s444386 run file

run.py

@@ -0,0 +1,50 @@
+import lzma
+import math
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LinearRegression
+from sklearn.pipeline import make_pipeline
+from sklearn.metrics import mean_squared_error
+import pandas as pd
+
+X_train = []
+Y_train = []
+
+stop = 0
+
+with lzma.open('train/train.tsv.xz', 'rt', encoding="utf-8") as f:
+    data = pd.read_csv(f, sep='\t', names=['Begin', 'End', 'Title', 'Publisher', 'Text'])
+
+
+data = data[['Text', 'Begin']]
+data = data[0:50000]
+
+X = data['Text']
+y = data['Begin']
+
+model = make_pipeline(TfidfVectorizer(), LinearRegression())
+model.fit(X, y)
+
+def readFile(filename):
+    X_dev = []
+    with open(filename, 'r', encoding="utf-8") as dev_in:
+        for line in dev_in:
+            text = line.split("\t")[0].strip()
+            X_dev.append(text)
+    return X_dev
+
+def writePred(filename, predictions):
+    with open(filename, "w") as out_file:
+        for pred in predictions:
+            out_file.write(str(pred) + "\n")
+
+x = readFile('dev-0/in.tsv')
+pred = model.predict(x)
+writePred('dev-0/out.tsv',pred)
+
+x = readFile('dev-1/in.tsv')
+pred = model.predict(x)
+writePred('dev-1/out.tsv',pred)
+
+x = readFile('test-A/in.tsv')
+pred = model.predict(x)
+writePred('test-A/out.tsv',pred)