28 lines
747 B
Python
28 lines
747 B
Python
from sklearn.naive_bayes import GaussianNB
|
|
import pandas as pd
|
|
from sklearn.naive_bayes import MultinomialNB
|
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
|
|
|
r_in = './train/train.tsv'
|
|
|
|
r_ind_ev = './dev-0/in.tsv'
|
|
tsv_read = pd.read_table(r_in, error_bad_lines=False, sep='\t', header=None)
|
|
tsv_read_dev = pd.read_table(r_ind_ev, error_bad_lines=False, sep='\t', header=None)
|
|
|
|
y_train = tsv_read[0].values
|
|
X_train = tsv_read[1].values
|
|
X_dev = tsv_read_dev[0].values
|
|
|
|
vectorizer = TfidfVectorizer()
|
|
counts = vectorizer.fit_transform(X_train)
|
|
|
|
|
|
classifier = MultinomialNB()
|
|
classifier.fit(counts, y_train)
|
|
|
|
counts2 = vectorizer.transform(X_dev)
|
|
predictions = classifier.predict(counts2)
|
|
|
|
predictions.tofile("./dev-0/out.tsv", sep='\n')
|
|
|