我有两个正在处理的数据文件。一个包含单词列表，其中包含有关这些单词的一些附加信息，另一个包含单词对（其中单词按其第一个表中的单词ID列出）及其频率。
词典文件（示例输出）
('wID', 'w1', 'w1cs', 'L1', 'c1')
('-----', '-----', '-----', '-----', '-----')
(1, ',', ',', ',', 'y')
(2, '.', '.', '.', 'y')
(3, 'the', 'the', 'the', 'at')
(4, 'and', 'and', 'and', 'cc')
(5, 'of', 'of', 'of', 'io')
Bigram文件（示例输出）
('freq', 'w1', 'w2')
(4, 22097, 161)
(1, 98664, 1320)
(1, 426515, 1345)
(1, 483675, 747)
(19, 63, 15496)
(2, 3011, 7944)
(1, 27985, 27778)
我使用sqlite创建了两个表，并从上面的文件上传了数据。
conn = sqlite3.connect('bigrams.db')
conn.text_factory = str
c = conn.cursor()
c.execute('pragma foreign_keys=ON')
词汇表
c.execute('''CREATE TABLE lex
(wID INT PRIMARY KEY, w1 TEXT, w1cs TEXT, L1 TEXT, c1 TEXT)''')
#I removed this index as per CL.'s suggestion
#c.execute('''DROP INDEX IF EXISTS lex_index''')
#c.execute('''CREATE INDEX lex_index ON lex (wID, w1, c1)''')
#and added this one
c.execute('''CREATE INDEX lex_w1_index ON lex (w1)''')
将数据插入词典表
#I replaced this code
# with open('/Users/.../lexicon.txt', "rb") as lex_file:
# for line in lex_file:
# currentRow = line.split('\t')
# try:
# data = [currentRow[0], currentRow[1], currentRow[2], currentRow[3], str(currentRow[4].strip('\r\n'))]
# c.executemany ('insert or replace into lex values (?, ?, ?, ?, ?)', (data,))
# except IndexError:
# pass
#with the one that Julian wrote
blocksize = 100000
with open('/Users/.../lexicon.txt', "rb") as lex_file:
data = []
line_counter = 0
for line in lex_file:
data.append(line.strip().split('\t'))
line_counter += 1
if line_counter % blocksize == 0:
try:
c.executemany ('insert or replace into lex values (?, ?, ?, ?, ?)', data)
conn.commit()
except IndexError:
block_start = line_counter - blocksize + 1
print 'Lex error lines {}-{}'.format(block_start, line_counter)
finally:
data = []
Bigram表
#I replaced this code to create table x2
#c.execute('''CREATE TABLE x2
# (freq INT, w1 INT, w2 INT, FOREIGN KEY(w1) REFERENCES lex(wID), FOREIGN KEY(w2) REFERENCES lex(wID))''')
#with the code that Julian suggested
c.execute('''CREATE TABLE x2
(freq INT, w1 INT, w2 INT,
FOREIGN KEY(w1) REFERENCES lex(wID),
FOREIGN KEY(w2) REFERENCES lex(wID),
PRIMARY KEY(w1, w2) )''')
将数据插入Bigram表
#Replaced this code
#with open('/Users/.../x2.txt', "rb") as x2_file:
# for line in x2_file:
# currentRow = line.split('\t')
# try:
# data = [str(currentRow[0].replace('\x00','').replace('\xff\xfe','')), str(currentRow[1].replace('\x00','')), str(currentRow[2].replace('\x00','').strip('\r\n'))]
# c.executemany('insert or replace into x2 values (?, ?, ?)', (data,))
# except IndexError:
# pass
#with this one suggested by Julian
with open('/Users/.../x2.txt', "rb") as x2_file:
data = []
line_counter = 0
for line in x2_file:
data.append(line.strip().replace('\x00','').replace('\xff\xfe','').split('\t'))
line_counter += 1
if line_counter % blocksize == 0:
try:
c.executemany('insert or replace into x2 values (?, ?, ?)', data)
conn.commit()
except IndexError:
block_start = line_counter - blocksize + 1
print 'x2 error lines {}-{}'.format(block_start, line_counter)
finally:
data = []
conn.close()
我希望能够检查数据中是否存在给定的单词对——例如“like new”
当我只指定第一个词时，程序工作正常。
cur.execute('''SELECT lex1.w1, lex2.w1 from x2
INNER JOIN lex as lex1 ON lex1.wID=x2.w1
INNER JOIN lex as lex2 ON lex2.wID=x2.w2
WHERE lex1.w1= “like” ’’’)
但是当我想搜索一对单词时，代码会慢得让人痛苦。
cur.execute('''SELECT lex1.w1, lex2.w1 from x2
INNER JOIN lex as lex1 ON lex1.wID=x2.w1
INNER JOIN lex as lex2 ON lex2.wID=x2.w2
WHERE lex1.w1=“like” AND lex2.w1= “new” ''')
我不知道我做错了什么。
任何帮助都将不胜感激。
最佳答案
像这样定义x2表。
c.execute('''CREATE TABLE x2
(freq INT, w1 INT, w2 INT,
FOREIGN KEY(w1) REFERENCES lex(wID),
FOREIGN KEY(w2) REFERENCES lex(wID),
PRIMARY KEY(w1, w2) )''')
除了语义正确之外，这还创建了一个永久索引，可以大大加快查询速度。在不指定（w1，w2）对是表的主键的情况下，每次运行该查询时都必须临时重新创建该索引，这是一个昂贵的操作。
下面这样的代码可以用来重新定义一个表，而不需要重新导入所有内容。
c.execute('''
create table x2_new (
freq INT, w1 INT, w2 INT,
FOREIGN KEY(w1) REFERENCES lex(wID),
FOREIGN KEY(w2) REFERENCES lex(wID),
PRIMARY KEY(w1, w2) )
''')
c.execute('insert into x2_new select * from x2')
c.execute('drop table x2')
c.execute('alter table x2_new rename to x2')
conn.commit()
下面的代码应该加快插入速度。
blocksize = 100000
with open('/Users/.../lexicon.txt', "rb") as lex_file:
data = []
line_counter = 0
for line in lex_file:
data.append(line.strip().split('\t'))
line_counter += 1
if line_counter % blocksize == 0:
try:
c.executemany ('insert or replace into lex values (?, ?, ?, ?, ?)', data)
conn.commit()
except IndexError:
block_start = line_counter - blocksize + 1
print 'Lex error lines {}-{}'.format(block_start, line_counter)
conn.rollback()
finally:
data = []
with open('/Users/.../x2.txt', "rb") as x2_file:
data = []
line_counter = 0
for line in x2_file:
data.append(line.strip().replace('\x00','').replace('\xff\xfe','').split('\t'))
line_counter += 1
if line_counter % blocksize == 0:
try:
c.executemany('insert or replace into x2 values (?, ?, ?)', data)
conn.commit()
except IndexError:
block_start = line_counter - blocksize + 1
print 'x2 error lines {}-{}'.format(block_start, line_counter)
conn.rollback()
finally:
data = []