26 lines
852 B
Python
26 lines
852 B
Python
from sklearn.naive_bayes import MultinomialNB
|
|
from sklearn.preprocessing import LabelEncoder
|
|
from sklearn.pipeline import Pipeline
|
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
|
import numpy as np
|
|
|
|
def getData(path):
|
|
with open(path) as source:
|
|
return source.readlines()
|
|
|
|
trainInData = getData('./train/in.tsv')
|
|
trainExpData = getData('./train/expected.tsv')
|
|
afterTransform = LabelEncoder().fit_transform(trainExpData)
|
|
pipeline = Pipeline(steps=[('tfidf', TfidfVectorizer()),('naive-bayes', MultinomialNB())])
|
|
|
|
model = pipeline.fit(trainInData, afterTransform)
|
|
|
|
def getResult(path):
|
|
dataToPredict = getData(path + 'in.tsv')
|
|
pred = model.predict(dataToPredict)
|
|
with open(path + "out.tsv", "w") as result:
|
|
for prediction in pred:
|
|
result.write(str(prediction) + '\n')
|
|
|
|
getResult('./dev-0/')
|
|
getResult('./test-A/') |