Я пытаюсь предсказать цены акций, используя python, пытаясь преобразовать набор данных в двумерный массив num для функции 'fit', используя это в качестве ссылки: sklearn Logisti c Регрессия «ValueError: Найден массив с dim 3. Ожидается оценщик <= 2.» </a>
next_day_open_values, nx, ny = next_day_open_values.shape
next_day_open_values = next_day_open_values.reshape((next_day_open_values,nx*ny))
y_normaliser = preprocessing.MinMaxScaler()
y_normaliser.fit((np.expand_dims( next_day_open_values, -1 )))
Я сталкивался с этой ошибкой:
<ipython-input-42-6ea43c55dc18> in csv_to_dataset(csv_path)
20
21 next_day_open_values, nx, ny = next_day_open_values.shape
---> 22 next_day_open_values = next_day_open_values.reshape((next_day_open_values,nx*ny))
23 y_normaliser = preprocessing.MinMaxScaler()
24 y_normaliser.fit((np.expand_dims( next_day_open_values, -1 )))
AttributeError: 'int' object has no attribute 'reshape'
Что пошло не так? Как я могу это исправить? Подробные ответы приветствуются.
Код, приведенный на данный момент, приведен ниже (я использую блокнот Jupyter):
import keras
from keras.models import Model
from keras.layers import Dense, Dropout, LSTM, Input, Activation
from keras import optimizers
import numpy as np
np.random.seed(4)
import tensorflow
tensorflow.random.set_seed(4)
import pandas as pd
from sklearn import preprocessing
import numpy as np
history_points = 50
def csv_to_dataset(csv_path):
data = pd.read_csv(csv_path)
data = data.drop('Date', axis=1)
data = data.drop(0, axis=0)
data_normaliser = preprocessing.MinMaxScaler()
data_normalised = data_normaliser.fit_transform(data)
# using the last {history_points} open high low close volume data points, predict the next open value
ohlcv_histories_normalised = np.array([data_normalised[i : i + history_points].copy() for i in range(len(data_normalised) - history_points)])
next_day_open_values_normalised = np.array([data_normalised[:,0][i + history_points].copy() for i in range(len(data_normalised) - history_points)])
next_day_open_values_normalised = np.expand_dims(next_day_open_values_normalised, -1)
next_day_open_values = np.array([data.iloc[:,0][i + history_points].copy() for i in range(len(data) - history_points)])
next_day_open_values = np.expand_dims(next_day_open_values_normalised, axis=-1)
next_day_open_values, nx, ny = next_day_open_values.shape
next_day_open_values = next_day_open_values.reshape((next_day_open_values,nx*ny))
y_normaliser = preprocessing.MinMaxScaler()
y_normaliser.fit((np.expand_dims( next_day_open_values, -1 )))
assert ohlcv_histories_normalised.shape[0] == next_day_open_values_normalised.shape[0]
return ohlcv_histories_normalised, next_day_open_values_normalised, next_day_open_values, y_normaliser
#dataset
hlcv_histories, next_day_open_values, unscaled_y, y_normaliser = csv_to_dataset('AMZN1.csv')
test_split = 0.9 # the percent of data to be used for testing
n = int(ohlcv_histories.shape[0] * test_split)
# splitting the dataset up into train and test sets
ohlcv_train = ohlcv_histories[:n]
y_train = next_day_open_values[:n]
ohlcv_test = ohlcv_histories[n:]
y_test = next_day_open_values[n:]
unscaled_y_test = unscaled_y[n:]
Не стесняйтесь исправлять / редактировать это.
Спасибо