30 lines
785 B
Python
30 lines
785 B
Python
|
import numpy as np
|
||
|
|
from sklearn.preprocessing import LabelEncoder
|
||
|
|
from sklearn.naive_bayes import MultinomialNB
|
||
|
|
from sklearn.pipeline import make_pipeline
|
||
|
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
||
|
|
|
||
|
|
with open("train/in.tsv") as f:
|
||
|
|
x_train = f.readlines()
|
||
|
|
|
||
|
|
with open("train/expected.tsv") as f:
|
||
|
|
y_train = f.readlines()
|
||
|
|
|
||
|
|
y_train = LabelEncoder().fit_transform(y_train)
|
||
|
|
|
||
|
|
pipeline = make_pipeline(TfidfVectorizer(),MultinomialNB())
|
||
|
|
|
||
|
|
model = pipeline.fit(x_train, y_train)
|
||
|
|
|
||
|
|
with open("dev-0/in.tsv") as f:
|
||
|
|
x_dev = f.readlines()
|
||
|
|
|
||
|
|
prediction = model.predict(x_dev)
|
||
|
|
np.savetxt("dev-0/out.tsv", prediction, fmt='%d')
|
||
|
|
|
||
|
|
with open("test-A/in.tsv") as f:
|
||
|
|
x_test = f.readlines()
|
||
|
|
|
||
|
|
prediction = model.predict(x_test)
|
||
|
|
np.savetxt("test-A/out.tsv", prediction, fmt='%d')
|