All pastes #801033 Raw Edit

Something

public python v1 · immutable
#801033 ·published 2007-11-28 22:40 UTC
rendered paste body
import cPickleimport MySQLdbfrom db import DataBasefrom pageRank import pageRankdb=DataBase();dbConn=db.db;dbCursor=db.cursordbCursor.execute("SELECT pl_from, page_id FROM pagelinks INNER JOIN page ON pagelinks.pl_title = page.page_title")wikipedia_links = dbCursor.fetchall()dbCursor.close();del dbCursorsparse_matrix, these_links, last_link_from = [], [1], 1for link_from, link_to in wikipedia_links:    if link_from != last_link_from:        sparse_matrix.append(these_links)        while link_from != last_link_from+1:            sparse_matrix.append([])            last_link_from += 1        these_links = [int(link_from)]    if link_to <= wikipedia_links[-1][0]-1:            these_links.append(int(link_to))    last_link_from = link_from# NOTE: Produces "Warning: overflow encountered in reduce" - no Google results!page_rank = pageRank(sparse_matrix, alpha=.85, convergence=.9)f=open("pagerank.pkl", "w")cPickle.dump(page_rank, f, 1)f.close()"""OUTPUT:>>> print wikipedia_links[0:100]((1L, 7553L), (1L, 9878L), (1L, 28592L), (1L, 2L), (1L, 185L), (1L, 14981L), (1L, 262L), (1L, 400L), (1L, 402L), (1L, 401L), (1L, 468L), (1L, 7825L), (1L, 469L), (1L, 3641L), (1L, 530L), (1L, 569L), (1L, 684L), (1L, 3935L), (1L, 944L), (2L, 1L), (2L, 29689L), (2L, 3539L), (2L, 76696L), (2L, 185L), (2L, 262L), (2L, 400L), (2L, 5940L), (2L, 402L), (2L, 401L), (2L, 468L), (2L, 469L), (2L, 3641L), (2L, 530L), (2L, 569L), (2L, 684L), (2L, 944L), (3L, 123L), (3L, 1939L), (3L, 8480L), (3L, 18477L), (3L, 4323L), (3L, 6142L), (3L, 706L), (3L, 1831L), (3L, 704L), (3L, 857L), (3L, 18412L), (3L, 1905L), (3L, 50891L), (3L, 5499L), (4L, 7958L), (4L, 18576L), (4L, 44235L), (4L, 64L), (4L, 5859L), (4L, 319L), (4L, 56587L), (4L, 7945L), (4L, 7692L), (4L, 319L), (4L, 54722L), (4L, 28495L), (4L, 48959L), (4L, 30762L), (4L, 42930L), (4L, 13179L), (4L, 4335L), (4L, 38798L), (4L, 704L), (4L, 1905L), (4L, 66L), (4L, 718L), (4L, 37968L), (4L, 916L), (4L, 1756L), (4L, 1890L), (4L, 8705L), (6L, 73414L), (6L, 49L), (6L, 29357L), (6L, 39460L), (6L, 21815L), (6L, 120L), (6L, 11450L), (6L, 134L), (6L, 59225L), (6L, 187L), (6L, 18401L), (6L, 5316L), (6L, 248L), (6L, 20727L), (6L, 216L), (6L, 12836L), (6L, 37200L), (6L, 64755L), (6L, 2133L), (6L, 5381L), (6L, 18930L), (6L, 391L), (6L, 7112L))>>> print sparse_matrix[0:10][[1, 7553, 9878, 28592, 2, 185, 14981, 262, 400, 402, 401, 468, 7825, 469, 3641, 530, 569, 684, 3935, 944], [2, 1, 29689, 3539, 76696, 185, 262, 400, 5940, 402, 401, 468, 469, 3641, 530, 569, 684, 944], [3, 123, 1939, 8480, 18477, 4323, 6142, 706, 1831, 704, 857, 18412, 1905, 50891, 5499], [4, 7958, 18576, 44235, 64, 5859, 319, 56587, 7945, 7692, 319, 54722, 28495, 48959, 30762, 42930, 13179, 4335, 38798, 704, 1905, 66, 718, 37968, 916, 1756, 1890, 8705], [], [6, 73414, 49, 29357, 39460, 21815, 120, 11450, 134, 59225, 187, 18401, 5316, 248, 20727, 216, 12836, 37200, 64755, 2133, 5381, 18930, 391, 7112, 7147, 28356, 6623, 4654, 4653, 6593, 62469, 30136, 472, 5874, 11274, 26710, 5007, 15311, 3886, 5875, 11616, 24939, 3336, 72086, 25297, 59275, 29089, 2875, 43495, 700, 5833, 3364, 726, 689, 23058, 67444, 50141, 6256, 35288, 15935], [], [8, 5461, 34241, 32, 5208, 5892, 46925, 3926, 55, 9381, 5719, 5720, 32619, 5721, 17732, 3632, 5722, 66835, 2843, 6435, 5723, 5724, 5725, 5726, 5727, 5728, 5729, 33447, 6309, 5730, 6575, 41329, 3793, 6551, 472, 5874, 5731, 22971, 5732, 5733, 591, 5871, 5734, 5735, 5736, 47376, 4963, 32544, 38406, 5737, 3794, 5738, 5739, 32620, 5740, 911, 5741, 5742, 5743, 1939, 8480, 18477], [9, 3927, 4701, 55806, 4700, 3610, 3705, 5861, 2126, 43916, 4464, 2950, 38976, 54986, 11599, 119, 2083, 32192, 219, 45570, 9476, 66710, 3283, 7368, 357, 355, 19787, 18820, 3257, 19782, 2061, 2949, 5863, 22108, 7638, 67733, 24823, 47878, 11026, 939, 38676, 7956, 71067, 5898, 4317, 1756, 1890, 8705], []]>>> page_rank[0:100]array([ 0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.], dtype=float32)"""