mirror of
https://github.com/newnius/YAO-optimizer.git
synced 2025-12-13 08:26:43 +00:00
update
This commit is contained in:
109
train.py
109
train.py
@@ -2,7 +2,6 @@ from pandas import DataFrame
|
||||
from pandas import Series
|
||||
from pandas import concat
|
||||
from pandas import read_csv
|
||||
from pandas import datetime
|
||||
from sklearn.metrics import mean_squared_error
|
||||
from sklearn.preprocessing import MinMaxScaler
|
||||
from keras.models import Sequential
|
||||
@@ -12,18 +11,13 @@ from math import sqrt
|
||||
import numpy
|
||||
|
||||
|
||||
# date-time parsing function for loading the dataset
|
||||
def parser(x):
|
||||
return datetime.strptime('190' + x, '%Y-%m')
|
||||
|
||||
|
||||
# frame a sequence as a supervised learning problem
|
||||
def timeseries_to_supervised(data, lag=1):
|
||||
df = DataFrame(data)
|
||||
columns = [df.shift(i) for i in range(1, lag + 1)]
|
||||
columns.append(df)
|
||||
df = concat(columns, axis=1)
|
||||
df.fillna(0, inplace=True)
|
||||
df = df.drop(0)
|
||||
return df
|
||||
|
||||
|
||||
@@ -56,8 +50,8 @@ def scale(train, test):
|
||||
|
||||
|
||||
# inverse scaling for a forecasted value
|
||||
def invert_scale(scaler, X, value):
|
||||
new_row = [x for x in X] + [value]
|
||||
def invert_scale(scaler, X, yhat):
|
||||
new_row = [x for x in X] + [yhat]
|
||||
array = numpy.array(new_row)
|
||||
array = array.reshape(1, len(array))
|
||||
inverted = scaler.inverse_transform(array)
|
||||
@@ -73,7 +67,6 @@ def fit_lstm(train, batch_size, nb_epoch, neurons):
|
||||
model.add(Dense(1))
|
||||
model.compile(loss='mean_squared_error', optimizer='adam')
|
||||
for i in range(nb_epoch):
|
||||
print("Epoch {}/{}".format(i, nb_epoch))
|
||||
model.fit(X, y, epochs=1, batch_size=batch_size, verbose=0, shuffle=False)
|
||||
model.reset_states()
|
||||
return model
|
||||
@@ -86,44 +79,62 @@ def forecast_lstm(model, batch_size, X):
|
||||
return yhat[0, 0]
|
||||
|
||||
|
||||
# run a repeated experiment
|
||||
def experiment(repeats, series, seed):
|
||||
# transform data to be stationary
|
||||
raw_values = series.values
|
||||
diff_values = difference(raw_values, 1)
|
||||
# transform data to be supervised learning
|
||||
supervised = timeseries_to_supervised(diff_values, 1)
|
||||
supervised_values = supervised.values
|
||||
# split data into train and test-sets
|
||||
train, test = supervised_values[0:-12], supervised_values[-12:]
|
||||
# transform the scale of the data
|
||||
scaler, train_scaled, test_scaled = scale(train, test)
|
||||
# run experiment
|
||||
error_scores = list()
|
||||
for r in range(repeats):
|
||||
# fit the model
|
||||
batch_size = 4
|
||||
train_trimmed = train_scaled[2:, :]
|
||||
lstm_model = fit_lstm(train_trimmed, batch_size, 3000, 4)
|
||||
# forecast the entire training dataset to build up state for forecasting
|
||||
if seed:
|
||||
train_reshaped = train_trimmed[:, 0].reshape(len(train_trimmed), 1, 1)
|
||||
lstm_model.predict(train_reshaped, batch_size=batch_size)
|
||||
# forecast test dataset
|
||||
test_reshaped = test_scaled[:, 0:-1]
|
||||
test_reshaped = test_reshaped.reshape(len(test_reshaped), 1, 1)
|
||||
output = lstm_model.predict(test_reshaped, batch_size=batch_size)
|
||||
predictions = list()
|
||||
for i in range(len(output)):
|
||||
yhat = output[i, 0]
|
||||
X = test_scaled[i, 0:-1]
|
||||
# invert scaling
|
||||
yhat = invert_scale(scaler, X, yhat)
|
||||
# invert differencing
|
||||
yhat = inverse_difference(raw_values, yhat, len(test_scaled) + 1 - i)
|
||||
# store forecast
|
||||
predictions.append(yhat)
|
||||
# report performance
|
||||
rmse = sqrt(mean_squared_error(raw_values[-12:], predictions))
|
||||
print('%d) Test RMSE: %.3f' % (r + 1, rmse))
|
||||
error_scores.append(rmse)
|
||||
return error_scores
|
||||
|
||||
|
||||
# load dataset
|
||||
series = read_csv('data.csv', header=0, index_col=0, squeeze=True)
|
||||
|
||||
# transform data to be stationary
|
||||
raw_values = series.values
|
||||
diff_values = difference(raw_values, 1)
|
||||
|
||||
# transform data to be supervised learning
|
||||
supervised = timeseries_to_supervised(diff_values, 1)
|
||||
supervised_values = supervised.values
|
||||
|
||||
# split data into train and test-sets
|
||||
train, test = supervised_values[0:-12], supervised_values[-12:]
|
||||
|
||||
# transform the scale of the data
|
||||
scaler, train_scaled, test_scaled = scale(train, test)
|
||||
|
||||
# fit the model
|
||||
lstm_model = fit_lstm(train_scaled, 1, 30, 4)
|
||||
# forecast the entire training dataset to build up state for forecasting
|
||||
train_reshaped = train_scaled[:, 0].reshape(len(train_scaled), 1, 1)
|
||||
lstm_model.predict(train_reshaped, batch_size=1)
|
||||
|
||||
# walk-forward validation on the test data
|
||||
predictions = list()
|
||||
for j in range(len(test_scaled)):
|
||||
# make one-step forecast
|
||||
X, y = test_scaled[j, 0:-1], test_scaled[j, -1]
|
||||
yhat = forecast_lstm(lstm_model, 1, X)
|
||||
# invert scaling
|
||||
yhat = invert_scale(scaler, X, yhat)
|
||||
# invert differencing
|
||||
yhat = inverse_difference(raw_values, yhat, len(test_scaled) + 1 - j)
|
||||
# store forecast
|
||||
predictions.append(yhat)
|
||||
expected = raw_values[len(train) + j + 1]
|
||||
print('Month=%d, Predicted=%f, Expected=%f' % (j + 1, yhat, expected))
|
||||
|
||||
# report performance
|
||||
rmse = sqrt(mean_squared_error(raw_values[-12:], predictions))
|
||||
print('Test RMSE: %.3f' % rmse)
|
||||
# experiment
|
||||
repeats = 30
|
||||
results = DataFrame()
|
||||
# with seeding
|
||||
with_seed = experiment(repeats, series, True)
|
||||
results['with-seed'] = with_seed
|
||||
# without seeding
|
||||
without_seed = experiment(repeats, series, False)
|
||||
results['without-seed'] = without_seed
|
||||
# summarize results
|
||||
print(results.describe())
|
||||
# save boxplot
|
||||
results.boxplot()
|
||||
|
||||
Reference in New Issue
Block a user