Add solution

run.py

@@ -0,0 +1,61 @@
+import pandas as pd
+import csv
+from statistics import mean
+from sklearn.linear_model import LinearRegression
+from sklearn.feature_extraction.text import TfidfVectorizer
+from spacy.lang.pl.stop_words import STOP_WORDS as pl_stop
+
+
+def write_file(fname, data):
+    with open(fname, 'w', newline='') as f:
+        tsv_output = csv.writer(f, delimiter='\n')
+        tsv_output.writerow(data)
+
+
+def get_data(fname):
+    with open(fname, 'r', encoding='utf8') as file:
+        return file.readlines()
+
+
+def preprocess_year(data, colnames):
+    return data[colnames].apply(lambda x: round(mean(x)), axis=1)
+
+
+def vectorize(data):
+    vectorizer = TfidfVectorizer(lowercase=True, stop_words=pl_stop)
+
+    vectorizer.fit(data['text'].to_numpy().ravel())
+    return vectorizer
+
+
+def train_model(data, vec):
+    model = LinearRegression()
+    model.fit(vec, data['year_avg'])
+
+    return model
+
+
+def predict_and_save(folder_name, model, vectorizer):
+    test_x = pd.DataFrame(get_data(f'{folder_name}/in.tsv'))
+    
+    test_tfidfs = vectorizer.transform(test_x[0].to_numpy().ravel())
+    predicted = model.predict(test_tfidfs)
+
+    write_file(f'{folder_name}/out.tsv', predicted)
+
+
+def main():
+    train = pd.read_csv('train/train.tsv.xz', sep='\t', nrows=50000, header=None, names=['begin', 'end', 'title_norm', 'symbol', 'text'])
+    vectorizer = vectorize(train)
+    tfidfs = vectorizer.transform(train['text'].to_numpy().ravel())
+
+    # Preprocessing
+    train['year_avg'] = preprocess_year(train, ['begin', 'end'])
+    model = train_model(train, tfidfs)
+
+    predict_and_save('test-A', model, vectorizer)
+    predict_and_save('dev-0', model, vectorizer)
+    predict_and_save('dev-1', model, vectorizer)
+
+
+main()