ireland-news-headlines/run.py
2022-06-07 16:35:00 +02:00

77 lines
1.8 KiB
Python

#!/usr/bin/env python
# coding: utf-8
# In[6]:
import vowpalwabbit
import pandas as pd
import re
# In[7]:
def prediction(path_in, path_out, model, categories):
data = pd.read_csv(path_in, header=None, sep='\t')
data = data.drop(1, axis=1)
data.columns = ['year', 'text']
data['train_input'] = data.apply(lambda row: to_vowpalwabbit(row, categories), axis=1)
with open(path_out, 'w', encoding='utf-8') as file:
for example in data['train_input']:
predicted = model.predict(example)
text_predicted = dict((value, key) for key, value in map_dict.items()).get(predicted)
file.write(str(text_predicted) + '\n')
# In[8]:
def to_vowpalwabbit(row, categories):
text = row['text'].replace('\n', ' ').lower().strip()
text = re.sub("[^a-zA-Z -']", '', text)
text = re.sub(" +", ' ', text)
year = row['year']
try:
category = categories[row['category']]
except KeyError:
category = ''
vw = f"{category} | year:{year} text:{text}\n"
return vw
# In[9]:
x_train = pd.read_csv('train/in.tsv', header=None, sep='\t')
x_train = x_train.drop(1, axis=1)
x_train.columns = ['year', 'text']
y_train = pd.read_csv('train/expected.tsv', header=None, sep='\t')
y_train.columns = ['category']
data = pd.concat([x_train, y_train], axis=1)
categories = {}
for i, x in enumerate(data['category'].unique()):
categories[x] = i+1
print(categories)
data['train_input'] = data.apply(lambda row: to_vowpalwabbit(row, categories), axis=1)
model = vowpalwabbit.Workspace('--oaa 3 --quiet')
for example in data['train_input']:
model.learn(example)
prediction('dev-0/in.tsv', 'dev-0/out.tsv', model, categories)
prediction('test-A/in.tsv', 'test-A/out.tsv', model, categories)
prediction('test-B/in.tsv', 'test-B/out.tsv', model, categories)