这是 Python 3 的 COPY FROM 的二进制等效项:
from io import BytesIO
from struct import pack
import psycopg2
# Two rows of data; "id" is not in the upstream data source
# Columns: node, ts, val1, val2
data = [(23253, 342, -15.336734, 2494627.949375),
(23256, 348, 43.23524, 2494827.949375)]
conn = psycopg2.connect("dbname=mydb user=postgres")
curs = conn.cursor()
# Determine starting value for sequence
curs.execute("SELECT nextval('num_data_id_seq')")
id_seq = curs.fetchone()[0]
# Make a binary file object for COPY FROM
cpy = BytesIO()
# 11-byte signature, no flags, no header extension
cpy.write(pack('!11sii', b'PGCOPY\n\377\r\n\0', 0, 0))
# Columns: id, node, ts, val1, val2
# Zip: (column position, format, size)
row_format = list(zip(range(-1, 4),
('i', 'i', 'h', 'f', 'd'),
( 4, 4, 2, 4, 8 )))
for row in data:
# Number of columns/fields (always 5)
cpy.write(pack('!h', 5))
for col, fmt, size in row_format:
value = (id_seq if col == -1 else row[col])
cpy.write(pack('!i' + fmt, size, value))
id_seq += 1 # manually increment sequence outside of database
# File trailer
cpy.write(pack('!h', -1))
# Copy data to database
cpy.seek(0)
curs.copy_expert("COPY num_data FROM STDIN WITH BINARY", cpy)
# Update sequence on database
curs.execute("SELECT setval('num_data_id_seq', %s, false)", (id_seq,))
conn.commit()
更新
我重写了上述编写 COPY 文件的方法。我在 Python 中的数据位于 NumPy 数组中,因此使用这些是有意义的。下面是一个例子data 有 1M 行,7 列:
import psycopg2
import numpy as np
from struct import pack
from io import BytesIO
from datetime import datetime
conn = psycopg2.connect("dbname=mydb user=postgres")
curs = conn.cursor()
# NumPy record array
shape = (7, 2000, 500)
print('Generating data with %i rows, %i columns' % (shape[1]*shape[2], shape[0]))
dtype = ([('id', 'i4'), ('node', 'i4'), ('ts', 'i2')] +
[('s' + str(x), 'f4') for x in range(shape[0])])
data = np.empty(shape[1]*shape[2], dtype)
data['id'] = np.arange(shape[1]*shape[2]) + 1
data['node'] = np.tile(np.arange(shape[1]) + 1, shape[2])
data['ts'] = np.repeat(np.arange(shape[2]) + 1, shape[1])
data['s0'] = np.random.rand(shape[1]*shape[2]) * 100
prv = 's0'
for nxt in data.dtype.names[4:]:
data[nxt] = data[prv] + np.random.rand(shape[1]*shape[2]) * 10
prv = nxt
在我的数据库中,我有两个看起来像这样的表:
CREATE TABLE num_data_binary
(
id integer PRIMARY KEY,
node integer NOT NULL,
ts smallint NOT NULL,
s0 real,
s1 real,
s2 real,
s3 real,
s4 real,
s5 real,
s6 real
) WITH (OIDS=FALSE);
还有另一个名为num_data_text的类似表。
这里有一些简单的辅助函数,通过使用 NumPy 记录数组中的信息为 COPY(文本和二进制格式)准备数据:
def prepare_text(dat):
cpy = BytesIO()
for row in dat:
cpy.write('\t'.join([repr(x) for x in row]) + '\n')
return(cpy)
def prepare_binary(dat):
pgcopy_dtype = [('num_fields','>i2')]
for field, dtype in dat.dtype.descr:
pgcopy_dtype += [(field + '_length', '>i4'),
(field, dtype.replace('<', '>'))]
pgcopy = np.empty(dat.shape, pgcopy_dtype)
pgcopy['num_fields'] = len(dat.dtype)
for i in range(len(dat.dtype)):
field = dat.dtype.names[i]
pgcopy[field + '_length'] = dat.dtype[i].alignment
pgcopy[field] = dat[field]
cpy = BytesIO()
cpy.write(pack('!11sii', b'PGCOPY\n\377\r\n\0', 0, 0))
cpy.write(pgcopy.tostring()) # all rows
cpy.write(pack('!h', -1)) # file trailer
return(cpy)
这就是我使用辅助函数对两种 COPY 格式方法进行基准测试的方式:
def time_pgcopy(dat, table, binary):
print('Processing copy object for ' + table)
tstart = datetime.now()
if binary:
cpy = prepare_binary(dat)
else: # text
cpy = prepare_text(dat)
tendw = datetime.now()
print('Copy object prepared in ' + str(tendw - tstart) + '; ' +
str(cpy.tell()) + ' bytes; transfering to database')
cpy.seek(0)
if binary:
curs.copy_expert('COPY ' + table + ' FROM STDIN WITH BINARY', cpy)
else: # text
curs.copy_from(cpy, table)
conn.commit()
tend = datetime.now()
print('Database copy time: ' + str(tend - tendw))
print(' Total time: ' + str(tend - tstart))
return
time_pgcopy(data, 'num_data_text', binary=False)
time_pgcopy(data, 'num_data_binary', binary=True)
这是最后两个time_pgcopy 命令的输出:
Processing copy object for num_data_text
Copy object prepared in 0:01:15.288695; 84355016 bytes; transfering to database
Database copy time: 0:00:37.929166
Total time: 0:01:53.217861
Processing copy object for num_data_binary
Copy object prepared in 0:00:01.296143; 80000021 bytes; transfering to database
Database copy time: 0:00:23.325952
Total time: 0:00:24.622095
因此,使用二进制方法,NumPy → 文件和文件 → 数据库步骤都更快。明显的区别在于 Python 如何准备 COPY 文件,这对于文本来说真的很慢。一般来说,二进制格式作为该模式的文本格式在 2/3 的时间内加载到数据库中。
最后,我比较了数据库中两个表中的值,看看数字是否不同。大约 1.46% 的行对列 s0 具有不同的值,而对于 s6,这一比例增加到 6.17%(可能与我使用的随机方法有关)。所有 70M 32 位浮点值之间的非零绝对差值介于 9.3132257e-010 和 7.6293945e-006 之间。文本和二进制加载方法之间的这些微小差异是由于文本格式方法所需的浮点→文本→浮点转换的精度损失。