s444501

run.py

@@ -0,0 +1,37 @@
+import csv
+from naivebayes import NaiveBayesTextClassifier
+from spacy.lang.en.stop_words import STOP_WORDS
+
+# Dane wejściowe rozpakowane ręcznie
+with open('train/in.tsv', 'r', encoding='utf8') as file:
+    reader = csv.reader(file, delimiter='\t')
+    train_in = [line[0] for line in reader]
+
+with open('train/expected.tsv', 'r', encoding='utf8') as file:
+    reader = csv.reader(file, delimiter='\t')
+    train_exp = [int(line[0]) for line in reader]
+
+with open('dev-0/in.tsv', 'r', encoding='utf8') as file:
+    reader = csv.reader(file, delimiter='\t')
+    dev_in = [line[0] for line in reader]
+
+with open('test-A/in.tsv', 'r', encoding='utf8') as file:
+    reader = csv.reader(file, delimiter='\t')
+    test_in = [line[0] for line in reader]
+
+# -------------------------------------------------------------------------------------------------------------------- #
+
+#CUTOFF = 289541 // 12
+CUTOFF = 16000
+classifier = NaiveBayesTextClassifier([0, 1], stop_words=STOP_WORDS)
+classifier.train(train_in[:CUTOFF], train_exp[:CUTOFF])
+dev_out = classifier.classify(dev_in)
+
+with open('dev-0/out.tsv', 'w') as file:
+    for x in dev_out:
+        file.write(str(x) + '\n')
+
+test_out = classifier.classify(test_in)
+with open('test-A/out.tsv', 'w') as file:
+    for x in test_out:
+        file.write(str(x) + '\n')