == 1 else data
expected = DataArray(data, dims=('band', 'y', 'x'),
coords={
'band': np.arange(nz) + 1,
'y': -np.arange(ny) * d + b + dy / 2,
'x': np.arange(nx) * c + a + dx / 2,
})
yield tmp_file, expected
@requires_rasterio
class TestRasterio(TestCase):
@requires_scipy_or_netCDF4
def test_serialization(self):
with create_tmp_geotiff() as (tmp_file, expected):
# Write it to a netcdf and read again (roundtrip)
with xr.open_rasterio(tmp_file) as rioda:
with create_tmp_file(suffix='.nc') as tmp_nc_file:
rioda.to_netcdf(tmp_nc_file)
with xr.open_dataarray(tmp_nc_file) as ncds:
assert_identical(rioda, ncds)
def test_utm(self):
with create_tmp_geotiff() as (tmp_file, expected):
with xr.open_rasterio(tmp_file) as rioda:
assert_allclose(rioda, expected)
assert isinstance(rioda.attrs['crs'], basestring)
assert isinstance(rioda.attrs['res'], tuple)
assert isinstance(rioda.attrs['is_tiled'], np.uint8)
assert isinstance(rioda.attrs['transform'], tuple)
np.testing.assert_array_equal(rioda.attrs['nodatavals'],
[np.NaN, np.NaN, np.NaN])
# Check no parse coords
with xr.open_rasterio(tmp_file, parse_coordinates=False) as rioda:
assert 'x' not in rioda.coords
assert 'y' not in rioda.coords
def test_non_rectilinear(self):
from rasterio.transform import from_origin
# Create a geotiff file with 2d coordinates
with create_tmp_geotiff(transform=from_origin(0, 3, 1, 1).rotation(45),
crs=None) as (tmp_file, _):
# Default is to not parse coords
with xr.open_rasterio(tmp_file) as rioda:
assert 'x' not in rioda.coords
assert 'y' not in rioda.coords
assert 'crs' not in rioda.attrs
assert isinstance(rioda.attrs['res'], tuple)
assert isinstance(rioda.attrs['is_tiled'], np.uint8)
assert isinstance(rioda.attrs['transform'], tuple)
# See if a warning is raised if we force it
with self.assertWarns("transformation isn't rectilinear"):
with xr.open_rasterio(tmp_file,
parse_coordinates=True) as rioda:
assert 'x' not in rioda.coords
assert 'y' not in rioda.coords
def test_platecarree(self):
with create_tmp_geotiff(8, 10, 1, transform_args=[1, 2, 0.5, 2.],
crs='+proj=latlong',
open_kwargs={'nodata': -9765}) \
as (tmp_file, expected):
with xr.open_rasterio(tmp_file) as rioda:
assert_allclose(rioda, expected)
assert isinstance(rioda.attrs['crs'], basestring)
assert isinstance(rioda.attrs['res'], tuple)
assert isinstance(rioda.attrs['is_tiled'], np.uint8)
assert isinstance(rioda.attrs['transform'], tuple)
np.testing.assert_array_equal(rioda.attrs['nodatavals'],
[-9765.])
def test_notransform(self):
# regression test for https://github.com/pydata/xarray/issues/1686
import rasterio
import warnings
# Create a geotiff file
with warnings.catch_warnings():
