TGCN_Simulation_reshape

ITSTGCN

Author

SEOYEON CHOI

Published

June 20, 2023

Simulation Study

Import

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

Fivenodes

df1 = pd.read_csv('./simulation_results/2023-06-21_22-15-12.csv')
df2 = pd.read_csv('./simulation_results/2023-06-21_22-40-10.csv')
df3 = pd.read_csv('./simulation_results/2023-06-21_23-05-22.csv')
df4 = pd.read_csv('./simulation_results/2023-06-21_23-30-38.csv')
df5 = pd.read_csv('./simulation_results/2023-06-21_23-56-42.csv')
df6 = pd.read_csv('./simulation_results/2023-06-22_00-22-04.csv')
df7 = pd.read_csv('./simulation_results/2023-06-22_00-47-43.csv')
df8 = pd.read_csv('./simulation_results/2023-06-22_01-12-10.csv')

df9 = pd.read_csv('./simulation_results/2023-07-18_18-27-03.csv')
df10 = pd.read_csv('./simulation_results/2023-07-18_18-53-09.csv')
df11 = pd.read_csv('./simulation_results/2023-07-18_19-20-02.csv')
df12 = pd.read_csv('./simulation_results/2023-07-18_19-47-32.csv')
df13 = pd.read_csv('./simulation_results/2023-07-18_20-14-25.csv')
df14 = pd.read_csv('./simulation_results/2023-07-18_20-41-14.csv')

data = pd.concat([df1,df2,df3,df4,df5,df6,df7,df8,df9,df10,df11,df12,df13,df14],axis=0)

data.to_csv('./simulation_results/Real_simulation_reshape/TGCN_fivedones_Simulation.csv',index=False)

data = pd.read_csv('./simulation_results/Real_simulation_reshape/TGCN_fivedones_Simulation.csv')

Baseline

data.query("method!='GNAR' and mrate==0").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='lags',facet_row='nof_filters',height=600)

Random

data.query("method!='GNAR' and mtype =='rand'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='inter_method',facet_row='nof_filters',height=600)

Block

data.query("method!='GNAR' and mtype =='block' ").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='inter_method',facet_row='nof_filters',height=600)

chickenpox

df1 = pd.read_csv('./simulation_results/2023-06-22_02-27-00.csv') # GNAR random
df2 = pd.read_csv('./simulation_results/2023-06-22_03-45-52.csv') # GNAR block
df3 = pd.read_csv('./simulation_results/2023-06-22_04-18-03.csv') # STGCN, ITSTGCN random 30%
df4 = pd.read_csv('./simulation_results/2023-06-22_04-50-08.csv') 
df5 = pd.read_csv('./simulation_results/2023-06-22_05-54-21.csv') 
df6 = pd.read_csv('./simulation_results/2023-06-22_07-05-46.csv')

df7 = pd.read_csv('./simulation_results/2023-07-18_21-22-24.csv') # GNAR random
df8 = pd.read_csv('./simulation_results/2023-07-18_22-04-58.csv') # GNAR block
df9 = pd.read_csv('./simulation_results/2023-07-18_22-44-53.csv') # STGCN, ITSTGCN random 30%
df10 = pd.read_csv('./simulation_results/2023-07-18_23-28-12.csv')

data = pd.concat([df1,df2,df3,df4,df5,df6,df7,df8,df9,df10],axis=0)

data.to_csv('./simulation_results/Real_simulation_reshape/TGCN_chikenpox_Simulation.csv',index=False)

data = pd.read_csv('./simulation_results/Real_simulation_reshape/TGCN_chikenpox_Simulation.csv')

Baseline

data.query("method!='GNAR' and mrate ==0 ").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='nof_filters',height=600)

Random

data.query("method!='GNAR' and mtype =='rand'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='nof_filters',facet_row='inter_method',height=800)

Block

data.query("method!='GNAR' and mtype =='block'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='inter_method',facet_row='lags',height=800)

Pedalme

df1 = pd.read_csv('./simulation_results/2023-06-22_07-32-36.csv') 
df2 = pd.read_csv('./simulation_results/2023-06-22_10-37-27.csv')

df3 = pd.read_csv('./simulation_results/2023-07-18_23-46-13.csv')

data = pd.concat([df1,df2,df3],axis=0)

data.to_csv('./simulation_results/Real_simulation_reshape/TGCN_pedalme_Simulation.csv',index=False)

data = pd.read_csv('./simulation_results/Real_simulation_reshape/TGCN_pedalme_Simulation.csv')

