In [1]:
import pandas as pd
In [2]:
import shl_pm
+-----------------------------------------------+
| Loaded SHL Prediction Module |
| Version 0.0.0.1 |
+-----------------------------------------------+
+-----------------------------------------------+
| SHL Prediction Module User Guide |
+-----------------------------------------------+
+-----------------------------------------------+
| Key Function I:
| shl_initialize(in_ccyy_mm='2017-07')
+-----------------------------------------------+
This function takes one input. Run this funciton once, before calling shl_predict_price_k_step()
Inputs:
(1) in_ccyy_mm: the (current) year month for predicting bidding price
string, i.e. '2017-07'
Outputs: N.A.
+-----------------------------------------------+
| Key Function II:
| shl_predict_price_k_step(in_current_time, in_current_price, in_k_seconds=1, return_value='f_1_step_pred_set_price_rounded')
+-----------------------------------------------+
This function takes four inputs then returns prediciton values in a python list.
Ensure this function is called 'once and only once' for EVERY second with price, starting from '11:29:00'!
This is to ensure prediction module could capture all actual prices for internal prediction calculation.
Inputs:
(1) in_current_time: current time/second of bidding price
string, i.e. '11:29:50'
(2) in_current_price : current bidding price
number/integer/float, i.e. 89400
(3) in_k_seconds : forecast price in the next k seconds
integer, default value = 1, i.e. 7
(4) return_value : return result of predicted price, or predicted set price = predicted price + dynamic increment
string, i.e. 89600 predicted price (return_value = 'f_1_step_pred_price_rounded')
string, i.e. 89800 predicted set price (return_value = 'f_1_step_pred_set_price_rounded')
Outputs:
(1) Returned restuls in python list
list of integer , i.e. [89800] (in_k_seconds = 1)
list of integers, i.e. [89800, 89900, 89900, 90000, 90100, 90100, 90200] (in_k_seconds = 7)
In [ ]:
In [3]:
## which month to predictsimulate?
# shl_sm_parm_ccyy_mm = '2017-04'
# shl_sm_parm_ccyy_mm_offset = 1647
# shl_sm_parm_ccyy_mm = '2017-05'
# shl_sm_parm_ccyy_mm_offset = 1708
shl_sm_parm_ccyy_mm = '2017-06'
shl_sm_parm_ccyy_mm_offset = 1769
# shl_sm_parm_ccyy_mm = '2017-07'
# shl_sm_parm_ccyy_mm_offset = 1830
# shl_sm_parm_ccyy_mm = '2017-08'
# shl_sm_parm_ccyy_mm_offset = 1830+61
# shl_sm_parm_ccyy_mm = '2017-09'
# shl_sm_parm_ccyy_mm_offset = 1830+61*2
# shl_sm_parm_ccyy_mm = '2017-10'
# shl_sm_parm_ccyy_mm_offset = 1830+61*3
# shl_sm_parm_ccyy_mm = '2017-11'
# shl_sm_parm_ccyy_mm_offset = 1830+61*4
# shl_sm_parm_ccyy_mm = '2017-12'
# shl_sm_parm_ccyy_mm_offset = 1830+61*5
#----------------------------------
shl_sm_data = pd.read_csv('shl_sm_data/shl_sm_data.csv')
shl_sm_data
Out[3]:
ccyy-mm
time
bid-price
0
2015-01
11:29:00
74000
1
2015-01
11:29:01
74000
2
2015-01
11:29:02
74000
3
2015-01
11:29:03
74000
4
2015-01
11:29:04
74000
5
2015-01
11:29:05
74000
6
2015-01
11:29:06
74000
7
2015-01
11:29:07
74000
8
2015-01
11:29:08
74000
9
2015-01
11:29:09
74000
10
2015-01
11:29:10
74000
11
2015-01
11:29:11
74000
12
2015-01
11:29:12
74000
13
2015-01
11:29:13
74000
14
2015-01
11:29:14
74000
15
2015-01
11:29:15
74000
16
2015-01
11:29:16
74000
17
2015-01
11:29:17
74000
18
2015-01
11:29:18
74000
19
2015-01
11:29:19
74000
20
2015-01
11:29:20
74000
21
2015-01
11:29:21
74000
22
2015-01
11:29:22
74000
23
2015-01
11:29:23
74000
24
2015-01
11:29:24
74000
25
2015-01
11:29:25
74000
26
2015-01
11:29:26
74000
27
2015-01
11:29:27
74000
28
2015-01
11:29:28
74000
29
2015-01
11:29:29
74000
...
...
...
...
2166
2017-12
11:29:31
90500
2167
2017-12
11:29:32
90500
2168
2017-12
11:29:33
90500
2169
2017-12
11:29:34
90500
2170
2017-12
11:29:35
90500
2171
2017-12
11:29:36
90600
2172
2017-12
11:29:37
90600
2173
2017-12
11:29:38
90600
2174
2017-12
11:29:39
90700
2175
2017-12
11:29:40
90700
2176
2017-12
11:29:41
90700
2177
2017-12
11:29:42
90700
2178
2017-12
11:29:43
90700
2179
2017-12
11:29:44
90800
2180
2017-12
11:29:45
90800
2181
2017-12
11:29:46
90800
2182
2017-12
11:29:47
90900
2183
2017-12
11:29:48
91000
2184
2017-12
11:29:49
91100
2185
2017-12
11:29:50
91100
2186
2017-12
11:29:51
91100
2187
2017-12
11:29:52
91100
2188
2017-12
11:29:53
91100
2189
2017-12
11:29:54
91200
2190
2017-12
11:29:55
91200
2191
2017-12
11:29:56
91200
2192
2017-12
11:29:57
91300
2193
2017-12
11:29:58
91300
2194
2017-12
11:29:59
91400
2195
2017-12
11:30:00
91600
2196 rows × 3 columns
In [4]:
shl_pm.shl_initialize(shl_sm_parm_ccyy_mm)
+-----------------------------------------------+
| shl_initialize() |
+-----------------------------------------------+
shl_global_parm_ccyy_mm : 2017-06
-------------------------------------------------
shl_global_parm_alpha : 0.777107313458705
shl_global_parm_beta : 0.179154416550987
shl_global_parm_gamma : 0.120598828573260
shl_global_parm_short_weight : 0.1250000000
shl_global_parm_short_weight_ratio: 0.0000000000
shl_global_parm_sec57_weight : 0.5000000000
shl_global_parm_month_weight : 0.9000000000
shl_global_parm_dynamic_increment : 300
-------------------------------------------------
prediction results dataframe: shl_data_pm_1_step
Empty DataFrame
Columns: []
Index: []
prediction results dataframe: shl_data_pm_k_step
Empty DataFrame
Columns: []
Index: []
In [5]:
# Upon receiving 11:29:00 second price, to predict till 11:29:49 <- one-step forward price forecasting
for i in range(shl_sm_parm_ccyy_mm_offset, shl_sm_parm_ccyy_mm_offset+50): # use csv data as simulatino
# for i in range(shl_sm_parm_ccyy_mm_offset, shl_sm_parm_ccyy_mm_offset+55): # use csv data as simulatino
print('\n<<<< Record No.: %5d >>>>' % i)
print(shl_sm_data['ccyy-mm'][i]) # format: ccyy-mm
print(shl_sm_data['time'][i]) # format: hh:mm:ss
print(shl_sm_data['bid-price'][i]) # format: integer
######################################################################################################################
# call prediction function, returned result is in 'list' format, i.e. [89400]
shl_sm_prediction_list_local_1 = shl_pm.shl_predict_price_k_step(shl_sm_data['time'][i], shl_sm_data['bid-price'][i],1) # <- one-step forward price forecasting
print(shl_sm_prediction_list_local_1)
######################################################################################################################
<<<< Record No.: 1769 >>>>
2017-06
11:29:00
88400
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:00
in_current_price : 88400.000000
*INFO* At time [ 11:29:00 ] Set shl_global_parm_base_price : 88399
*INFO* f_current_datetime : 2017-06 11:29:00
*INFO* f_current_si : 0.0023822132
*INFO* f_current_price4pm : 1
*INFO* f_current_price4pmsi : 419.7777140577
*INFO* f_1_step_time : 11:29:01
*INFO* f_1_step_si : 0.0148610887
-------------------------------------------------
==>> Prediction Restuls in Python List : [88700]
[88700]
<<<< Record No.: 1770 >>>>
2017-06
11:29:01
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:01
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:01
*INFO* f_current_si : 0.0148610887
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 6796.2719464957
*INFO* f_1_step_time : 11:29:02
*INFO* f_1_step_si : 0.0237690555
previous_pred_les_level : 419.7777140577
previous_pred_les_trend : 0.0000000000
f_1_step_pred_les_level : 5374.9980163125
f_1_step_pred_les_trend : 887.7496021321
f_1_step_pred_les : 6262.7476184446
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 6262.7476184446
f_1_step_pred_price_inc : 148.8595956607
f_1_step_pred_price : 88547.8595956607
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1771 >>>>
2017-06
11:29:02
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:02
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:02
*INFO* f_current_si : 0.0237690555
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 4249.2222732132
*INFO* f_1_step_time : 11:29:03
*INFO* f_1_step_si : 0.0309433438
previous_pred_les_level : 5374.9980163125
previous_pred_les_trend : 887.7496021321
f_1_step_pred_les_level : 4698.0223468308
f_1_step_pred_les_trend : 607.4221590335
f_1_step_pred_les : 5305.4445058643
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 5305.4445058643
f_1_step_pred_price_inc : 164.1681935706
f_1_step_pred_price : 88563.1681935706
f_1_step_pred_price_rounded : 88600
f_1_step_pred_set_price_rounded : 88900
-------------------------------------------------
==>> Prediction Restuls in Python List : [88900]
[88900]
<<<< Record No.: 1772 >>>>
2017-06
11:29:03
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:03
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:03
*INFO* f_current_si : 0.0309433438
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 3264.0299161348
*INFO* f_1_step_time : 11:29:04
*INFO* f_1_step_si : 0.0392121078
previous_pred_les_level : 4698.0223468308
previous_pred_les_trend : 607.4221590335
f_1_step_pred_les_level : 3719.0462983842
f_1_step_pred_les_trend : 323.2119137549
f_1_step_pred_les : 4042.2582121391
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 4042.2582121391
f_1_step_pred_price_inc : 158.5054649628
f_1_step_pred_price : 88557.5054649628
f_1_step_pred_price_rounded : 88600
f_1_step_pred_set_price_rounded : 88900
-------------------------------------------------
==>> Prediction Restuls in Python List : [88900]
[88900]
<<<< Record No.: 1773 >>>>