# rasterio throws a NotGeoreferencedWarning here, which is
# expected since we test rasterio's defaults in this case.
warnings.filterwarnings('ignore', category=UserWarning,
message='Dataset has no geotransform set')
with create_tmp_file(suffix='.tif') as tmp_file:
# data
nx, ny, nz = 4, 3, 3
data = np.arange(nx * ny * nz,
dtype=rasterio.float32).reshape(nz, ny, nx)
with rasterio.open(
tmp_file, 'w',
driver='GTiff', height=ny, width=nx, count=nz,
dtype=rasterio.float32) as s:
s.write(data)
# Tests
expected = DataArray(data,
dims=('band', 'y', 'x'),
coords={'band': [1, 2, 3],
'y': [0.5, 1.5, 2.5],
'x': [0.5, 1.5, 2.5, 3.5],
})
with xr.open_rasterio(tmp_file) as rioda:
assert_allclose(rioda, expected)
assert isinstance(rioda.attrs['res'], tuple)
assert isinstance(rioda.attrs['is_tiled'], np.uint8)
assert isinstance(rioda.attrs['transform'], tuple)
def test_indexing(self):
with create_tmp_geotiff(8, 10, 3, transform_args=[1, 2, 0.5, 2.],
crs='+proj=latlong') as (tmp_file, expected):
with xr.open_rasterio(tmp_file, cache=False) as actual:
# tests
# assert_allclose checks all data + coordinates
assert_allclose(actual, expected)
assert not actual.variable._in_memory
# Basic indexer
ind = {'x': slice(2, 5), 'y': slice(5, 7)}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
ind = {'band': slice(1, 2), 'x': slice(2, 5), 'y': slice(5, 7)}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
ind = {'band': slice(1, 2), 'x': slice(2, 5), 'y': 0}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
# orthogonal indexer
ind = {'band': np.array([2, 1, 0]),
'x': np.array([1, 0]), 'y': np.array([0, 2])}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
ind = {'band': np.array([2, 1, 0]),
'x': np.array([1, 0]), 'y': 0}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
# minus-stepped slice
ind = {'band': np.array([2, 1, 0]),
'x': slice(-1, None, -1), 'y': 0}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
ind = {'band': np.array([2, 1, 0]),
'x': 1, 'y': slice(-1, 1, -2)}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
# None is selected
ind = {'band': np.array([2, 1, 0]),
'x': 1, 'y': slice(2, 2, 1)}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
# vectorized indexer
ind = {'band': DataArray([2, 1, 0], dims='a'),
'x': DataArray([1, 0, 0], dims='a'),
'y': np.array([0, 2])}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
ind = {
'band': DataArray([[2, 1, 0], [1, 0, 2]], dims=['a', 'b']),
'x': DataArray([[1, 0, 0], [0, 1, 0]], dims=['a', 'b']),
'y': 0}
assert_allclose(expected.isel(**ind), actual.isel(**ind))
assert not actual.variable._in_memory
# Selecting lists of bands is fine
ex = expected.isel(band=[1, 2])
ac = actual.isel(band=[1, 2])
assert_allclose(ac, ex)
ex = expected.isel(band=[0, 2])
ac = actual.isel(band=[0, 2])
assert_allclose(ac, ex)
# Integer indexing
ex = expected.isel(band=1)
ac = actual.isel(band=1)
assert_allclose(ac, ex)
ex = expected.isel(x=1, y=2)
ac = actual.isel(x=1, y=2)
assert_allclose(ac, ex)
ex = expected.isel(band=0, x=1, y=2)
ac = actual.isel(band=0, x=1, y=2)
assert_allclose(ac, ex)
# Mixed
ex = actual.isel(x=slice(2), y=slice(2))
ac = actual.isel(x=[0, 1], y=[0, 1])
assert_allclose(ac, ex)
ex = expected.isel(band=0, x=1, y=slice(5, 7))
ac = actual.isel(band=0, x=1, y=slice(5, 7))
assert_allclose(ac, ex)
ex = expected.isel(band=0, x=slice(2, 5), y=2)
ac = actual.isel(band=0, x=slice(2, 5), y=2)
assert_allclose(ac, ex)
# One-element lists
ex = expected.isel(band=[0], x=slice(2, 5), y=[2])
ac = actual.isel(band=[0], x=slice(2, 5), y=[2])
assert_allclose(ac, ex)
def test_caching(self):
with create_tmp_geotiff(8, 10, 3, transform_args=[1, 2, 0.5, 2.],
crs='+proj=latlong') as (tmp_file, expected):
# Cache is the default
with xr.open_rasterio(tmp_file) as actual:
# This should cache everything
assert_allclose(actual, expected)
# once cached, non-windowed indexing should become possible
ac = actual.isel(x=[2, 4])
ex = expected.isel(x=[2, 4])
assert_allclose(ac, ex)
@requires_dask
def test_chunks(self):
with create_tmp_geotiff(8, 10, 3, transform_args=[1, 2, 0.5, 2.],
crs='+proj=latlong') as (tmp_file, expected):
# Chunk at open time
with xr.open_rasterio(tmp_file, chunks=(1, 2, 2)) as actual:
import dask.array as da
self.assertIsInstance(actual.data, da.Array)
assert 'open_rasterio' in actual.data.name
# do some arithmetic
ac = actual.mean()
ex = expected.mean()
assert_allclose(ac, ex)
ac = actual.sel(band=1).mean(dim='x')
ex = expected.sel(band=1).mean(dim='x')
assert_allclose(ac, ex)
def test_ENVI_tags(self):
rasterio = pytest.importorskip('rasterio', minversion='1.0a')
from rasterio.transform import from_origin
# Create an ENVI file with some tags in the ENVI namespace
# this test uses a custom driver, so we can't use create_tmp_geotiff
with create_tmp_file(suffix='.dat') as tmp_file:
# data
nx, ny, nz = 4, 3, 3
data = np.arange(nx * ny * nz,
dtype=rasterio.float32).reshape(nz, ny, nx)
transform = from_origin(5000, 80000, 1000, 2000.)
