/usr/lib/python3/dist-packages/pandas/io/pytables.py is in python3-pandas 0.13.1-2ubuntu2.
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 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 | """
High level interface to PyTables for reading and writing pandas data structures
to disk
"""
# pylint: disable-msg=E1101,W0613,W0603
from datetime import datetime, date
import time
import re
import copy
import itertools
import warnings
import os
import numpy as np
from pandas import (Series, TimeSeries, DataFrame, Panel, Panel4D, Index,
MultiIndex, Int64Index, Timestamp, _np_version_under1p7)
from pandas.sparse.api import SparseSeries, SparseDataFrame, SparsePanel
from pandas.sparse.array import BlockIndex, IntIndex
from pandas.tseries.api import PeriodIndex, DatetimeIndex
from pandas.core.base import StringMixin
from pandas.core.common import adjoin, pprint_thing
from pandas.core.algorithms import match, unique
from pandas.core.categorical import Categorical
from pandas.core.common import _asarray_tuplesafe
from pandas.core.internals import BlockManager, make_block
from pandas.core.reshape import block2d_to_blocknd, factor_indexer
from pandas.core.index import _ensure_index
from pandas.tseries.timedeltas import _coerce_scalar_to_timedelta_type
import pandas.core.common as com
from pandas.tools.merge import concat
from pandas import compat
from pandas.compat import u_safe as u, PY3, range, lrange
from pandas.io.common import PerformanceWarning
from pandas.core.config import get_option
from pandas.computation.pytables import Expr, maybe_expression
import pandas.lib as lib
import pandas.algos as algos
import pandas.tslib as tslib
from contextlib import contextmanager
# versioning attribute
_version = '0.10.1'
# PY3 encoding if we don't specify
_default_encoding = 'UTF-8'
def _ensure_decoded(s):
""" if we have bytes, decode them to unicde """
if isinstance(s, np.bytes_):
s = s.decode('UTF-8')
return s
def _ensure_encoding(encoding):
# set the encoding if we need
if encoding is None:
if PY3:
encoding = _default_encoding
return encoding
Term = Expr
def _ensure_term(where):
"""
ensure that the where is a Term or a list of Term
this makes sure that we are capturing the scope of variables
that are passed
create the terms here with a frame_level=2 (we are 2 levels down)
"""
# only consider list/tuple here as an ndarray is automaticaly a coordinate
# list
if isinstance(where, (list, tuple)):
where = [w if not maybe_expression(w) else Term(w, scope_level=2)
for w in where if w is not None]
elif maybe_expression(where):
where = Term(where, scope_level=2)
return where
class PossibleDataLossError(Exception):
pass
class ClosedFileError(Exception):
pass
class IncompatibilityWarning(Warning):
pass
incompatibility_doc = """
where criteria is being ignored as this version [%s] is too old (or
not-defined), read the file in and write it out to a new file to upgrade (with
the copy_to method)
"""
class AttributeConflictWarning(Warning):
pass
attribute_conflict_doc = """
the [%s] attribute of the existing index is [%s] which conflicts with the new
[%s], resetting the attribute to None
"""
class DuplicateWarning(Warning):
pass
duplicate_doc = """
duplicate entries in table, taking most recently appended
"""
performance_doc = """
your performance may suffer as PyTables will pickle object types that it cannot
map directly to c-types [inferred_type->%s,key->%s] [items->%s]
"""
# formats
_FORMAT_MAP = {
u('f'): 'fixed',
u('fixed'): 'fixed',
u('t'): 'table',
u('table'): 'table',
}
format_deprecate_doc = """
the table keyword has been deprecated
use the format='fixed(f)|table(t)' keyword instead
fixed(f) : specifies the Fixed format
and is the default for put operations
table(t) : specifies the Table format
and is the default for append operations
"""
# map object types
_TYPE_MAP = {
Series: u('series'),
SparseSeries: u('sparse_series'),
TimeSeries: u('series'),
DataFrame: u('frame'),
SparseDataFrame: u('sparse_frame'),
Panel: u('wide'),
Panel4D: u('ndim'),
SparsePanel: u('sparse_panel')
}
# storer class map
_STORER_MAP = {
u('TimeSeries'): 'LegacySeriesFixed',
u('Series'): 'LegacySeriesFixed',
u('DataFrame'): 'LegacyFrameFixed',
u('DataMatrix'): 'LegacyFrameFixed',
u('series'): 'SeriesFixed',
u('sparse_series'): 'SparseSeriesFixed',
u('frame'): 'FrameFixed',
u('sparse_frame'): 'SparseFrameFixed',
u('wide'): 'PanelFixed',
u('sparse_panel'): 'SparsePanelFixed',
}
# table class map
_TABLE_MAP = {
u('generic_table'): 'GenericTable',
u('appendable_series'): 'AppendableSeriesTable',
u('appendable_multiseries'): 'AppendableMultiSeriesTable',
u('appendable_frame'): 'AppendableFrameTable',
u('appendable_multiframe'): 'AppendableMultiFrameTable',
u('appendable_panel'): 'AppendablePanelTable',
u('appendable_ndim'): 'AppendableNDimTable',
u('worm'): 'WORMTable',
u('legacy_frame'): 'LegacyFrameTable',
u('legacy_panel'): 'LegacyPanelTable',
}
# axes map
_AXES_MAP = {
DataFrame: [0],
Panel: [1, 2],
Panel4D: [1, 2, 3],
}
# register our configuration options
from pandas.core import config
dropna_doc = """
: boolean
drop ALL nan rows when appending to a table
"""
format_doc = """
: format
default format writing format, if None, then
put will default to 'fixed' and append will default to 'table'
"""
with config.config_prefix('io.hdf'):
config.register_option('dropna_table', True, dropna_doc,
validator=config.is_bool)
config.register_option(
'default_format', None, format_doc,
validator=config.is_one_of_factory(['fixed', 'table', None])
)
# oh the troubles to reduce import time
_table_mod = None
_table_supports_index = False
_table_file_open_policy_is_strict = False
def _tables():
global _table_mod
global _table_supports_index
global _table_file_open_policy_is_strict
if _table_mod is None:
import tables
from distutils.version import LooseVersion
_table_mod = tables
# version requirements
ver = tables.__version__
_table_supports_index = LooseVersion(ver) >= '2.3'
# set the file open policy
# return the file open policy; this changes as of pytables 3.1
# depending on the HDF5 version
try:
_table_file_open_policy_is_strict = tables.file._FILE_OPEN_POLICY == 'strict'
except:
pass
return _table_mod
@contextmanager
def get_store(path, **kwargs):
"""
Creates an HDFStore instance. This function can be used in a with statement
Parameters
----------
same as HDFStore
Examples
--------
>>> from pandas import DataFrame
>>> from numpy.random import randn
>>> bar = DataFrame(randn(10, 4))
>>> with get_store('test.h5') as store:
... store['foo'] = bar # write to HDF5
... bar = store['foo'] # retrieve
"""
store = None
try:
store = HDFStore(path, **kwargs)
yield store
finally:
if store is not None:
store.close()
# interface to/from ###
def to_hdf(path_or_buf, key, value, mode=None, complevel=None, complib=None,
append=None, **kwargs):
""" store this object, close it if we opened it """
if append:
f = lambda store: store.append(key, value, **kwargs)
else:
f = lambda store: store.put(key, value, **kwargs)
if isinstance(path_or_buf, compat.string_types):
with get_store(path_or_buf, mode=mode, complevel=complevel,
complib=complib) as store:
f(store)
else:
f(path_or_buf)
def read_hdf(path_or_buf, key, **kwargs):
""" read from the store, close it if we opened it
Retrieve pandas object stored in file, optionally based on where
criteria
Parameters
----------
path_or_buf : path (string), or buffer to read from
key : group identifier in the store
where : list of Term (or convertable) objects, optional
start : optional, integer (defaults to None), row number to start
selection
stop : optional, integer (defaults to None), row number to stop
selection
columns : optional, a list of columns that if not None, will limit the
return columns
iterator : optional, boolean, return an iterator, default False
chunksize : optional, nrows to include in iteration, return an iterator
auto_close : optional, boolean, should automatically close the store
when finished, default is False
Returns
-------
The selected object
"""
# grab the scope
if 'where' in kwargs:
kwargs['where'] = _ensure_term(kwargs['where'])
f = lambda store, auto_close: store.select(
key, auto_close=auto_close, **kwargs)
if isinstance(path_or_buf, compat.string_types):
# can't auto open/close if we are using an iterator
# so delegate to the iterator
store = HDFStore(path_or_buf, **kwargs)
try:
return f(store, True)
except:
# if there is an error, close the store
try:
store.close()
except:
pass
raise
# a passed store; user controls open/close
f(path_or_buf, False)
class HDFStore(StringMixin):
"""
dict-like IO interface for storing pandas objects in PyTables
either Fixed or Table format.
Parameters
----------
path : string
File path to HDF5 file
mode : {'a', 'w', 'r', 'r+'}, default 'a'
``'r'``
Read-only; no data can be modified.
``'w'``
Write; a new file is created (an existing file with the same
name would be deleted).
``'a'``
Append; an existing file is opened for reading and writing,
and if the file does not exist it is created.
``'r+'``
It is similar to ``'a'``, but the file must already exist.
complevel : int, 1-9, default 0
If a complib is specified compression will be applied
where possible
complib : {'zlib', 'bzip2', 'lzo', 'blosc', None}, default None
If complevel is > 0 apply compression to objects written
in the store wherever possible
fletcher32 : bool, default False
If applying compression use the fletcher32 checksum
Examples
--------
>>> from pandas import DataFrame
>>> from numpy.random import randn
>>> bar = DataFrame(randn(10, 4))
>>> store = HDFStore('test.h5')
>>> store['foo'] = bar # write to HDF5
>>> bar = store['foo'] # retrieve
>>> store.close()
"""
def __init__(self, path, mode=None, complevel=None, complib=None,
fletcher32=False, **kwargs):
try:
import tables
except ImportError: # pragma: no cover
raise ImportError('HDFStore requires PyTables')
self._path = path
if mode is None:
mode = 'a'
self._mode = mode
self._handle = None
self._complevel = complevel
self._complib = complib
self._fletcher32 = fletcher32
self._filters = None
self.open(mode=mode, **kwargs)
@property
def root(self):
""" return the root node """
self._check_if_open()
return self._handle.root
@property
def filename(self):
return self._path
def __getitem__(self, key):
return self.get(key)
def __setitem__(self, key, value):
self.put(key, value)
def __delitem__(self, key):
return self.remove(key)
def __getattr__(self, name):
""" allow attribute access to get stores """
self._check_if_open()
try:
return self.get(name)
except:
pass
raise AttributeError("'%s' object has no attribute '%s'" %
(type(self).__name__, name))
def __contains__(self, key):
""" check for existance of this key
can match the exact pathname or the pathnm w/o the leading '/'
"""
node = self.get_node(key)
if node is not None:
name = node._v_pathname
if name == key or name[1:] == key:
return True
return False
def __len__(self):
return len(self.groups())
def __unicode__(self):
output = '%s\nFile path: %s\n' % (type(self), pprint_thing(self._path))
if self.is_open:
lkeys = list(self.keys())
if len(lkeys):
keys = []
values = []
for k in lkeys:
try:
s = self.get_storer(k)
if s is not None:
keys.append(pprint_thing(s.pathname or k))
values.append(
pprint_thing(s or 'invalid_HDFStore node'))
except Exception as detail:
keys.append(k)
values.append("[invalid_HDFStore node: %s]"
% pprint_thing(detail))
output += adjoin(12, keys, values)
else:
output += 'Empty'
else:
output += "File is CLOSED"
return output
def keys(self):
"""
Return a (potentially unordered) list of the keys corresponding to the
objects stored in the HDFStore. These are ABSOLUTE path-names (e.g.
have the leading '/'
"""
return [n._v_pathname for n in self.groups()]
def items(self):
"""
iterate on key->group
"""
for g in self.groups():
yield g._v_pathname, g
iteritems = items
def open(self, mode='a', **kwargs):
"""
Open the file in the specified mode
Parameters
----------
mode : {'a', 'w', 'r', 'r+'}, default 'a'
See HDFStore docstring or tables.openFile for info about modes
"""
tables = _tables()
if self._mode != mode:
# if we are changing a write mode to read, ok
if self._mode in ['a', 'w'] and mode in ['r', 'r+']:
pass
elif mode in ['w']:
# this would truncate, raise here
if self.is_open:
raise PossibleDataLossError(
"Re-opening the file [{0}] with mode [{1}] "
"will delete the current file!"
.format(self._path, self._mode)
)
self._mode = mode
# close and reopen the handle
if self.is_open:
self.close()
if self._complib is not None:
if self._complevel is None:
self._complevel = 9
self._filters = _tables().Filters(self._complevel,
self._complib,
fletcher32=self._fletcher32)
try:
self._handle = tables.openFile(self._path, self._mode, **kwargs)
except (IOError) as e: # pragma: no cover
if 'can not be written' in str(e):
print('Opening %s in read-only mode' % self._path)
self._handle = tables.openFile(self._path, 'r', **kwargs)
else:
raise
except (ValueError) as e:
# trap PyTables >= 3.1 FILE_OPEN_POLICY exception
# to provide an updated message
if 'FILE_OPEN_POLICY' in str(e):
e = ValueError("PyTables [{version}] no longer supports opening multiple files\n"
"even in read-only mode on this HDF5 version [{hdf_version}]. You can accept this\n"
"and not open the same file multiple times at once,\n"
"upgrade the HDF5 version, or downgrade to PyTables 3.0.0 which allows\n"
"files to be opened multiple times at once\n".format(version=tables.__version__,
hdf_version=tables.getHDF5Version()))
raise e
except (Exception) as e:
# trying to read from a non-existant file causes an error which
# is not part of IOError, make it one
if self._mode == 'r' and 'Unable to open/create file' in str(e):
raise IOError(str(e))
raise
def close(self):
"""
Close the PyTables file handle
"""
if self._handle is not None:
self._handle.close()
self._handle = None
@property
def is_open(self):
"""
return a boolean indicating whether the file is open
"""
if self._handle is None:
return False
return bool(self._handle.isopen)
def flush(self, fsync=False):
"""
Force all buffered modifications to be written to disk.
