我有以下代碼：
import re
def get_filename():
"""gets the file"""
filename = input("Please enter filename: ")
return filename
def get_words_from_file(filename):
"""getting the data and printing it word by word"""
infile = open(filename, 'r', encoding='utf-8')
outfile = infile.read().splitlines()
words = []
reading = False
for let in outfile:
if let.startswith("*** START OF")and reading == False:
reading = True
elif let.startswith("*** END OF SYNTHETIC TEST CASE ***") or let.startswith("*** END"):
return words
elif reading:
let = let.lower()
words.extend(re.findall("[a-z] [-'][a-z] |[a-z] [']?|[a-z] ", let))
return words
def calculate(words):
"""gjhwjghwg2"""
all_times = []
max_word_length = 0
number_of_words = len(words)
average = sum(len(word) for word in words) / number_of_words
for word in words:
if len(word)>max_word_length:
max_word_length=len(word)
frequency = {word: 0 for word in words}
for word in words:
frequency[word] = 1
max_frequency = max(frequency.values())
result = (number_of_words, average, max_word_length, max_frequency)
return result
def get_frequency(words):
"""ghjhgwejhgwjgw"""
len_count = []
frequency_1 = {word: 0 for word in words}
for word in words:
frequency_1[word] = 1
answer = (frequency_1, len_count)
return answer
def print_results(stats_tuple, lengthy):
"""calculate the goods"""
(frequency_1, len_count) = lengthy
(number_of_words, average, max_word_length, max_frequency) = stats_tuple
print("")
print("Word summary (all words):")
print(" Number of words = {0}".format(number_of_words))
print(" Average word length = {:.2f}".format(average))
print(" Maximum word length = {0}".format(max_word_length))
print(" Maximum frequency = {0}".format(max_frequency))
print("")
print(" Len Freq")
for word_len in range(1, max(len_count) 1):
print(f'{frequency_1}\t{len_count.get(frequency_1, 0)}')
def main():
"""ghkghwgjkwhgw"""
filename = get_filename()
data = get_words_from_file(filename)
stats = calculate(data)
lengthy = get_frequency(data)
print_results(stats, lengthy)
main()
在不匯入任何其他內容的情況下，我將如何制作一個列印長度和頻率的表格。
例如：在帶有“a blah ba ba”文本的檔案中，它將列印：
Len Freq
1 1
2 2
3 0
4 1
讓我感到困惑的是如何將所有單詞的長度加在一起，我應該用所有相同長度的單詞制作一個新串列然后計算該串列的長度，還是有更好的方法來做到這一點。
uj5u.com熱心網友回復：
您可以使用模塊中Counter的a 。collections然后回圈從 1 到最大計數的長度。如果 counts 字典中不存在長度，則寫入0，否則寫入相應的值。
from collections import Counter
filename = 'test.txt'
with open(filename) as fin:
words = fin.read().split()
counts = Counter(len(word) for word in words)
print('Len Freq')
for length in range(1, max(counts.keys()) 1):
print(f'{length:4d} {counts.get(length, 0):5d}')
如果輸入檔案包括：
a blah ba ba
那么這給出了：
Len Freq
1 1
2 2
3 0
4 1
請注意，max(counts.keys())為清楚起見，以這種方式撰寫，但max(counts)可以改為使用（因為如果您迭代字典，就像max這里所做的那樣 - 并且Counter物件本質上是字典 - 然后您迭代它的鍵）。
此示例假設您有一個可以存盤在記憶體中的相對較小的檔案。如果您有一個更大的檔案，那么您可以執行以下操作，以避免這樣做：
from collections import Counter
filename = 'test.txt'
def iter_lengths(filename):
with open(filename) as fin:
for line in fin:
for word in line.split():
yield len(word)
counts = Counter(iter_lengths(filename))
print('Len Freq')
for length in range(1, max(counts) 1):
print(f'{length:4d} {counts.get(length, 0):5d}')
uj5u.com熱心網友回復：
len_count = {}
with open(filename, "r") as file:
for line in file:
for word in line.split():
word_len = len(word)
if not word_len in len_count:
len_count[word_len] = 1
else:
len_count[word_len] = 1
然后你可以列印兩列：
print("Len\tFreq")
for word_len in range(1, max(len_count) 1):
print(f'{word_len}\t{len_count.get(word_len, 0)}')
編輯：處理空檔案：
max_len_count = 0 if not len_count else max(len_count)
for word_len in range(1, max_len_count 1):
print(f'{word_len}\t{len_count.get(word_len, 0)}')
轉載請註明出處，本文鏈接：https://www.uj5u.com/net/483061.html