with rasterio.open(
tmp_file, 'w',
driver='ENVI', height=ny, width=nx, count=nz,
crs={'units': 'm', 'no_defs': True, 'ellps': 'WGS84',
'proj': 'utm', 'zone': 18},
transform=transform,
dtype=rasterio.float32) as s:
s.update_tags(
ns='ENVI',
description='{Tagged file}',
wavelength='{123.000000, 234.234000, 345.345678}',
fwhm='{1.000000, 0.234000, 0.000345}')
s.write(data)
dx, dy = s.res[0], -s.res[1]
# Tests
coords = {
'band': [1, 2, 3],
'y': -np.arange(ny) * 2000 + 80000 + dy / 2,
'x': np.arange(nx) * 1000 + 5000 + dx / 2,
'wavelength': ('band', np.array([123, 234.234, 345.345678])),
'fwhm': ('band', np.array([1, 0.234, 0.000345])),
}
expected = DataArray(data, dims=('band', 'y', 'x'), coords=coords)
with xr.open_rasterio(tmp_file) as rioda:
assert_allclose(rioda, expected)
assert isinstance(rioda.attrs['crs'], basestring)
assert isinstance(rioda.attrs['res'], tuple)
assert isinstance(rioda.attrs['is_tiled'], np.uint8)
assert isinstance(rioda.attrs['transform'], tuple)
# from ENVI tags
assert isinstance(rioda.attrs['description'], basestring)
assert isinstance(rioda.attrs['map_info'], basestring)
assert isinstance(rioda.attrs['samples'], basestring)
def test_no_mftime(self):
# rasterio can accept "filename" urguments that are actually urls,
# including paths to remote files.
# In issue #1816, we found that these caused dask to break, because
# the modification time was used to determine the dask token. This
# tests ensure we can still chunk such files when reading with
# rasterio.
with create_tmp_geotiff(8, 10, 3, transform_args=[1, 2, 0.5, 2.],
crs='+proj=latlong') as (tmp_file, expected):
with mock.patch('os.path.getmtime', side_effect=OSError):
with xr.open_rasterio(tmp_file, chunks=(1, 2, 2)) as actual:
import dask.array as da
self.assertIsInstance(actual.data, da.Array)
assert_allclose(actual, expected)
@network
def test_http_url(self):
# more examples urls here
# http://download.osgeo.org/geotiff/samples/
url = 'http://download.osgeo.org/geotiff/samples/made_up/ntf_nord.tif'
with xr.open_rasterio(url) as actual:
assert actual.shape == (1, 512, 512)
# make sure chunking works
with xr.open_rasterio(url, chunks=(1, 256, 256)) as actual:
import dask.array as da
self.assertIsInstance(actual.data, da.Array)
class TestEncodingInvalid(TestCase):
def test_extract_nc4_variable_encoding(self):
var = xr.Variable(('x',), [1, 2, 3], {}, {'foo': 'bar'})
with raises_regex(ValueError, 'unexpected encoding'):
_extract_nc4_variable_encoding(var, raise_on_invalid=True)
var = xr.Variable(('x',), [1, 2, 3], {}, {'chunking': (2, 1)})
encoding = _extract_nc4_variable_encoding(var)
self.assertEqual({}, encoding)
# regression test
var = xr.Variable(('x',), [1, 2, 3], {}, {'shuffle': True})
encoding = _extract_nc4_variable_encoding(var, raise_on_invalid=True)
self.assertEqual({'shuffle': True}, encoding)
def test_extract_h5nc_encoding(self):
# not supported with h5netcdf (yet)
var = xr.Variable(('x',), [1, 2, 3], {},
{'least_sigificant_digit': 2})
with raises_regex(ValueError, 'unexpected encoding'):
_extract_nc4_variable_encoding(var, raise_on_invalid=True)
class MiscObject:
pass
@requires_netCDF4
class TestValidateAttrs(TestCase):
def test_validating_attrs(self):
def new_dataset():
return Dataset({'data': ('y', np.arange(10.0))},
{'y': np.arange(10)})
def new_dataset_and_dataset_attrs():
ds = new_dataset()
return ds, ds.attrs
def new_dataset_and_data_attrs():
ds = new_dataset()
return ds, ds.data.attrs
def new_dataset_and_coord_attrs():
ds = new_dataset()
return ds, ds.coords['y'].attrs
for new_dataset_and_attrs in [new_dataset_and_dataset_attrs,
