[英]python - increase efficiency of large-file search by readlines(size)
我是Python新手,我目前正在使用Python 2.我有一些源文件,每個源文件都包含大量數據(大約1900萬行)。 它看起來如下:
apple \t N \t apple
n&apos
garden \t N \t garden
b\ta\md
great \t Adj \t great
nice \t Adj \t (unknown)
etc
我的任務是在每個文件的第3列搜索一些目標詞,並且每次在語料庫中找到目標詞時,必須將該詞前后的10個詞添加到多維詞典中。
編輯:應排除包含'&','\\'或字符串'(未知)'的行。
我嘗試使用readlines()和enumerate()來解決這個問題,如下面的代碼所示。 代碼執行它應該做的事情但顯然對源文件中提供的數據量不夠高效。
我知道readlines()或read()不應該用於大型數據集,因為它將整個文件加載到內存中。 然而,逐行讀取文件,我沒有設法使用枚舉方法來獲取目標詞之前和之后的10個單詞。 我也不能使用mmap,因為我沒有權限在該文件上使用它。
所以,我認為具有一定大小限制的readlines方法將是最有效的解決方案。 然而,為此,我不會做出一些錯誤,因為每次達到大小限制結束時,目標字不會被捕獲,因為代碼剛剛破壞了10個字?
def get_target_to_dict(file):
targets_dict = {}
with open(file) as f:
for line in f:
targets_dict[line.strip()] = {}
return targets_dict
targets_dict = get_target_to_dict('targets_uniq.txt')
# browse directory and process each file
# find the target words to include the 10 words before and after to the dictionary
# exclude lines starting with <,-,; to just have raw text
def get_co_occurence(path_file_dir, targets, results):
lines = []
for file in os.listdir(path_file_dir):
if file.startswith('corpus'):
path_file = os.path.join(path_file_dir, file)
with gzip.open(path_file) as corpusfile:
# PROBLEMATIC CODE HERE
# lines = corpusfile.readlines()
for line in corpusfile:
if re.match('[A-Z]|[a-z]', line):
if '(unknown)' in line:
continue
elif '\\' in line:
continue
elif '&' in line:
continue
lines.append(line)
for i, line in enumerate(lines):
line = line.strip()
if re.match('[A-Z][a-z]', line):
parts = line.split('\t')
lemma = parts[2]
if lemma in targets:
pos = parts[1]
if pos not in targets[lemma]:
targets[lemma][pos] = {}
counts = targets[lemma][pos]
context = []
# look at 10 previous lines
for j in range(max(0, i-10), i):
context.append(lines[j])
# look at the next 10 lines
for j in range(i+1, min(i+11, len(lines))):
context.append(lines[j])
# END OF PROBLEMATIC CODE
for context_line in context:
context_line = context_line.strip()
parts_context = context_line.split('\t')
context_lemma = parts_context[2]
if context_lemma not in counts:
counts[context_lemma] = {}
context_pos = parts_context[1]
if context_pos not in counts[context_lemma]:
counts[context_lemma][context_pos] = 0
counts[context_lemma][context_pos] += 1
csvwriter = csv.writer(results, delimiter='\t')
for k,v in targets.iteritems():
for k2,v2 in v.iteritems():
for k3,v3 in v2.iteritems():
for k4,v4 in v3.iteritems():
csvwriter.writerow([str(k), str(k2), str(k3), str(k4), str(v4)])
#print(str(k) + "\t" + str(k2) + "\t" + str(k3) + "\t" + str(k4) + "\t" + str(v4))
results = open('results_corpus.csv', 'wb')
word_occurrence = get_co_occurence(path_file_dir, targets_dict, results)
我復制整個代碼的部分是出於完整性的原因,因為它是一個函數的一部分,它從所有提取的信息中創建一個多維字典,然后將其寫入csv文件。
我真的很感激任何提示或建議使這個代碼更有效。
編輯我更正了代碼,因此它考慮了目標詞之前和之后的確切10個單詞
我的想法是創建一個緩沖區來存儲10行之前和另一個緩沖區存儲10行之后,當讀取文件時,它將被推入緩沖區之前,如果大小超過10則緩沖區將彈出
對於后緩沖區,我從文件迭代器1克隆另一個迭代器。 然后在循環內並行運行迭代器,使用克隆迭代器運行10次迭代以獲得10行之后。
這樣可以避免使用readlines()並將整個文件加載到內存中。 希望它在實際情況下適合您
編輯:如果第3列不包含'&','\\','(未知)'中的任何一個,則只填充之前的緩沖區。還要將split('\\ t')更改為split()所以它會照顧所有空格或制表符
import itertools
def get_co_occurence(path_file_dir, targets, results):
excluded_words = ['&', '\\', '(unknown)'] # modify excluded words here
for file in os.listdir(path_file_dir):
if file.startswith('testset'):
path_file = os.path.join(path_file_dir, file)
with open(path_file) as corpusfile:
# CHANGED CODE HERE
before_buf = [] # buffer to store before 10 lines
after_buf = [] # buffer to store after 10 lines