Parameters
----------
fsync : bool (default False)
call ``os.fsync()`` on the file handle to force writing to disk.
Notes
-----
Without ``fsync=True``, flushing may not guarantee that the OS writes
to disk. With fsync, the operation will block until the OS claims the
file has been written; however, other caching layers may still
interfere.
"""
if self._handle is not None:
self._handle.flush()
if fsync:
try:
os.fsync(self._handle.fileno())
except:
pass
def get(self, key):
"""
Retrieve pandas object stored in file
Parameters
----------
key : object
Returns
-------
obj : type of object stored in file
"""
group = self.get_node(key)
if group is None:
raise KeyError('No object named %s in the file' % key)
return self._read_group(group)
def select(self, key, where=None, start=None, stop=None, columns=None,
iterator=False, chunksize=None, auto_close=False, **kwargs):
"""
Retrieve pandas object stored in file, optionally based on where
criteria
Parameters
----------
key : object
where : list of Term (or convertable) objects, optional
start : integer (defaults to None), row number to start selection
stop : integer (defaults to None), row number to stop selection
columns : a list of columns that if not None, will limit the return
columns
iterator : boolean, return an iterator, default False
chunksize : nrows to include in iteration, return an iterator
auto_close : boolean, should automatically close the store when
finished, default is False
Returns
-------
The selected object
"""
group = self.get_node(key)
if group is None:
raise KeyError('No object named %s in the file' % key)
# create the storer and axes
where = _ensure_term(where)
s = self._create_storer(group)
s.infer_axes()
# what we are actually going to do for a chunk
def func(_start, _stop):
return s.read(where=where, start=_start, stop=_stop,
columns=columns, **kwargs)
if iterator or chunksize is not None:
if not s.is_table:
raise TypeError(
"can only use an iterator or chunksize on a table")
return TableIterator(self, func, nrows=s.nrows, start=start,
stop=stop, chunksize=chunksize,
auto_close=auto_close)
return TableIterator(self, func, nrows=s.nrows, start=start, stop=stop,
auto_close=auto_close).get_values()
def select_as_coordinates(
self, key, where=None, start=None, stop=None, **kwargs):
"""
return the selection as an Index
Parameters
----------
key : object
where : list of Term (or convertable) objects, optional
start : integer (defaults to None), row number to start selection
stop : integer (defaults to None), row number to stop selection
"""
where = _ensure_term(where)
return self.get_storer(key).read_coordinates(where=where, start=start,
stop=stop, **kwargs)
def unique(self, key, column, **kwargs):
warnings.warn("unique(key,column) is deprecated\n"
"use select_column(key,column).unique() instead",
FutureWarning)
return self.get_storer(key).read_column(column=column,
**kwargs).unique()
def select_column(self, key, column, **kwargs):
"""
return a single column from the table. This is generally only useful to
select an indexable
Parameters
----------
key : object
column: the column of interest
Exceptions
----------
raises KeyError if the column is not found (or key is not a valid
store)
raises ValueError if the column can not be extracted individually (it
is part of a data block)
"""
return self.get_storer(key).read_column(column=column, **kwargs)
def select_as_multiple(self, keys, where=None, selector=None, columns=None,
start=None, stop=None, iterator=False,
chunksize=None, auto_close=False, **kwargs):
""" Retrieve pandas objects from multiple tables
Parameters
----------
keys : a list of the tables
selector : the table to apply the where criteria (defaults to keys[0]
if not supplied)
columns : the columns I want back
start : integer (defaults to None), row number to start selection
stop : integer (defaults to None), row number to stop selection
iterator : boolean, return an iterator, default False
chunksize : nrows to include in iteration, return an iterator
Exceptions
----------
raise if any of the keys don't refer to tables or if they are not ALL
THE SAME DIMENSIONS
"""
# default to single select
where = _ensure_term(where)
if isinstance(keys, (list, tuple)) and len(keys) == 1:
keys = keys[0]
if isinstance(keys, compat.string_types):
return self.select(key=keys, where=where, columns=columns,
start=start, stop=stop, iterator=iterator,
chunksize=chunksize, **kwargs)
if not isinstance(keys, (list, tuple)):
raise TypeError("keys must be a list/tuple")
if not len(keys):
raise ValueError("keys must have a non-zero length")
if selector is None:
selector = keys[0]
# collect the tables
tbls = [self.get_storer(k) for k in keys]
# validate rows
nrows = None
for t, k in zip(tbls, keys):
if t is None:
raise TypeError("Invalid table [%s]" % k)
if not t.is_table:
raise TypeError(
"object [%s] is not a table, and cannot be used in all "
"select as multiple" % t.pathname
)
if nrows is None:
nrows = t.nrows
elif t.nrows != nrows:
raise ValueError(
"all tables must have exactly the same nrows!")
# select coordinates from the selector table
try:
c = self.select_as_coordinates(
selector, where, start=start, stop=stop)
nrows = len(c)
except Exception:
raise ValueError("invalid selector [%s]" % selector)
def func(_start, _stop):
# collect the returns objs
objs = [t.read(where=c[_start:_stop], columns=columns)
for t in tbls]
# axis is the concentation axes
axis = list(set([t.non_index_axes[0][0] for t in tbls]))[0]
# concat and return
return concat(objs, axis=axis,
verify_integrity=False).consolidate()
if iterator or chunksize is not None:
return TableIterator(self, func, nrows=nrows, start=start,
stop=stop, chunksize=chunksize,
auto_close=auto_close)
return TableIterator(self, func, nrows=nrows, start=start, stop=stop,
auto_close=auto_close).get_values()
def put(self, key, value, format=None, append=False, **kwargs):
"""
Store object in HDFStore
Parameters
----------
key : object
value : {Series, DataFrame, Panel}
format : 'fixed(f)|table(t)', default is 'fixed'
fixed(f) : Fixed format
Fast writing/reading. Not-appendable, nor searchable
table(t) : Table format
Write as a PyTables Table structure which may perform
worse but allow more flexible operations like searching
/ selecting subsets of the data
append : boolean, default False
This will force Table format, append the input data to the
existing.
encoding : default None, provide an encoding for strings
"""
if format is None:
format = get_option("io.hdf.default_format") or 'fixed'
kwargs = self._validate_format(format, kwargs)
self._write_to_group(key, value, append=append, **kwargs)
def remove(self, key, where=None, start=None, stop=None):
"""
Remove pandas object partially by specifying the where condition
Parameters
----------
key : string
Node to remove or delete rows from
where : list of Term (or convertable) objects, optional
start : integer (defaults to None), row number to start selection
stop : integer (defaults to None), row number to stop selection
Returns
-------
number of rows removed (or None if not a Table)
Exceptions
----------
raises KeyError if key is not a valid store
"""
where = _ensure_term(where)
try:
s = self.get_storer(key)
except:
if where is not None:
raise ValueError(
"trying to remove a node with a non-None where clause!")
# we are actually trying to remove a node (with children)
s = self.get_node(key)
if s is not None:
s._f_remove(recursive=True)
return None
if s is None:
raise KeyError('No object named %s in the file' % key)
# remove the node
if where is None:
s.group._f_remove(recursive=True)
# delete from the table
else:
if not s.is_table:
raise ValueError(
'can only remove with where on objects written as tables')
return s.delete(where=where, start=start, stop=stop)
def append(self, key, value, format=None, append=True, columns=None,
dropna=None, **kwargs):
"""
Append to Table in file. Node must already exist and be Table
format.
Parameters
----------
key : object
value : {Series, DataFrame, Panel, Panel4D}
format: 'table' is the default
table(t) : table format
Write as a PyTables Table structure which may perform
worse but allow more flexible operations like searching
/ selecting subsets of the data
append : boolean, default True, append the input data to the
existing
data_columns : list of columns to create as data columns, or True to
use all columns
min_itemsize : dict of columns that specify minimum string sizes
nan_rep : string to use as string nan represenation
chunksize : size to chunk the writing
expectedrows : expected TOTAL row size of this table
encoding : default None, provide an encoding for strings
dropna : boolean, default True, do not write an ALL nan row to
the store settable by the option 'io.hdf.dropna_table'
Notes
-----
Does *not* check if data being appended overlaps with existing
data in the table, so be careful
"""
if columns is not None:
raise TypeError("columns is not a supported keyword in append, "
"try data_columns")
if dropna is None:
dropna = get_option("io.hdf.dropna_table")
if format is None:
format = get_option("io.hdf.default_format") or 'table'
kwargs = self._validate_format(format, kwargs)
self._write_to_group(key, value, append=append, dropna=dropna,
**kwargs)
def append_to_multiple(self, d, value, selector, data_columns=None,
axes=None, dropna=True, **kwargs):
"""
Append to multiple tables
Parameters
----------
d : a dict of table_name to table_columns, None is acceptable as the
values of one node (this will get all the remaining columns)
value : a pandas object
selector : a string that designates the indexable table; all of its
columns will be designed as data_columns, unless data_columns is
passed, in which case these are used
data_columns : list of columns to create as data columns, or True to
use all columns
dropna : if evaluates to True, drop rows from all tables if any single
row in each table has all NaN
Notes
-----
axes parameter is currently not accepted
"""
if axes is not None:
raise TypeError("axes is currently not accepted as a parameter to"
" append_to_multiple; you can create the "
"tables independently instead")
if not isinstance(d, dict):
raise ValueError(
"append_to_multiple must have a dictionary specified as the "
"way to split the value"
)
if selector not in d:
raise ValueError(
"append_to_multiple requires a selector that is in passed dict"
)
# figure out the splitting axis (the non_index_axis)
axis = list(set(range(value.ndim)) - set(_AXES_MAP[type(value)]))[0]
# figure out how to split the value
remain_key = None
remain_values = []
for k, v in d.items():
if v is None:
if remain_key is not None:
raise ValueError(
"append_to_multiple can only have one value in d that "
"is None"
)
remain_key = k
else:
remain_values.extend(v)
if remain_key is not None:
ordered = value.axes[axis]
ordd = ordered - Index(remain_values)
ordd = sorted(ordered.get_indexer(ordd))
d[remain_key] = ordered.take(ordd)
# data_columns
if data_columns is None:
data_columns = d[selector]
# ensure rows are synchronized across the tables
if dropna:
idxs = (value[cols].dropna(how='all').index for cols in d.values())
valid_index = next(idxs)
for index in idxs:
valid_index = valid_index.intersection(index)
value = value.ix[valid_index]
# append
for k, v in d.items():
dc = data_columns if k == selector else None
# compute the val
val = value.reindex_axis(v, axis=axis)
self.append(k, val, data_columns=dc, **kwargs)
def create_table_index(self, key, **kwargs):
""" Create a pytables index on the table
Paramaters
----------
key : object (the node to index)
Exceptions
----------
raises if the node is not a table
"""
# version requirements
_tables()
if not _table_supports_index:
raise ValueError("PyTables >= 2.3 is required for table indexing")
s = self.get_storer(key)
if s is None:
return
if not s.is_table:
raise TypeError(
"cannot create table index on a Fixed format store")
s.create_index(**kwargs)
def groups(self):
"""return a list of all the top-level nodes (that are not themselves a
pandas storage object)
"""
_tables()
self._check_if_open()
return [
g for g in self._handle.walkNodes()
if (getattr(g._v_attrs, 'pandas_type', None) or
getattr(g, 'table', None) or
(isinstance(g, _table_mod.table.Table) and
g._v_name != u('table')))
]
def get_node(self, key):
""" return the node with the key or None if it does not exist """
self._check_if_open()
try:
if not key.startswith('/'):
key = '/' + key
return self._handle.getNode(self.root, key)
except:
return None
def get_storer(self, key):
""" return the storer object for a key, raise if not in the file """
group = self.get_node(key)
if group is None:
return None
s = self._create_storer(group)
s.infer_axes()
return s
def copy(self, file, mode='w', propindexes=True, keys=None, complib=None,
complevel=None, fletcher32=False, overwrite=True):
""" copy the existing store to a new file, upgrading in place
Parameters
----------
propindexes: restore indexes in copied file (defaults to True)
keys : list of keys to include in the copy (defaults to all)
overwrite : overwrite (remove and replace) existing nodes in the
new store (default is True)
mode, complib, complevel, fletcher32 same as in HDFStore.__init__
Returns
-------
open file handle of the new store
"""
new_store = HDFStore(
file,
mode=mode,
complib=complib,
complevel=complevel,
fletcher32=fletcher32)
if keys is None:
keys = list(self.keys())
if not isinstance(keys, (tuple, list)):
keys = [keys]
for k in keys:
s = self.get_storer(k)
if s is not None:
if k in new_store:
if overwrite:
new_store.remove(k)
data = self.select(k)
if s.is_table:
index = False
if propindexes:
index = [a.name for a in s.axes if a.is_indexed]
new_store.append(
k, data, index=index,
data_columns=getattr(s, 'data_columns', None),
encoding=s.encoding
)
else:
new_store.put(k, data, encoding=s.encoding)
return new_store
# private methods ######
def _check_if_open(self):
if not self.is_open:
raise ClosedFileError("{0} file is not open!".format(self._path))
def _validate_format(self, format, kwargs):
""" validate / deprecate formats; return the new kwargs """
kwargs = kwargs.copy()
# table arg
table = kwargs.pop('table', None)
if table is not None:
warnings.warn(format_deprecate_doc, FutureWarning)
if table:
format = 'table'
else:
format = 'fixed'
# validate
try:
kwargs['format'] = _FORMAT_MAP[format.lower()]
except:
raise TypeError("invalid HDFStore format specified [{0}]"
.format(format))
return kwargs
def _create_storer(self, group, format=None, value=None, append=False,
**kwargs):
""" return a suitable class to operate """
def error(t):
raise TypeError(
"cannot properly create the storer for: [%s] [group->%s,"
"value->%s,format->%s,append->%s,kwargs->%s]"
% (t, group, type(value), format, append, kwargs)
)
pt = _ensure_decoded(getattr(group._v_attrs, 'pandas_type', None))
tt = _ensure_decoded(getattr(group._v_attrs, 'table_type', None))
# infer the pt from the passed value
if pt is None:
if value is None:
_tables()
if (getattr(group, 'table', None) or
isinstance(group, _table_mod.table.Table)):
pt = u('frame_table')
tt = u('generic_table')
else:
raise TypeError(
"cannot create a storer if the object is not existing "
"nor a value are passed")
else:
try:
pt = _TYPE_MAP[type(value)]
except:
error('_TYPE_MAP')
