.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
d2l.DATA_HUB['time_machine'] = (d2l.DATA_URL + 'timemachine.txt',
'090b5e7e70c295757f55df93cb0a180b9691891a')
def read_time_machine(): #@save
"""将时间机器数据集加载到文本行的列表中"""
with open(d2l.download('time_machine'), 'r') as f:
lines = f.readlines()
return [re.sub('[^A-Za-z]+', ' ', line).strip().lower() for line in lines]
lines = read_time_machine()
print(f'# 文本总行数: {len(lines)}')
print(lines[0])
print(lines[10])
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
# 文本总行数: 3221
the time machine by h g wells
twinkled and his usually pale face was flushed and animated the
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
d2l.DATA_HUB['time_machine'] = (d2l.DATA_URL + 'timemachine.txt',
'090b5e7e70c295757f55df93cb0a180b9691891a')
def read_time_machine(): #@save
"""将时间机器数据集加载到文本行的列表中"""
with open(d2l.download('time_machine'), 'r') as f:
lines = f.readlines()
return [re.sub('[^A-Za-z]+', ' ', line).strip().lower() for line in lines]
lines = read_time_machine()
print(f'# 文本总行数: {len(lines)}')
print(lines[0])
print(lines[10])
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
Downloading ../data/timemachine.txt from http://d2l-data.s3-accelerate.amazonaws.com/timemachine.txt...
# 文本总行数: 3221
the time machine by h g wells
twinkled and his usually pale face was flushed and animated the
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
d2l.DATA_HUB['time_machine'] = (d2l.DATA_URL + 'timemachine.txt',
'090b5e7e70c295757f55df93cb0a180b9691891a')
def read_time_machine(): #@save
"""将时间机器数据集加载到文本行的列表中"""
with open(d2l.download('time_machine'), 'r') as f:
lines = f.readlines()
return [re.sub('[^A-Za-z]+', ' ', line).strip().lower() for line in lines]
lines = read_time_machine()
print(f'# 文本总行数: {len(lines)}')
print(lines[0])
print(lines[10])
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
# 文本总行数: 3221
the time machine by h g wells
twinkled and his usually pale face was flushed and animated the
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
d2l.DATA_HUB['time_machine'] = (d2l.DATA_URL + 'timemachine.txt',
'090b5e7e70c295757f55df93cb0a180b9691891a')
def read_time_machine(): #@save
"""将时间机器数据集加载到文本行的列表中"""
with open(d2l.download('time_machine'), 'r') as f:
lines = f.readlines()
return [re.sub('[^A-Za-z]+', ' ', line).strip().lower() for line in lines]
lines = read_time_machine()
print(f'# 文本总行数: {len(lines)}')
print(lines[0])
print(lines[10])
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
# 文本总行数: 3221
the time machine by h g wells
twinkled and his usually pale face was flushed and animated the
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def tokenize(lines, token='word'): #@save
"""将文本行拆分为单词或字符词元"""
if token == 'word':
return [line.split() for line in lines]
elif token == 'char':
return [list(line) for line in lines]
else:
print('错误：未知词元类型：' + token)
tokens = tokenize(lines)
for i in range(11):
print(tokens[i])
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
['the', 'time', 'machine', 'by', 'h', 'g', 'wells']
[]
[]
[]
[]
['i']
[]
[]
['the', 'time', 'traveller', 'for', 'so', 'it', 'will', 'be', 'convenient', 'to', 'speak', 'of', 'him']
['was', 'expounding', 'a', 'recondite', 'matter', 'to', 'us', 'his', 'grey', 'eyes', 'shone', 'and']
['twinkled', 'and', 'his', 'usually', 'pale', 'face', 'was', 'flushed', 'and', 'animated', 'the']
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def tokenize(lines, token='word'): #@save
"""将文本行拆分为单词或字符词元"""
if token == 'word':
return [line.split() for line in lines]
elif token == 'char':
return [list(line) for line in lines]
else:
print('错误：未知词元类型：' + token)
tokens = tokenize(lines)
for i in range(11):
print(tokens[i])
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
['the', 'time', 'machine', 'by', 'h', 'g', 'wells']
[]
[]
[]
[]
['i']
[]
[]
['the', 'time', 'traveller', 'for', 'so', 'it', 'will', 'be', 'convenient', 'to', 'speak', 'of', 'him']
['was', 'expounding', 'a', 'recondite', 'matter', 'to', 'us', 'his', 'grey', 'eyes', 'shone', 'and']
['twinkled', 'and', 'his', 'usually', 'pale', 'face', 'was', 'flushed', 'and', 'animated', 'the']
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def tokenize(lines, token='word'): #@save
"""将文本行拆分为单词或字符词元"""
if token == 'word':
return [line.split() for line in lines]
elif token == 'char':
return [list(line) for line in lines]
else:
print('错误：未知词元类型：' + token)
tokens = tokenize(lines)
for i in range(11):
print(tokens[i])
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
['the', 'time', 'machine', 'by', 'h', 'g', 'wells']
[]
[]
[]
[]
['i']
[]
[]
['the', 'time', 'traveller', 'for', 'so', 'it', 'will', 'be', 'convenient', 'to', 'speak', 'of', 'him']
['was', 'expounding', 'a', 'recondite', 'matter', 'to', 'us', 'his', 'grey', 'eyes', 'shone', 'and']
['twinkled', 'and', 'his', 'usually', 'pale', 'face', 'was', 'flushed', 'and', 'animated', 'the']
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def tokenize(lines, token='word'): #@save
"""将文本行拆分为单词或字符词元"""
if token == 'word':
return [line.split() for line in lines]
elif token == 'char':
return [list(line) for line in lines]
else:
print('错误：未知词元类型：' + token)
tokens = tokenize(lines)
for i in range(11):
print(tokens[i])
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
['the', 'time', 'machine', 'by', 'h', 'g', 'wells']
[]
[]
[]
[]
['i']
[]
[]
['the', 'time', 'traveller', 'for', 'so', 'it', 'will', 'be', 'convenient', 'to', 'speak', 'of', 'him']
['was', 'expounding', 'a', 'recondite', 'matter', 'to', 'us', 'his', 'grey', 'eyes', 'shone', 'and']
['twinkled', 'and', 'his', 'usually', 'pale', 'face', 'was', 'flushed', 'and', 'animated', 'the']
.. raw:: html
.. raw:: html