s444476 add solution

run.py

@@ -0,0 +1,36 @@
+import pandas as pd
+from sklearn.naive_bayes import GaussianNB
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+print("Wczytywanie zbioru treningowego")
+#, error_bad_lines=False
+train = pd.read_csv("train/train.tsv", sep='\t', header=None)
+
+# print(train)
+# train = train.dropna()
+X_train = train[1]
+Y_train = train[0]
+print(len(X_train))
+print(len(Y_train))
+
+print("Wczytywanie pliku do predykcji")
+pred_x = []
+with open("dev-0/in.tsv", encoding='utf-8') as f:
+    for line in f:
+        pred_x.append(line)
+
+print("Wektoryzacja")
+vectorizer = TfidfVectorizer()
+X_train = vectorizer.fit_transform(X_train)
+pred_x = vectorizer.transform(pred_x)
+
+
+print("Uczenie modelu")
+model = GaussianNB()
+model.fit(X_train.toarray(), Y_train)
+
+print("Predykcja wyników")
+pred_y = model.predict(pred_x.toarray())
+
+print("Zapis do pliku")
+pd.DataFrame(pred_y).to_csv("dev-0/out.tsv", header=False, index=None)