# we are actually a table
if format == 'table':
pt += u('_table')
# a storer node
if u('table') not in pt:
try:
return globals()[_STORER_MAP[pt]](self, group, **kwargs)
except:
error('_STORER_MAP')
# existing node (and must be a table)
if tt is None:
# if we are a writer, determin the tt
if value is not None:
if pt == u('series_table'):
index = getattr(value, 'index', None)
if index is not None:
if index.nlevels == 1:
tt = u('appendable_series')
elif index.nlevels > 1:
tt = u('appendable_multiseries')
elif pt == u('frame_table'):
index = getattr(value, 'index', None)
if index is not None:
if index.nlevels == 1:
tt = u('appendable_frame')
elif index.nlevels > 1:
tt = u('appendable_multiframe')
elif pt == u('wide_table'):
tt = u('appendable_panel')
elif pt == u('ndim_table'):
tt = u('appendable_ndim')
else:
# distiguish between a frame/table
tt = u('legacy_panel')
try:
fields = group.table._v_attrs.fields
if len(fields) == 1 and fields[0] == u('value'):
tt = u('legacy_frame')
except:
pass
try:
return globals()[_TABLE_MAP[tt]](self, group, **kwargs)
except:
error('_TABLE_MAP')
def _write_to_group(self, key, value, format, index=True, append=False,
complib=None, encoding=None, **kwargs):
group = self.get_node(key)
# remove the node if we are not appending
if group is not None and not append:
self._handle.removeNode(group, recursive=True)
group = None
# we don't want to store a table node at all if are object is 0-len
# as there are not dtypes
if getattr(value, 'empty', None) and (format == 'table' or append):
return
if group is None:
paths = key.split('/')
# recursively create the groups
path = '/'
for p in paths:
if not len(p):
continue
new_path = path
if not path.endswith('/'):
new_path += '/'
new_path += p
group = self.get_node(new_path)
if group is None:
group = self._handle.createGroup(path, p)
path = new_path
s = self._create_storer(group, format, value, append=append,
encoding=encoding, **kwargs)
if append:
# raise if we are trying to append to a Fixed format,
# or a table that exists (and we are putting)
if (not s.is_table or
(s.is_table and format == 'fixed' and s.is_exists)):
raise ValueError('Can only append to Tables')
if not s.is_exists:
s.set_object_info()
else:
s.set_object_info()
if not s.is_table and complib:
raise ValueError(
'Compression not supported on Fixed format stores'
)
# write the object
s.write(obj=value, append=append, complib=complib, **kwargs)
if s.is_table and index:
s.create_index(columns=index)
def _read_group(self, group, **kwargs):
s = self._create_storer(group)
s.infer_axes()
return s.read(**kwargs)
class TableIterator(object):
""" define the iteration interface on a table
Parameters
----------
store : the reference store
func : the function to get results
nrows : the rows to iterate on
start : the passed start value (default is None)
stop : the passed stop value (default is None)
chunksize : the passed chunking valeu (default is 50000)
auto_close : boolean, automatically close the store at the end of
iteration, default is False
kwargs : the passed kwargs
"""
def __init__(self, store, func, nrows, start=None, stop=None,
chunksize=None, auto_close=False):
self.store = store
self.func = func
self.nrows = nrows or 0
self.start = start or 0
if stop is None:
stop = self.nrows
self.stop = min(self.nrows, stop)
if chunksize is None:
chunksize = 100000
self.chunksize = chunksize
self.auto_close = auto_close
def __iter__(self):
current = self.start
while current < self.stop:
stop = current + self.chunksize
v = self.func(current, stop)
current = stop
if v is None:
continue
yield v
self.close()
def close(self):
if self.auto_close:
self.store.close()
def get_values(self):
results = self.func(self.start, self.stop)
self.close()
return results
class IndexCol(StringMixin):
""" an index column description class
Parameters
----------
axis : axis which I reference
values : the ndarray like converted values
kind : a string description of this type
typ : the pytables type
pos : the position in the pytables
"""
is_an_indexable = True
is_data_indexable = True
_info_fields = ['freq', 'tz', 'index_name']
def __init__(self, values=None, kind=None, typ=None, cname=None,
itemsize=None, name=None, axis=None, kind_attr=None, pos=None,
freq=None, tz=None, index_name=None, **kwargs):
self.values = values
self.kind = kind
self.typ = typ
self.itemsize = itemsize
self.name = name
self.cname = cname
self.kind_attr = kind_attr
self.axis = axis
self.pos = pos
self.freq = freq
self.tz = tz
self.index_name = index_name
self.table = None
if name is not None:
self.set_name(name, kind_attr)
if pos is not None:
self.set_pos(pos)
def set_name(self, name, kind_attr=None):
""" set the name of this indexer """
self.name = name
self.kind_attr = kind_attr or "%s_kind" % name
if self.cname is None:
self.cname = name
return self
def set_axis(self, axis):
""" set the axis over which I index """
self.axis = axis
return self
def set_pos(self, pos):
""" set the position of this column in the Table """
self.pos = pos
if pos is not None and self.typ is not None:
self.typ._v_pos = pos
return self
def set_table(self, table):
self.table = table
return self
def __unicode__(self):
temp = tuple(
map(pprint_thing,
(self.name,
self.cname,
self.axis,
self.pos,
self.kind)))
return "name->%s,cname->%s,axis->%s,pos->%s,kind->%s" % temp
def __eq__(self, other):
""" compare 2 col items """
return all([getattr(self, a, None) == getattr(other, a, None)
for a in ['name', 'cname', 'axis', 'pos']])
def __ne__(self, other):
return not self.__eq__(other)
@property
def is_indexed(self):
""" return whether I am an indexed column """
try:
return getattr(self.table.cols, self.cname).is_indexed
except:
False
def copy(self):
new_self = copy.copy(self)
return new_self
def infer(self, table):
"""infer this column from the table: create and return a new object"""
new_self = self.copy()
new_self.set_table(table)
new_self.get_attr()
return new_self
def convert(self, values, nan_rep, encoding):
""" set the values from this selection: take = take ownership """
try:
values = values[self.cname]
except:
pass
values = _maybe_convert(values, self.kind, encoding)
kwargs = dict()
if self.freq is not None:
kwargs['freq'] = _ensure_decoded(self.freq)
if self.index_name is not None:
kwargs['name'] = _ensure_decoded(self.index_name)
try:
self.values = Index(values, **kwargs)
except:
# if the output freq is different that what we recorded,
# it should be None (see also 'doc example part 2')
if 'freq' in kwargs:
kwargs['freq'] = None
self.values = Index(values, **kwargs)
# set the timezone if indicated
# we stored in utc, so reverse to local timezone
if self.tz is not None:
self.values = self.values.tz_localize(
'UTC').tz_convert(_ensure_decoded(self.tz))
return self
def take_data(self):
""" return the values & release the memory """
self.values, values = None, self.values
return values
@property
def attrs(self):
return self.table._v_attrs
@property
def description(self):
return self.table.description
@property
def col(self):
""" return my current col description """
return getattr(self.description, self.cname, None)
@property
def cvalues(self):
""" return my cython values """
return self.values
def __iter__(self):
return iter(self.values)
def maybe_set_size(self, min_itemsize=None, **kwargs):
""" maybe set a string col itemsize:
min_itemsize can be an interger or a dict with this columns name
with an integer size """
if _ensure_decoded(self.kind) == u('string'):
if isinstance(min_itemsize, dict):
min_itemsize = min_itemsize.get(self.name)
if min_itemsize is not None and self.typ.itemsize < min_itemsize:
self.typ = _tables(
).StringCol(itemsize=min_itemsize, pos=self.pos)
def validate_and_set(self, table, append, **kwargs):
self.set_table(table)
self.validate_col()
self.validate_attr(append)
self.set_attr()
def validate_col(self, itemsize=None):
""" validate this column: return the compared against itemsize """
# validate this column for string truncation (or reset to the max size)
if _ensure_decoded(self.kind) == u('string'):
c = self.col
if c is not None:
if itemsize is None:
itemsize = self.itemsize
if c.itemsize < itemsize:
raise ValueError(
"Trying to store a string with len [%s] in [%s] "
"column but\nthis column has a limit of [%s]!\n"
"Consider using min_itemsize to preset the sizes on "
"these columns" % (itemsize, self.cname, c.itemsize))
return c.itemsize
return None
def validate_attr(self, append):
# check for backwards incompatibility
if append:
existing_kind = getattr(self.attrs, self.kind_attr, None)
if existing_kind is not None and existing_kind != self.kind:
raise TypeError("incompatible kind in col [%s - %s]" %
(existing_kind, self.kind))
def update_info(self, info):
""" set/update the info for this indexable with the key/value
if there is a conflict raise/warn as needed """
for key in self._info_fields:
value = getattr(self, key, None)
idx = _get_info(info, self.name)
existing_value = idx.get(key)
if key in idx and value is not None and existing_value != value:
# frequency/name just warn
if key in ['freq', 'index_name']:
ws = attribute_conflict_doc % (key, existing_value, value)
warnings.warn(ws, AttributeConflictWarning)
# reset
idx[key] = None
setattr(self, key, None)
else:
raise ValueError(
"invalid info for [%s] for [%s], existing_value [%s] "
"conflicts with new value [%s]"
% (self.name, key, existing_value, value))
else:
if value is not None or existing_value is not None:
idx[key] = value
return self
def set_info(self, info):
""" set my state from the passed info """
idx = info.get(self.name)
if idx is not None:
self.__dict__.update(idx)
def get_attr(self):
""" set the kind for this colummn """
self.kind = getattr(self.attrs, self.kind_attr, None)
def set_attr(self):
""" set the kind for this colummn """
setattr(self.attrs, self.kind_attr, self.kind)
class GenericIndexCol(IndexCol):
""" an index which is not represented in the data of the table """
@property
def is_indexed(self):
return False
def convert(self, values, nan_rep, encoding):
""" set the values from this selection: take = take ownership """
self.values = Int64Index(np.arange(self.table.nrows))
return self
def get_attr(self):
pass
def set_attr(self):
pass
class DataCol(IndexCol):
""" a data holding column, by definition this is not indexable
Parameters
----------
data : the actual data
cname : the column name in the table to hold the data (typically
values)
"""
is_an_indexable = False
is_data_indexable = False
_info_fields = ['tz']
@classmethod
def create_for_block(
cls, i=None, name=None, cname=None, version=None, **kwargs):
""" return a new datacol with the block i """
if cname is None:
cname = name or 'values_block_%d' % i
if name is None:
name = cname
# prior to 0.10.1, we named values blocks like: values_block_0 an the
# name values_0
try:
if version[0] == 0 and version[1] <= 10 and version[2] == 0:
m = re.search("values_block_(\d+)", name)
if m:
name = "values_%s" % m.groups()[0]
except:
pass
return cls(name=name, cname=cname, **kwargs)
def __init__(self, values=None, kind=None, typ=None,
cname=None, data=None, block=None, **kwargs):
super(DataCol, self).__init__(
values=values, kind=kind, typ=typ, cname=cname, **kwargs)
self.dtype = None
self.dtype_attr = u("%s_dtype" % self.name)
self.set_data(data)
def __unicode__(self):
return "name->%s,cname->%s,dtype->%s,shape->%s" % (
self.name, self.cname, self.dtype, self.shape
)
def __eq__(self, other):
""" compare 2 col items """
return all([getattr(self, a, None) == getattr(other, a, None)
for a in ['name', 'cname', 'dtype', 'pos']])
def set_data(self, data, dtype=None):
self.data = data
if data is not None:
if dtype is not None:
self.dtype = dtype
self.set_kind()
elif self.dtype is None:
self.dtype = data.dtype.name
self.set_kind()
def take_data(self):
""" return the data & release the memory """
self.data, data = None, self.data
return data
def set_kind(self):
# set my kind if we can
if self.dtype is not None:
dtype = _ensure_decoded(self.dtype)
if dtype.startswith(u('string')) or dtype.startswith(u('bytes')):
self.kind = 'string'
elif dtype.startswith(u('float')):
self.kind = 'float'
elif dtype.startswith(u('int')) or dtype.startswith(u('uint')):
self.kind = 'integer'
elif dtype.startswith(u('date')):
self.kind = 'datetime'
elif dtype.startswith(u('timedelta')):
self.kind = 'timedelta'
elif dtype.startswith(u('bool')):
self.kind = 'bool'
else:
raise AssertionError(
"cannot interpret dtype of [%s] in [%s]" % (dtype, self))
# set my typ if we need
if self.typ is None:
self.typ = getattr(self.description, self.cname, None)
def set_atom(self, block, existing_col, min_itemsize,
nan_rep, info, encoding=None, **kwargs):
""" create and setup my atom from the block b """
self.values = list(block.items)
dtype = block.dtype.name
rvalues = block.values.ravel()
inferred_type = lib.infer_dtype(rvalues)
if inferred_type == 'datetime64':
self.set_atom_datetime64(block)
elif dtype == 'timedelta64[ns]':
if _np_version_under1p7:
raise TypeError(
"timdelta64 is not supported under under numpy < 1.7")
self.set_atom_timedelta64(block)
elif inferred_type == 'date':
raise TypeError(
"[date] is not implemented as a table column")
elif inferred_type == 'datetime':
if getattr(rvalues[0], 'tzinfo', None) is not None:
# if this block has more than one timezone, raise
if len(set([r.tzinfo for r in rvalues])) != 1:
raise TypeError(
"too many timezones in this block, create separate "
"data columns"
)
# convert this column to datetime64[ns] utc, and save the tz
index = DatetimeIndex(rvalues)
tz = getattr(index, 'tz', None)
if tz is None:
raise TypeError(
"invalid timezone specification")
values = index.tz_convert('UTC').values.view('i8')
# store a converted timezone
zone = tslib.get_timezone(index.tz)
if zone is None:
zone = tslib.tot_seconds(index.tz.utcoffset())
self.tz = zone
self.update_info(info)
self.set_atom_datetime64(
block, values.reshape(block.values.shape))
else:
raise TypeError(
"[datetime] is not implemented as a table column")
elif inferred_type == 'unicode':
raise TypeError(
"[unicode] is not implemented as a table column")
# this is basically a catchall; if say a datetime64 has nans then will
# end up here ###
elif inferred_type == 'string' or dtype == 'object':
self.set_atom_string(
block,
existing_col,
min_itemsize,
nan_rep,
encoding)
else:
self.set_atom_data(block)
return self
def get_atom_string(self, block, itemsize):
return _tables().StringCol(itemsize=itemsize, shape=block.shape[0])
def set_atom_string(
self, block, existing_col, min_itemsize, nan_rep, encoding):
# fill nan items with myself, don't disturb the blocks by
# trying to downcast
block = block.fillna(nan_rep, downcast=False)[0]
data = block.values
# see if we have a valid string type
inferred_type = lib.infer_dtype(data.ravel())
if inferred_type != 'string':
# we cannot serialize this data, so report an exception on a column
# by column basis
for item in block.items:
col = block.get(item)
inferred_type = lib.infer_dtype(col.ravel())
if inferred_type != 'string':
raise TypeError(
"Cannot serialize the column [%s] because\n"
"its data contents are [%s] object dtype"
% (item, inferred_type)
)
# itemsize is the maximum length of a string (along any dimension)
itemsize = lib.max_len_string_array(com._ensure_object(data.ravel()))
