s444421

run.py

@@ -0,0 +1,96 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[59]:
+
+
+import pandas as pd
+from sklearn.linear_model import LinearRegression
+from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
+from sklearn.metrics import mean_squared_error
+from sklearn.pipeline import make_pipeline
+
+
+# In[60]:
+
+
+colnames = ['start', 'text']
+data = pd.read_csv('train/train.tsv', sep='\t', names=colnames, usecols=[0, 4])
+
+
+# In[66]:
+
+
+x_train = data['text']
+y_train = data['start']
+
+
+# In[67]:
+
+
+tfidf_vectorizer=TfidfVectorizer(use_idf=True, max_df=0.95)
+tfidf_vectorizer.fit_transform(x_train.values)
+x_train_prepared = tfidf_vectorizer.transform(x_train.values)
+
+
+# In[68]:
+
+
+lr = LinearRegression()
+model = lr.fit(x_train_prepared, y_train)
+
+
+# In[69]:
+
+
+y_dev0_exp = pd.read_csv('dev-0/expected.tsv', sep='\t', names=['text'])
+
+f = open("dev-0/in.tsv", "r", encoding='utf-8')
+lines_dev_0 = f.readlines()
+x_dev0 = pd.DataFrame(lines_dev_0)
+x_dev0.rename(columns = {0 : 'text'}, inplace = True)
+
+x_dev0_prepared = tfidf_vectorizer.transform(x_dev0['text'].values)
+y_dev0_pred = model.predict(x_dev0_prepared)
+
+file = open('dev-0/out.tsv', 'w')
+for y in y_dev0_pred:
+    file.write(f'{y}\n')
+file.close()
+
+
+# In[74]:
+
+
+y_dev1_exp = pd.read_csv('dev-1/expected.tsv', sep='\t', names=['text'])
+
+f = open("dev-1/in.tsv", "r", encoding='utf-8')
+lines_dev_1 = f.readlines()
+x_dev1 = pd.DataFrame(lines_dev_1)
+x_dev1.rename(columns = {0 : 'text'}, inplace = True)
+
+x_dev1_prepared = tfidf_vectorizer.transform(x_dev1['text'].values)
+y_dev1_pred = model.predict(x_dev1_prepared)
+
+file = open('dev-1/out.tsv', 'w')
+for y in y_dev1_pred:
+    file.write(f'{y}\n')
+file.close()
+
+
+# In[76]:
+
+
+f = open("test-A/in.tsv", "r", encoding='utf-8')
+lines_test = f.readlines()
+x_test = pd.DataFrame(lines_test)
+x_test.rename(columns = {0 : 'text'}, inplace = True)
+
+x_test_prepared = tfidf_vectorizer.transform(x_test['text'].values)
+y_test_pred = model.predict(x_test_prepared)
+
+file = open('test-A/out.tsv', 'w')
+for y in y_test_pred:
+    file.write(f'{y}\n')
+file.close()
+