Data = DM.data_to_MD(DM.fullData_to_data(FullTimeData))
Time = DM.time_to_HMS(DM.fullData_to_time(FullTimeData))
X = np.column_stack((DigitData, Data, Time))
X = np.asarray(X).astype('float32')
Y = np.asarray(Y).astype('int')
#нормализация
np.random.seed(2)
indices = DM.mixedIndex(X)
X = X[indices]
Y = Y[indices]
#нормализация
X = DM.normalization(X)
Y = DM.to_one_hot(Y)
from keras import models
from keras import layers
from keras import regularizers
from keras.optimizers import RMSprop
model = models.Sequential()
model.add(layers.Dense(32, activation='relu', input_shape=(X.shape[1], )))
model.add(layers.Dropout(0.15))
model.add(layers.Dense(32, activation='relu'))
model.add(layers.Dropout(0.02))
#model.add(layers.Dense(32,activation='relu'))
#model.add(layers.Dense(16,activation='relu'))
model.add(layers.Dense(3, activation='softmax'))
delimiter=";",
skip_header=1)
#%%
#8.2 Обработка и нормализация данных
#доп. стоблец баллы для компаний с разрешёнными в sic-кодами
ballSic = DM.covid19SicCode(SIC_codes, sucsSIC_codes)
X = np.column_stack((fiches, ballSic, adspends_s1[:, :-3]))
Y = adspends_s1[:, -3:]
X = np.asarray(X).astype('float32')
Y = np.asarray(Y).astype('int')
X, mean, std = DM.normalization(X)
# перемешивание данных
indices = DM.mixedIndex(X)
X = X[indices]
Y = Y[indices]
#%%
#8.3 Инициализация модели
from keras import models
from keras import layers
from keras import regularizers
model = models.Sequential()
model.add(layers.Dense(32, activation='relu', input_shape=(X.shape[1], )))
AnswerTypes = ["interest_level"]
tupeConvert = {"interest_level": {"low": 0, "medium": 1, "high": 2}}
DigitData = np.array(DM.get_categories(dataJS, DigitTypes))
FullTimeData = DM.get_categories(dataJS, FullTimeTypes)
Data = DM.data_to_MD(DM.fullData_to_data(FullTimeData))
Time = DM.time_to_HMS(DM.fullData_to_time(FullTimeData))
TextData = np.asarray(DM.get_arr(dataJS, TextTypes))
AnswerData = np.array(
DM.get_arr(DM.modifier_fiches_type(dataJS, tupeConvert), AnswerTypes))
X_1 = np.column_stack((DigitData, Data, Time))
X_1 = np.asarray(X_1).astype('float32')
X_1 = DM.normalization(X_1)
X_2 = TextData
Y = DM.to_one_hot(AnswerData)
#нормализация
indices = DM.mixedIndex(X_1)
X_1 = X_1[indices]
X_2 = X_2[indices]
Y = Y[indices]
tokinizer = Tokenizer(num_words=3000)
tokinizer.fit_on_texts(X_2)
sequences = tokinizer.texts_to_sequences(X_2)
sucsSIC_codes = np.genfromtxt("data/DataSet/sucsSIC_codes.csv",
dtype='str',
delimiter=";",
skip_header=1)
ballSic = DM.covid19SicCode(SIC_codes, sucsSIC_codes)
X1 = np.column_stack((fiches[:, :4], ballSic))
X2 = np.column_stack((adspends_s1[:, :-3], fiches[:, -3:]))
Y = adspends_s1[:, -3:]
X1 = np.asarray(X1).astype('float32')
X2 = np.asarray(X2).astype('float32')
Y = np.asarray(Y).astype('int')
X1, mean1, std1 = DM.normalization(X1)
X2, mean2, std2 = DM.normalization(X2)
#Y = DM.normalization(Y)
np.random.seed(426)
indices = DM.mixedIndex(X1)
X1 = X1[indices]
X2 = X2[indices]
Y = Y[indices]
from keras import models
from keras.models import Model
from keras import layers
from keras import Input
from keras import regularizers