# specified min_itemsize?
if isinstance(min_itemsize, dict):
min_itemsize = int(min_itemsize.get(
self.name) or min_itemsize.get('values') or 0)
itemsize = max(min_itemsize or 0, itemsize)
# check for column in the values conflicts
if existing_col is not None:
eci = existing_col.validate_col(itemsize)
if eci > itemsize:
itemsize = eci
self.itemsize = itemsize
self.kind = 'string'
self.typ = self.get_atom_string(block, itemsize)
self.set_data(self.convert_string_data(data, itemsize, encoding))
def convert_string_data(self, data, itemsize, encoding):
return _convert_string_array(data, encoding, itemsize)
def get_atom_coltype(self):
""" return the PyTables column class for this column """
if self.kind.startswith('uint'):
col_name = "UInt%sCol" % self.kind[4:]
else:
col_name = "%sCol" % self.kind.capitalize()
return getattr(_tables(), col_name)
def get_atom_data(self, block):
return self.get_atom_coltype()(shape=block.shape[0])
def set_atom_data(self, block):
self.kind = block.dtype.name
self.typ = self.get_atom_data(block)
self.set_data(block.values.astype(self.typ.type))
def get_atom_datetime64(self, block):
return _tables().Int64Col(shape=block.shape[0])
def set_atom_datetime64(self, block, values=None):
self.kind = 'datetime64'
self.typ = self.get_atom_datetime64(block)
if values is None:
values = block.values.view('i8')
self.set_data(values, 'datetime64')
def get_atom_timedelta64(self, block):
return _tables().Int64Col(shape=block.shape[0])
def set_atom_timedelta64(self, block, values=None):
self.kind = 'timedelta64'
self.typ = self.get_atom_timedelta64(block)
if values is None:
values = block.values.view('i8')
self.set_data(values, 'timedelta64')
@property
def shape(self):
return getattr(self.data, 'shape', None)
@property
def cvalues(self):
""" return my cython values """
return self.data
def validate_attr(self, append):
"""validate that we have the same order as the existing & same dtype"""
if append:
existing_fields = getattr(self.attrs, self.kind_attr, None)
if (existing_fields is not None and
existing_fields != list(self.values)):
raise ValueError("appended items do not match existing items"
" in table!")
existing_dtype = getattr(self.attrs, self.dtype_attr, None)
if (existing_dtype is not None and
existing_dtype != self.dtype):
raise ValueError("appended items dtype do not match existing "
"items dtype in table!")
def convert(self, values, nan_rep, encoding):
"""set the data from this selection (and convert to the correct dtype
if we can)
"""
try:
values = values[self.cname]
except:
pass
self.set_data(values)
# convert to the correct dtype
if self.dtype is not None:
dtype = _ensure_decoded(self.dtype)
# reverse converts
if dtype == u('datetime64'):
# recreate the timezone
if self.tz is not None:
# data should be 2-dim here
# we stored as utc, so just set the tz
index = DatetimeIndex(
self.data.ravel(), tz='UTC').tz_convert(self.tz)
self.data = np.array(
index.tolist(), dtype=object).reshape(self.data.shape)
else:
self.data = np.asarray(self.data, dtype='M8[ns]')
elif dtype == u('timedelta64'):
self.data = np.asarray(self.data, dtype='m8[ns]')
elif dtype == u('date'):
try:
self.data = np.array(
[date.fromordinal(v) for v in self.data], dtype=object)
except ValueError:
self.data = np.array(
[date.fromtimestamp(v) for v in self.data],
dtype=object)
elif dtype == u('datetime'):
self.data = np.array(
[datetime.fromtimestamp(v) for v in self.data],
dtype=object)
else:
try:
self.data = self.data.astype(dtype)
except:
self.data = self.data.astype('O')
# convert nans / decode
if _ensure_decoded(self.kind) == u('string'):
self.data = _unconvert_string_array(
self.data, nan_rep=nan_rep, encoding=encoding)
return self
def get_attr(self):
""" get the data for this colummn """
self.values = getattr(self.attrs, self.kind_attr, None)
self.dtype = getattr(self.attrs, self.dtype_attr, None)
self.set_kind()
def set_attr(self):
""" set the data for this colummn """
setattr(self.attrs, self.kind_attr, self.values)
if self.dtype is not None:
setattr(self.attrs, self.dtype_attr, self.dtype)
class DataIndexableCol(DataCol):
""" represent a data column that can be indexed """
is_data_indexable = True
def get_atom_string(self, block, itemsize):
return _tables().StringCol(itemsize=itemsize)
def get_atom_data(self, block):
return self.get_atom_coltype()()
def get_atom_datetime64(self, block):
return _tables().Int64Col()
def get_atom_timedelta64(self, block):
return _tables().Int64Col()
class GenericDataIndexableCol(DataIndexableCol):
""" represent a generic pytables data column """
def get_attr(self):
pass
class Fixed(StringMixin):
""" represent an object in my store
facilitate read/write of various types of objects
this is an abstract base class
Parameters
----------
parent : my parent HDFStore
group : the group node where the table resides
"""
pandas_kind = None
obj_type = None
ndim = None
is_table = False
def __init__(self, parent, group, encoding=None, **kwargs):
self.parent = parent
self.group = group
self.encoding = _ensure_encoding(encoding)
self.set_version()
@property
def is_old_version(self):
return (self.version[0] <= 0 and self.version[1] <= 10 and
self.version[2] < 1)
def set_version(self):
""" compute and set our version """
version = _ensure_decoded(
getattr(self.group._v_attrs, 'pandas_version', None))
try:
self.version = tuple([int(x) for x in version.split('.')])
if len(self.version) == 2:
self.version = self.version + (0,)
except:
self.version = (0, 0, 0)
@property
def pandas_type(self):
return _ensure_decoded(getattr(self.group._v_attrs,
'pandas_type', None))
@property
def format_type(self):
return 'fixed'
def __unicode__(self):
""" return a pretty representation of myself """
self.infer_axes()
s = self.shape
if s is not None:
if isinstance(s, (list, tuple)):
s = "[%s]" % ','.join([pprint_thing(x) for x in s])
return "%-12.12s (shape->%s)" % (self.pandas_type, s)
return self.pandas_type
def set_object_info(self):
""" set my pandas type & version """
self.attrs.pandas_type = str(self.pandas_kind)
self.attrs.pandas_version = str(_version)
self.set_version()
def copy(self):
new_self = copy.copy(self)
return new_self
@property
def storage_obj_type(self):
return self.obj_type
@property
def shape(self):
return self.nrows
@property
def pathname(self):
return self.group._v_pathname
@property
def _handle(self):
return self.parent._handle
@property
def _filters(self):
return self.parent._filters
@property
def _complevel(self):
return self.parent._complevel
@property
def _fletcher32(self):
return self.parent._fletcher32
@property
def _complib(self):
return self.parent._complib
@property
def attrs(self):
return self.group._v_attrs
def set_attrs(self):
""" set our object attributes """
pass
def get_attrs(self):
""" get our object attributes """
pass
@property
def storable(self):
""" return my storable """
return self.group
@property
def is_exists(self):
return False
@property
def nrows(self):
return getattr(self.storable, 'nrows', None)
def validate(self, other):
""" validate against an existing storable """
if other is None:
return
return True
def validate_version(self, where=None):
""" are we trying to operate on an old version? """
return True
def infer_axes(self):
""" infer the axes of my storer
return a boolean indicating if we have a valid storer or not """
s = self.storable
if s is None:
return False
self.get_attrs()
return True
def read(self, **kwargs):
raise NotImplementedError(
"cannot read on an abstract storer: subclasses should implement")
def write(self, **kwargs):
raise NotImplementedError(
"cannot write on an abstract storer: sublcasses should implement")
def delete(self, where=None, **kwargs):
"""support fully deleting the node in its entirety (only) - where
specification must be None
"""
if where is None:
self._handle.removeNode(self.group, recursive=True)
return None
raise TypeError("cannot delete on an abstract storer")
class GenericFixed(Fixed):
""" a generified fixed version """
_index_type_map = {DatetimeIndex: 'datetime', PeriodIndex: 'period'}
_reverse_index_map = dict([(v, k)
for k, v in compat.iteritems(_index_type_map)])
attributes = []
# indexer helpders
def _class_to_alias(self, cls):
return self._index_type_map.get(cls, '')
def _alias_to_class(self, alias):
if isinstance(alias, type): # pragma: no cover
# compat: for a short period of time master stored types
return alias
return self._reverse_index_map.get(alias, Index)
def _get_index_factory(self, klass):
if klass == DatetimeIndex:
def f(values, freq=None, tz=None):
return DatetimeIndex._simple_new(values, None, freq=freq,
tz=tz)
return f
return klass
def validate_read(self, kwargs):
if kwargs.get('columns') is not None:
raise TypeError("cannot pass a column specification when reading "
"a Fixed format store. this store must be "
"selected in its entirety")
if kwargs.get('where') is not None:
raise TypeError("cannot pass a where specification when reading "
"from a Fixed format store. this store must be "
"selected in its entirety")
@property
def is_exists(self):
return True
def set_attrs(self):
""" set our object attributes """
self.attrs.encoding = self.encoding
def get_attrs(self):
""" retrieve our attributes """
self.encoding = _ensure_encoding(getattr(self.attrs, 'encoding', None))
for n in self.attributes:
setattr(self, n, _ensure_decoded(getattr(self.attrs, n, None)))
def write(self, obj, **kwargs):
self.set_attrs()
def read_array(self, key):
""" read an array for the specified node (off of group """
import tables
node = getattr(self.group, key)
data = node[:]
attrs = node._v_attrs
transposed = getattr(attrs, 'transposed', False)
if isinstance(node, tables.VLArray):
ret = data[0]
else:
dtype = getattr(attrs, 'value_type', None)
shape = getattr(attrs, 'shape', None)
if shape is not None:
# length 0 axis
ret = np.empty(shape, dtype=dtype)
else:
ret = data
if dtype == u('datetime64'):
ret = np.array(ret, dtype='M8[ns]')
elif dtype == u('timedelta64'):
if _np_version_under1p7:
raise TypeError(
"timedelta64 is not supported under under numpy < 1.7")
ret = np.array(ret, dtype='m8[ns]')
if transposed:
return ret.T
else:
return ret
def read_index(self, key):
variety = _ensure_decoded(getattr(self.attrs, '%s_variety' % key))
if variety == u('multi'):
return self.read_multi_index(key)
elif variety == u('block'):
return self.read_block_index(key)
elif variety == u('sparseint'):
return self.read_sparse_intindex(key)
elif variety == u('regular'):
_, index = self.read_index_node(getattr(self.group, key))
return index
else: # pragma: no cover
raise TypeError('unrecognized index variety: %s' % variety)
def write_index(self, key, index):
if isinstance(index, MultiIndex):
setattr(self.attrs, '%s_variety' % key, 'multi')
self.write_multi_index(key, index)
elif isinstance(index, BlockIndex):
setattr(self.attrs, '%s_variety' % key, 'block')
self.write_block_index(key, index)
elif isinstance(index, IntIndex):
setattr(self.attrs, '%s_variety' % key, 'sparseint')
self.write_sparse_intindex(key, index)
else:
setattr(self.attrs, '%s_variety' % key, 'regular')
converted = _convert_index(index, self.encoding,
self.format_type).set_name('index')
self.write_array(key, converted.values)
node = getattr(self.group, key)
node._v_attrs.kind = converted.kind
node._v_attrs.name = index.name
if isinstance(index, (DatetimeIndex, PeriodIndex)):
node._v_attrs.index_class = self._class_to_alias(type(index))
if hasattr(index, 'freq'):
node._v_attrs.freq = index.freq
if hasattr(index, 'tz') and index.tz is not None:
zone = tslib.get_timezone(index.tz)
if zone is None:
zone = tslib.tot_seconds(index.tz.utcoffset())
node._v_attrs.tz = zone
def write_block_index(self, key, index):
self.write_array('%s_blocs' % key, index.blocs)
self.write_array('%s_blengths' % key, index.blengths)
setattr(self.attrs, '%s_length' % key, index.length)
def read_block_index(self, key):
length = getattr(self.attrs, '%s_length' % key)
blocs = self.read_array('%s_blocs' % key)
blengths = self.read_array('%s_blengths' % key)
return BlockIndex(length, blocs, blengths)
def write_sparse_intindex(self, key, index):
self.write_array('%s_indices' % key, index.indices)
setattr(self.attrs, '%s_length' % key, index.length)
def read_sparse_intindex(self, key):
length = getattr(self.attrs, '%s_length' % key)
indices = self.read_array('%s_indices' % key)
return IntIndex(length, indices)
def write_multi_index(self, key, index):
setattr(self.attrs, '%s_nlevels' % key, index.nlevels)
for i, (lev, lab, name) in enumerate(zip(index.levels,
index.labels,
index.names)):
# write the level
level_key = '%s_level%d' % (key, i)
conv_level = _convert_index(lev, self.encoding,
self.format_type).set_name(level_key)
self.write_array(level_key, conv_level.values)
node = getattr(self.group, level_key)
node._v_attrs.kind = conv_level.kind
node._v_attrs.name = name
# write the name
setattr(node._v_attrs, '%s_name%d' % (key, i), name)
# write the labels
label_key = '%s_label%d' % (key, i)
self.write_array(label_key, lab)
def read_multi_index(self, key):
nlevels = getattr(self.attrs, '%s_nlevels' % key)
levels = []
labels = []
names = []
for i in range(nlevels):
level_key = '%s_level%d' % (key, i)
name, lev = self.read_index_node(getattr(self.group, level_key))
levels.append(lev)
names.append(name)
label_key = '%s_label%d' % (key, i)
lab = self.read_array(label_key)
labels.append(lab)
return MultiIndex(levels=levels, labels=labels, names=names,
verify_integrity=True)
def read_index_node(self, node):
data = node[:]