2017-06
11:29:04
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:04
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:04
*INFO* f_current_si : 0.0392121078
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 2575.7350355198
*INFO* f_1_step_time : 11:29:05
*INFO* f_1_step_si : 0.0387689298
previous_pred_les_level : 3719.0462983842
previous_pred_les_trend : 323.2119137549
f_1_step_pred_les_level : 2902.6123262315
f_1_step_pred_les_trend : 119.0393199904
f_1_step_pred_les : 3021.6516462219
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 3021.6516462219
f_1_step_pred_price_inc : 117.1462004869
f_1_step_pred_price : 88516.1462004869
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1774 >>>>
2017-06
11:29:05
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:05
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:05
*INFO* f_current_si : 0.0387689298
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 2605.1789558691
*INFO* f_1_step_time : 11:29:06
*INFO* f_1_step_si : 0.0757339541
previous_pred_les_level : 2902.6123262315
previous_pred_les_trend : 119.0393199904
f_1_step_pred_les_level : 2698.0076726929
f_1_step_pred_les_trend : 61.0570727425
f_1_step_pred_les : 2759.0647454354
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 2759.0647454354
f_1_step_pred_price_inc : 208.9548827838
f_1_step_pred_price : 88607.9548827838
f_1_step_pred_price_rounded : 88600
f_1_step_pred_set_price_rounded : 88900
-------------------------------------------------
==>> Prediction Restuls in Python List : [88900]
[88900]
<<<< Record No.: 1775 >>>>
2017-06
11:29:06
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:06
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:06
*INFO* f_current_si : 0.0757339541
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 1333.6158292953
*INFO* f_1_step_time : 11:29:07
*INFO* f_1_step_si : 0.0941974492
previous_pred_les_level : 2698.0076726929
previous_pred_les_trend : 61.0570727425
f_1_step_pred_les_level : 1651.3379677411
f_1_step_pred_les_trend : -137.3970718132
f_1_step_pred_les : 1513.9408959279
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 1513.9408959279
f_1_step_pred_price_inc : 142.6093705948
f_1_step_pred_price : 88541.6093705948
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1776 >>>>
2017-06
11:29:07
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:07
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:07
*INFO* f_current_si : 0.0941974492
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 1072.2158708854
*INFO* f_1_step_time : 11:29:08
*INFO* f_1_step_si : 0.1333750997
previous_pred_les_level : 1651.3379677411
previous_pred_les_trend : -137.3970718132
f_1_step_pred_les_level : 1170.6731484297
f_1_step_pred_les_trend : -198.8950048370
f_1_step_pred_les : 971.7781435927
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 971.7781435927
f_1_step_pred_price_inc : 129.6110068231
f_1_step_pred_price : 88528.6110068231
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1777 >>>>
2017-06
11:29:08
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:08
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:08
*INFO* f_current_si : 0.1333750997
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 757.2627889299
*INFO* f_1_step_time : 11:29:09
*INFO* f_1_step_si : 0.2041837362
previous_pred_les_level : 1170.6731484297
previous_pred_les_trend : -198.8950048370
f_1_step_pred_les_level : 805.0766926351
f_1_step_pred_les_trend : -228.7603060215
f_1_step_pred_les : 576.3163866135
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 576.3163866135
f_1_step_pred_price_inc : 117.6744330551
f_1_step_pred_price : 88516.6744330551
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1778 >>>>
2017-06
11:29:09
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:09
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:09
*INFO* f_current_si : 0.2041837362
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 494.6525216798
*INFO* f_1_step_time : 11:29:10
*INFO* f_1_step_si : 0.2321693821
previous_pred_les_level : 805.0766926351
previous_pred_les_trend : -228.7603060215
f_1_step_pred_les_level : 512.8547999283
f_1_step_pred_les_trend : -240.1297295575
f_1_step_pred_les : 272.7250703707
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 272.7250703707
f_1_step_pred_price_inc : 63.3184110718
f_1_step_pred_price : 88462.3184110718
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1779 >>>>
2017-06
11:29:10
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:10
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:10
*INFO* f_current_si : 0.2321693821
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 435.0272162739
*INFO* f_1_step_time : 11:29:11
*INFO* f_1_step_si : 0.2946054876
previous_pred_les_level : 512.8547999283
previous_pred_les_trend : -240.1297295575
f_1_step_pred_les_level : 398.8512549422
f_1_step_pred_les_trend : -217.5336665488
f_1_step_pred_les : 181.3175883933
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 181.3175883933
f_1_step_pred_price_inc : 53.4171565479
f_1_step_pred_price : 88452.4171565479
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1780 >>>>
2017-06
11:29:11
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:11
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:11
*INFO* f_current_si : 0.2946054876
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 342.8313600204
*INFO* f_1_step_time : 11:29:12
*INFO* f_1_step_si : 0.3488655530
previous_pred_les_level : 398.8512549422
previous_pred_les_trend : -217.5336665488
f_1_step_pred_les_level : 306.8311215490
f_1_step_pred_les_trend : -195.0473627471
f_1_step_pred_les : 111.7837588020
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 111.7837588020
f_1_step_pred_price_inc : 38.9975028352
f_1_step_pred_price : 88437.9975028352
f_1_step_pred_price_rounded : 88400
f_1_step_pred_set_price_rounded : 88700
-------------------------------------------------
==>> Prediction Restuls in Python List : [88700]
[88700]
<<<< Record No.: 1781 >>>>
2017-06
11:29:12
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:12
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:12
*INFO* f_current_si : 0.3488655530
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 289.5098100697
*INFO* f_1_step_time : 11:29:13
*INFO* f_1_step_si : 0.3571459028
previous_pred_les_level : 306.8311215490
previous_pred_les_trend : -195.0473627471
f_1_step_pred_les_level : 249.8959730343
f_1_step_pred_les_trend : -170.3039495877
f_1_step_pred_les : 79.5920234466
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 79.5920234466
f_1_step_pred_price_inc : 28.4259650669
f_1_step_pred_price : 88427.4259650669
f_1_step_pred_price_rounded : 88400
f_1_step_pred_set_price_rounded : 88700
-------------------------------------------------
==>> Prediction Restuls in Python List : [88700]
[88700]
<<<< Record No.: 1782 >>>>
2017-06
11:29:13
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:13
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:13
*INFO* f_current_si : 0.3571459028
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 282.7975883738
*INFO* f_1_step_time : 11:29:14
*INFO* f_1_step_si : 0.3775201623
previous_pred_les_level : 249.8959730343
previous_pred_les_trend : -170.3039495877
f_1_step_pred_les_level : 237.5045540870
f_1_step_pred_les_trend : -142.0132222947
f_1_step_pred_les : 95.4913317923
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 95.4913317923
f_1_step_pred_price_inc : 36.0499030778
f_1_step_pred_price : 88435.0499030778
f_1_step_pred_price_rounded : 88400
f_1_step_pred_set_price_rounded : 88700
-------------------------------------------------
==>> Prediction Restuls in Python List : [88700]
[88700]
<<<< Record No.: 1783 >>>>
2017-06
11:29:14
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:14
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:14
*INFO* f_current_si : 0.3775201623
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 267.5353797818
*INFO* f_1_step_time : 11:29:15
*INFO* f_1_step_si : 0.4092913787
previous_pred_les_level : 237.5045540870
previous_pred_les_trend : -142.0132222947
f_1_step_pred_les_level : 229.1880197220
f_1_step_pred_les_trend : -118.0608701739
f_1_step_pred_les : 111.1271495481
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 111.1271495481
f_1_step_pred_price_inc : 45.4833842537
f_1_step_pred_price : 88444.4833842537
f_1_step_pred_price_rounded : 88400
f_1_step_pred_set_price_rounded : 88700
-------------------------------------------------
==>> Prediction Restuls in Python List : [88700]
[88700]
<<<< Record No.: 1784 >>>>
2017-06
11:29:15
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:15
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:15
*INFO* f_current_si : 0.4092913787
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 246.7679634778
*INFO* f_1_step_time : 11:29:16
*INFO* f_1_step_si : 0.4206648773
previous_pred_les_level : 229.1880197220
previous_pred_les_trend : -118.0608701739
f_1_step_pred_les_level : 216.5346180564
f_1_step_pred_les_trend : -99.1766566532
f_1_step_pred_les : 117.3579614032
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 117.3579614032
f_1_step_pred_price_inc : 49.3683724375
f_1_step_pred_price : 88448.3683724375
f_1_step_pred_price_rounded : 88400
f_1_step_pred_set_price_rounded : 88700
