Naive-Bayes using library

.gitignore

@@ -6,3 +6,6 @@
 *.o
 .DS_Store
 .token
+
+env/
+geval/

bayes.py

@@ -0,0 +1,33 @@
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.preprocessing import LabelEncoder
+from sklearn.pipeline import Pipeline
+
+with open('train/in.tsv') as f:
+    data_train_X = f.readlines()
+
+with open('train/expected.tsv') as f:
+    data_train_Y = f.readlines()
+
+with open('dev-0/in.tsv') as f:
+    data_dev_X = f.readlines()
+
+with open('test-A/in.tsv') as f:
+    data_test_X = f.readlines()
+
+data_train_Y = LabelEncoder().fit_transform(data_train_Y)
+model = Pipeline(steps=[('tfidf', TfidfVectorizer()),('bayes', MultinomialNB())])
+
+clf = model.fit(data_train_X, data_train_Y)
+
+with open('train/out.tsv', 'w') as writer:
+    for result in clf.predict(data_train_X):
+        writer.write(str(result) + '\n')
+
+with open('dev-0/out.tsv', 'w') as writer:
+    for result in clf.predict(data_dev_X):
+        writer.write(str(result) + '\n')
+
+with open('test-A/out.tsv', 'w') as writer:
+    for result in clf.predict(data_test_X):
+        writer.write(str(result) + '\n')

requirements.txt

@@ -0,0 +1,10 @@
+joblib==1.0.1
+numpy==1.20.2
+pandas==1.2.4
+python-dateutil==2.8.1
+pytz==2021.1
+scikit-learn==0.24.2
+scipy==1.6.3
+six==1.16.0
+sklearn==0.0
+threadpoolctl==2.1.0