# If the index was an empty array write_array_empty() will
# have written a sentinel. Here we relace it with the original.
if ('shape' in node._v_attrs and
self._is_empty_array(getattr(node._v_attrs, 'shape'))):
data = np.empty(getattr(node._v_attrs, 'shape'),
dtype=getattr(node._v_attrs, 'value_type'))
kind = _ensure_decoded(node._v_attrs.kind)
name = None
if 'name' in node._v_attrs:
name = node._v_attrs.name
index_class = self._alias_to_class(getattr(node._v_attrs,
'index_class', ''))
factory = self._get_index_factory(index_class)
kwargs = {}
if u('freq') in node._v_attrs:
kwargs['freq'] = node._v_attrs['freq']
if u('tz') in node._v_attrs:
kwargs['tz'] = node._v_attrs['tz']
if kind in (u('date'), u('datetime')):
index = factory(
_unconvert_index(data, kind, encoding=self.encoding),
dtype=object, **kwargs)
else:
index = factory(
_unconvert_index(data, kind, encoding=self.encoding), **kwargs)
index.name = name
return name, index
def write_array_empty(self, key, value):
""" write a 0-len array """
# ugly hack for length 0 axes
arr = np.empty((1,) * value.ndim)
self._handle.createArray(self.group, key, arr)
getattr(self.group, key)._v_attrs.value_type = str(value.dtype)
getattr(self.group, key)._v_attrs.shape = value.shape
def _is_empty_array(self, shape):
"""Returns true if any axis is zero length."""
return any(x == 0 for x in shape)
def write_array(self, key, value, items=None):
if key in self.group:
self._handle.removeNode(self.group, key)
# Transform needed to interface with pytables row/col notation
empty_array = self._is_empty_array(value.shape)
transposed = False
if not empty_array:
value = value.T
transposed = True
if self._filters is not None:
atom = None
try:
# get the atom for this datatype
atom = _tables().Atom.from_dtype(value.dtype)
except ValueError:
pass
if atom is not None:
# create an empty chunked array and fill it from value
if not empty_array:
ca = self._handle.createCArray(self.group, key, atom,
value.shape,
filters=self._filters)
ca[:] = value
getattr(self.group, key)._v_attrs.transposed = transposed
else:
self.write_array_empty(key, value)
return
if value.dtype.type == np.object_:
# infer the type, warn if we have a non-string type here (for
# performance)
inferred_type = lib.infer_dtype(value.ravel())
if empty_array:
pass
elif inferred_type == 'string':
pass
else:
try:
items = list(items)
except:
pass
ws = performance_doc % (inferred_type, key, items)
warnings.warn(ws, PerformanceWarning)
vlarr = self._handle.createVLArray(self.group, key,
_tables().ObjectAtom())
vlarr.append(value)
else:
if empty_array:
self.write_array_empty(key, value)
else:
if value.dtype.type == np.datetime64:
self._handle.createArray(self.group, key, value.view('i8'))
getattr(
self.group, key)._v_attrs.value_type = 'datetime64'
elif value.dtype.type == np.timedelta64:
self._handle.createArray(self.group, key, value.view('i8'))
getattr(
self.group, key)._v_attrs.value_type = 'timedelta64'
else:
self._handle.createArray(self.group, key, value)
getattr(self.group, key)._v_attrs.transposed = transposed
class LegacyFixed(GenericFixed):
def read_index_legacy(self, key):
node = getattr(self.group, key)
data = node[:]
kind = node._v_attrs.kind
return _unconvert_index_legacy(data, kind, encoding=self.encoding)
class LegacySeriesFixed(LegacyFixed):
def read(self, **kwargs):
self.validate_read(kwargs)
index = self.read_index_legacy('index')
values = self.read_array('values')
return Series(values, index=index)
class LegacyFrameFixed(LegacyFixed):
def read(self, **kwargs):
self.validate_read(kwargs)
index = self.read_index_legacy('index')
columns = self.read_index_legacy('columns')
values = self.read_array('values')
return DataFrame(values, index=index, columns=columns)
class SeriesFixed(GenericFixed):
pandas_kind = u('series')
attributes = ['name']
@property
def shape(self):
try:
return len(getattr(self.group, 'values')),
except:
return None
def read(self, **kwargs):
self.validate_read(kwargs)
index = self.read_index('index')
values = self.read_array('values')
return Series(values, index=index, name=self.name)
def write(self, obj, **kwargs):
super(SeriesFixed, self).write(obj, **kwargs)
self.write_index('index', obj.index)
self.write_array('values', obj.values)
self.attrs.name = obj.name
class SparseSeriesFixed(GenericFixed):
pandas_kind = u('sparse_series')
attributes = ['name', 'fill_value', 'kind']
def read(self, **kwargs):
self.validate_read(kwargs)
index = self.read_index('index')
sp_values = self.read_array('sp_values')
sp_index = self.read_index('sp_index')
return SparseSeries(sp_values, index=index, sparse_index=sp_index,
kind=self.kind or u('block'),
fill_value=self.fill_value,
name=self.name)
def write(self, obj, **kwargs):
super(SparseSeriesFixed, self).write(obj, **kwargs)
self.write_index('index', obj.index)
self.write_index('sp_index', obj.sp_index)
self.write_array('sp_values', obj.sp_values)
self.attrs.name = obj.name
self.attrs.fill_value = obj.fill_value
self.attrs.kind = obj.kind
class SparseFrameFixed(GenericFixed):
pandas_kind = u('sparse_frame')
attributes = ['default_kind', 'default_fill_value']
def read(self, **kwargs):
self.validate_read(kwargs)
columns = self.read_index('columns')
sdict = {}
for c in columns:
key = 'sparse_series_%s' % c
s = SparseSeriesFixed(self.parent, getattr(self.group, key))
s.infer_axes()
sdict[c] = s.read()
return SparseDataFrame(sdict, columns=columns,
default_kind=self.default_kind,
default_fill_value=self.default_fill_value)
def write(self, obj, **kwargs):
""" write it as a collection of individual sparse series """
super(SparseFrameFixed, self).write(obj, **kwargs)
for name, ss in compat.iteritems(obj):
key = 'sparse_series_%s' % name
if key not in self.group._v_children:
node = self._handle.createGroup(self.group, key)
else:
node = getattr(self.group, key)
s = SparseSeriesFixed(self.parent, node)
s.write(ss)
self.attrs.default_fill_value = obj.default_fill_value
self.attrs.default_kind = obj.default_kind
self.write_index('columns', obj.columns)
class SparsePanelFixed(GenericFixed):
pandas_kind = u('sparse_panel')
attributes = ['default_kind', 'default_fill_value']
def read(self, **kwargs):
self.validate_read(kwargs)
items = self.read_index('items')
sdict = {}
for name in items:
key = 'sparse_frame_%s' % name
s = SparseFrameFixed(self.parent, getattr(self.group, key))
s.infer_axes()
sdict[name] = s.read()
return SparsePanel(sdict, items=items, default_kind=self.default_kind,
default_fill_value=self.default_fill_value)
def write(self, obj, **kwargs):
super(SparsePanelFixed, self).write(obj, **kwargs)
self.attrs.default_fill_value = obj.default_fill_value
self.attrs.default_kind = obj.default_kind
self.write_index('items', obj.items)
for name, sdf in compat.iteritems(obj):
key = 'sparse_frame_%s' % name
if key not in self.group._v_children:
node = self._handle.createGroup(self.group, key)
else:
node = getattr(self.group, key)
s = SparseFrameFixed(self.parent, node)
s.write(sdf)
class BlockManagerFixed(GenericFixed):
attributes = ['ndim', 'nblocks']
is_shape_reversed = False
@property
def shape(self):
try:
ndim = self.ndim
# items
items = 0
for i in range(self.nblocks):
node = getattr(self.group, 'block%d_items' % i)
shape = getattr(node, 'shape', None)
if shape is not None:
items += shape[0]
# data shape
node = getattr(self.group, 'block0_values')
shape = getattr(node, 'shape', None)
if shape is not None:
shape = list(shape[0:(ndim - 1)])
else:
shape = []
shape.append(items)
# hacky - this works for frames, but is reversed for panels
if self.is_shape_reversed:
shape = shape[::-1]
return shape
except:
return None
def read(self, **kwargs):
self.validate_read(kwargs)
axes = []
for i in range(self.ndim):
ax = self.read_index('axis%d' % i)
axes.append(ax)
items = axes[0]
blocks = []
for i in range(self.nblocks):
blk_items = self.read_index('block%d_items' % i)
values = self.read_array('block%d_values' % i)
blk = make_block(values, blk_items, items)
blocks.append(blk)
return self.obj_type(BlockManager(blocks, axes))
def write(self, obj, **kwargs):
super(BlockManagerFixed, self).write(obj, **kwargs)
data = obj._data
if not data.is_consolidated():
data = data.consolidate()
self.attrs.ndim = data.ndim
for i, ax in enumerate(data.axes):
self.write_index('axis%d' % i, ax)
# Supporting mixed-type DataFrame objects...nontrivial
self.attrs.nblocks = nblocks = len(data.blocks)
for i in range(nblocks):
blk = data.blocks[i]
# I have no idea why, but writing values before items fixed #2299
self.write_array('block%d_values' % i, blk.values, items=blk.items)
self.write_index('block%d_items' % i, blk.items)
class FrameFixed(BlockManagerFixed):
pandas_kind = u('frame')
obj_type = DataFrame
class PanelFixed(BlockManagerFixed):
pandas_kind = u('wide')
obj_type = Panel
is_shape_reversed = True
def write(self, obj, **kwargs):
obj._consolidate_inplace()
return super(PanelFixed, self).write(obj, **kwargs)
class Table(Fixed):
""" represent a table:
facilitate read/write of various types of tables
Attrs in Table Node
-------------------
These are attributes that are store in the main table node, they are
necessary to recreate these tables when read back in.