Baseline

data.query("mrate ==0 and lags!=2").plot.box(backend='plotly',x='epoch',color='method',y='mse',facet_col='nof_filters',facet_row='lags',height=400)

random

data.query("method!='GNAR' and mtype =='rand' and lags!=2").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='nof_filters',facet_row='inter_method',height=800)

block

data.query("method!='GNAR' and mtype =='block' and lags!=2 ").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='nof_filters',facet_row='inter_method',height=800)

weight matrix time, node 고려한 결과

df1 = pd.read_csv('./simulation_results/2023-06-21_22-29-02.csv')
df2 = pd.read_csv('./simulation_results/2023-06-21_22-51-34.csv')

data2 = pd.concat([df1,df2],axis=0)

data2.to_csv('./simulation_results/Real_simulation_reshape/TGCN_pedalme_Simulation_itstgcnsnd.csv',index=False)

data2 = pd.read_csv('./simulation_results/Real_simulation_reshape/TGCN_pedalme_Simulation_itstgcnsnd.csv')

data2.query("mtype=='rand'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='inter_method',facet_row='nof_filters',height=1000)

data2.query("mtype=='block'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='inter_method',facet_row='nof_filters',height=1000)

Wikimath

df1 = pd.read_csv('./simulation_results/2023-06-22_15-11-43.csv')
df2 = pd.read_csv('./simulation_results/2023-06-24_03-36-59.csv')
df3 = pd.read_csv('./simulation_results/2023-06-24_10-08-34.csv')
df4 = pd.read_csv('./simulation_results/2023-06-24_19-33-58.csv')
df5 = pd.read_csv('./simulation_results/2023-06-25_04-53-42.csv')
df6 = pd.read_csv('./simulation_results/2023-06-25_11-10-17.csv')
df7 = pd.read_csv('./simulation_results/2023-06-25_17-18-10.csv')
df8 = pd.read_csv('./simulation_results/2023-06-25_23-36-43.csv')
df9 = pd.read_csv('./simulation_results/2023-06-26_06-47-01.csv') # block
df10 = pd.read_csv('./simulation_results/2023-06-26_13-53-42.csv') # block
df11 = pd.read_csv('./simulation_results/2023-06-26_20-18-18.csv') # block

df12 = pd.read_csv('./simulation_results/2023-08-02_04-31-56.csv')
df13 = pd.read_csv('./simulation_results/2023-08-02_09-27-54.csv')
df14 = pd.read_csv('./simulation_results/2023-08-02_13-51-08.csv')
df15 = pd.read_csv('./simulation_results/2023-08-02_18-39-58.csv')
df16 = pd.read_csv('./simulation_results/2023-08-02_23-07-03.csv')
df17 = pd.read_csv('./simulation_results/2023-08-03_03-56-12.csv')
df18 = pd.read_csv('./simulation_results/2023-08-03_08-46-30.csv')
df19 = pd.read_csv('./simulation_results/2023-08-03_13-12-15.csv')
df20 = pd.read_csv('./simulation_results/2023-08-03_17-55-50.csv') # block
df21 = pd.read_csv('./simulation_results/2023-08-03_22-21-01.csv') # block
df22 = pd.read_csv('./simulation_results/2023-08-04_03-06-37.csv') # block
df23 = pd.read_csv('./simulation_results/2023-08-04_07-53-37.csv') # block

data = pd.concat([df1,df2,df3,df4,df5,df6,df7,df8,df9,df10,df11,df12,df13,df14,df15,df16,df17,df18,df19,df20,df21,df22,df23],axis=0)

data.to_csv('./simulation_results/Real_simulation_reshape/TGCN_wikimath.csv',index=False)

data = pd.read_csv('./simulation_results/Real_simulation_reshape/TGCN_wikimath.csv')

Baseline

data.query("mrate==0 and method!='GNAR'").plot.box(backend='plotly',x='mrate',color='method',y='mse',height=600)

random

data.query("mtype=='rand' and mrate !=0 and method!='GNAR'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='lags',facet_row='nof_filters',height=800)

block

data.query("mtype=='block' and method!='GNAR'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='lags',facet_row='nof_filters',height=1200)

missing values on the same nodes

df1 = pd.read_csv('./simulation_results/2023-06-27_03-08-38.csv') # STGCN IT-STGCN block
df2 = pd.read_csv('./simulation_results/2023-06-27_15-49-21.csv') # STGCN IT-STGCN
df3 = pd.read_csv('./simulation_results/2023-06-27_09-33-29.csv')

data = pd.concat([df1],axis=0)

data.to_csv('./simulation_results/Real_simulation_reshape/TGCN_wikimath_GSO_st.csv',index=False)

data = pd.read_csv('./simulation_results/Real_simulation_reshape/TGCN_wikimath_GSO_st.csv')

data.query("method!='GNAR' and mtype =='block' ").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='inter_method',facet_row='lags',height=800)

