Commit
•
098aa7e
1
Parent(s):
a276bc9
Update README.md
Browse files
README.md
CHANGED
@@ -75,6 +75,7 @@ class TextProcessor:
|
|
75 |
self.stripped_BIO_TAGS = []
|
76 |
|
77 |
def read_file(self):
|
|
|
78 |
with open(self.filename, 'r') as f:
|
79 |
text = f.read()
|
80 |
self.sentences = self.sent_detector.tokenize(text.strip())
|
@@ -157,7 +158,7 @@ class TextProcessor:
|
|
157 |
output_file.write("TOKEN\tPERS\tLOCS\n"+"\n".join(["\t".join(x) for x in self.stripped_BIO_TAGS]))
|
158 |
|
159 |
# Usage:
|
160 |
-
processor = TextProcessor('
|
161 |
processor.read_file()
|
162 |
processor.process_sentences()
|
163 |
processor.apply_model(pipe)
|
|
|
75 |
self.stripped_BIO_TAGS = []
|
76 |
|
77 |
def read_file(self):
|
78 |
+
#Reading a txt file with one document per line.
|
79 |
with open(self.filename, 'r') as f:
|
80 |
text = f.read()
|
81 |
self.sentences = self.sent_detector.tokenize(text.strip())
|
|
|
158 |
output_file.write("TOKEN\tPERS\tLOCS\n"+"\n".join(["\t".join(x) for x in self.stripped_BIO_TAGS]))
|
159 |
|
160 |
# Usage:
|
161 |
+
processor = TextProcessor('my_docs_file.txt')
|
162 |
processor.read_file()
|
163 |
processor.process_sentences()
|
164 |
processor.apply_model(pipe)
|