index_axes : a list of tuples of the (original indexing axis and
index column)
non_index_axes: a list of tuples of the (original index axis and
columns on a non-indexing axis)
values_axes : a list of the columns which comprise the data of this
table
data_columns : a list of the columns that we are allowing indexing
(these become single columns in values_axes), or True to force all
columns
nan_rep : the string to use for nan representations for string
objects
levels : the names of levels
"""
pandas_kind = u('wide_table')
table_type = None
levels = 1
is_table = True
is_shape_reversed = False
def __init__(self, *args, **kwargs):
super(Table, self).__init__(*args, **kwargs)
self.index_axes = []
self.non_index_axes = []
self.values_axes = []
self.data_columns = []
self.info = dict()
self.nan_rep = None
self.selection = None
@property
def table_type_short(self):
return self.table_type.split('_')[0]
@property
def format_type(self):
return 'table'
def __unicode__(self):
""" return a pretty representatgion of myself """
self.infer_axes()
dc = ",dc->[%s]" % ','.join(
self.data_columns) if len(self.data_columns) else ''
ver = ''
if self.is_old_version:
ver = "[%s]" % '.'.join([str(x) for x in self.version])
return "%-12.12s%s (typ->%s,nrows->%s,ncols->%s,indexers->[%s]%s)" % (
self.pandas_type, ver, self.table_type_short, self.nrows,
self.ncols, ','.join([a.name for a in self.index_axes]), dc
)
def __getitem__(self, c):
""" return the axis for c """
for a in self.axes:
if c == a.name:
return a
return None
def validate(self, other):
""" validate against an existing table """
if other is None:
return
if other.table_type != self.table_type:
raise TypeError("incompatible table_type with existing [%s - %s]" %
(other.table_type, self.table_type))
for c in ['index_axes', 'non_index_axes', 'values_axes']:
sv = getattr(self, c, None)
ov = getattr(other, c, None)
if sv != ov:
# show the error for the specific axes
for i, sax in enumerate(sv):
oax = ov[i]
if sax != oax:
raise ValueError(
"invalid combinate of [%s] on appending data [%s] "
"vs current table [%s]" % (c, sax, oax))
# should never get here
raise Exception(
"invalid combinate of [%s] on appending data [%s] vs "
"current table [%s]" % (c, sv, ov))
@property
def is_multi_index(self):
"""the levels attribute is 1 or a list in the case of a multi-index"""
return isinstance(self.levels, list)
def validate_multiindex(self, obj):
"""validate that we can store the multi-index; reset and return the
new object
"""
levels = [l if l is not None else "level_{0}".format(i)
for i, l in enumerate(obj.index.names)]
try:
return obj.reset_index(), levels
except ValueError:
raise ValueError("duplicate names/columns in the multi-index when "
"storing as a table")
@property
def nrows_expected(self):
""" based on our axes, compute the expected nrows """
return np.prod([i.cvalues.shape[0] for i in self.index_axes])
@property
def is_exists(self):
""" has this table been created """
return u('table') in self.group
@property
def storable(self):
return getattr(self.group, 'table', None)
@property
def table(self):
""" return the table group (this is my storable) """
return self.storable
@property
def dtype(self):
return self.table.dtype
@property
def description(self):
return self.table.description
@property
def axes(self):
return itertools.chain(self.index_axes, self.values_axes)
@property
def ncols(self):
""" the number of total columns in the values axes """
return sum([len(a.values) for a in self.values_axes])
@property
def is_transposed(self):
return False
@property
def data_orientation(self):
"""return a tuple of my permutated axes, non_indexable at the front"""
return tuple(itertools.chain([int(a[0]) for a in self.non_index_axes],
[int(a.axis) for a in self.index_axes]))
def queryables(self):
""" return a dict of the kinds allowable columns for this object """
# compute the values_axes queryables
return dict(
[(a.cname, a.kind) for a in self.index_axes] +
[(self.storage_obj_type._AXIS_NAMES[axis], None)
for axis, values in self.non_index_axes] +
[(v.cname, v.kind) for v in self.values_axes
if v.name in set(self.data_columns)]
)
def index_cols(self):
""" return a list of my index cols """
return [(i.axis, i.cname) for i in self.index_axes]
def values_cols(self):
""" return a list of my values cols """
return [i.cname for i in self.values_axes]
def set_info(self):
""" update our table index info """
self.attrs.info = self.info
def set_attrs(self):
""" set our table type & indexables """
self.attrs.table_type = str(self.table_type)
self.attrs.index_cols = self.index_cols()
self.attrs.values_cols = self.values_cols()
self.attrs.non_index_axes = self.non_index_axes
self.attrs.data_columns = self.data_columns
self.attrs.nan_rep = self.nan_rep
self.attrs.encoding = self.encoding
self.attrs.levels = self.levels
self.set_info()
def get_attrs(self):
""" retrieve our attributes """
self.non_index_axes = getattr(
self.attrs, 'non_index_axes', None) or []
self.data_columns = getattr(
self.attrs, 'data_columns', None) or []
self.info = getattr(
self.attrs, 'info', None) or dict()
self.nan_rep = getattr(self.attrs, 'nan_rep', None)
self.encoding = _ensure_encoding(
getattr(self.attrs, 'encoding', None))
self.levels = getattr(
self.attrs, 'levels', None) or []
t = self.table
self.index_axes = [
a.infer(t) for a in self.indexables if a.is_an_indexable
]
self.values_axes = [
a.infer(t) for a in self.indexables if not a.is_an_indexable
]
def validate_version(self, where=None):
""" are we trying to operate on an old version? """
if where is not None:
if (self.version[0] <= 0 and self.version[1] <= 10 and
self.version[2] < 1):
ws = incompatibility_doc % '.'.join(
[str(x) for x in self.version])
warnings.warn(ws, IncompatibilityWarning)
def validate_min_itemsize(self, min_itemsize):
"""validate the min_itemisze doesn't contain items that are not in the
axes this needs data_columns to be defined
"""
if min_itemsize is None:
return
if not isinstance(min_itemsize, dict):
return
q = self.queryables()
for k, v in min_itemsize.items():
# ok, apply generally
if k == 'values':
continue
if k not in q:
raise ValueError(
"min_itemsize has the key [%s] which is not an axis or "
"data_column" % k)
@property
def indexables(self):
""" create/cache the indexables if they don't exist """
if self._indexables is None:
self._indexables = []
# index columns
self._indexables.extend([
IndexCol(name=name, axis=axis, pos=i)
for i, (axis, name) in enumerate(self.attrs.index_cols)
])
# values columns
dc = set(self.data_columns)
base_pos = len(self._indexables)
def f(i, c):
klass = DataCol
if c in dc:
klass = DataIndexableCol
return klass.create_for_block(i=i, name=c, pos=base_pos + i,
version=self.version)
self._indexables.extend(
[f(i, c) for i, c in enumerate(self.attrs.values_cols)])
return self._indexables
def create_index(self, columns=None, optlevel=None, kind=None):
"""
Create a pytables index on the specified columns
note: cannot index Time64Col() currently; PyTables must be >= 2.3
Paramaters
----------
columns : False (don't create an index), True (create all columns
index), None or list_like (the indexers to index)
optlevel: optimization level (defaults to 6)
kind : kind of index (defaults to 'medium')
Exceptions
----------
raises if the node is not a table
"""
if not self.infer_axes():
return
if columns is False:
return
# index all indexables and data_columns
if columns is None or columns is True:
columns = [a.cname for a in self.axes if a.is_data_indexable]
if not isinstance(columns, (tuple, list)):
columns = [columns]
kw = dict()
if optlevel is not None:
kw['optlevel'] = optlevel
if kind is not None:
kw['kind'] = kind
table = self.table
for c in columns:
v = getattr(table.cols, c, None)
if v is not None:
# remove the index if the kind/optlevel have changed
if v.is_indexed:
index = v.index
cur_optlevel = index.optlevel
cur_kind = index.kind
if kind is not None and cur_kind != kind:
v.removeIndex()
else:
kw['kind'] = cur_kind
if optlevel is not None and cur_optlevel != optlevel:
v.removeIndex()
else:
kw['optlevel'] = cur_optlevel
# create the index
if not v.is_indexed:
v.createIndex(**kw)
def read_axes(self, where, **kwargs):
"""create and return the axes sniffed from the table: return boolean
for success
"""
# validate the version
self.validate_version(where)
# infer the data kind
if not self.infer_axes():
return False
# create the selection
self.selection = Selection(self, where=where, **kwargs)
values = self.selection.select()
# convert the data
for a in self.axes:
a.set_info(self.info)
a.convert(values, nan_rep=self.nan_rep, encoding=self.encoding)
return True
def get_object(self, obj):
""" return the data for this obj """
return obj
def validate_data_columns(self, data_columns, min_itemsize):
"""take the input data_columns and min_itemize and create a data
columns spec
"""
if not len(self.non_index_axes):
return []
axis, axis_labels = self.non_index_axes[0]
info = self.info.get(axis, dict())
if info.get('type') == 'MultiIndex' and data_columns:
raise ValueError("cannot use a multi-index on axis [{0}] with "
"data_columns {1}".format(axis, data_columns))
# evaluate the passed data_columns, True == use all columns
# take only valide axis labels
if data_columns is True:
data_columns = axis_labels
elif data_columns is None:
data_columns = []
# if min_itemsize is a dict, add the keys (exclude 'values')
if isinstance(min_itemsize, dict):
existing_data_columns = set(data_columns)
data_columns.extend([
k for k in min_itemsize.keys()
if k != 'values' and k not in existing_data_columns
])
# return valid columns in the order of our axis
return [c for c in data_columns if c in axis_labels]
def create_axes(self, axes, obj, validate=True, nan_rep=None,
data_columns=None, min_itemsize=None, **kwargs):
""" create and return the axes
leagcy tables create an indexable column, indexable index,
non-indexable fields
Parameters:
-----------
axes: a list of the axes in order to create (names or numbers of
the axes)
obj : the object to create axes on
validate: validate the obj against an existing object already
written
min_itemsize: a dict of the min size for a column in bytes
nan_rep : a values to use for string column nan_rep
encoding : the encoding for string values
data_columns : a list of columns that we want to create separate to
allow indexing (or True will force all columns)
"""
# set the default axes if needed
if axes is None:
try:
axes = _AXES_MAP[type(obj)]
except:
raise TypeError("cannot properly create the storer for: "
"[group->%s,value->%s]"
% (self.group._v_name, type(obj)))
# map axes to numbers
axes = [obj._get_axis_number(a) for a in axes]
# do we have an existing table (if so, use its axes & data_columns)
if self.infer_axes():
existing_table = self.copy()
existing_table.infer_axes()
axes = [a.axis for a in existing_table.index_axes]
data_columns = existing_table.data_columns
nan_rep = existing_table.nan_rep
self.encoding = existing_table.encoding
self.info = copy.copy(existing_table.info)
else:
existing_table = None
# currently support on ndim-1 axes
if len(axes) != self.ndim - 1:
raise ValueError(
"currently only support ndim-1 indexers in an AppendableTable")
# create according to the new data
self.non_index_axes = []
self.data_columns = []
# nan_representation
if nan_rep is None:
nan_rep = 'nan'
self.nan_rep = nan_rep
# create axes to index and non_index
index_axes_map = dict()
for i, a in enumerate(obj.axes):
if i in axes:
name = obj._AXIS_NAMES[i]
index_axes_map[i] = _convert_index(
a, self.encoding, self.format_type
).set_name(name).set_axis(i)
else:
# we might be able to change the axes on the appending data if
# necessary
append_axis = list(a)
if existing_table is not None:
indexer = len(self.non_index_axes)
exist_axis = existing_table.non_index_axes[indexer][1]
if append_axis != exist_axis:
# ahah! -> reindex
if sorted(append_axis) == sorted(exist_axis):
append_axis = exist_axis
# the non_index_axes info
info = _get_info(self.info, i)
info['names'] = list(a.names)
info['type'] = a.__class__.__name__
self.non_index_axes.append((i, append_axis))
# set axis positions (based on the axes)
self.index_axes = [
index_axes_map[a].set_pos(j).update_info(self.info)
for j, a in enumerate(axes)
]
j = len(self.index_axes)
# check for column conflicts
if validate:
for a in self.axes:
a.maybe_set_size(min_itemsize=min_itemsize)
# reindex by our non_index_axes & compute data_columns
for a in self.non_index_axes:
obj = _reindex_axis(obj, a[0], a[1])
# figure out data_columns and get out blocks
block_obj = self.get_object(obj).consolidate()
blocks = block_obj._data.blocks
if len(self.non_index_axes):
axis, axis_labels = self.non_index_axes[0]
data_columns = self.validate_data_columns(
data_columns, min_itemsize)
if len(data_columns):
blocks = block_obj.reindex_axis(
Index(axis_labels) - Index(data_columns),
axis=axis
)._data.blocks
for c in data_columns:
blocks.extend(
block_obj.reindex_axis([c], axis=axis)._data.blocks)
