naive bayes

bayes.py

@@ -0,0 +1,30 @@
+import numpy as np
+import pandas as pd
+import gzip
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.feature_extraction.text import CountVectorizer
+
+bayes = MultinomialNB()
+vec_q = CountVectorizer()
+
+with gzip.open('./train/train.tsv.gz', 'rb') as f:
+    train = pd.read_csv(f, error_bad_lines=False, header=None, sep="\t")
+dev = pd.read_csv("./dev-0/in.tsv", error_bad_lines=False, header=None, sep="\t")
+test = pd.read_csv("./test-A/in.tsv", error_bad_lines=False, header=None, sep="\t")
+
+# model
+X_train, y_train = train[0].astype(str).tolist(), train[1].astype(str).tolist()
+y_train=vec_q.fit_transform(y_train)
+bayes.fit(y_train, X_train)
+
+# dev 
+X_dev = dev[0].astype(str).tolist()
+y_dev = vec_q.transform(X_dev)
+dev_pred = bayes.predict(y_dev)
+pd.DataFrame(dev_pred).to_csv('./dev-0/out.tsv', sep='\t', index=False, header=False)
+
+# test
+X_test = train[0].astype(str).tolist()
+y_test = vec_q.transform(X_test)
+test_pred = bayes.predict(y_test)
+pd.DataFrame(test_pred).to_csv('./test-A/out.tsv', sep='\t', index=False, header=False)