This commit is contained in:
JPogodzinski 2021-05-04 09:40:40 +02:00
parent 91607d349b
commit 933b59370a
3 changed files with 10915 additions and 12 deletions

5452
dev-0/out.tsv Normal file

File diff suppressed because it is too large Load Diff

30
main.py
View File

@ -1,22 +1,24 @@
from sklearn.naive_bayes import MultinomialNB from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
import pandas as pd import pandas as pd
import numpy as np import numpy as np
from stop_words import get_stop_words
cv = CountVectorizer(strip_accents='ascii', token_pattern=u'(?ui)\\b\\w*[a-z]+\\w*\\b', lowercase=True) stop_words = get_stop_words('polish')
v = TfidfVectorizer(stop_words=None)
naive_bayes=MultinomialNB() naive_bayes=MultinomialNB()
ball_train = pd.read_csv('train/train.tsv', sep='\t', error_bad_lines=False, header=None) ball_train = pd.read_csv('train/train.tsv', sep='\t', error_bad_lines=False, header=None)
print(ball_train.head())
print(len(ball_train))
print(pd.DataFrame(ball_train[0]))
print(pd.DataFrame(ball_train[1]))
y_train = pd.DataFrame(ball_train[0]) y_train = pd.DataFrame(ball_train[0])
x_train = pd.DataFrame(ball_train[1]) x_train = pd.DataFrame(ball_train[1])
x_train.cv=cv.transform(x_train) x_np=x_train.to_numpy()
x_np = [str(item) for item in x_np]
naive_bayes.fit(x_train.cv, y_train) x_train=v.fit_transform(x_np)
naive_bayes.fit(x_train, y_train)
ball_dev = pd.read_csv('dev-0/in.tsv', sep='\t', error_bad_lines=False, header=None) ball_dev = pd.read_csv('dev-0/in.tsv', sep='\t', error_bad_lines=False, header=None)
with open('dev-0/expected.tsv', 'r') as dev_exp_f: with open('dev-0/expected.tsv', 'r') as dev_exp_f:
@ -24,15 +26,19 @@ with open('dev-0/expected.tsv', 'r') as dev_exp_f:
X_dev = pd.DataFrame(ball_dev) X_dev = pd.DataFrame(ball_dev)
X_dev.cv=cv.transform(X_dev) X_dev_np=X_dev.to_numpy()
X_dev_np = [str(item) for item in X_dev_np]
X_dev=v.transform(X_dev_np)
Y_dev_predicted = naive_bayes.predict(X_dev.cv) Y_dev_predicted = naive_bayes.predict(X_dev)
pd.DataFrame(Y_dev_predicted).to_csv('dev-0/out.tsv', sep='\t', index=False, header=False) pd.DataFrame(Y_dev_predicted).to_csv('dev-0/out.tsv', sep='\t', index=False, header=False)
ball_test=pd.read_csv('test-A/in.tsv', sep='\t', error_bad_lines=False, header=None) ball_test=pd.read_csv('test-A/in.tsv', sep='\t', error_bad_lines=False, header=None)
X_test = pd.DataFrame(ball_test) X_test = pd.DataFrame(ball_test)
X_test.cv=cv.transform(X_test) X_test_np=X_test.to_numpy()
X_test_np = [str(item) for item in X_test_np]
X_test=v.transform(X_test_np)
Y_test_predicted = naive_bayes.predict(X_test.cv) Y_test_predicted = naive_bayes.predict(X_test)
pd.DataFrame(Y_test_predicted).to_csv('test-A/out.tsv', sep='\t', index=False, header=False) pd.DataFrame(Y_test_predicted).to_csv('test-A/out.tsv', sep='\t', index=False, header=False)

5445
test-A/out.tsv Normal file

File diff suppressed because it is too large Load Diff