Last active
September 7, 2020 19:54
-
-
Save josht-jpg/79d18578be4a11a57b10372f13b6d882 to your computer and use it in GitHub Desktop.
AdaBoost setup
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
notes_tokens = nltk.word_tokenize(notes) | |
crime_tokens = nltk.word_tokenize(crime) | |
idiot_tokens = nltk.word_tokenize(idiot) | |
possessed_tokens = nltk.word_tokenize(possessed) | |
brothers_tokens = nltk.word_tokenize(brothers) | |
notes_str = " ".join(notes_tokens) | |
notes_sentences = notes_str.split(".") | |
crime_str = " ".join(crime_tokens) | |
crime_sentences = crime_str.split(".") | |
idiot_str = " ".join(idiot_tokens) | |
idiot_sentences = idiot_str.split(".") | |
possessed_str = " ".join(possessed_tokens) | |
possessed_sentences = possessed_str.split(".") | |
brothers_str = " ".join(brothers_tokens) | |
brothers_sentences = brothers_str.split(".") | |
sentences = pd.Series(notes_sentences + crime_sentences + idiot_sentences \ | |
+ possessed_sentences + brothers_sentences) | |
sentences = sentences[sentences.apply(lambda x: len(x) > 1)] | |
np.random.seed(2020) | |
to_label_train = sentences.iloc[np.random.randint(0, len(sentences), 100)] | |
np.random.seed(42) | |
to_label_test = sentences.iloc[np.random.randint(0, len(sentences), 30)] | |
#In hindsight, I've realized there many cleaner alternatives to the above 5 lines. | |
#One of which would be to use Sklearn's train_test_split function. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment