snorkel labeling functions.py

from snorkel.labeling import labeling_function
from textblob import TextBlob
import re

@labeling_function()
def lf_keyword_my(x):
    """Many spam comments talk about 'my channel', 'my video', etc."""
    return SPAM if "my" in x.text.lower() else ABSTAIN

@labeling_function()
def lf_regex_check_out(x):
    """Spam comments say 'check out my video', 'check it out', etc."""
    return SPAM if re.search(r"check.*out", x.text, flags=re.I) else ABSTAIN

@labeling_function()
def lf_regex_check_out(x):
    """Spam comments say 'check out my video', 'check it out', etc."""
    return SPAM if re.search(r"check.*out", x.text, flags=re.I) else ABSTAIN


@labeling_function()
def lf_textblob_polarity(x):
    """
    We use a third-party sentiment classification model, TextBlob.

    We combine this with the heuristic that non-spam comments are often positive.
    """
    return NOT_SPAM if TextBlob(x.text).sentiment.polarity > 0.3 else ABSTAIN