用Keras-LSTM预测未来价值
我创建了一个LSTM销售预测模型,该模型在列车和测试集上非常有效。现在我想预测整个数据集中的日期以外的日期 我试着遵循这个答案,但我真的不知道如何调整我的代码来做未来的预测 另外,我更改了我的代码用Keras-LSTM预测未来价值,keras,deep-learning,lstm,prediction,Keras,Deep Learning,Lstm,Prediction,我创建了一个LSTM销售预测模型,该模型在列车和测试集上非常有效。现在我想预测整个数据集中的日期以外的日期 我试着遵循这个答案,但我真的不知道如何调整我的代码来做未来的预测 另外,我更改了我的代码 X_train, y_train = train_set_scaled[:, 1:], train_set_scaled[:, 0:1] X_train = X_train.reshape(X_train.shape[0], 1, X_train.shape[1]) X_test, y_test =
X_train, y_train = train_set_scaled[:, 1:], train_set_scaled[:, 0:1]
X_train = X_train.reshape(X_train.shape[0], 1, X_train.shape[1])
X_test, y_test = test_set_scaled[:, 1:], test_set_scaled[:, 0:1]
X_test = X_test.reshape(X_test.shape[0], 1, X_test.shape[1])
到
在尝试解决方案之后
以下是进行培训和建模的代码:
# changed to initial
for df in m:
train_set, test_set = m[df][0:-6].values, m[df][-6:].values
#apply Min Max Scaler
scaler = MinMaxScaler(feature_range=(-1, 1))
scaler = scaler.fit(train_set)
# reshape training set
train_set = train_set.reshape(train_set.shape[0], train_set.shape[1])
train_set_scaled = scaler.transform(train_set)
# reshape test set
test_set = test_set.reshape(test_set.shape[0], test_set.shape[1])
test_set_scaled = scaler.transform(test_set)
#build the LSTM Model
X_train, y_train = train_set_scaled[:, 1:], train_set_scaled[:, 0:1]
X_train = X_train.reshape(X_train.shape[0], 1, X_train.shape[1])
X_test, y_test = test_set_scaled[:, 1:], test_set_scaled[:, 0:1]
X_test = X_test.reshape(X_test.shape[0], 1, X_test.shape[1])
print('Fitting model for: {}'.format(df))
#fit our LSTM Model
model = Sequential()
model.add(LSTM(4, batch_input_shape=(1, X_train.shape[1], X_train.shape[2]), stateful=True))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(X_train, y_train, nb_epoch=500, batch_size=1, verbose=1, shuffle=False)
# model.save('lstm_model.h5')
print('Predictions for: {}'.format(df))
#check prediction
y_pred = model.predict(X_test,batch_size=1)
print('Inverse Transform for: {}'.format(df))
#inverse transformation to see actual sales
#reshape y_pred
y_pred = y_pred.reshape(y_pred.shape[0], 1, y_pred.shape[1])
#rebuild test set for inverse transform
pred_test_set = []
for index in range(0,len(y_pred)):
print (np.concatenate([y_pred[index],X_test[index]],axis=1))
pred_test_set.append(np.concatenate([y_pred[index],X_test[index]],axis=1))
#reshape pred_test_set
pred_test_set = np.array(pred_test_set)
pred_test_set = pred_test_set.reshape(pred_test_set.shape[0], pred_test_set.shape[2])
#inverse transform
pred_test_set_inverted = scaler.inverse_transform(pred_test_set)
我希望预测超出数据集中的数据范围
更新:我训练了模型,并在测试集上进行了预测。将这些作为另一个LSTM模型的输入,以拟合和预测12个月。这对我有用。也改变了我的最后一个致密层(以上),一次预测1个点,而不是像以前那样预测7个点。
下面是代码:
from numpy import array
for df in d:
if df in list_df:
# df_ADIDAS DYN PUL DEO 150 FCA5421
#KEEP
result_list = []
sales_dates = list(d["{}".format(df)][-7:].Month)
act_sales = list(d["{}".format(df)][-7:].Sale)
for index in range(0,len(pred_test_set_inverted)):
result_dict = {}
result_dict['pred_value'] = int(pred_test_set_inverted[index][0] + act_sales[index]) #change to 0 ffrom act_sales[index]
result_dict['date'] = sales_dates[index] #>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>REVIEW
result_list.append(result_dict)
df_result = pd.DataFrame(result_list)
predictions = list(df_result['pred_value'])
forecasts = []
result_list
for i in range(len(result_list)):
forecasts.append(result_list[i]['pred_value'])
def split_sequence(sequence, n_steps):
X, y = list(), list()
for i in range(len(sequence)):
# find the end of this pattern
end_ix = i + n_steps
# check if we are beyond the sequence
if end_ix > len(sequence)-1:
break
