If we have time should we look at the relative word frequencies?
I think it would look something like this:
For the positive words:
relative_frequencies = {word: count / total_words for word, count in word_counter.items()}
return relative_frequencies
For the negative words:
relative_frequencies = {word: count / total_words for word, count in negative_word_counter.items()}
return relative_frequencies
And then something like this:
(sentimentalORnegative)_word_relative_freq = {}
for gender in genders: (sentimentalORnegative)_word_relativefreq[gender] = analyze(sentimentalORnegative)_words_by_gender(data, gender)
Does this make sense? I would try to run it myself, but the code is not running on my laptop right now for some reason.
If we have time should we look at the relative word frequencies?
I think it would look something like this:
For the positive words: relative_frequencies = {word: count / total_words for word, count in word_counter.items()} return relative_frequencies
For the negative words: relative_frequencies = {word: count / total_words for word, count in negative_word_counter.items()} return relative_frequencies
And then something like this: (sentimentalORnegative)_word_relative_freq = {} for gender in genders: (sentimentalORnegative)_word_relativefreq[gender] = analyze(sentimentalORnegative)_words_by_gender(data, gender)
Does this make sense? I would try to run it myself, but the code is not running on my laptop right now for some reason.