sport-text-classification-b.../.ipynb_checkpoints/run-checkpoint.py
2022-05-10 23:56:56 +02:00

34 lines
858 B
Python

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline
from sklearn.metrics import accuracy_score
df = pd.read_csv("train/train.tsv", sep="\t", header=None, error_bad_lines=False)
dev_x = pd.read_csv("dev-0/in.tsv", sep="\t", header=None, error_bad_lines=False)
test_x = pd.read_csv("test-A/in.tsv", sep="\t", header=None, error_bad_lines=False)
x = df[1]
y = df[0]
model = make_pipeline(TfidfVectorizer(), MultinomialNB())
model.fit(x,y)
pred_dev = model.predict(dev_x[0])
pred_test = model.predict(test_x[0])
with open('dev-0/out.tsv', 'wt') as f:
for pred in pred_dev:
f.write(str(pred)+'\n')
with open('test-A/out.tsv', 'wt') as f:
for pred in pred_test:
f.write(str(pred)+'\n')