42 lines
1.0 KiB
Python
42 lines
1.0 KiB
Python
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
||
|
|
from sklearn.linear_model import LogisticRegression
|
||
|
|
import lzma
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
X = []
|
||
|
|
Y = []
|
||
|
|
with lzma.open('train/in.tsv.xz', 'r') as file:
|
||
|
|
for line in file:
|
||
|
|
line = line.strip()
|
||
|
|
X.append(line.decode("utf-8"))
|
||
|
|
print("step 1")
|
||
|
|
with open('train/expected.tsv', 'r') as file:
|
||
|
|
for line in file:
|
||
|
|
line = line.strip()
|
||
|
|
Y.append(int(line))
|
||
|
|
print("step 2")
|
||
|
|
vectorizer = TfidfVectorizer()
|
||
|
|
X = vectorizer.fit_transform(X)
|
||
|
|
|
||
|
|
print("step 3")
|
||
|
|
model = LogisticRegression()
|
||
|
|
model.fit(X, Y)
|
||
|
|
|
||
|
|
print("step 4")
|
||
|
|
X_dev = []
|
||
|
|
Y_dev = []
|
||
|
|
with open('test-A/in.tsv', 'r') as file:
|
||
|
|
for line in file:
|
||
|
|
line = line.strip()
|
||
|
|
X_dev.append(line)
|
||
|
|
|
||
|
|
print("step 5")
|
||
|
|
X_dev = vectorizer.transform(X_dev)
|
||
|
|
prediction = model.predict(X_dev)
|
||
|
|
|
||
|
|
print("step 6")
|
||
|
|
f = open("test-A/out.tsv", "a")
|
||
|
|
for p in prediction:
|
||
|
|
f.write(str(p) + '\n')
|
||
|
|
f.close()
|