36 lines
708 B
Python
36 lines
708 B
Python
#!/usr/bin/env python
|
|
# coding: utf-8
|
|
|
|
# In[1]:
|
|
|
|
|
|
import pandas as pd
|
|
import csv
|
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
|
from sklearn.cluster import KMeans
|
|
|
|
|
|
# In[2]:
|
|
|
|
|
|
#dev0
|
|
dev0_data = pd.read_csv('dev-0/in.tsv', header=None, quoting=csv.QUOTE_NONE, sep='\t')
|
|
|
|
dev0_y = KMeans(n_clusters=50).fit_predict(TfidfVectorizer().fit_transform(dev0_data[0].values))
|
|
|
|
#zapis wyników
|
|
dev0_y.tofile('dev-0/out.tsv', sep='\n')
|
|
|
|
|
|
# In[3]:
|
|
|
|
|
|
#TestA
|
|
testA_data = pd.read_csv('test-A/in.tsv', header=None, quoting=csv.QUOTE_NONE, sep='\t')
|
|
|
|
testA_y = KMeans(n_clusters=50).fit_predict(TfidfVectorizer().fit_transform(testA_data[0].values))
|
|
|
|
#zapis wyników
|
|
testA_y.tofile('test-A/out.tsv', sep='\n')
|
|
|