Upload usage-file.py
Browse files
how-to-tokenize-an-text-file-and-save-it/usage-file.py
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import nltk
|
2 |
+
from nltk.tokenize import word_tokenize
|
3 |
+
|
4 |
+
# load your data
|
5 |
+
with open('data.txt', 'r') as file:
|
6 |
+
data = file.read()
|
7 |
+
|
8 |
+
# tokenize the data
|
9 |
+
tokens = word_tokenize(data)
|
10 |
+
|
11 |
+
# save the tokenized data to a file
|
12 |
+
with open('tokenized_data.txt', 'w') as file:
|
13 |
+
for token in tokens:
|
14 |
+
file.write("%s\n" % token)
|