-------------------------------------------------
==>> Prediction Restuls in Python List : [88700]
[88700]
<<<< Record No.: 1785 >>>>
2017-06
11:29:16
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:16
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:16
*INFO* f_current_si : 0.4206648773
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 240.0961084292
*INFO* f_1_step_time : 11:29:17
*INFO* f_1_step_si : 0.4638547583
previous_pred_les_level : 216.5346180564
previous_pred_les_trend : -99.1766566532
f_1_step_pred_les_level : 212.7386730975
f_1_step_pred_les_trend : -82.0887808994
f_1_step_pred_les : 130.6498921981
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 130.6498921981
f_1_step_pred_price_inc : 60.6025741668
f_1_step_pred_price : 88459.6025741668
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1786 >>>>
2017-06
11:29:17
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:17
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:17
*INFO* f_current_si : 0.4638547583
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 217.7405711463
*INFO* f_1_step_time : 11:29:18
*INFO* f_1_step_si : 0.4951657818
previous_pred_les_level : 212.7386730975
previous_pred_les_trend : -82.0887808994
f_1_step_pred_les_level : 198.3286957429
f_1_step_pred_les_trend : -69.9638243374
f_1_step_pred_les : 128.3648714054
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 128.3648714054
f_1_step_pred_price_inc : 63.5618919076
f_1_step_pred_price : 88462.5618919075
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1787 >>>>
2017-06
11:29:18
88500
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:18
in_current_price : 88500.000000
*INFO* f_current_datetime : 2017-06 11:29:18
*INFO* f_current_si : 0.4951657818
*INFO* f_current_price4pm : 101
*INFO* f_current_price4pmsi : 203.9720911833
*INFO* f_1_step_time : 11:29:19
*INFO* f_1_step_si : 0.5080609123
previous_pred_les_level : 198.3286957429
previous_pred_les_trend : -69.9638243374
f_1_step_pred_les_level : 187.1197948451
f_1_step_pred_les_trend : -59.4376203091
f_1_step_pred_les : 127.6821745360
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 127.6821745360
f_1_step_pred_price_inc : 64.8703220840
f_1_step_pred_price : 88463.8703220840
f_1_step_pred_price_rounded : 88500
f_1_step_pred_set_price_rounded : 88800
-------------------------------------------------
==>> Prediction Restuls in Python List : [88800]
[88800]
<<<< Record No.: 1788 >>>>
2017-06
11:29:19
88600
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:19
in_current_price : 88600.000000
*INFO* f_current_datetime : 2017-06 11:29:19
*INFO* f_current_si : 0.5080609123
*INFO* f_current_price4pm : 201
*INFO* f_current_price4pmsi : 395.6218538349
*INFO* f_1_step_time : 11:29:20
*INFO* f_1_step_si : 0.5316053511
previous_pred_les_level : 187.1197948451
previous_pred_les_trend : -59.4376203091
f_1_step_pred_les_level : 335.9000588849
f_1_step_pred_les_trend : -22.1344667231
f_1_step_pred_les : 313.7655921619
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 313.7655921619
f_1_step_pred_price_inc : 166.7994677876
f_1_step_pred_price : 88565.7994677876
f_1_step_pred_price_rounded : 88600
f_1_step_pred_set_price_rounded : 88900
-------------------------------------------------
==>> Prediction Restuls in Python List : [88900]
[88900]
<<<< Record No.: 1789 >>>>
2017-06
11:29:20
88600
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:20
in_current_price : 88600.000000
*INFO* f_current_datetime : 2017-06 11:29:20
*INFO* f_current_si : 0.5316053511
*INFO* f_current_price4pm : 201
*INFO* f_current_price4pmsi : 378.1000314991
*INFO* f_1_step_time : 11:29:21
*INFO* f_1_step_si : 0.5724520024
previous_pred_les_level : 335.9000588849
previous_pred_les_trend : -22.1344667231
f_1_step_pred_les_level : 363.7603554781
f_1_step_pred_les_trend : -13.1776840706
f_1_step_pred_les : 350.5826714075
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 350.5826714075
f_1_step_pred_price_inc : 200.6917522398
f_1_step_pred_price : 88599.6917522398
f_1_step_pred_price_rounded : 88600
f_1_step_pred_set_price_rounded : 88900
-------------------------------------------------
==>> Prediction Restuls in Python List : [88900]
[88900]
<<<< Record No.: 1790 >>>>
2017-06
11:29:21
88600
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:21
in_current_price : 88600.000000
*INFO* f_current_datetime : 2017-06 11:29:21
*INFO* f_current_si : 0.5724520024
*INFO* f_current_price4pm : 201
*INFO* f_current_price4pmsi : 351.1211405873
*INFO* f_1_step_time : 11:29:22
*INFO* f_1_step_si : 0.5843722489
previous_pred_les_level : 363.7603554781
previous_pred_les_trend : -13.1776840706
f_1_step_pred_les_level : 351.0011197452
f_1_step_pred_les_trend : -13.1027172028
f_1_step_pred_les : 337.8984025425
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 337.8984025425
f_1_step_pred_price_inc : 197.4584493937
f_1_step_pred_price : 88596.4584493937
f_1_step_pred_price_rounded : 88600
f_1_step_pred_set_price_rounded : 88900
-------------------------------------------------
==>> Prediction Restuls in Python List : [88900]
[88900]
<<<< Record No.: 1791 >>>>
2017-06
11:29:22
88600
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:22
in_current_price : 88600.000000
*INFO* f_current_datetime : 2017-06 11:29:22
*INFO* f_current_si : 0.5843722489
*INFO* f_current_price4pm : 201
*INFO* f_current_price4pmsi : 343.9588385283
*INFO* f_1_step_time : 11:29:23
*INFO* f_1_step_si : 0.5966521604
previous_pred_les_level : 351.0011197452
previous_pred_les_trend : -13.1027172028
f_1_step_pred_les_level : 342.6080116698
f_1_step_pred_les_trend : -12.2589699274
f_1_step_pred_les : 330.3490417424
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 330.3490417424
f_1_step_pred_price_inc : 197.1034694274
f_1_step_pred_price : 88596.1034694274
f_1_step_pred_price_rounded : 88600
f_1_step_pred_set_price_rounded : 88900
-------------------------------------------------
==>> Prediction Restuls in Python List : [88900]
[88900]
<<<< Record No.: 1792 >>>>
2017-06
11:29:23
88600
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:23
in_current_price : 88600.000000
*INFO* f_current_datetime : 2017-06 11:29:23
*INFO* f_current_si : 0.5966521604
*INFO* f_current_price4pm : 201
*INFO* f_current_price4pmsi : 336.8796986838
*INFO* f_1_step_time : 11:29:24
*INFO* f_1_step_si : 0.6276205911
previous_pred_les_level : 342.6080116698
previous_pred_les_trend : -12.2589699274
f_1_step_pred_les_level : 335.4240630132
f_1_step_pred_les_trend : -11.3497574526
f_1_step_pred_les : 324.0743055606
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 324.0743055606
f_1_step_pred_price_inc : 203.3957072119
f_1_step_pred_price : 88602.3957072119
f_1_step_pred_price_rounded : 88600
f_1_step_pred_set_price_rounded : 88900
-------------------------------------------------
==>> Prediction Restuls in Python List : [88900]
[88900]
<<<< Record No.: 1793 >>>>
2017-06
11:29:24
88600
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:24
in_current_price : 88600.000000
*INFO* f_current_datetime : 2017-06 11:29:24
*INFO* f_current_si : 0.6276205911
*INFO* f_current_price4pm : 201
*INFO* f_current_price4pmsi : 320.2571790260
*INFO* f_1_step_time : 11:29:25
*INFO* f_1_step_si : 0.6615943855
previous_pred_les_level : 335.4240630132
previous_pred_les_trend : -11.3497574526
f_1_step_pred_les_level : 321.1079886141
f_1_step_pred_les_trend : -11.8811862345
f_1_step_pred_les : 309.2268023797
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 309.2268023797
f_1_step_pred_price_inc : 204.5827162878
f_1_step_pred_price : 88603.5827162878
f_1_step_pred_price_rounded : 88600
f_1_step_pred_set_price_rounded : 88900
-------------------------------------------------
==>> Prediction Restuls in Python List : [88900]
[88900]
<<<< Record No.: 1794 >>>>
2017-06
11:29:25
88700
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:25
in_current_price : 88700.000000
*INFO* f_current_datetime : 2017-06 11:29:25
*INFO* f_current_si : 0.6615943855
*INFO* f_current_price4pm : 301
*INFO* f_current_price4pmsi : 454.9615392991
*INFO* f_1_step_time : 11:29:26
*INFO* f_1_step_si : 0.6796086803
previous_pred_les_level : 321.1079886141
previous_pred_les_trend : -11.8811862345
f_1_step_pred_les_level : 422.4783322647
f_1_step_pred_les_trend : 8.4083255256
f_1_step_pred_les : 430.8866577903
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 430.8866577903
f_1_step_pred_price_inc : 292.8343128567
f_1_step_pred_price : 88691.8343128567
f_1_step_pred_price_rounded : 88700
f_1_step_pred_set_price_rounded : 89000
-------------------------------------------------
==>> Prediction Restuls in Python List : [89000]
[89000]
<<<< Record No.: 1795 >>>>
2017-06
11:29:26
88700
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:26
in_current_price : 88700.000000
*INFO* f_current_datetime : 2017-06 11:29:26
*INFO* f_current_si : 0.6796086803
*INFO* f_current_price4pm : 301
*INFO* f_current_price4pmsi : 442.9019356702
*INFO* f_1_step_time : 11:29:27
*INFO* f_1_step_si : 0.7008853554
previous_pred_les_level : 422.4783322647
previous_pred_les_trend : 8.4083255256
f_1_step_pred_les_level : 440.2238181040
f_1_step_pred_les_trend : 10.0811190338
f_1_step_pred_les : 450.3049371378
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 450.3049371378
