31 lines
1.1 KiB
Python
31 lines
1.1 KiB
Python
import numpy as np
|
|
from sklearn import preprocessing
|
|
from sklearn.naive_bayes import GaussianNB
|
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
|
le=preprocessing.LabelEncoder()
|
|
|
|
with open("train/in.tsv") as f:
|
|
data = f.readlines()
|
|
vectorizer = TfidfVectorizer(ngram_range=(1,2), use_idf = False)
|
|
vectorizer = TfidfVectorizer()
|
|
x = vectorizer.fit_transform(data)
|
|
X=x.toarray()
|
|
with open("train/expected.tsv") as ff:
|
|
Y = ff.readlines()
|
|
Y=le.fit_transform(Y)
|
|
with open("dev-0/in.tsv") as d:
|
|
fil = d.readlines()
|
|
vectorizer = TfidfVectorizer(ngram_range=(1,2), use_idf = False)
|
|
vectorizer = TfidfVectorizer()
|
|
r=vectorizer.fit_transform(fil)
|
|
r=r.toarray()
|
|
r=r.reshape(-1,1)
|
|
gnb = GaussianNB()
|
|
model=gnb.fit(X, Y)
|
|
y_pred=model.predict(X)
|
|
print(y_pred)
|
|
y_pred=np.array(y_pred)
|
|
t=np.array2string(y_pred, precision=2, separator='\n',suppress_small=True)
|
|
f = open("dev-0/out.tsv", "a")
|
|
f.write(t)
|