new_dataset_and_data_attrs,
new_dataset_and_coord_attrs]:
ds, attrs = new_dataset_and_attrs()
attrs[123] = 'test'
with raises_regex(TypeError, 'Invalid name for attr'):
ds.to_netcdf('test.nc')
ds, attrs = new_dataset_and_attrs()
attrs[MiscObject()] = 'test'
with raises_regex(TypeError, 'Invalid name for attr'):
ds.to_netcdf('test.nc')
ds, attrs = new_dataset_and_attrs()
attrs[''] = 'test'
with raises_regex(ValueError, 'Invalid name for attr'):
ds.to_netcdf('test.nc')
# This one should work
ds, attrs = new_dataset_and_attrs()
attrs['test'] = 'test'
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
ds, attrs = new_dataset_and_attrs()
attrs['test'] = {'a': 5}
with raises_regex(TypeError, 'Invalid value for attr'):
ds.to_netcdf('test.nc')
ds, attrs = new_dataset_and_attrs()
attrs['test'] = MiscObject()
with raises_regex(TypeError, 'Invalid value for attr'):
ds.to_netcdf('test.nc')
ds, attrs = new_dataset_and_attrs()
attrs['test'] = 5
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
ds, attrs = new_dataset_and_attrs()
attrs['test'] = 3.14
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
ds, attrs = new_dataset_and_attrs()
attrs['test'] = [1, 2, 3, 4]
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
ds, attrs = new_dataset_and_attrs()
attrs['test'] = (1.9, 2.5)
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
ds, attrs = new_dataset_and_attrs()
attrs['test'] = np.arange(5)
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
ds, attrs = new_dataset_and_attrs()
attrs['test'] = np.arange(12).reshape(3, 4)
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
ds, attrs = new_dataset_and_attrs()
attrs['test'] = 'This is a string'
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
ds, attrs = new_dataset_and_attrs()
attrs['test'] = ''
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
ds, attrs = new_dataset_and_attrs()
attrs['test'] = np.arange(12).reshape(3, 4)
with create_tmp_file() as tmp_file:
ds.to_netcdf(tmp_file)
@requires_scipy_or_netCDF4
class TestDataArrayToNetCDF(TestCase):
def test_dataarray_to_netcdf_no_name(self):
original_da = DataArray(np.arange(12).reshape((3, 4)))
with create_tmp_file() as tmp:
original_da.to_netcdf(tmp)
with open_dataarray(tmp) as loaded_da:
assert_identical(original_da, loaded_da)
def test_dataarray_to_netcdf_with_name(self):
original_da = DataArray(np.arange(12).reshape((3, 4)),
name='test')
with create_tmp_file() as tmp:
original_da.to_netcdf(tmp)
with open_dataarray(tmp) as loaded_da:
assert_identical(original_da, loaded_da)
def test_dataarray_to_netcdf_coord_name_clash(self):
original_da = DataArray(np.arange(12).reshape((3, 4)),
dims=['x', 'y'],
name='x')
with create_tmp_file() as tmp:
original_da.to_netcdf(tmp)
with open_dataarray(tmp) as loaded_da:
assert_identical(original_da, loaded_da)
def test_open_dataarray_options(self):
data = DataArray(
np.arange(5), coords={'y': ('x', range(5))}, dims=['x'])
with create_tmp_file() as tmp:
data.to_netcdf(tmp)
expected = data.drop('y')
with open_dataarray(tmp, drop_variables=['y']) as loaded:
assert_identical(expected, loaded)
def test_dataarray_to_netcdf_return_bytes(self):
# regression test for GH1410
data = xr.DataArray([1, 2, 3])
output = data.to_netcdf()
assert isinstance(output, bytes)
@requires_pathlib
def test_dataarray_to_netcdf_no_name_pathlib(self):
original_da = DataArray(np.arange(12).reshape((3, 4)))
with create_tmp_file() as tmp:
tmp = Path(tmp)
original_da.to_netcdf(tmp)
with open_dataarray(tmp) as loaded_da:
assert_identical(original_da, loaded_da)
|