f_1_step_pred_price_inc : 315.6121359060
f_1_step_pred_price : 88714.6121359060
f_1_step_pred_price_rounded : 88700
f_1_step_pred_set_price_rounded : 89000
-------------------------------------------------
==>> Prediction Restuls in Python List : [89000]
[89000]
<<<< Record No.: 1796 >>>>
2017-06
11:29:27
88700
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:27
in_current_price : 88700.000000
*INFO* f_current_datetime : 2017-06 11:29:27
*INFO* f_current_si : 0.7008853554
*INFO* f_current_price4pm : 301
*INFO* f_current_price4pmsi : 429.4568258264
*INFO* f_1_step_time : 11:29:28
*INFO* f_1_step_si : 0.7258007706
previous_pred_les_level : 440.2238181040
previous_pred_les_trend : 10.0811190338
f_1_step_pred_les_level : 434.1037173659
f_1_step_pred_les_trend : 7.1785989582
f_1_step_pred_les : 441.2823163241
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 441.2823163241
f_1_step_pred_price_inc : 320.2830452621
f_1_step_pred_price : 88719.2830452621
f_1_step_pred_price_rounded : 88700
f_1_step_pred_set_price_rounded : 89000
-------------------------------------------------
==>> Prediction Restuls in Python List : [89000]
[89000]
<<<< Record No.: 1797 >>>>
2017-06
11:29:28
88700
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:28
in_current_price : 88700.000000
*INFO* f_current_datetime : 2017-06 11:29:28
*INFO* f_current_si : 0.7258007706
*INFO* f_current_price4pm : 301
*INFO* f_current_price4pmsi : 414.7143571240
*INFO* f_1_step_time : 11:29:29
*INFO* f_1_step_si : 0.7406630214
previous_pred_les_level : 434.1037173659
previous_pred_les_trend : 7.1785989582
f_1_step_pred_les_level : 420.6361609260
f_1_step_pred_les_trend : 3.4797490338
f_1_step_pred_les : 424.1159099598
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 424.1159099598
f_1_step_pred_price_inc : 314.1269713077
f_1_step_pred_price : 88713.1269713077
f_1_step_pred_price_rounded : 88700
f_1_step_pred_set_price_rounded : 89000
-------------------------------------------------
==>> Prediction Restuls in Python List : [89000]
[89000]
<<<< Record No.: 1798 >>>>
2017-06
11:29:29
88700
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:29
in_current_price : 88700.000000
*INFO* f_current_datetime : 2017-06 11:29:29
*INFO* f_current_si : 0.7406630214
*INFO* f_current_price4pm : 301
*INFO* f_current_price4pmsi : 406.3926391499
*INFO* f_1_step_time : 11:29:30
*INFO* f_1_step_si : 0.7749686948
previous_pred_les_level : 420.6361609260
previous_pred_les_trend : 3.4797490338
f_1_step_pred_les_level : 410.3430265950
f_1_step_pred_les_trend : 1.0122761504
f_1_step_pred_les : 411.3553027454
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 411.3553027454
f_1_step_pred_price_inc : 318.7874820707
f_1_step_pred_price : 88717.7874820708
f_1_step_pred_price_rounded : 88700
f_1_step_pred_set_price_rounded : 89000
-------------------------------------------------
==>> Prediction Restuls in Python List : [89000]
[89000]
<<<< Record No.: 1799 >>>>
2017-06
11:29:30
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:30
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:30
*INFO* f_current_si : 0.7749686948
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 517.4402562152
*INFO* f_1_step_time : 11:29:31
*INFO* f_1_step_si : 0.7967683455
previous_pred_les_level : 410.3430265950
previous_pred_les_trend : 1.0122761504
f_1_step_pred_les_level : 493.7946959347
f_1_step_pred_les_trend : 15.7816575380
f_1_step_pred_les : 509.5763534728
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 509.5763534728
f_1_step_pred_price_inc : 406.0143080522
f_1_step_pred_price : 88805.0143080522
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1800 >>>>
2017-06
11:29:31
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:31
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:31
*INFO* f_current_si : 0.7967683455
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 503.2830461637
*INFO* f_1_step_time : 11:29:32
*INFO* f_1_step_si : 0.8239920952
previous_pred_les_level : 493.7946959347
previous_pred_les_trend : 15.7816575380
f_1_step_pred_les_level : 504.6857783371
f_1_step_pred_les_trend : 14.9054894030
f_1_step_pred_les : 519.5912677400
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 519.5912677400
f_1_step_pred_price_inc : 428.1390973348
f_1_step_pred_price : 88827.1390973348
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1801 >>>>
2017-06
11:29:32
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:32
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:32
*INFO* f_current_si : 0.8239920952
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 486.6551540394
*INFO* f_1_step_time : 11:29:33
*INFO* f_1_step_si : 0.8456485559
previous_pred_les_level : 504.6857783371
previous_pred_les_trend : 14.9054894030
f_1_step_pred_les_level : 493.9963729064
f_1_step_pred_les_trend : 10.3200509524
f_1_step_pred_les : 504.3164238588
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 504.3164238588
f_1_step_pred_price_inc : 426.4744555749
f_1_step_pred_price : 88825.4744555749
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1802 >>>>
2017-06
11:29:33
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:33
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:33
*INFO* f_current_si : 0.8456485559
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 474.1922601080
*INFO* f_1_step_time : 11:29:34
*INFO* f_1_step_si : 0.8708946861
previous_pred_les_level : 493.9963729064
previous_pred_les_trend : 10.3200509524
f_1_step_pred_les_level : 480.9067158962
f_1_step_pred_les_trend : 6.1260983807
f_1_step_pred_les : 487.0328142769
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 487.0328142769
f_1_step_pred_price_inc : 424.1542898994
f_1_step_pred_price : 88823.1542898994
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1803 >>>>
2017-06
11:29:34
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:34
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:34
*INFO* f_current_si : 0.8708946861
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 460.4460291357
*INFO* f_1_step_time : 11:29:35
*INFO* f_1_step_si : 0.9278569942
previous_pred_les_level : 480.9067158962
previous_pred_les_trend : 6.1260983807
f_1_step_pred_les_level : 466.3720291023
f_1_step_pred_les_trend : 2.4246274673
f_1_step_pred_les : 468.7966565696
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 468.7966565696
f_1_step_pred_price_inc : 434.9762566352
f_1_step_pred_price : 88833.9762566352
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1804 >>>>
2017-06
11:29:35
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:35
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:35
*INFO* f_current_si : 0.9278569942
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 432.1786681844
*INFO* f_1_step_time : 11:29:36
*INFO* f_1_step_si : 0.9616321097
previous_pred_les_level : 466.3720291023
previous_pred_les_trend : 2.4246274673
f_1_step_pred_les_level : 440.3405499913
f_1_step_pred_les_trend : -2.6734097041
f_1_step_pred_les : 437.6671402872
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 437.6671402872
f_1_step_pred_price_inc : 420.8747754763
f_1_step_pred_price : 88819.8747754763
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1805 >>>>
2017-06
11:29:36
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:36
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:36
*INFO* f_current_si : 0.9616321097
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 416.9993867096
*INFO* f_1_step_time : 11:29:37
*INFO* f_1_step_si : 0.9787400282
previous_pred_les_level : 440.3405499913
previous_pred_les_trend : -2.6734097041
f_1_step_pred_les_level : 421.6060778293
f_1_step_pred_les_trend : -5.5508199779
f_1_step_pred_les : 416.0552578514
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 416.0552578514
f_1_step_pred_price_inc : 407.2099347858
f_1_step_pred_price : 88806.2099347858
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1806 >>>>
2017-06
11:29:37
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:37
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:37
*INFO* f_current_si : 0.9787400282
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 409.7104322520
*INFO* f_1_step_time : 11:29:38
*INFO* f_1_step_si : 0.9870518518
previous_pred_les_level : 421.6060778293
previous_pred_les_trend : -5.5508199779
f_1_step_pred_les_level : 411.1246474755
f_1_step_pred_les_trend : -6.4341606030
f_1_step_pred_les : 404.6904868724
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 404.6904868724
f_1_step_pred_price_inc : 399.4504944668
f_1_step_pred_price : 88798.4504944668
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1807 >>>>
2017-06
11:29:38
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:38
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:38
*INFO* f_current_si : 0.9870518518
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 406.2603188224
*INFO* f_1_step_time : 11:29:39
*INFO* f_1_step_si : 1.0277287334
previous_pred_les_level : 411.1246474755
previous_pred_les_trend : -6.4341606030
f_1_step_pred_les_level : 405.9104147617
f_1_step_pred_les_trend : -6.2156051338
f_1_step_pred_les : 399.6948096279
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 399.6948096279
f_1_step_pred_price_inc : 410.7778404440
f_1_step_pred_price : 88809.7778404440
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1808 >>>>
