data_augmentation.py

import numpy as np
import pandas as pd
pd.set_option('display.max_rows',1000)
pd.set_option('display.max_columns',1000)

train = pd.read_csv("./data/VUA/VUA_train_features2.csv")
train_DA = pd.read_csv("./data/VUA/VUA_verb_features.csv")
train_DA2 = pd.read_csv("./data/VUA/VUA_allpos_features.csv")
print(train.shape)
print(train_DA.shape)
print(train_DA2.shape)
train_DA['label'] = pd.read_csv("./submit/vua_verb_answer12.txt", usecols=['label'])
train_DA2['label'] = pd.read_csv("./submit/vua_allpos_answer13.txt", usecols=['label'])
train_all = pd.concat((train,train_DA))
train_all = pd.concat((train_all,train_DA2))
print(train_all.shape)
print(train_all[-10:])
train_all.to_csv('./data/VUA2/VUA_train_da2.csv', index=False, header=True)

train = pd.read_csv("./data/TOEFI/TOEFI_train_features2.csv")
train_DA = pd.read_csv("./data/TOEFI/TOEFI_verb_features.csv")
train_DA2 = pd.read_csv("./data/TOEFI/TOEFI_allpos_features.csv")
print(train.shape)
print(train_DA.shape)
print(train_DA2.shape)
train_DA['label'] = pd.read_csv("./submit/toefi_verb_answer27.txt", usecols=['label'])
train_DA2['label'] = pd.read_csv("./submit/toefi_allpos_answer26.txt", usecols=['label'])
train_all = pd.concat((train,train_DA))
train_all = pd.concat((train_all,train_DA2))
print(train_all.shape)
print(train_all[-10:])
train_all.to_csv('./data/TOEFI/TOEFI_train_da2.csv', index=False, header=True)