keyword example

keyword.py

# this model is the most naive one
# find the occurences of the keywords listed and consider them to be matched.
# TODO will be to apply a Bag of Words model or some sort and assign credit score

# read raw caption files
caption_data, metadata = next(load_caption_files(path_to_caption_file))                        
# combine captions by 10 seconds (i.e. make time blocks)
X = split_caption_to_X(caption_data)

keywords = ['caption', 'type=story', 'type=commercial']
model = KeywordSearch(keywords)

is_matched = model.predict(X)
matched_lines = self.X[is_matched]

# matched_lines is a boolean vector
# e.g. [True, False, False, False, ... True, ... False]