39 lines
1.3 KiB
Python
39 lines
1.3 KiB
Python
import gensim as gensim
|
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
|
from sklearn.naive_bayes import GaussianNB, MultinomialNB
|
|
from stop_words import get_stop_words
|
|
import os
|
|
import pandas as pd
|
|
|
|
def read_train_file(inDirectory):
|
|
colnames = ['Y', 'X']
|
|
df_train = pd.read_csv(inDirectory, sep="\t", names=colnames)
|
|
return df_train
|
|
|
|
def read_evaluate_file(inDirectory):
|
|
colnames = ['X']
|
|
df_evaulate = pd.read_csv(inDirectory, sep="\n", names=colnames)
|
|
return df_evaulate
|
|
|
|
def naivBayersWithTFIDFTrain(inDirectory):
|
|
df_train = read_train_file(inDirectory)
|
|
train_vectorized_corpus = vectorizer.fit_transform(df_train['X'])
|
|
gnb.fit(train_vectorized_corpus, df_train['Y'])
|
|
|
|
def naivBayersWithTFIDFEvaluate(inDirectory, outDirectory):
|
|
df_evaluate = read_evaluate_file(inDirectory)
|
|
evaluate_vectorized_corpus = vectorizer.transform(df_evaluate['X'])
|
|
evaluate = gnb.predict(evaluate_vectorized_corpus)
|
|
with open(outDirectory, 'w') as file:
|
|
for e in evaluate:
|
|
file.write("%i\n" % e)
|
|
|
|
vectorizer = TfidfVectorizer(stop_words=get_stop_words('polish'))
|
|
gnb = MultinomialNB()
|
|
|
|
naivBayersWithTFIDFTrain("train/train.tsv")
|
|
naivBayersWithTFIDFEvaluate("dev-0/in.tsv", "dev-0/out.tsv")
|
|
naivBayersWithTFIDFEvaluate("test-A/in.tsv", "test-A/out.tsv")
|
|
|
|
|
|
os.system("./geval -t dev-0") |