# reorder the blocks in the same order as the existing_table if we can
if existing_table is not None:
by_items = dict([(tuple(b.items.tolist()), b) for b in blocks])
new_blocks = []
for ea in existing_table.values_axes:
items = tuple(ea.values)
try:
b = by_items.pop(items)
new_blocks.append(b)
except:
raise ValueError(
"cannot match existing table structure for [%s] on "
"appending data" % ','.join(com.pprint_thing(item) for
item in items))
blocks = new_blocks
# add my values
self.values_axes = []
for i, b in enumerate(blocks):
# shape of the data column are the indexable axes
klass = DataCol
name = None
# we have a data_column
if (data_columns and len(b.items) == 1 and
b.items[0] in data_columns):
klass = DataIndexableCol
name = b.items[0]
self.data_columns.append(name)
# make sure that we match up the existing columns
# if we have an existing table
if existing_table is not None and validate:
try:
existing_col = existing_table.values_axes[i]
except:
raise ValueError("Incompatible appended table [%s] with "
"existing table [%s]"
% (blocks, existing_table.values_axes))
else:
existing_col = None
try:
col = klass.create_for_block(
i=i, name=name, version=self.version)
col.set_atom(block=b,
existing_col=existing_col,
min_itemsize=min_itemsize,
nan_rep=nan_rep,
encoding=self.encoding,
info=self.info,
**kwargs)
col.set_pos(j)
self.values_axes.append(col)
except (NotImplementedError, ValueError, TypeError) as e:
raise e
except Exception as detail:
raise Exception(
"cannot find the correct atom type -> "
"[dtype->%s,items->%s] %s"
% (b.dtype.name, b.items, str(detail))
)
j += 1
# validate our min_itemsize
self.validate_min_itemsize(min_itemsize)
# validate the axes if we have an existing table
if validate:
self.validate(existing_table)
def process_axes(self, obj, columns=None):
""" process axes filters """
# make sure to include levels if we have them
if columns is not None and self.is_multi_index:
for n in self.levels:
if n not in columns:
columns.insert(0, n)
# reorder by any non_index_axes & limit to the select columns
for axis, labels in self.non_index_axes:
obj = _reindex_axis(obj, axis, labels, columns)
# apply the selection filters (but keep in the same order)
if self.selection.filter is not None:
for field, op, filt in self.selection.filter.format():
def process_filter(field, filt):
for axis_name in obj._AXIS_NAMES.values():
axis_number = obj._get_axis_number(axis_name)
axis_values = obj._get_axis(axis_name)
# see if the field is the name of an axis
if field == axis_name:
# if we have a multi-index, then need to include
# the levels
if self.is_multi_index:
filt = filt + Index(self.levels)
takers = op(axis_values, filt)
return obj.ix._getitem_axis(takers,
axis=axis_number)
# this might be the name of a file IN an axis
elif field in axis_values:
# we need to filter on this dimension
values = _ensure_index(getattr(obj, field).values)
filt = _ensure_index(filt)
# hack until we support reversed dim flags
if isinstance(obj, DataFrame):
axis_number = 1 - axis_number
takers = op(values, filt)
return obj.ix._getitem_axis(takers,
axis=axis_number)
raise ValueError(
"cannot find the field [%s] for filtering!" % field)
obj = process_filter(field, filt)
return obj
def create_description(self, complib=None, complevel=None,
fletcher32=False, expectedrows=None):
""" create the description of the table from the axes & values """
# expected rows estimate
if expectedrows is None:
expectedrows = max(self.nrows_expected, 10000)
d = dict(name='table', expectedrows=expectedrows)
# description from the axes & values
d['description'] = dict([(a.cname, a.typ) for a in self.axes])
if complib:
if complevel is None:
complevel = self._complevel or 9
filters = _tables().Filters(
complevel=complevel, complib=complib,
fletcher32=fletcher32 or self._fletcher32)
d['filters'] = filters
elif self._filters is not None:
d['filters'] = self._filters
return d
def read_coordinates(self, where=None, start=None, stop=None, **kwargs):
"""select coordinates (row numbers) from a table; return the
coordinates object
"""
# validate the version
self.validate_version(where)
# infer the data kind
if not self.infer_axes():
return False
# create the selection
self.selection = Selection(
self, where=where, start=start, stop=stop, **kwargs)
return Index(self.selection.select_coords())
def read_column(self, column, where=None, **kwargs):
"""return a single column from the table, generally only indexables
are interesting
"""
# validate the version
self.validate_version()
# infer the data kind
if not self.infer_axes():
return False
if where is not None:
raise TypeError("read_column does not currently accept a where "
"clause")
# find the axes
for a in self.axes:
if column == a.name:
if not a.is_data_indexable:
raise ValueError(
"column [%s] can not be extracted individually; it is "
"not data indexable" % column)
# column must be an indexable or a data column
c = getattr(self.table.cols, column)
a.set_info(self.info)
return Series(a.convert(c[:], nan_rep=self.nan_rep,
encoding=self.encoding).take_data())
raise KeyError("column [%s] not found in the table" % column)
class WORMTable(Table):
""" a write-once read-many table: this format DOES NOT ALLOW appending to a
table. writing is a one-time operation the data are stored in a format
that allows for searching the data on disk
"""
table_type = u('worm')
def read(self, **kwargs):
""" read the indicies and the indexing array, calculate offset rows and
return """
raise NotImplementedError("WORMTable needs to implement read")
def write(self, **kwargs):
""" write in a format that we can search later on (but cannot append
to): write out the indicies and the values using _write_array
(e.g. a CArray) create an indexing table so that we can search
"""
raise NotImplementedError("WORKTable needs to implement write")
class LegacyTable(Table):
""" an appendable table: allow append/query/delete operations to a
(possibily) already existing appendable table this table ALLOWS
append (but doesn't require them), and stores the data in a format
that can be easily searched
"""
_indexables = [
IndexCol(name='index', axis=1, pos=0),
IndexCol(name='column', axis=2, pos=1, index_kind='columns_kind'),
DataCol(name='fields', cname='values', kind_attr='fields', pos=2)
]
table_type = u('legacy')
ndim = 3
def write(self, **kwargs):
raise TypeError("write operations are not allowed on legacy tables!")
def read(self, where=None, columns=None, **kwargs):
"""we have n indexable columns, with an arbitrary number of data
axes
"""
if not self.read_axes(where=where, **kwargs):
return None
factors = [Categorical.from_array(a.values) for a in self.index_axes]
levels = [f.levels for f in factors]
N = [len(f.levels) for f in factors]
labels = [f.labels for f in factors]
# compute the key
key = factor_indexer(N[1:], labels)
objs = []
if len(unique(key)) == len(key):
sorter, _ = algos.groupsort_indexer(
com._ensure_int64(key), np.prod(N))
sorter = com._ensure_platform_int(sorter)
# create the objs
for c in self.values_axes:
# the data need to be sorted
sorted_values = c.take_data().take(sorter, axis=0)
if sorted_values.ndim == 1:
sorted_values = sorted_values.reshape(sorted_values.shape[0],1)
take_labels = [l.take(sorter) for l in labels]
items = Index(c.values)
block = block2d_to_blocknd(
sorted_values, items, tuple(N), take_labels)
# create the object
mgr = BlockManager([block], [items] + levels)
obj = self.obj_type(mgr)
# permute if needed
if self.is_transposed:
obj = obj.transpose(
*tuple(Series(self.data_orientation).argsort()))
objs.append(obj)
else:
warnings.warn(duplicate_doc, DuplicateWarning)
# reconstruct
long_index = MultiIndex.from_arrays(
[i.values for i in self.index_axes])
for c in self.values_axes:
lp = DataFrame(c.data, index=long_index, columns=c.values)
# need a better algorithm
tuple_index = long_index._tuple_index
unique_tuples = lib.fast_unique(tuple_index)
unique_tuples = _asarray_tuplesafe(unique_tuples)
indexer = match(unique_tuples, tuple_index)
indexer = com._ensure_platform_int(indexer)
new_index = long_index.take(indexer)
new_values = lp.values.take(indexer, axis=0)
lp = DataFrame(new_values, index=new_index, columns=lp.columns)
objs.append(lp.to_panel())
# create the composite object
if len(objs) == 1:
wp = objs[0]
else:
wp = concat(objs, axis=0, verify_integrity=False).consolidate()
# apply the selection filters & axis orderings
wp = self.process_axes(wp, columns=columns)
return wp
class LegacyFrameTable(LegacyTable):
""" support the legacy frame table """
pandas_kind = u('frame_table')
table_type = u('legacy_frame')
obj_type = Panel
def read(self, *args, **kwargs):
return super(LegacyFrameTable, self).read(*args, **kwargs)['value']
class LegacyPanelTable(LegacyTable):
""" support the legacy panel table """
table_type = u('legacy_panel')
obj_type = Panel
class AppendableTable(LegacyTable):
""" suppor the new appendable table formats """
_indexables = None
table_type = u('appendable')
def write(self, obj, axes=None, append=False, complib=None,
complevel=None, fletcher32=None, min_itemsize=None,
chunksize=None, expectedrows=None, dropna=True, **kwargs):
if not append and self.is_exists:
self._handle.removeNode(self.group, 'table')
# create the axes
self.create_axes(axes=axes, obj=obj, validate=append,
min_itemsize=min_itemsize,
**kwargs)
if not self.is_exists:
# create the table
options = self.create_description(complib=complib,
complevel=complevel,
fletcher32=fletcher32,
expectedrows=expectedrows)
# set the table attributes
self.set_attrs()
# create the table
table = self._handle.createTable(self.group, **options)
else:
table = self.table
# update my info
self.set_info()
# validate the axes and set the kinds
for a in self.axes:
a.validate_and_set(table, append)
# add the rows
self.write_data(chunksize, dropna=dropna)
def write_data(self, chunksize, dropna=True):
""" we form the data into a 2-d including indexes,values,mask
write chunk-by-chunk """
names = self.dtype.names
nrows = self.nrows_expected
# if dropna==True, then drop ALL nan rows
if dropna:
masks = []
for a in self.values_axes:
# figure the mask: only do if we can successfully process this
# column, otherwise ignore the mask
mask = com.isnull(a.data).all(axis=0)
masks.append(mask.astype('u1'))
# consolidate masks
mask = masks[0]
for m in masks[1:]:
mask = mask & m
mask = mask.ravel()
else:
mask = np.empty(nrows, dtype='u1')
mask.fill(False)
# broadcast the indexes if needed
indexes = [a.cvalues for a in self.index_axes]
nindexes = len(indexes)
bindexes = []
for i, idx in enumerate(indexes):
# broadcast to all other indexes except myself
if i > 0 and i < nindexes:
repeater = np.prod(
[indexes[bi].shape[0] for bi in range(0, i)])
idx = np.tile(idx, repeater)
if i < nindexes - 1:
repeater = np.prod([indexes[bi].shape[0]
for bi in range(i + 1, nindexes)])
idx = np.repeat(idx, repeater)
bindexes.append(idx)
# transpose the values so first dimension is last
# reshape the values if needed
values = [a.take_data() for a in self.values_axes]
values = [v.transpose(np.roll(np.arange(v.ndim), v.ndim - 1))
for v in values]
bvalues = []
for i, v in enumerate(values):
new_shape = (nrows,) + self.dtype[names[nindexes + i]].shape
bvalues.append(values[i].ravel().reshape(new_shape))
# write the chunks
if chunksize is None:
chunksize = 100000
chunks = int(nrows / chunksize) + 1
for i in range(chunks):
start_i = i * chunksize
end_i = min((i + 1) * chunksize, nrows)
if start_i >= end_i:
break
self.write_data_chunk(
indexes=[a[start_i:end_i] for a in bindexes],
mask=mask[start_i:end_i],
values=[v[start_i:end_i] for v in bvalues])
def write_data_chunk(self, indexes, mask, values):
# 0 len
for v in values:
if not np.prod(v.shape):
return
try:
nrows = indexes[0].shape[0]
rows = np.empty(nrows, dtype=self.dtype)
names = self.dtype.names
nindexes = len(indexes)
# indexes
for i, idx in enumerate(indexes):
rows[names[i]] = idx
# values
for i, v in enumerate(values):
rows[names[i + nindexes]] = v
# mask
rows = rows[~mask.ravel().astype(bool)]
except Exception as detail:
raise Exception("cannot create row-data -> %s" % detail)
try:
if len(rows):
self.table.append(rows)
self.table.flush()
except Exception as detail:
raise TypeError("tables cannot write this data -> %s" % detail)
def delete(self, where=None, **kwargs):
# delete all rows (and return the nrows)
if where is None or not len(where):
nrows = self.nrows
self._handle.removeNode(self.group, recursive=True)
return nrows
# infer the data kind
if not self.infer_axes():
return None
# create the selection
table = self.table
self.selection = Selection(self, where, **kwargs)
values = self.selection.select_coords()
# delete the rows in reverse order
l = Series(values).order()
ln = len(l)
if ln:
# construct groups of consecutive rows
diff = l.diff()
groups = list(diff[diff > 1].index)
# 1 group
if not len(groups):
groups = [0]
# final element
if groups[-1] != ln:
groups.append(ln)
# initial element
if groups[0] != 0:
groups.insert(0, 0)
