# split for training and testing
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from util.load_text import load_BERT, predict_text
import numpy as np
from tensorflow.keras.utils import to_categorical
from sklearn.metrics import accuracy_score, confusion_matrix
from util.load_audio import load_all_models, stacked_dataset, fit_logistic
from scipy.special import softmax
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from util.load_text import load_BERT, predict_text
bert_model = load_BERT(model_type='regression')
from util.load_audio import load_all_models, stacked_dataset, fit_logistic
n_members = 10
all_models = load_all_models(n_members, model_type = '4_categories')
kf = KFold(n_splits=5, shuffle = True, random_state = 31)
test_text_acc = []
test_audio_acc = []
ensemble_acc = []
print('Loaded %d models!' % len(all_models))
print('')
# split for training and testing
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from util.load_text import load_BERT, predict_text
import numpy as np
from tensorflow.keras.utils import to_categorical
from sklearn.metrics import accuracy_score, confusion_matrix
from util.load_audio import load_all_models, stacked_dataset, fit_logistic
from scipy.special import softmax
from sklearn.linear_model import LogisticRegression
kf = KFold(n_splits=5, shuffle=True, random_state=31)
#load text model and predict
bert_model = load_BERT(model_type='3_categories')
#load audio models
n_members = 10
all_models = load_all_models(n_members, model_type='3_categories')
print('Loaded %d models!' % len(all_models))
print('')
for num, indices in enumerate(kf.split(audio_y)):
print('===== Start CV {} out of 5 ====='.format(num + 1))
print('.')
train_index = indices[0]
test_index = indices[1]