2017-06
11:29:39
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:39
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:39
*INFO* f_current_si : 1.0277287334
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 390.1807811432
*INFO* f_1_step_time : 11:29:40
*INFO* f_1_step_si : 1.0732818240
previous_pred_les_level : 405.9104147617
previous_pred_les_trend : -6.2156051338
f_1_step_pred_les_level : 392.3013885120
f_1_step_pred_les_trend : -7.5401691801
f_1_step_pred_les : 384.7612193319
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 384.7612193319
f_1_step_pred_price_inc : 412.9572233069
f_1_step_pred_price : 88811.9572233069
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1809 >>>>
2017-06
11:29:40
88800
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:40
in_current_price : 88800.000000
*INFO* f_current_datetime : 2017-06 11:29:40
*INFO* f_current_si : 1.0732818240
*INFO* f_current_price4pm : 401
*INFO* f_current_price4pmsi : 373.6204145227
*INFO* f_1_step_time : 11:29:41
*INFO* f_1_step_si : 1.1014312083
previous_pred_les_level : 392.3013885120
previous_pred_les_trend : -7.5401691801
f_1_step_pred_les_level : 376.1036184369
f_1_step_pred_les_trend : -9.0912166172
f_1_step_pred_les : 367.0124018197
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 367.0124018197
f_1_step_pred_price_inc : 404.2389131860
f_1_step_pred_price : 88803.2389131860
f_1_step_pred_price_rounded : 88800
f_1_step_pred_set_price_rounded : 89100
-------------------------------------------------
==>> Prediction Restuls in Python List : [89100]
[89100]
<<<< Record No.: 1810 >>>>
2017-06
11:29:41
88900
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:41
in_current_price : 88900.000000
*INFO* f_current_datetime : 2017-06 11:29:41
*INFO* f_current_si : 1.1014312083
*INFO* f_current_price4pm : 501
*INFO* f_current_price4pmsi : 454.8627242797
*INFO* f_1_step_time : 11:29:42
*INFO* f_1_step_si : 1.1636423891
previous_pred_les_level : 376.1036184369
previous_pred_les_trend : -9.0912166172
f_1_step_pred_les_level : 435.2815298931
f_1_step_pred_les_trend : 3.1394991912
f_1_step_pred_les : 438.4210290843
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 438.4210290843
f_1_step_pred_price_inc : 510.1652937123
f_1_step_pred_price : 88909.1652937123
f_1_step_pred_price_rounded : 88900
f_1_step_pred_set_price_rounded : 89200
-------------------------------------------------
==>> Prediction Restuls in Python List : [89200]
[89200]
<<<< Record No.: 1811 >>>>
2017-06
11:29:42
88900
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:42
in_current_price : 88900.000000
*INFO* f_current_datetime : 2017-06 11:29:42
*INFO* f_current_si : 1.1636423891
*INFO* f_current_price4pm : 501
*INFO* f_current_price4pmsi : 430.5446455852
*INFO* f_1_step_time : 11:29:43
*INFO* f_1_step_si : 1.2770115614
previous_pred_les_level : 435.2815298931
previous_pred_les_trend : 3.1394991912
f_1_step_pred_les_level : 432.3002338635
f_1_step_pred_les_trend : 2.0429316946
f_1_step_pred_les : 434.3431655582
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 434.3431655582
f_1_step_pred_price_inc : 554.6612440165
f_1_step_pred_price : 88953.6612440165
f_1_step_pred_price_rounded : 89000
f_1_step_pred_set_price_rounded : 89300
-------------------------------------------------
==>> Prediction Restuls in Python List : [89300]
[89300]
<<<< Record No.: 1812 >>>>
2017-06
11:29:43
89000
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:43
in_current_price : 89000.000000
*INFO* f_current_datetime : 2017-06 11:29:43
*INFO* f_current_si : 1.2770115614
*INFO* f_current_price4pm : 601
*INFO* f_current_price4pmsi : 470.6300382737
*INFO* f_1_step_time : 11:29:44
*INFO* f_1_step_si : 1.3885120709
previous_pred_les_level : 432.3002338635
previous_pred_les_trend : 2.0429316946
f_1_step_pred_les_level : 462.5419597280
f_1_step_pred_les_trend : 7.0948702116
f_1_step_pred_les : 469.6368299395
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 469.6368299395
f_1_step_pred_price_inc : 652.0964073328
f_1_step_pred_price : 89051.0964073328
f_1_step_pred_price_rounded : 89100
f_1_step_pred_set_price_rounded : 89400
-------------------------------------------------
==>> Prediction Restuls in Python List : [89400]
[89400]
<<<< Record No.: 1813 >>>>
2017-06
11:29:44
89000
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:44
in_current_price : 89000.000000
*INFO* f_current_datetime : 2017-06 11:29:44
*INFO* f_current_si : 1.3885120709
*INFO* f_current_price4pm : 601
*INFO* f_current_price4pmsi : 432.8374326553
*INFO* f_1_step_time : 11:29:45
*INFO* f_1_step_si : 1.4408790775
previous_pred_les_level : 462.5419597280
previous_pred_les_trend : 7.0948702116
f_1_step_pred_les_level : 441.0397491791
f_1_step_pred_les_trend : 1.9715768929
f_1_step_pred_les : 443.0113260719
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 443.0113260719
f_1_step_pred_price_inc : 638.3257508481
f_1_step_pred_price : 89037.3257508481
f_1_step_pred_price_rounded : 89000
f_1_step_pred_set_price_rounded : 89300
-------------------------------------------------
==>> Prediction Restuls in Python List : [89300]
[89300]
<<<< Record No.: 1814 >>>>
2017-06
11:29:45
89100
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:45
in_current_price : 89100.000000
*INFO* f_current_datetime : 2017-06 11:29:45
*INFO* f_current_si : 1.4408790775
*INFO* f_current_price4pm : 701
*INFO* f_current_price4pmsi : 486.5085564287
*INFO* f_1_step_time : 11:29:46
*INFO* f_1_step_si : 1.5694557714
previous_pred_les_level : 441.0397491791
previous_pred_les_trend : 1.9715768929
f_1_step_pred_les_level : 476.8133418974
f_1_step_pred_les_trend : 8.0273573163
f_1_step_pred_les : 484.8406992137
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 484.8406992137
f_1_step_pred_price_inc : 760.9360335720
f_1_step_pred_price : 89159.9360335720
f_1_step_pred_price_rounded : 89200
f_1_step_pred_set_price_rounded : 89500
-------------------------------------------------
==>> Prediction Restuls in Python List : [89500]
[89500]
<<<< Record No.: 1815 >>>>
2017-06
11:29:46
89100
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:46
in_current_price : 89100.000000
*INFO* f_current_datetime : 2017-06 11:29:46
*INFO* f_current_si : 1.5694557714
*INFO* f_current_price4pm : 701
*INFO* f_current_price4pmsi : 446.6516437044
*INFO* f_1_step_time : 11:29:47
*INFO* f_1_step_si : 1.6448651013
previous_pred_les_level : 476.8133418974
previous_pred_les_trend : 8.0273573163
f_1_step_pred_les_level : 455.1637048833
f_1_step_pred_les_trend : 2.7105927121
f_1_step_pred_les : 457.8742975954
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 457.8742975954
f_1_step_pred_price_inc : 753.1414529177
f_1_step_pred_price : 89152.1414529177
f_1_step_pred_price_rounded : 89200
f_1_step_pred_set_price_rounded : 89500
-------------------------------------------------
==>> Prediction Restuls in Python List : [89500]
[89500]
<<<< Record No.: 1816 >>>>
2017-06
11:29:47
89100
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:47
in_current_price : 89100.000000
*INFO* f_current_datetime : 2017-06 11:29:47
*INFO* f_current_si : 1.6448651013
*INFO* f_current_price4pm : 701
*INFO* f_current_price4pmsi : 426.1747662021
*INFO* f_1_step_time : 11:29:48
*INFO* f_1_step_si : 1.7484231604
previous_pred_les_level : 455.1637048833
previous_pred_les_trend : 2.7105927121
f_1_step_pred_les_level : 433.2403599165
f_1_step_pred_les_trend : -1.7026860202
f_1_step_pred_les : 431.5376738963
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 431.5376738963
f_1_step_pred_price_inc : 754.5104636382
f_1_step_pred_price : 89153.5104636382
f_1_step_pred_price_rounded : 89200
f_1_step_pred_set_price_rounded : 89500
-------------------------------------------------
==>> Prediction Restuls in Python List : [89500]
[89500]
<<<< Record No.: 1817 >>>>
2017-06
11:29:48
89100
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:48
in_current_price : 89100.000000
*INFO* f_current_datetime : 2017-06 11:29:48
*INFO* f_current_si : 1.7484231604
*INFO* f_current_price4pm : 701
*INFO* f_current_price4pmsi : 400.9326894456
*INFO* f_1_step_time : 11:29:49
*INFO* f_1_step_si : 1.7903136447
previous_pred_les_level : 433.2403599165
previous_pred_les_trend : -1.7026860202
f_1_step_pred_les_level : 407.7543166514
f_1_step_pred_les_trend : -5.9635795110
f_1_step_pred_les : 401.7907371404
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 401.7907371404
f_1_step_pred_price_inc : 719.3314390018
f_1_step_pred_price : 89118.3314390018
f_1_step_pred_price_rounded : 89100
f_1_step_pred_set_price_rounded : 89400
-------------------------------------------------
==>> Prediction Restuls in Python List : [89400]
[89400]
<<<< Record No.: 1818 >>>>
2017-06
11:29:49
89100
==>> Forecasting 1 out of next 1 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:49
in_current_price : 89100.000000
*INFO* f_current_datetime : 2017-06 11:29:49
*INFO* f_current_si : 1.7903136447
*INFO* f_current_price4pm : 701
*INFO* f_current_price4pmsi : 391.5515038885
*INFO* f_1_step_time : 11:29:50
*INFO* f_1_step_si : 1.9309782795
previous_pred_les_level : 407.7543166514
previous_pred_les_trend : -5.9635795110
f_1_step_pred_les_level : 393.8337540961
f_1_step_pred_les_trend : -7.3891081658
f_1_step_pred_les : 386.4446459303