# we must remove in reverse order!
pg = groups.pop()
for g in reversed(groups):
rows = l.take(lrange(g, pg))
table.removeRows(start=rows[rows.index[0]
], stop=rows[rows.index[-1]] + 1)
pg = g
self.table.flush()
# return the number of rows removed
return ln
class AppendableFrameTable(AppendableTable):
""" suppor the new appendable table formats """
pandas_kind = u('frame_table')
table_type = u('appendable_frame')
ndim = 2
obj_type = DataFrame
@property
def is_transposed(self):
return self.index_axes[0].axis == 1
def get_object(self, obj):
""" these are written transposed """
if self.is_transposed:
obj = obj.T
return obj
def read(self, where=None, columns=None, **kwargs):
if not self.read_axes(where=where, **kwargs):
return None
info = (self.info.get(self.non_index_axes[0][0], dict())
if len(self.non_index_axes) else dict())
index = self.index_axes[0].values
frames = []
for a in self.values_axes:
# we could have a multi-index constructor here
# _ensure_index doesn't recognized our list-of-tuples here
if info.get('type') == 'MultiIndex':
cols = MultiIndex.from_tuples(a.values)
else:
cols = Index(a.values)
names = info.get('names')
if names is not None:
cols.set_names(names, inplace=True)
if self.is_transposed:
values = a.cvalues
index_ = cols
cols_ = Index(index, name=getattr(index, 'name', None))
else:
values = a.cvalues.T
index_ = Index(index, name=getattr(index, 'name', None))
cols_ = cols
# if we have a DataIndexableCol, its shape will only be 1 dim
if values.ndim == 1:
values = values.reshape(1, values.shape[0])
block = make_block(values, cols_, cols_)
mgr = BlockManager([block], [cols_, index_])
frames.append(DataFrame(mgr))
if len(frames) == 1:
df = frames[0]
else:
df = concat(frames, axis=1, verify_integrity=False).consolidate()
# apply the selection filters & axis orderings
df = self.process_axes(df, columns=columns)
return df
class AppendableSeriesTable(AppendableFrameTable):
""" support the new appendable table formats """
pandas_kind = u('series_table')
table_type = u('appendable_series')
ndim = 2
obj_type = Series
storage_obj_type = DataFrame
@property
def is_transposed(self):
return False
def get_object(self, obj):
return obj
def write(self, obj, data_columns=None, **kwargs):
""" we are going to write this as a frame table """
if not isinstance(obj, DataFrame):
name = obj.name or 'values'
obj = DataFrame({name: obj}, index=obj.index)
obj.columns = [name]
return super(AppendableSeriesTable, self).write(
obj=obj, data_columns=obj.columns, **kwargs)
def read(self, columns=None, **kwargs):
is_multi_index = self.is_multi_index
if columns is not None and is_multi_index:
for n in self.levels:
if n not in columns:
columns.insert(0, n)
s = super(AppendableSeriesTable, self).read(columns=columns, **kwargs)
if is_multi_index:
s.set_index(self.levels, inplace=True)
s = s.iloc[:, 0]
# remove the default name
if s.name == 'values':
s.name = None
return s
class AppendableMultiSeriesTable(AppendableSeriesTable):
""" support the new appendable table formats """
pandas_kind = u('series_table')
table_type = u('appendable_multiseries')
def write(self, obj, **kwargs):
""" we are going to write this as a frame table """
name = obj.name or 'values'
obj, self.levels = self.validate_multiindex(obj)
cols = list(self.levels)
cols.append(name)
obj.columns = cols
return super(AppendableMultiSeriesTable, self).write(obj=obj, **kwargs)
class GenericTable(AppendableFrameTable):
""" a table that read/writes the generic pytables table format """
pandas_kind = u('frame_table')
table_type = u('generic_table')
ndim = 2
obj_type = DataFrame
@property
def pandas_type(self):
return self.pandas_kind
@property
def storable(self):
return getattr(self.group, 'table', None) or self.group
def get_attrs(self):
""" retrieve our attributes """
self.non_index_axes = []
self.nan_rep = None
self.levels = []
t = self.table
self.index_axes = [a.infer(t)
for a in self.indexables if a.is_an_indexable]
self.values_axes = [a.infer(t)
for a in self.indexables if not a.is_an_indexable]
self.data_columns = [a.name for a in self.values_axes]
@property
def indexables(self):
""" create the indexables from the table description """
if self._indexables is None:
d = self.description
# the index columns is just a simple index
self._indexables = [GenericIndexCol(name='index', axis=0)]
for i, n in enumerate(d._v_names):
dc = GenericDataIndexableCol(
name=n, pos=i, values=[n], version=self.version)
self._indexables.append(dc)
return self._indexables
def write(self, **kwargs):
raise NotImplementedError("cannot write on an generic table")
class AppendableMultiFrameTable(AppendableFrameTable):
""" a frame with a multi-index """
table_type = u('appendable_multiframe')
obj_type = DataFrame
ndim = 2
_re_levels = re.compile("^level_\d+$")
@property
def table_type_short(self):
return u('appendable_multi')
def write(self, obj, data_columns=None, **kwargs):
if data_columns is None:
data_columns = []
elif data_columns is True:
data_columns = obj.columns[:]
obj, self.levels = self.validate_multiindex(obj)
for n in self.levels:
if n not in data_columns:
data_columns.insert(0, n)
return super(AppendableMultiFrameTable, self).write(
obj=obj, data_columns=data_columns, **kwargs)
def read(self, **kwargs):
df = super(AppendableMultiFrameTable, self).read(**kwargs)
df = df.set_index(self.levels)
# remove names for 'level_%d'
df.index = df.index.set_names([
None if self._re_levels.search(l) else l for l in df.index.names
])
return df
class AppendablePanelTable(AppendableTable):
""" suppor the new appendable table formats """
table_type = u('appendable_panel')
ndim = 3
obj_type = Panel
def get_object(self, obj):
""" these are written transposed """
if self.is_transposed:
obj = obj.transpose(*self.data_orientation)
return obj
@property
def is_transposed(self):
return self.data_orientation != tuple(range(self.ndim))
class AppendableNDimTable(AppendablePanelTable):
""" suppor the new appendable table formats """
table_type = u('appendable_ndim')
ndim = 4
obj_type = Panel4D
def _reindex_axis(obj, axis, labels, other=None):
ax = obj._get_axis(axis)
labels = _ensure_index(labels)
# try not to reindex even if other is provided
# if it equals our current index
if other is not None:
other = _ensure_index(other)
if (other is None or labels.equals(other)) and labels.equals(ax):
return obj
labels = _ensure_index(labels.unique())
if other is not None:
labels = labels & _ensure_index(other.unique())
if not labels.equals(ax):
slicer = [slice(None, None)] * obj.ndim
slicer[axis] = labels
obj = obj.loc[tuple(slicer)]
return obj
def _get_info(info, name):
""" get/create the info for this name """
try:
idx = info[name]
except:
idx = info[name] = dict()
return idx
def _convert_index(index, encoding=None, format_type=None):
index_name = getattr(index, 'name', None)
if isinstance(index, DatetimeIndex):
converted = index.asi8
return IndexCol(converted, 'datetime64', _tables().Int64Col(),
freq=getattr(index, 'freq', None),
tz=getattr(index, 'tz', None),
index_name=index_name)
elif isinstance(index, (Int64Index, PeriodIndex)):
atom = _tables().Int64Col()
return IndexCol(
index.values, 'integer', atom, freq=getattr(index, 'freq', None),
index_name=index_name)
if isinstance(index, MultiIndex):
raise TypeError('MultiIndex not supported here!')
inferred_type = lib.infer_dtype(index)
values = np.asarray(index)
if inferred_type == 'datetime64':
converted = values.view('i8')
return IndexCol(converted, 'datetime64', _tables().Int64Col(),
freq=getattr(index, 'freq', None),
tz=getattr(index, 'tz', None),
index_name=index_name)
elif inferred_type == 'datetime':
converted = np.array([(time.mktime(v.timetuple()) +
v.microsecond / 1E6) for v in values],
dtype=np.float64)
return IndexCol(converted, 'datetime', _tables().Time64Col(),
index_name=index_name)
elif inferred_type == 'date':
converted = np.array([v.toordinal() for v in values],
dtype=np.int32)
return IndexCol(converted, 'date', _tables().Time32Col(),
index_name=index_name)
elif inferred_type == 'string':
# atom = _tables().ObjectAtom()
# return np.asarray(values, dtype='O'), 'object', atom
converted = _convert_string_array(values, encoding)
itemsize = converted.dtype.itemsize
return IndexCol(
converted, 'string', _tables().StringCol(itemsize),
itemsize=itemsize, index_name=index_name
)
elif inferred_type == 'unicode':
if format_type == 'fixed':
atom = _tables().ObjectAtom()
return IndexCol(np.asarray(values, dtype='O'), 'object', atom,
index_name=index_name)
raise TypeError(
"[unicode] is not supported as a in index type for [{0}] formats"
.format(format_type)
)
elif inferred_type == 'integer':
# take a guess for now, hope the values fit
atom = _tables().Int64Col()
return IndexCol(np.asarray(values, dtype=np.int64), 'integer', atom,
index_name=index_name)
elif inferred_type == 'floating':
atom = _tables().Float64Col()
return IndexCol(np.asarray(values, dtype=np.float64), 'float', atom,
index_name=index_name)
else: # pragma: no cover
atom = _tables().ObjectAtom()
return IndexCol(np.asarray(values, dtype='O'), 'object', atom,
index_name=index_name)
def _unconvert_index(data, kind, encoding=None):
kind = _ensure_decoded(kind)
if kind == u('datetime64'):
index = DatetimeIndex(data)
elif kind == u('datetime'):
index = np.array([datetime.fromtimestamp(v) for v in data],
dtype=object)
elif kind == u('date'):
try:
index = np.array(
[date.fromordinal(v) for v in data], dtype=object)
except (ValueError):
index = np.array(
[date.fromtimestamp(v) for v in data], dtype=object)
elif kind in (u('integer'), u('float')):
index = np.array(data)
elif kind in (u('string')):
index = _unconvert_string_array(data, nan_rep=None, encoding=encoding)
elif kind == u('object'):
index = np.array(data[0])
else: # pragma: no cover
raise ValueError('unrecognized index type %s' % kind)
return index
def _unconvert_index_legacy(data, kind, legacy=False, encoding=None):
kind = _ensure_decoded(kind)
if kind == u('datetime'):
index = lib.time64_to_datetime(data)
elif kind in (u('integer')):
index = np.array(data, dtype=object)
elif kind in (u('string')):
index = _unconvert_string_array(data, nan_rep=None, encoding=encoding)
else: # pragma: no cover
raise ValueError('unrecognized index type %s' % kind)
return index
def _convert_string_array(data, encoding, itemsize=None):
# encode if needed
if encoding is not None and len(data):
f = np.vectorize(lambda x: x.encode(encoding), otypes=[np.object])
data = f(data)
# create the sized dtype
if itemsize is None:
itemsize = lib.max_len_string_array(com._ensure_object(data.ravel()))
data = np.array(data, dtype="S%d" % itemsize)
return data
def _unconvert_string_array(data, nan_rep=None, encoding=None):
""" deserialize a string array, possibly decoding """
shape = data.shape
data = np.array(data.ravel(), dtype=object)
# guard against a None encoding in PY3 (because of a legacy
# where the passed encoding is actually None)
encoding = _ensure_encoding(encoding)
if encoding is not None and len(data):
try:
data = data.astype(str).astype(object)
except:
f = np.vectorize(lambda x: x.decode(encoding), otypes=[np.object])
data = f(data)
if nan_rep is None:
nan_rep = 'nan'
data = lib.string_array_replace_from_nan_rep(data, nan_rep)
return data.reshape(shape)
def _maybe_convert(values, val_kind, encoding):
if _need_convert(val_kind):
conv = _get_converter(val_kind, encoding)
# conv = np.frompyfunc(conv, 1, 1)
values = conv(values)
return values
def _get_converter(kind, encoding):
kind = _ensure_decoded(kind)
if kind == 'datetime64':
return lambda x: np.array(x, dtype='M8[ns]')
elif kind == 'datetime':
return lib.convert_timestamps
elif kind == 'string':
return lambda x: _unconvert_string_array(x, encoding=encoding)
else: # pragma: no cover
raise ValueError('invalid kind %s' % kind)
def _need_convert(kind):
kind = _ensure_decoded(kind)
if kind in (u('datetime'), u('datetime64'), u('string')):
return True
return False
class Selection(object):
"""
Carries out a selection operation on a tables.Table object.
Parameters
----------
table : a Table object
where : list of Terms (or convertable to)
start, stop: indicies to start and/or stop selection
"""
def __init__(self, table, where=None, start=None, stop=None, **kwargs):
self.table = table
self.where = where
self.start = start
self.stop = stop
self.condition = None
self.filter = None
self.terms = None
self.coordinates = None
if com.is_list_like(where):
# see if we have a passed coordinate like
try:
inferred = lib.infer_dtype(where)
if inferred == 'integer' or inferred == 'boolean':
where = np.array(where)
if where.dtype == np.bool_:
start, stop = self.start, self.stop
if start is None:
start = 0
if stop is None:
stop = self.table.nrows
self.coordinates = np.arange(start, stop)[where]
elif issubclass(where.dtype.type, np.integer):
if ((self.start is not None and
(where < self.start).any()) or
(self.stop is not None and
(where >= self.stop).any())):
raise ValueError(
"where must have index locations >= start and "
"< stop"
)
self.coordinates = where
except:
pass
if self.coordinates is None:
self.terms = self.generate(where)
# create the numexpr & the filter
if self.terms is not None:
self.condition, self.filter = self.terms.evaluate()
def generate(self, where):
""" where can be a : dict,list,tuple,string """
if where is None:
return None
q = self.table.queryables()
try:
return Expr(where, queryables=q, encoding=self.table.encoding)
except NameError as detail:
# raise a nice message, suggesting that the user should use
# data_columns
raise ValueError(
"The passed where expression: {0}\n"
" contains an invalid variable reference\n"
" all of the variable refrences must be a "
"reference to\n"
" an axis (e.g. 'index' or 'columns'), or a "
"data_column\n"
" The currently defined references are: {1}\n"
.format(where, ','.join(q.keys()))
)
def select(self):
"""
generate the selection
"""
if self.condition is not None:
return self.table.table.readWhere(self.condition.format(),
start=self.start, stop=self.stop)
elif self.coordinates is not None:
return self.table.table.readCoordinates(self.coordinates)
return self.table.table.read(start=self.start, stop=self.stop)
def select_coords(self):
"""
generate the selection
"""
if self.condition is None:
return np.arange(self.table.nrows)
return self.table.table.getWhereList(self.condition.format(),
start=self.start, stop=self.stop,
sort=True)
# utilities ###
def timeit(key, df, fn=None, remove=True, **kwargs):
if fn is None:
fn = 'timeit.h5'
store = HDFStore(fn, mode='w')
store.append(key, df, **kwargs)
store.close()
if remove:
os.remove(fn)
|