# gather input and output parts of the pattern
seq_x, seq_y = sequence[i:end_ix], sequence[end_ix]
X.append(seq_x)
y.append(seq_y)
return array(X), array(y)
# choose a number of time steps
n_steps = 4
# split into samples
X, y = split_sequence(forecasts, n_steps)
# summarize the data
# for i in range(len(X)):
# print(X[i], y[i])
n_features = 1
X = X.reshape((X.shape[0], X.shape[1], n_features))
# define model
model = Sequential()
model.add(LSTM(50, activation='relu', input_shape=(n_steps, n_features)))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')
# fit model
model.fit(X, y, epochs=200, verbose=0)
# demonstrate prediction
x_input = array(predictions[-4:])
x_input = x_input.reshape((1, n_steps, n_features))
yhat = model.predict(x_input, verbose=0)
#print(yhat)
currentStep = yhat[:, -1:]
print('Twelve Month Prediction for {}'.format(df))
for i in range(12):
if i == 0:
x_input = x_input.reshape((1, n_steps, n_features))
yhat = model.predict(x_input, verbose=0)
print(yhat)
else:
x0_input = np.append(x_input, [currentStep[i-1]])
x0_input = x0_input.reshape((1, n_steps+1, n_features))
x_input = x0_input[:,1:]
yhat = model.predict(x_input)
currentStep = np.append(currentStep, yhat[:,-1:])
print(yhat)
你的最后一个致密层表示你一次预测7个点。保存这些预测并再次将它们输入模型以预测下一个7。这使得它同时有14个预测。等等或者将节点数量和y的形状从7更改为相应的数量,然后再次训练。谢谢。我正在做这个,我会发布一个更新。嗨,我是一个新手。我已经将我的模型用于预测,但无法将其传递给新模型进行预测。你能分享你的代码吗。你能用你的代码开始一个新问题吗?我不明白你的解决方案。您拥有的新模型只对您已经拥有的测试集进行了预测?如果
model.fit()
中没有原始数据中的任何数据,这怎么可能有任何准确性?
from numpy import array
for df in d:
if df in list_df:
# df_ADIDAS DYN PUL DEO 150 FCA5421
#KEEP
result_list = []
sales_dates = list(d["{}".format(df)][-7:].Month)
act_sales = list(d["{}".format(df)][-7:].Sale)
for index in range(0,len(pred_test_set_inverted)):
result_dict = {}
result_dict['pred_value'] = int(pred_test_set_inverted[index][0] + act_sales[index]) #change to 0 ffrom act_sales[index]
result_dict['date'] = sales_dates[index] #>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>REVIEW
result_list.append(result_dict)
df_result = pd.DataFrame(result_list)
predictions = list(df_result['pred_value'])
forecasts = []
result_list
for i in range(len(result_list)):
forecasts.append(result_list[i]['pred_value'])
def split_sequence(sequence, n_steps):
X, y = list(), list()
for i in range(len(sequence)):
# find the end of this pattern
end_ix = i + n_steps
# check if we are beyond the sequence
if end_ix > len(sequence)-1:
break
# gather input and output parts of the pattern
seq_x, seq_y = sequence[i:end_ix], sequence[end_ix]
X.append(seq_x)
y.append(seq_y)
return array(X), array(y)
# choose a number of time steps
n_steps = 4
# split into samples
X, y = split_sequence(forecasts, n_steps)
# summarize the data
# for i in range(len(X)):
# print(X[i], y[i])
n_features = 1
X = X.reshape((X.shape[0], X.shape[1], n_features))
# define model
model = Sequential()
model.add(LSTM(50, activation='relu', input_shape=(n_steps, n_features)))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')
# fit model
model.fit(X, y, epochs=200, verbose=0)
# demonstrate prediction
x_input = array(predictions[-4:])
x_input = x_input.reshape((1, n_steps, n_features))
yhat = model.predict(x_input, verbose=0)
#print(yhat)
currentStep = yhat[:, -1:]
print('Twelve Month Prediction for {}'.format(df))
for i in range(12):
if i == 0:
x_input = x_input.reshape((1, n_steps, n_features))
yhat = model.predict(x_input, verbose=0)
print(yhat)
else:
x0_input = np.append(x_input, [currentStep[i-1]])
x0_input = x0_input.reshape((1, n_steps+1, n_features))
x_input = x0_input[:,1:]
yhat = model.predict(x_input)
currentStep = np.append(currentStep, yhat[:,-1:])
print(yhat)