f_1_step_pred_adj_misc : 0.0000000000
pred_les + pred_adj_misc : 386.4446459303
f_1_step_pred_price_inc : 746.2162175027
f_1_step_pred_price : 89145.2162175027
f_1_step_pred_price_rounded : 89100
f_1_step_pred_set_price_rounded : 89400
-------------------------------------------------
==>> Prediction Restuls in Python List : [89400]
[89400]
In [6]:
# Upon receiving 11:29:50 second price, to predict till 11:30:00 <- ten-step forward price forecasting
for i in range(shl_sm_parm_ccyy_mm_offset+50, shl_sm_parm_ccyy_mm_offset+51): # use csv data as simulation
print('\n<<<< Record No.: %5d >>>>' % i)
print(shl_sm_data['ccyy-mm'][i]) # format: ccyy-mm
print(shl_sm_data['time'][i]) # format: hh:mm:ss
print(shl_sm_data['bid-price'][i]) # format: integer/boost-trap-float
######################################################################################################################
# call prediction function, returned result is in 'list' format, i.e. [89400, 89400, 89400, 89500, 89500, 89500, 89500, 89600, 89600, 89600]
shl_sm_prediction_list_local_k = shl_pm.shl_predict_price_k_step(shl_sm_data['time'][i], shl_sm_data['bid-price'][i],10) # <- ten-step forward price forecasting
print(shl_sm_prediction_list_local_k)
######################################################################################################################
<<<< Record No.: 1819 >>>>
2017-06
11:29:50
89100
==>> Forecasting 1 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:50
in_current_price : 89100.000000
*INFO* f_current_datetime : 2017-06 11:29:50
*INFO* f_current_si : 1.9309782795
*INFO* f_current_price4pm : 701
*INFO* f_current_price4pmsi : 363.0284231878
*INFO* f_1_step_time : 11:29:51
*INFO* f_1_step_si : 2.0018259434
*INFO* sec50_error : 45.2162175027
*INFO* sec46_49_error : 183.9193891297
*INFO* shl_global_parm_short_weight_misc : 45.8271213265
*INFO* shl_global_parm_short_weight_ratio : 1
previous_pred_les_level : 393.8337540961
previous_pred_les_trend : -7.3891081658
f_1_step_pred_les_level : 368.2477279835
f_1_step_pred_les_trend : -10.6491663836
f_1_step_pred_les : 357.5985616000
f_1_step_pred_adj_misc : 0.6908371436
pred_les + pred_adj_misc : 358.2893987436
f_1_step_pred_price_inc : 717.2330136484
f_1_step_pred_price : 89116.2330136484
f_1_step_pred_price_rounded : 89100
f_1_step_pred_set_price_rounded : 89400
-------------------------------------------------
==>> Forecasting 2 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:51
in_current_price : 89116.233014
*INFO* f_current_datetime : 2017-06 11:29:51
*INFO* f_current_si : 2.0018259434
*INFO* f_current_price4pm : 717
*INFO* f_current_price4pmsi : 358.2893987436
*INFO* f_1_step_time : 11:29:52
*INFO* f_1_step_si : 2.0608409575
*INFO* shl_global_parm_short_weight_ratio : 2
previous_pred_les_level : 368.2477279835
previous_pred_les_trend : -10.6491663836
f_1_step_pred_les_level : 358.1354161967
f_1_step_pred_les_trend : -10.5529865115
f_1_step_pred_les : 347.5824296851
f_1_step_pred_adj_misc : 1.3816742872
pred_les + pred_adj_misc : 348.9641039723
f_1_step_pred_price_inc : 719.1595181679
f_1_step_pred_price : 89118.1595181679
f_1_step_pred_price_rounded : 89100
f_1_step_pred_set_price_rounded : 89400
-------------------------------------------------
==>> Forecasting 3 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:52
in_current_price : 89118.159518
*INFO* f_current_datetime : 2017-06 11:29:52
*INFO* f_current_si : 2.0608409575
*INFO* f_current_price4pm : 719
*INFO* f_current_price4pmsi : 348.9641039723
*INFO* f_1_step_time : 11:29:53
*INFO* f_1_step_si : 2.1669312844
*INFO* shl_global_parm_short_weight_ratio : 3
previous_pred_les_level : 358.1354161967
previous_pred_les_trend : -10.5529865115
f_1_step_pred_les_level : 348.6561388785
f_1_step_pred_les_trend : -10.3606267674
f_1_step_pred_les : 338.2955121111
f_1_step_pred_adj_misc : 2.0725114308
pred_les + pred_adj_misc : 340.3680235419
f_1_step_pred_price_inc : 737.5541184282
f_1_step_pred_price : 89136.5541184282
f_1_step_pred_price_rounded : 89100
f_1_step_pred_set_price_rounded : 89400
-------------------------------------------------
==>> Forecasting 4 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:53
in_current_price : 89136.554118
*INFO* f_current_datetime : 2017-06 11:29:53
*INFO* f_current_si : 2.1669312844
*INFO* f_current_price4pm : 737
*INFO* f_current_price4pmsi : 340.3680235419
*INFO* f_1_step_time : 11:29:54
*INFO* f_1_step_si : 2.2854831719
*INFO* shl_global_parm_short_weight_ratio : 4
previous_pred_les_level : 348.6561388785
previous_pred_les_trend : -10.3606267674
f_1_step_pred_les_level : 339.9060759012
f_1_step_pred_les_trend : -10.0720871513
f_1_step_pred_les : 329.8339887499
f_1_step_pred_adj_misc : 2.7633485744
pred_les + pred_adj_misc : 332.5973373243
f_1_step_pred_price_inc : 760.1456174595
f_1_step_pred_price : 89159.1456174595
f_1_step_pred_price_rounded : 89200
f_1_step_pred_set_price_rounded : 89500
-------------------------------------------------
==>> Forecasting 5 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:54
in_current_price : 89159.145617
*INFO* f_current_datetime : 2017-06 11:29:54
*INFO* f_current_si : 2.2854831719
*INFO* f_current_price4pm : 760
*INFO* f_current_price4pmsi : 332.5973373243
*INFO* f_1_step_time : 11:29:55
*INFO* f_1_step_si : 2.4051380825
*INFO* shl_global_parm_short_weight_ratio : 5
previous_pred_les_level : 339.9060759012
previous_pred_les_trend : -10.0720871513
f_1_step_pred_les_level : 331.9814071367
f_1_step_pred_les_trend : -9.6873676631
f_1_step_pred_les : 322.2940394736
f_1_step_pred_adj_misc : 3.4541857180
pred_les + pred_adj_misc : 325.7482251916
f_1_step_pred_price_inc : 783.4694617175
f_1_step_pred_price : 89182.4694617175
f_1_step_pred_price_rounded : 89200
f_1_step_pred_set_price_rounded : 89500
-------------------------------------------------
==>> Forecasting 6 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:55
in_current_price : 89182.469462
*INFO* f_current_datetime : 2017-06 11:29:55
*INFO* f_current_si : 2.4051380825
*INFO* f_current_price4pm : 783
*INFO* f_current_price4pmsi : 325.7482251916
*INFO* f_1_step_time : 11:29:56
*INFO* f_1_step_si : 2.5395496217
*INFO* shl_global_parm_short_weight_ratio : 6
previous_pred_les_level : 331.9814071367
previous_pred_les_trend : -9.6873676631
f_1_step_pred_les_level : 324.9783124571
f_1_step_pred_les_trend : -9.2064683029
f_1_step_pred_les : 315.7718441542
f_1_step_pred_adj_misc : 4.1450228616
pred_les + pred_adj_misc : 319.9168670159
f_1_step_pred_price_inc : 812.4447586070
f_1_step_pred_price : 89211.4447586070
f_1_step_pred_price_rounded : 89200
f_1_step_pred_set_price_rounded : 89500
-------------------------------------------------
==>> Forecasting 7 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:56
in_current_price : 89211.444759
*INFO* f_current_datetime : 2017-06 11:29:56
*INFO* f_current_si : 2.5395496217
*INFO* f_current_price4pm : 812
*INFO* f_current_price4pmsi : 319.9168670159
*INFO* f_1_step_time : 11:29:57
*INFO* f_1_step_si : 2.6922988441
*INFO* shl_global_parm_short_weight_ratio : 7
previous_pred_les_level : 324.9783124571
previous_pred_les_trend : -9.2064683029
f_1_step_pred_les_level : 318.9929717345
f_1_step_pred_les_trend : -8.6293890706
f_1_step_pred_les : 310.3635826639
f_1_step_pred_adj_misc : 4.8358600053
pred_les + pred_adj_misc : 315.1994426691
f_1_step_pred_price_inc : 848.6110951716
f_1_step_pred_price : 89247.6110951716
f_1_step_pred_price_rounded : 89200
f_1_step_pred_set_price_rounded : 89500
-------------------------------------------------
==>> Forecasting 8 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:57
in_current_price : 89247.611095
*INFO* f_current_datetime : 2017-06 11:29:57
*INFO* f_current_si : 2.6922988441
*INFO* f_current_price4pm : 848
*INFO* f_current_price4pmsi : 315.1994426691
*INFO* f_1_step_time : 11:29:58
*INFO* f_1_step_si : 2.7559213247
*INFO* shl_global_parm_short_weight_ratio : 8
previous_pred_les_level : 318.9929717345
previous_pred_les_trend : -8.6293890706
f_1_step_pred_les_level : 314.1215648408
f_1_step_pred_les_trend : -7.9561299663
f_1_step_pred_les : 306.1654348745
f_1_step_pred_adj_misc : 5.5266971489
pred_les + pred_adj_misc : 311.6921320234
f_1_step_pred_price_inc : 858.9989933841
f_1_step_pred_price : 89257.9989933841
f_1_step_pred_price_rounded : 89300
f_1_step_pred_set_price_rounded : 89600
-------------------------------------------------
==>> Forecasting 9 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:58
in_current_price : 89257.998993
*INFO* f_current_datetime : 2017-06 11:29:58
*INFO* f_current_si : 2.7559213247
*INFO* f_current_price4pm : 858
*INFO* f_current_price4pmsi : 311.6921320234
*INFO* f_1_step_time : 11:29:59
*INFO* f_1_step_si : 2.9170470952
*INFO* shl_global_parm_short_weight_ratio : 9
previous_pred_les_level : 314.1215648408
previous_pred_les_trend : -7.9561299663
f_1_step_pred_les_level : 310.4602716481
f_1_step_pred_les_trend : -7.1866909899
f_1_step_pred_les : 303.2735806582
f_1_step_pred_adj_misc : 6.2175342925
pred_les + pred_adj_misc : 309.4911149507
f_1_step_pred_price_inc : 902.8001578506
f_1_step_pred_price : 89301.8001578506
f_1_step_pred_price_rounded : 89300
f_1_step_pred_set_price_rounded : 89600
-------------------------------------------------
==>> Forecasting 10 out of next 10 seconds/steps...