Windmilsmall

df1 = pd.read_csv('./simulation_results/2023-08-16_19-42-08.csv') # STGCN IT-STGCN 70%
df2 = pd.read_csv('./simulation_results/2023-08-17_08-35-00.csv') # STGCN IT-STGCN
df3 = pd.read_csv('./simulation_results/2023-08-17_20-55-05.csv') # STGCN IT-STGCN
df4 = pd.read_csv('./simulation_results/2023-08-18_09-48-46.csv') # STGCN IT-STGCN
df5 = pd.read_csv('./simulation_results/2023-08-18_22-44-05.csv') # STGCN IT-STGCN
df6 = pd.read_csv('./simulation_results/2023-08-19_11-47-24.csv') # GNAR 30%, 50%, 70% # 뭔가 일단 필요없어서 데이터셋에서 뺌
df7 = pd.read_csv('./simulation_results/2023-08-20_00-42-42.csv') # STGCN IT-STGCN
df8 = pd.read_csv('./simulation_results/2023-08-20_13-37-41.csv') # STGCN IT-STGCN
df9 = pd.read_csv('./simulation_results/2023-08-21_02-04-28.csv') # STGCN IT-STGCN
df10 = pd.read_csv('./simulation_results/2023-08-21_14-58-42.csv') # STGCN IT-STGCN
df11 = pd.read_csv('./simulation_results/2023-08-22_03-53-21.csv') # STGCN IT-STGCN
df12 = pd.read_csv('./simulation_results/2023-08-22_15-38-15.csv') # STGCN IT-STGCN
df13 = pd.read_csv('./simulation_results/2023-08-23_00-02-26.csv') # STGCN IT-STGCN
df14 = pd.read_csv('./simulation_results/2023-08-23_09-48-41.csv') # STGCN IT-STGCN
df15 = pd.read_csv('./simulation_results/2023-08-23_23-24-27.csv') # STGCN IT-STGCN
df16 = pd.read_csv('./simulation_results/2023-08-24_09-32-34.csv') # STGCN IT-STGCN
df17 = pd.read_csv('./simulation_results/2023-08-24_22-10-18.csv') # STGCN IT-STGCN
df18 = pd.read_csv('./simulation_results/2023-08-26_11-12-49.csv') # STGCN IT-STGCN
df19 = pd.read_csv('./simulation_results/2023-08-26_20-03-41.csv') # STGCN IT-STGCN
df20 = pd.read_csv('./simulation_results/2023-08-27_04-46-19.csv') # STGCN IT-STGCN
df21 = pd.read_csv('./simulation_results/2023-08-28_12-14-20.csv') # STGCN IT-STGCN
df22 = pd.read_csv('./simulation_results/2023-08-28_20-59-57.csv') # STGCN IT-STGCN
df23 = pd.read_csv('./simulation_results/2023-08-29_05-48-59.csv') # STGCN IT-STGCN
df24 = pd.read_csv('./simulation_results/2023-08-30_02-48-51.csv') # STGCN IT-STGCN
df25 = pd.read_csv('./simulation_results/2023-08-30_11-42-39.csv') # STGCN IT-STGCN
df26 = pd.read_csv('./simulation_results/2023-08-30_20-54-21.csv') # STGCN IT-STGCN
df27 = pd.read_csv('./simulation_results/2023-08-31_05-47-37.csv') # STGCN IT-STGCN
df28 = pd.read_csv('./simulation_results/2023-09-01_15-58-53.csv') # STGCN IT-STGCN
df29 = pd.read_csv('./simulation_results/2023-09-02_00-41-49.csv') # STGCN IT-STGCN
df30 = pd.read_csv('./simulation_results/2023-09-02_09-32-19.csv') # STGCN IT-STGCN
# block
df31 = pd.read_csv('./simulation_results/2023-08-24_15-22-46.csv') # GNAR 70%
df32 = pd.read_csv('./simulation_results/2023-08-26_10-59-04.csv') # GNAR 
df33 = pd.read_csv('./simulation_results/2023-08-26_19-42-49.csv')
df34 = pd.read_csv('./simulation_results/2023-08-27_04-09-13.csv')
df35 = pd.read_csv('./simulation_results/2023-08-27_12-43-40.csv')
df36 = pd.read_csv('./simulation_results/2023-08-27_22-09-30.csv')
df37 = pd.read_csv('./simulation_results/2023-08-28_10-42-12.csv')
df38 = pd.read_csv('./simulation_results/2023-08-28_19-25-57.csv')
df39 = pd.read_csv('./simulation_results/2023-08-29_03-54-36.csv')
df40 = pd.read_csv('./simulation_results/2023-08-29_15-15-30.csv')
df41 = pd.read_csv('./simulation_results/2023-08-30_00-10-00.csv')
