54 lines
1.7 KiB
Python
54 lines
1.7 KiB
Python
'''
|
|
Csv Handler
|
|
===========
|
|
|
|
CsvHandler writes articles' information to csv file and reads it.
|
|
'''
|
|
|
|
import csv
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
class CsvHandler:
|
|
|
|
def read_csv(csv_file, usecols=None):
|
|
df = pd.read_csv(csv_file,
|
|
sep='|',
|
|
header=0,
|
|
engine='python',
|
|
usecols=usecols,
|
|
decimal='.',
|
|
quotechar='\'',
|
|
#nrows = 200,
|
|
quoting=csv.QUOTE_NONE)
|
|
return df
|
|
|
|
def write_csv(df, file_name):
|
|
df.to_csv(file_name,
|
|
sep='|')
|
|
print('# saved {} article(s) in {}'.format(len(df), file_name))
|
|
|
|
def select_randoms(df, n):
|
|
'''selects n random samples from dataset.
|
|
params: df DataFrame to select items from,
|
|
n number of items to select randomly,
|
|
returns new DataFrame with only selected items
|
|
'''
|
|
# new empty DataFrame
|
|
# df_samples = pd.DataFrame(columns=['rands','title','text','label'])
|
|
# initialize random => reproducible sequence
|
|
np.random.seed(5)
|
|
# pseudorandom float -1.0 <= x <= 1.0 for every sample
|
|
# pd.Series()
|
|
# add new column 'Random'
|
|
df['Random'] = pd.Series(np.random.randn(len(df)), index=df.index)
|
|
# sort DataFrame by random numbers
|
|
df = df.sort_values('Random')
|
|
# return first n elements of randomly sorted dataset
|
|
return df.iloc[0:n]
|
|
|
|
if __name__ == '__main__':
|
|
df = CsvHandler.read_csv('classification_labelled_corrected.csv')
|
|
df_new = CsvHandler.select_randoms(df, 10)
|
|
CsvHandler.write_csv(df_new, 'samples_10.csv') |