corpusfile, corpusfile_clone = itertools.tee(corpusfile) # clone file iterator to access next 10 lines
for line in corpusfile:
line = line.strip()
if re.match('[A-Z]|[a-z]', line):
parts = line.split()
lemma = parts[2]
# before buffer handling, fill buffer excluded line contains any of excluded words
if not any(w in line for w in excluded_words):
before_buf.append(line) # append to before buffer
if len(before_buf)>11:
before_buf.pop(0) # keep the buffer at size 10
# next buffer handling
while len(after_buf)<=10:
try:
after = next(corpusfile_clone) # advance 1 iterator
after_lemma = ''
after_tmp = after.split()
if re.match('[A-Z]|[a-z]', after) and len(after_tmp)>2:
after_lemma = after_tmp[2]
except StopIteration:
break # copy iterator will exhaust 1st coz its 10 iteration ahead
if after_lemma and not any(w in after for w in excluded_words):
after_buf.append(after) # append to buffer
# print 'after',z,after, ' - ',after_lemma
if (after_buf and line in after_buf[0]):
after_buf.pop(0) # pop off one ready for next
if lemma in targets:
pos = parts[1]
if pos not in targets[lemma]:
targets[lemma][pos] = {}
counts = targets[lemma][pos]
# context = []
# look at 10 previous lines
context= before_buf[:-1] # minus out current line
# look at the next 10 lines
context.extend(after_buf)
# END OF CHANGED CODE
# CONTINUE YOUR STUFF HERE WITH CONTEXT
用Python 3.5編寫的功能替代方案。 我簡化了你的例子,雙方只拿了5個字。 關於垃圾值過濾還有其他簡化,但它只需要稍作修改。 我將使用PyPI中的包fn
來使這個功能代碼更自然地閱讀。
from typing import List, Tuple
from itertools import groupby, filterfalse
from fn import F
首先我們需要提取列:
def getcol3(line: str) -> str:
return line.split("\t")[2]
然后我們需要將行拆分為由謂詞分隔的塊:
TARGET_WORDS = {"target1", "target2"}
# this is out predicate
def istarget(word: str) -> bool:
return word in TARGET_WORDS
讓我們過濾垃圾並寫一個函數來取最后一個和前5個單詞:
def isjunk(word: str) -> bool:
return word == "(unknown)"
def first_and_last(words: List[str]) -> (List[str], List[str]):
first = words[:5]
last = words[-5:]
return first, last
現在,讓我們來看看小組:
words = (F() >> (map, str.strip) >> (filter, bool) >> (map, getcol3) >> (filterfalse, isjunk))(lines)
groups = groupby(words, istarget)
現在,處理組
def is_target_group(group: Tuple[str, List[str]]) -> bool:
return istarget(group[0])
def unpack_word_group(group: Tuple[str, List[str]]) -> List[str]:
return [*group[1]]
def unpack_target_group(group: Tuple[str, List[str]]) -> List[str]:
return [group[0]]
def process_group(group: Tuple[str, List[str]]):
return (unpack_target_group(group) if is_target_group(group)
else first_and_last(unpack_word_group(group)))
最后的步驟是:
words = list(map(process_group, groups))
PS
這是我的測試用例:
from io import StringIO
buffer = """
_\t_\tword
_\t_\tword
_\t_\tword
_\t_\t(unknown)
_\t_\tword
_\t_\tword
_\t_\ttarget1
_\t_\tword
_\t_\t(unknown)
_\t_\tword
_\t_\tword
_\t_\tword
_\t_\ttarget2
_\t_\tword
_\t_\t(unknown)
_\t_\tword
_\t_\tword
_\t_\tword
_\t_\t(unknown)
_\t_\tword
_\t_\tword
_\t_\ttarget1
_\t_\tword
_\t_\t(unknown)
_\t_\tword
_\t_\tword
_\t_\tword
"""
# this simulates an opened file
lines = StringIO(buffer)
給定此文件,您將獲得此輸出:
[(['word', 'word', 'word', 'word', 'word'],
['word', 'word', 'word', 'word', 'word']),
(['target1'], ['target1']),
(['word', 'word', 'word', 'word'], ['word', 'word', 'word', 'word']),
(['target2'], ['target2']),
(['word', 'word', 'word', 'word', 'word'],
['word', 'word', 'word', 'word', 'word']),
(['target1'], ['target1']),
(['word', 'word', 'word', 'word'], ['word', 'word', 'word', 'word'])]
從這里你可以刪除前5個單詞和最后5個單詞。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.