df42 = pd.read_csv('./simulation_results/2023-08-30_08-53-22.csv')
df43 = pd.read_csv('./simulation_results/2023-08-30_17-30-31.csv')
df44 = pd.read_csv('./simulation_results/2023-08-31_02-27-19.csv')
df45 = pd.read_csv('./simulation_results/2023-08-31_09-54-50.csv')
df46 = pd.read_csv('./simulation_results/2023-08-31_16-39-53.csv')
df47 = pd.read_csv('./simulation_results/2023-08-31_23-18-31.csv')
df48 = pd.read_csv('./simulation_results/2023-09-01_05-57-03.csv')
df49 = pd.read_csv('./simulation_results/2023-09-01_14-33-57.csv')
df50 = pd.read_csv('./simulation_results/2023-09-01_23-13-01.csv')
df51 = pd.read_csv('./simulation_results/2023-09-02_08-05-53.csv')
df52 = pd.read_csv('./simulation_results/2023-09-02_15-07-14.csv')
df53 = pd.read_csv('./simulation_results/2023-09-02_21-50-40.csv')
df54 = pd.read_csv('./simulation_results/2023-09-03_04-33-04.csv')
df55 = pd.read_csv('./simulation_results/2023-09-03_12-31-38.csv')
df56 = pd.read_csv('./simulation_results/2023-09-03_21-49-24.csv')
df57 = pd.read_csv('./simulation_results/2023-09-04_07-04-08.csv')
df58 = pd.read_csv('./simulation_results/2023-09-04_16-14-26.csv')
df59 = pd.read_csv('./simulation_results/2023-09-05_01-28-56.csv')
df60 = pd.read_csv('./simulation_results/2023-09-05_10-46-37.csv')
# baseline
df61 = pd.read_csv('./simulation_results/2023-08-29_22-19-12.csv')
df62 = pd.read_csv('./simulation_results/2023-08-30_07-18-55.csv')
df63 = pd.read_csv('./simulation_results/2023-08-30_16-15-48.csv')
df64 = pd.read_csv('./simulation_results/2023-08-31_01-13-27.csv')
df65 = pd.read_csv('./simulation_results/2023-08-31_09-11-54.csv')
df66 = pd.read_csv('./simulation_results/2023-08-31_15-58-53.csv')
df67 = pd.read_csv('./simulation_results/2023-08-31_22-39-44.csv')
df68 = pd.read_csv('./simulation_results/2023-09-01_05-18-21.csv') # 확인 후 block 만 넣기!
df69 = pd.read_csv('./simulation_results/2023-09-01_13-30-19.csv')
df70 = pd.read_csv('./simulation_results/2023-09-01_22-17-33.csv')
df71 = pd.read_csv('./simulation_results/2023-09-02_07-12-30.csv')
df72 = pd.read_csv('./simulation_results/2023-09-02_14-39-23.csv')
df73 = pd.read_csv('./simulation_results/2023-09-02_21-28-14.csv')
df74 = pd.read_csv('./simulation_results/2023-09-03_04-16-10.csv')
df75 = pd.read_csv('./simulation_results/2023-09-03_12-15-29.csv')
df76 = pd.read_csv('./simulation_results/2023-09-03_21-33-23.csv')
df77 = pd.read_csv('./simulation_results/2023-09-04_06-48-19.csv')
df78 = pd.read_csv('./simulation_results/2023-09-04_15-58-28.csv')
df79 = pd.read_csv('./simulation_results/2023-09-05_01-13-09.csv')
df80 = pd.read_csv('./simulation_results/2023-09-05_10-30-29.csv')
df81 = pd.read_csv('./simulation_results/2023-09-05_17-34-15.csv')
df82 = pd.read_csv('./simulation_results/2023-09-06_00-34-28.csv')
df83 = pd.read_csv('./simulation_results/2023-09-06_07-42-04.csv')
df84 = pd.read_csv('./simulation_results/2023-09-06_17-00-30.csv')
df85 = pd.read_csv('./simulation_results/2023-09-07_02-13-26.csv')
df86 = pd.read_csv('./simulation_results/2023-09-07_11-08-50.csv')
df87 = pd.read_csv('./simulation_results/2023-09-07_20-26-14.csv')
df88 = pd.read_csv('./simulation_results/2023-09-08_05-37-59.csv')
df89 = pd.read_csv('./simulation_results/2023-09-08_14-51-14.csv')
df90 = pd.read_csv('./simulation_results/2023-09-08_23-55-49.csv')

