Looking for some help here... so stuck.. Below is my code and the error I'm getting. Thanks for all your help.
def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
"""
Frame a time series as a supervised learning dataset.
Arguments:
data: Sequence of observations as a list or NumPy array.
n_in: Number of lag observations as input (X).
n_out: Number of observations as output (y).
dropnan: Boolean whether or not to drop rows with NaN values.
Returns:
Pandas DataFrame of series framed for supervised learning.
"""
n_vars = 1 if type(data) is list else data.shape[1]
df = DataFrame(data)
cols, names = list(), list()
# input sequence (t-n, ... t-1)
for i in range(n_in, 0, -1):
cols.append(df.shift(i))
names += [('var%d(t-%d)' % (j+1, i)) for j in range(n_vars)]
# forecast sequence (t, t+1, ... t+n)
for i in range(0, n_out):
cols.append(df.shift(-i))
if i == 0:
names += [('var%d(t)' % (j+1)) for j in range(n_vars)]
else:
names += [('var%d(t+%d)' % (j+1, i)) for j in range(n_vars)]
# put it all together
agg = concat(cols, axis=1)
agg.columns = names
# drop rows with NaN values
if dropnan:
agg.dropna(inplace=True)
return agg
# load dataset
dataset = pd.read_csv('newdf2.csv', header=0, index_col=0)
dataset = dataset.drop('Monthday.Key', axis = 1)
dataset.head()
values = dataset.values
# integer encode direction
encoder = LabelEncoder()
values[:,4] = encoder.fit_transform(values[:,4])
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# frame as supervised learning
reframed = series_to_supervised(scaled, 1, 1)
# drop columns we don't want to predict
reframed.drop(reframed.columns[[2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,20,21,22,23,24]], axis=1, inplace=True)
print(reframed.head())
# split into train and test sets
values = reframed.values
n_train_hours = round(len(dataset) *.7)
train = values[:n_train_hours, :]
test = values[n_train_hours:, :]
# split into input and outputs
train_X, train_y = train[:, :-1], train[:, -1]
test_X, test_y = test[:, :-1], test[:, -1]
# reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], 1, train_X.shape[1]))
test_X = test_X.reshape((test_X.shape[0], 1, test_X.shape[1]))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)
#(799, 1, 22) (799,) (342, 1, 22) (342,)
# make a prediction
yhat = model.predict(test_X)
test_X = test_X.reshape((test_X.shape[0], test_X.shape[2]))
inv_yhat = concatenate((yhat, test_X[:, 1:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
This is the error I'm getting:
ValueError Traceback (most recent call last) in ----> 1 inv_yhat = scaler.inverse_transform(inv_yhat)
~\Anaconda3\lib\site-packages\sklearn\preprocessing\data.py in inverse_transform(self, X) 383 X = check_array(X, copy=self.copy, dtype=FLOAT_DTYPES) 384 --> 385 X -= self.min_ 386 X /= self.scale_ 387 return X
ValueError: operands could not be broadcast together with shapes (342,22) (23,) (342,22)
