Update README.md
Browse files
README.md
CHANGED
@@ -5,7 +5,14 @@ tags:
|
|
5 |
language:
|
6 |
- en
|
7 |
widget:
|
8 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
datasets:
|
10 |
- sagard21/autotrain-data-code-explainer
|
11 |
co2_eq_emissions:
|
|
|
5 |
language:
|
6 |
- en
|
7 |
widget:
|
8 |
+
- text: >
|
9 |
+
def preprocess(text: str) -> str:
|
10 |
+
text = str(text)
|
11 |
+
text = text.replace('\\n', ' ')
|
12 |
+
tokenized_text = text.split(' ')
|
13 |
+
preprocessed_text = " ".join([token for token in tokenized_text if token])
|
14 |
+
|
15 |
+
return preprocessed_text
|
16 |
datasets:
|
17 |
- sagard21/autotrain-data-code-explainer
|
18 |
co2_eq_emissions:
|