File size: 911 Bytes
0601dad
 
 
 
74f30e9
 
0601dad
 
 
 
 
 
 
 
74f30e9
 
 
 
 
 
 
 
 
 
 
 
 
0601dad
 
 
 
 
 
 
 
 
74f30e9
fb1c532
74f30e9
fb1c532
74f30e9
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
"""
    utils.py - Utility functions for the project.
"""


def postprocess(text: str):
    """
    postprocess - remove common values in scraped dataset

    Args:
        text (str): the text to postprocess
    """

    replacements = {
        "ENA": "<COMPANY>",
        "Enron": "<COMPANY>",
        "Enron Corporation": "<COMPANY>",
        "Sony Pictures Entertainment": "<COMPANY>",
        "Columbia Pictures": "<COMPANY>",
        "Sony": "<COMPANY>",
        "Columbia": "<COMPANY>",
        "Hillary": "Jane",
        "Clinton": "Smith",
        "Amy": "Jane",
        "Sara": "Jane",
        "Harambe": "Jane",
        "Pascal": "<PERSON>",
    }

    # replace common values, also check lowercase
    for k, v in replacements.items():
        text = text.replace(k, v)
        text = text.replace(k.lower(), v)

    return text


def clear(**kwargs):
    """for use with buttons"""

    return ""