Execute for full train set

mian.py

@@ -0,0 +1,46 @@
+import csv
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LinearRegression
+from stop_words import get_stop_words
+import os
+import pandas as pd
+
+def read_train_file(inDirectory):
+    colnames = ['start_date', 'end_date', 'title', 'sort_title', 'data']
+    df_train = pd.read_csv(inDirectory, sep="\t", names=colnames)
+    return df_train
+
+def read_evaluate_file(inDirectory):
+    colnames = ['data']
+    df_evaluate = pd.read_csv(inDirectory, sep="\t", names=colnames, quoting=csv.QUOTE_NONE, error_bad_lines=False)
+    return df_evaluate
+
+def train_date_mean(df):
+    date_mean = (df['start_date'] + df['end_date']) / 2
+    return date_mean
+
+def linearRegresionTrain():
+    df = read_train_file('train/train.tsv')
+    date_mean_df = train_date_mean(df)
+    train_vectorized_corpus = vectorizer.fit_transform(df['data'])
+    reg.fit(train_vectorized_corpus, date_mean_df)
+
+def linearRegresionEvaluate(inDirectory, outDirectory):
+    df_evaluate = read_evaluate_file(inDirectory)
+    evaluate_vectorized_corpus = vectorizer.transform(df_evaluate['data'])
+    evaluate = reg.predict(evaluate_vectorized_corpus)
+    with open(outDirectory, 'w') as file:
+        for e in evaluate:
+            file.write("%f\n" % e)
+
+
+vectorizer = TfidfVectorizer(stop_words=get_stop_words('polish'))
+reg = LinearRegression()
+linearRegresionTrain()
+linearRegresionEvaluate('dev-0/in.tsv', 'dev-0/out.tsv')
+linearRegresionEvaluate('dev-1/in.tsv', 'dev-1/out.tsv')
+linearRegresionEvaluate('test-A/in.tsv', 'test-A/out.tsv')
+
+
+os.system("./geval -t dev-0")
+os.system("./geval -t dev-1")