Spaces:
Running
Running
Delete maven_text_preprocessing.py
Browse files- maven_text_preprocessing.py +0 -27
maven_text_preprocessing.py
DELETED
|
@@ -1,27 +0,0 @@
|
|
| 1 |
-
# import necessary libraries
|
| 2 |
-
import pandas as pd
|
| 3 |
-
import spacy
|
| 4 |
-
|
| 5 |
-
# download the spacy model
|
| 6 |
-
nlp = spacy.load("en_core_web_sm")
|
| 7 |
-
|
| 8 |
-
# helper functions from text preprocessing section
|
| 9 |
-
def lower_replace(series):
|
| 10 |
-
output = series.str.lower()
|
| 11 |
-
output = output.str.replace(r'\[.*?\]', '', regex=True)
|
| 12 |
-
output = output.str.replace(r'[^\w\s]', '', regex=True)
|
| 13 |
-
return output
|
| 14 |
-
|
| 15 |
-
def token_lemma_nonstop(text):
|
| 16 |
-
doc = nlp(text)
|
| 17 |
-
output = [token.lemma_ for token in doc if not token.is_stop]
|
| 18 |
-
return ' '.join(output)
|
| 19 |
-
|
| 20 |
-
def clean_and_normalize(series):
|
| 21 |
-
output = lower_replace(series)
|
| 22 |
-
output = output.apply(token_lemma_nonstop)
|
| 23 |
-
return output
|
| 24 |
-
|
| 25 |
-
# allow command-line execution
|
| 26 |
-
if __name__ == "__main__":
|
| 27 |
-
print("Text preprocessing module ready to use.")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|