# ### Figure 1: Continuous vs Batch LSTM
# fig = plt.figure()
# # NRMSE_StaticLSTM = plotLSTMresult('results/nyc_taxi_experiment_one_shot/',
# # window, xaxis=xaxis_datetime, label='static lstm')
# (nrmseLSTM6000, expResultLSTM6000) = \
# plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window6001.0/',
# window, xaxis=xaxisDate, label='continuous LSTM-6000')
# plt.legend()
# plt.savefig(figPath + 'continuousVsbatch.pdf')
#
### Figure 2: Continuous LSTM with different window size
fig = plt.figure()
(nrmseLSTM1000, expResultLSTM1000) = \
plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window1001.0/',
window, xaxis=xaxisDate, label='continuous LSTM-1000')
(nrmseLSTM3000, expResultLSTM3000) = \
plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window3001.0/',
window, xaxis=xaxisDate, label='continuous LSTM-3000')
(nrmseLSTM6000, expResultLSTM6000) = \
plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window6001.0/',
window, xaxis=xaxisDate, label='continuous LSTM-6000')
dataSet = 'nyc_taxi'
filePath = './prediction/' + dataSet + '_TM_pred.csv'
(tmTruth, tmPrediction) = loadExperimentResult('./prediction/' + dataSet +
'_TM_pred.csv')
# ### Figure 1: Continuous vs Batch LSTM
# fig = plt.figure()
# # NRMSE_StaticLSTM = plotLSTMresult('results/nyc_taxi_experiment_one_shot/',
# # window, xaxis=xaxis_datetime, label='static lstm')
# (nrmseLSTM6000, expResultLSTM6000) = \
# plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window6001.0/',
# window, xaxis=xaxisDate, label='continuous LSTM-6000')
# plt.legend()
# plt.savefig(figPath + 'continuousVsbatch.pdf')
#
### Figure 2: Continuous LSTM with different window size
fig = plt.figure()
(nrmseLSTM1000, expResultLSTM1000) = plotLSTMresult(
'results/nyc_taxi_experiment_continuous/learning_window1001.0/',
window, xaxis=xaxisDate, label='continuous LSTM-1000')
(nrmseLSTM3000, expResultLSTM3000) = plotLSTMresult(
'results/nyc_taxi_experiment_continuous/learning_window3001.0/',
window, xaxis=xaxisDate, label='continuous LSTM-3000')
(nrmseLSTM6000, expResultLSTM6000) = plotLSTMresult(
'results/nyc_taxi_experiment_continuous/learning_window6001.0/',
window, xaxis=xaxisDate, label='continuous LSTM-6000')
(nrmseLSTMonline, expResultLSTMonline) = plotLSTMresult(
'results/nyc_taxi_experiment_continuous_online/learning_window100.0/',
window, xaxis=xaxisDate, label='continuous LSTM-online')
dataSet = 'nyc_taxi'
# # ### Figure 1: Continuous vs Batch LSTM
# fig = plt.figure()
# # NRMSE_StaticLSTM = plotLSTMresult('results/nyc_taxi_experiment_one_shot/',
# # window, xaxis=xaxis_datetime, label='static lstm')
# (nrmseLSTM6000, expResultLSTM6000) = \
# plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window6001.0/',
# window, xaxis=xaxisDate, label='continuous LSTM-6000')
# plt.legend()
# plt.savefig(figPath + 'continuousVsbatch.pdf')
### Figure 2: Continuous LSTM with different window size
fig = plt.figure()
(nrmseLSTM1000, expResultLSTM1000) = plotLSTMresult(
'results/nyc_taxi_experiment_continuous/learning_window1001.0/',
window,
xaxis=xaxisDate,
label='continuous LSTM-1000')
# (nrmseLSTM3000, expResultLSTM3000) = plotLSTMresult(
# 'results/nyc_taxi_experiment_continuous/learning_window3001.0/',
# window, xaxis=xaxisDate, label='continuous LSTM-3000')
#
# (nrmseLSTM6000, expResultLSTM6000) = plotLSTMresult(
# 'results/nyc_taxi_experiment_continuous/learning_window6001.0/',
# window, xaxis=xaxisDate, label='continuous LSTM-6000')
#
# (nrmseLSTMonline, expResultLSTMonline) = plotLSTMresult(
# 'results/nyc_taxi_experiment_continuous_online/learning_window100.0/',
# window, xaxis=xaxisDate, label='continuous LSTM-online')
data = pd.read_csv(filePath, header=0, skiprows=[1, 2], names=['datetime', 'value', 'timeofday', 'dayofweek'])
xaxis_datetime = pd.to_datetime(data['datetime'])
def computeAltMAPE(truth, prediction, startFrom=0):
return np.nanmean(np.abs(truth[startFrom:] - prediction[startFrom:]))/np.nanmean(np.abs(truth[startFrom:]))
expResult = ExperimentResult('results/nyc_taxi_experiment_continuous/learning_window6001.0/')
### Figure 1: Continuous vs Batch LSTM
fig = plt.figure()
# NRMSE_StaticLSTM = plotLSTMresult('results/nyc_taxi_experiment_one_shot/',
# window, xaxis=xaxis_datetime, label='static lstm')
(NRMSE_LSTM6000, expResult_LSTM6000) = \
plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window6001.0/',
window, xaxis=xaxis_datetime, label='continuous LSTM-6000')
plt.legend()
plt.savefig(figPath + 'continuousVsbatch.pdf')
### Figure 2: Continuous LSTM with different window size
fig = plt.figure()
(NRMSE_LSTM1000, expResult_LSTM1000) = \
plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window1001.0/',
window, xaxis=xaxis_datetime, label='continuous LSTM-1000')
(NRMSE_LSTM3000, expResult_LSTM3000) = \
plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window3001.0/',
window, xaxis=xaxis_datetime, label='continuous LSTM-3000')
# ### Figure 1: Continuous vs Batch LSTM
# fig = plt.figure()
# # NRMSE_StaticLSTM = plotLSTMresult('results/nyc_taxi_experiment_one_shot/',
# # window, xaxis=xaxis_datetime, label='static lstm')
# (nrmseLSTM6000, expResultLSTM6000) = \
# plotLSTMresult('results/nyc_taxi_experiment_continuous/learning_window6001.0/',
# window, xaxis=xaxisDate, label='continuous LSTM-6000')
# plt.legend()
# plt.savefig(figPath + 'continuousVsbatch.pdf')
#
### Figure 2: Continuous LSTM with different window size
fig = plt.figure()
(nrmseLSTM1000, expResultLSTM1000) = plotLSTMresult(
'results/nyc_taxi_experiment_continuous/learning_window1001.0/',
window, xaxis=xaxisDate, label='continuous LSTM-1000')
(nrmseLSTM3000, expResultLSTM3000) = plotLSTMresult(
'results/nyc_taxi_experiment_continuous/learning_window3001.0/',
window, xaxis=xaxisDate, label='continuous LSTM-3000')
(nrmseLSTM6000, expResultLSTM6000) = plotLSTMresult(
'results/nyc_taxi_experiment_continuous/learning_window6001.0/',
window, xaxis=xaxisDate, label='continuous LSTM-6000')
(nrmseLSTMonline, expResultLSTMonline) = plotLSTMresult(
'results/nyc_taxi_experiment_continuous_online/learning_window100.0/',
window, xaxis=xaxisDate, label='continuous LSTM-online')
dataSet = 'nyc_taxi'