478841

run.py

@@ -0,0 +1,42 @@
+import pandas as pd
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+
+# * Training data loading
+with open('train/in.tsv', 'r', encoding='utf-8') as f:
+    x_train = pd.DataFrame(f.readlines(), columns=['text'])
+y_train = pd.read_csv('train/expected.tsv', sep='\t',
+                      names=['paranormal'], encoding='utf-8')
+# *Validation data loading
+with open('dev-0/in.tsv', 'r', encoding='utf-8') as f:
+    x_dev = pd.DataFrame(f.readlines(), columns=['text'])
+# * Test data loading
+with open('test-A/in.tsv', 'r', encoding='utf-8') as f:
+    x_test = pd.DataFrame(f.readlines(), columns=['text'])
+
+# * Training data preparation
+tfidf_vectorizer = TfidfVectorizer(max_df=0.95, max_features=500)
+x_train_vectorized = tfidf_vectorizer.fit_transform(
+    x_train['text'].values)
+
+# * Model training
+mnb_model = MultinomialNB().fit(x_train_vectorized, y_train.values.ravel())
+
+# * Validation data preparation
+x_dev_prepared = tfidf_vectorizer.transform(x_dev['text'].values)
+# * Validation data predictions
+predictions = mnb_model.predict(x_dev_prepared)
+# * Validation predicitons saving
+with open('dev-0/out.tsv', 'w') as f:
+    for pred in predictions:
+        f.write(f'{pred}\n')
+
+# * Test data preparation
+x_test_vectorized = tfidf_vectorizer.transform(x_test['text'].values)
+# * Test data predictions
+predictions = mnb_model.predict(x_test_vectorized)
+# * Test predictions saving
+with open('test-A/out.tsv', 'w') as f:
+    for pred in predictions:
+        f.write(f'{pred}\n')