+-----------------------------------------------+
| shl_predict_price_1_step() |
+-----------------------------------------------+
current_ccyy_mm : 2017-06
in_current_time : 11:29:59
in_current_price : 89301.800158
*INFO* f_current_datetime : 2017-06 11:29:59
*INFO* f_current_si : 2.9170470952
*INFO* f_current_price4pm : 902
*INFO* f_current_price4pmsi : 309.4911149507
*INFO* f_1_step_time : 11:30:00
*INFO* f_1_step_si : 3.0648617499
*INFO* shl_global_parm_short_weight_ratio : 10
previous_pred_les_level : 310.4602716481
previous_pred_les_trend : -7.1866909899
f_1_step_pred_les_level : 308.1052720286
f_1_step_pred_les_trend : -6.3210721415
f_1_step_pred_les : 301.7841998870
f_1_step_pred_adj_misc : 6.9083714361
pred_les + pred_adj_misc : 308.6925713231
f_1_step_pred_price_inc : 946.1000543343
f_1_step_pred_price : 89345.1000543343
f_1_step_pred_price_rounded : 89300
f_1_step_pred_set_price_rounded : 89600
-------------------------------------------------
==>> Prediction Restuls in Python List : [89400, 89400, 89400, 89500, 89500, 89500, 89500, 89600, 89600, 89600]
[89400, 89400, 89400, 89500, 89500, 89500, 89500, 89600, 89600, 89600]
In [7]:
print(shl_sm_prediction_list_local_k)
[89400, 89400, 89400, 89500, 89500, 89500, 89500, 89600, 89600, 89600]
In [8]:
shl_pm.shl_data_pm_1_step.tail(11)
Out[8]:
ccyy-mm
f_1_step_pred_adj_misc
f_1_step_pred_les
f_1_step_pred_les_level
f_1_step_pred_les_trend
f_1_step_pred_price
f_1_step_pred_price_inc
f_1_step_pred_price_rounded
f_1_step_pred_set_price_rounded
f_1_step_si
f_1_step_time
f_current_bid
f_current_datetime
f_current_price4pm
f_current_price4pmsi
f_current_si
40
2017-06
0.000000
367.012402
376.103618
-9.091217
88803.238913
404.238913
88800.0
89100.0
1.101431
11:29:41
88800.0
2017-06 11:29:40
401.0
373.620415
1.073282
41
2017-06
0.000000
438.421029
435.281530
3.139499
88909.165294
510.165294
88900.0
89200.0
1.163642
11:29:42
88900.0
2017-06 11:29:41
501.0
454.862724
1.101431
42
2017-06
0.000000
434.343166
432.300234
2.042932
88953.661244
554.661244
89000.0
89300.0
1.277012
11:29:43
88900.0
2017-06 11:29:42
501.0
430.544646
1.163642
43
2017-06
0.000000
469.636830
462.541960
7.094870
89051.096407
652.096407
89100.0
89400.0
1.388512
11:29:44
89000.0
2017-06 11:29:43
601.0
470.630038
1.277012
44
2017-06
0.000000
443.011326
441.039749
1.971577
89037.325751
638.325751
89000.0
89300.0
1.440879
11:29:45
89000.0
2017-06 11:29:44
601.0
432.837433
1.388512
45
2017-06
0.000000
484.840699
476.813342
8.027357
89159.936034
760.936034
89200.0
89500.0
1.569456
11:29:46
89100.0
2017-06 11:29:45
701.0
486.508556
1.440879
46
2017-06
0.000000
457.874298
455.163705
2.710593
89152.141453
753.141453
89200.0
89500.0
1.644865
11:29:47
89100.0
2017-06 11:29:46
701.0
446.651644
1.569456
47
2017-06
0.000000
431.537674
433.240360
-1.702686
89153.510464
754.510464
89200.0
89500.0
1.748423
11:29:48
89100.0
2017-06 11:29:47
701.0
426.174766
1.644865
48
2017-06
0.000000
401.790737
407.754317
-5.963580
89118.331439
719.331439
89100.0
89400.0
1.790314
11:29:49
89100.0
2017-06 11:29:48
701.0
400.932689
1.748423
49
2017-06
0.000000
386.444646
393.833754
-7.389108
89145.216218
746.216218
89100.0
89400.0
1.930978
11:29:50
89100.0
2017-06 11:29:49
701.0
391.551504
1.790314
50
2017-06
0.690837
357.598562
368.247728
-10.649166
89116.233014
717.233014
89100.0
89400.0
2.001826
11:29:51
89100.0
2017-06 11:29:50
701.0
363.028423
1.930978
In [9]:
shl_pm.shl_data_pm_k_step.tail(20)
Out[9]:
ccyy-mm
f_1_step_pred_adj_misc
f_1_step_pred_les
f_1_step_pred_les_level
f_1_step_pred_les_trend
f_1_step_pred_price
f_1_step_pred_price_inc
f_1_step_pred_price_rounded
f_1_step_pred_set_price_rounded
f_1_step_si
f_1_step_time
f_current_bid
f_current_datetime
f_current_price4pm
f_current_price4pmsi
f_current_si
40
2017-06
0.000000
367.012402
376.103618
-9.091217
88803.238913
404.238913
88800.0
89100.0
1.101431
11:29:41
88800.000000
2017-06 11:29:40
401.000000
373.620415
1.073282
41
2017-06
0.000000
438.421029
435.281530
3.139499
88909.165294
510.165294
88900.0
89200.0
1.163642
11:29:42
88900.000000
2017-06 11:29:41
501.000000
454.862724
1.101431
42
2017-06
0.000000
434.343166
432.300234
2.042932
88953.661244
554.661244
89000.0
89300.0
1.277012
11:29:43
88900.000000
2017-06 11:29:42
501.000000
430.544646
1.163642
43
2017-06
0.000000
469.636830
462.541960
7.094870
89051.096407
652.096407
89100.0
89400.0
1.388512
11:29:44
89000.000000
2017-06 11:29:43
601.000000
470.630038
1.277012
44
2017-06
0.000000
443.011326
441.039749
1.971577
89037.325751
638.325751
89000.0
89300.0
1.440879
11:29:45
89000.000000
2017-06 11:29:44
601.000000
432.837433
1.388512
45
2017-06
0.000000
484.840699
476.813342
8.027357
89159.936034
760.936034
89200.0
89500.0
1.569456
11:29:46
89100.000000
2017-06 11:29:45
701.000000
486.508556
1.440879
46
2017-06
0.000000
457.874298
455.163705
2.710593
89152.141453
753.141453
89200.0
89500.0
1.644865
11:29:47
89100.000000
2017-06 11:29:46
701.000000
446.651644
1.569456
47
2017-06
0.000000
431.537674
433.240360
-1.702686
89153.510464
754.510464
89200.0
89500.0
1.748423
11:29:48
89100.000000
2017-06 11:29:47
701.000000
426.174766
1.644865
48
2017-06
0.000000
401.790737
407.754317
-5.963580
89118.331439
719.331439
89100.0
89400.0
1.790314
11:29:49
89100.000000
2017-06 11:29:48
701.000000
400.932689
1.748423
49
2017-06
0.000000
386.444646
393.833754
-7.389108
89145.216218
746.216218
89100.0
89400.0
1.930978
11:29:50
89100.000000
2017-06 11:29:49
701.000000
391.551504
1.790314
50
2017-06
0.690837
357.598562
368.247728
-10.649166
89116.233014
717.233014
89100.0
89400.0
2.001826
11:29:51
89100.000000
2017-06 11:29:50
701.000000
363.028423
1.930978
51
2017-06
1.381674
347.582430
358.135416
-10.552987
89118.159518
719.159518
89100.0
89400.0
2.060841
11:29:52
89116.233014
2017-06 11:29:51
717.233014
358.289399
2.001826
52
2017-06
2.072511
338.295512
348.656139
-10.360627
89136.554118
737.554118
89100.0
89400.0
2.166931
11:29:53
89118.159518
2017-06 11:29:52
719.159518
348.964104
2.060841
53
2017-06
2.763349
329.833989
339.906076
-10.072087
89159.145617
760.145617
89200.0
89500.0
2.285483
11:29:54
89136.554118
2017-06 11:29:53
737.554118
340.368024
2.166931
54
2017-06
3.454186
322.294039
331.981407
-9.687368
89182.469462
783.469462
89200.0
89500.0
2.405138
11:29:55
89159.145617
2017-06 11:29:54
760.145617
332.597337
2.285483
55
2017-06
4.145023
315.771844
324.978312
-9.206468
89211.444759
812.444759
89200.0
89500.0
2.539550
11:29:56
89182.469462
2017-06 11:29:55
783.469462
325.748225
2.405138
56
2017-06
4.835860
310.363583
318.992972
-8.629389
89247.611095
848.611095
89200.0
89500.0
2.692299
11:29:57
89211.444759
2017-06 11:29:56
812.444759
319.916867
2.539550
57
2017-06
5.526697
306.165435
314.121565
-7.956130
89257.998993
858.998993
89300.0
89600.0
2.755921
11:29:58
89247.611095
2017-06 11:29:57
848.611095
315.199443
2.692299
58
2017-06
6.217534
303.273581
310.460272
-7.186691
89301.800158
902.800158
89300.0
89600.0
2.917047
11:29:59