data = pd.concat([df1,df2,df3,df4,df5,df6,df7,df8,df9,df10,df11,df12,df13,df14,df15,df16,df17,df18,df19,df20,df21,df22,df23,df24,df25,df26,df27,df28,df29,df30,
                  df31,df32,df33,df34,df35,df36,df37,df38,df39,df40,df41,df42,df43,df44,df45,df46,df47,df48,df49,df50,df51,df52,df53,df54,df55,df56,df57,df58,df59,df60,
                  df61,df62,df63,df64,df65,df66,df67,df68,df69,df70,df71,df72,df73,df74,df75,df76,df77,df78,df79,df80,df81,df82,df83,df84,df85,df86,df87,df88,df89,df90
                 ],axis=0)

data.to_csv('./simulation_results/Real_simulation_reshape/TGCN_windmillsmall.csv',index=False)

data = pd.read_csv('./simulation_results/Real_simulation_reshape/TGCN_windmillsmall.csv')

Baseline

data.query("method!='GNAR' and mrate ==0 ").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='lags',height=800)

random

data.query("method!='GNAR' and mtype =='rand' ").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='lags',facet_row='inter_method',height=800)

block

data.query("method!='GNAR' and mtype =='block' ").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='lags',facet_row='inter_method',height=800)

Montevideobus

df1 = pd.read_csv('./simulation_results/2023-06-22_10-28-10.csv') # lags 8
df2 = pd.read_csv('./simulation_results/2023-06-22_13-31-48.csv') # lags 8
df3 = pd.read_csv('./simulation_results/2023-06-22_15-51-24.csv') # lags 8
df4 = pd.read_csv('./simulation_results/2023-06-22_17-59-22.csv') # lags 8
df5 = pd.read_csv('./simulation_results/2023-06-22_20-08-49.csv') # lags 8
df6 = pd.read_csv('./simulation_results/2023-06-22_22-23-50.csv') # lags 8

df7 = pd.read_csv('./simulation_results/2023-07-25_01-37-20.csv') # lags 8
df8 = pd.read_csv('./simulation_results/2023-07-25_03-55-32.csv') # lags 8
df9 = pd.read_csv('./simulation_results/2023-07-25_06-16-34.csv') # lags 8
df10 = pd.read_csv('./simulation_results/2023-07-25_08-33-19.csv') # lags 8
df11 = pd.read_csv('./simulation_results/2023-07-25_10-34-08.csv') # lags 8
df12 = pd.read_csv('./simulation_results/2023-07-25_12-34-19.csv') # lags 8
df13 = pd.read_csv('./simulation_results/2023-07-25_14-26-43.csv') # lags 8
df14 = pd.read_csv('./simulation_results/2023-07-25_16-24-54.csv') # lags 8
df15 = pd.read_csv('./simulation_results/2023-07-25_18-28-28.csv') # lags 8

data = pd.concat([df1,df2,df3,df4,df5,df6,df7,df8,df9,df10,df11,df12,df13,df14,df15],axis=0)

data.to_csv('./simulation_results/Real_simulation_reshape/TGCN_monte.csv',index=False)

data = pd.read_csv('./simulation_results/Real_simulation_reshape/TGCN_monte.csv')

Baseline

data.query("mrate==0 and method!='GNAR'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='lags',facet_row='nof_filters',height=600)

random

data.query("mtype=='rand' and mrate !=0 and method!='GNAR'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='lags',facet_row='inter_method',height=800)

block

data.query("mtype=='block' and method!='GNAR'").plot.box(backend='plotly',x='mrate',color='method',y='mse',facet_col='lags',facet_row='nof_filters',height=1200)