ARMA_GBR/SVR ValueError: Expected 2D array, got 1D array instead: array=[2856.3394 2850.637 2844.9326 2837.7214]. Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

Hi, i have a problem concerning executing the code

number [12]
features = 4 # this number is derived from the paper "The stock price based on the ARIMA_SVM combination model _ cheng changpin.(Chinese)". Since the prediction is the best when using 4 days close price to predict
forward =30
window = 150 # the rolling window should be as large as possible. Better larger than 100, since the time series ARMA model can't get inverted matrics if the time series is too short 
length = 1
index_predict, index_real = [], []
for i in range(forward):
    test_window = test_C[i:i+window]
    coeff = WT(test_window, lv=4, n=4)
    results = AR_MA(coeff)
    Y_ = NonlinReg(coeff, regressor='GBR', length=length, features = features)[-1:]
    D_series = []
    for j in range(len(results)):
        D_series.append(results[j].predict(window, window+length-1, dynamic=True))
    index_predict.append(Y_)
    index_real.append(test_C[i+window:i+window+length].values)

it give me this error

ValueError                                Traceback (most recent call last)
<ipython-input-13-b2d1bf8912bc> in <module>
      8     coeff = WT(test_window, lv=4, n=4)
      9     results = AR_MA(coeff)
---> 10     Y_ = NonlinReg(coeff, regressor='GBR', length=length, features = features)[-1:]
     11     D_series = []
     12     for j in range(len(results)):

~/PycharmProjects/PHBS_TQFML-StockIndex-Wavelet-Transformation-ARIMA-ML-Model/Project/model.py in NonlinReg(coeff, regressor, features, interval, length)
    136         for i in range(length):
    137             X_ = np.concatenate((X_, np.array([np.concatenate((X_[-1][-features+1:], Y_[[-interval-1]]))])))
--> 138             Y_ = np.concatenate((Y_, gbr.predict(X_[-1])))
    139 
    140     if regressor == 'SVR':

/usr/local/lib/python3.6/dist-packages/sklearn/ensemble/_gb.py in predict(self, X)
   2565             The predicted values.
   2566         """
-> 2567         X = check_array(X, dtype=DTYPE, order="C", accept_sparse='csr')
   2568         # In regression we can directly return the raw value from the trees.
   2569         return self._raw_predict(X).ravel()

/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    554                     "Reshape your data either using array.reshape(-1, 1) if "
    555                     "your data has a single feature or array.reshape(1, -1) "
--> 556                     "if it contains a single sample.".format(array))
    557 
    558         # in the future np.flexible dtypes will be handled like object dtypes

ValueError: Expected 2D array, got 1D array instead:
array=[2856.3394 2850.637  2844.9326 2837.7214].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

SunHao95 / PHBS_TQFML-StockIndex-Wavelet-Transformation-ARIMA-ML-Model

ARMA_GBR/SVR ValueError: Expected 2D array, got 1D array instead: array=[2856.3394 2850.637 2844.9326 2837.7214]. Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample. #1

it give me this error