89257.998993
2017-06 11:29:58
858.998993
311.692132
2.755921
59
2017-06
6.908371
301.784200
308.105272
-6.321072
89345.100054
946.100054
89300.0
89600.0
3.064862
11:30:00
89301.800158
2017-06 11:29:59
902.800158
309.491115
2.917047
In [ ]:
In [10]:
%matplotlib inline
import matplotlib.pyplot as plt
In [11]:
shl_data_pm_k_step_local = shl_pm.shl_data_pm_k_step.copy()
shl_data_pm_k_step_local.index = shl_data_pm_k_step_local.index + 1
shl_data_pm_k_step_local
Out[11]:
ccyy-mm
f_1_step_pred_adj_misc
f_1_step_pred_les
f_1_step_pred_les_level
f_1_step_pred_les_trend
f_1_step_pred_price
f_1_step_pred_price_inc
f_1_step_pred_price_rounded
f_1_step_pred_set_price_rounded
f_1_step_si
f_1_step_time
f_current_bid
f_current_datetime
f_current_price4pm
f_current_price4pmsi
f_current_si
1
2017-06
0.000000
419.777714
419.777714
0.000000
88405.238354
6.238354
88400.0
88700.0
0.014861
11:29:01
88400.000000
2017-06 11:29:00
1.000000
419.777714
0.002382
2
2017-06
0.000000
6262.747618
5374.998016
887.749602
88547.859596
148.859596
88500.0
88800.0
0.023769
11:29:02
88500.000000
2017-06 11:29:01
101.000000
6796.271946
0.014861
3
2017-06
0.000000
5305.444506
4698.022347
607.422159
88563.168194
164.168194
88600.0
88900.0
0.030943
11:29:03
88500.000000
2017-06 11:29:02
101.000000
4249.222273
0.023769
4
2017-06
0.000000
4042.258212
3719.046298
323.211914
88557.505465
158.505465
88600.0
88900.0
0.039212
11:29:04
88500.000000
2017-06 11:29:03
101.000000
3264.029916
0.030943
5
2017-06
0.000000
3021.651646
2902.612326
119.039320
88516.146200
117.146200
88500.0
88800.0
0.038769
11:29:05
88500.000000
2017-06 11:29:04
101.000000
2575.735036
0.039212
6
2017-06
0.000000
2759.064745
2698.007673
61.057073
88607.954883
208.954883
88600.0
88900.0
0.075734
11:29:06
88500.000000
2017-06 11:29:05
101.000000
2605.178956
0.038769
7
2017-06
0.000000
1513.940896
1651.337968
-137.397072
88541.609371
142.609371
88500.0
88800.0
0.094197
11:29:07
88500.000000
2017-06 11:29:06
101.000000
1333.615829
0.075734
8
2017-06
0.000000
971.778144
1170.673148
-198.895005
88528.611007
129.611007
88500.0
88800.0
0.133375
11:29:08
88500.000000
2017-06 11:29:07
101.000000
1072.215871
0.094197
9
2017-06
0.000000
576.316387
805.076693
-228.760306
88516.674433
117.674433
88500.0
88800.0
0.204184
11:29:09
88500.000000
2017-06 11:29:08
101.000000
757.262789
0.133375
10
2017-06
0.000000
272.725070
512.854800
-240.129730
88462.318411
63.318411
88500.0
88800.0
0.232169
11:29:10
88500.000000
2017-06 11:29:09
101.000000
494.652522
0.204184
11
2017-06
0.000000
181.317588
398.851255
-217.533667
88452.417157
53.417157
88500.0
88800.0
0.294605
11:29:11
88500.000000
2017-06 11:29:10
101.000000
435.027216
0.232169
12
2017-06
0.000000
111.783759
306.831122
-195.047363
88437.997503
38.997503
88400.0
88700.0
0.348866
11:29:12
88500.000000
2017-06 11:29:11
101.000000
342.831360
0.294605
13
2017-06
0.000000
79.592023
249.895973
-170.303950
88427.425965
28.425965
88400.0
88700.0
0.357146
11:29:13
88500.000000
2017-06 11:29:12
101.000000
289.509810
0.348866
14
2017-06
0.000000
95.491332
237.504554
-142.013222
88435.049903
36.049903
88400.0
88700.0
0.377520
11:29:14
88500.000000
2017-06 11:29:13
101.000000
282.797588
0.357146
15
2017-06
0.000000
111.127150
229.188020
-118.060870
88444.483384
45.483384
88400.0
88700.0
0.409291
11:29:15
88500.000000
2017-06 11:29:14
101.000000
267.535380
0.377520
16
2017-06
0.000000
117.357961
216.534618
-99.176657
88448.368372
49.368372
88400.0
88700.0
0.420665
11:29:16
88500.000000
2017-06 11:29:15
101.000000
246.767963
0.409291
17
2017-06
0.000000
130.649892
212.738673
-82.088781
88459.602574
60.602574
88500.0
88800.0
0.463855
11:29:17
88500.000000
2017-06 11:29:16
101.000000
240.096108
0.420665
18
2017-06
0.000000
128.364871
198.328696
-69.963824
88462.561892
63.561892
88500.0
88800.0
0.495166
11:29:18
88500.000000
2017-06 11:29:17
101.000000
217.740571
0.463855
19
2017-06
0.000000
127.682175
187.119795
-59.437620
88463.870322
64.870322
88500.0
88800.0
0.508061
11:29:19
88500.000000
2017-06 11:29:18
101.000000
203.972091
0.495166
20
2017-06
0.000000
313.765592
335.900059
-22.134467
88565.799468
166.799468
88600.0
88900.0
0.531605
11:29:20
88600.000000
2017-06 11:29:19
201.000000
395.621854
0.508061
21
2017-06
0.000000
350.582671
363.760355
-13.177684
88599.691752
200.691752
88600.0
88900.0
0.572452
11:29:21
88600.000000
2017-06 11:29:20
201.000000
378.100031
0.531605
22
2017-06
0.000000
337.898403
351.001120
-13.102717
88596.458449
197.458449
88600.0
88900.0
0.584372
11:29:22
88600.000000
2017-06 11:29:21
201.000000
351.121141
0.572452
23
2017-06
0.000000
330.349042
342.608012
-12.258970
88596.103469
197.103469
88600.0
88900.0
0.596652
11:29:23
88600.000000
2017-06 11:29:22
201.000000
343.958839
0.584372
24
2017-06
0.000000
324.074306
335.424063
-11.349757
88602.395707
203.395707
88600.0
88900.0
0.627621
11:29:24
88600.000000
2017-06 11:29:23
201.000000
336.879699
0.596652
25
2017-06
0.000000
309.226802
321.107989
-11.881186
88603.582716
204.582716
88600.0
88900.0
0.661594
11:29:25
88600.000000
2017-06 11:29:24
201.000000
320.257179
0.627621
26
2017-06
0.000000
430.886658
422.478332
8.408326
88691.834313
292.834313
88700.0
89000.0
0.679609
11:29:26
88700.000000
2017-06 11:29:25
301.000000
454.961539
0.661594
27
2017-06
0.000000
450.304937
440.223818
10.081119
88714.612136
315.612136
88700.0
89000.0
0.700885
11:29:27
88700.000000
2017-06 11:29:26
301.000000
442.901936
0.679609
28
2017-06
0.000000
441.282316
434.103717
7.178599
88719.283045
320.283045
88700.0
89000.0
0.725801
11:29:28
88700.000000
2017-06 11:29:27
301.000000
429.456826
0.700885
29
2017-06
0.000000
424.115910
420.636161
3.479749
88713.126971
314.126971
88700.0
89000.0
0.740663
11:29:29
88700.000000
2017-06 11:29:28
301.000000
414.714357
0.725801
30
2017-06
0.000000
411.355303
410.343027
1.012276
88717.787482
318.787482
88700.0
89000.0
0.774969
11:29:30
88700.000000
2017-06 11:29:29
301.000000
406.392639
0.740663
31
2017-06
0.000000
509.576353
493.794696
15.781658
88805.014308
406.014308
88800.0
89100.0
0.796768
11:29:31
88800.000000
2017-06 11:29:30
401.000000
517.440256
0.774969
32
2017-06
0.000000
519.591268
504.685778
14.905489
88827.139097
428.139097
88800.0
89100.0
0.823992
11:29:32
88800.000000
2017-06 11:29:31
401.000000
503.283046
0.796768
33
2017-06
0.000000
504.316424
493.996373
10.320051
88825.474456
426.474456
88800.0
89100.0
0.845649
11:29:33
88800.000000
2017-06 11:29:32
401.000000
486.655154
0.823992
34
2017-06
0.000000
487.032814
480.906716
6.126098
88823.154290
424.154290
88800.0
89100.0
0.870895
11:29:34
88800.000000
2017-06 11:29:33
401.000000
474.192260
0.845649
35
2017-06
0.000000
468.796657
466.372029
2.424627
88833.976257
434.976257
88800.0
89100.0
0.927857
11:29:35
88800.000000
2017-06 11:29:34
401.000000
460.446029
0.870895
36
2017-06
0.000000
437.667140
440.340550
-2.673410
88819.874775
420.874775
88800.0
89100.0
0.961632
11:29:36
88800.000000
2017-06 11:29:35
401.000000
432.178668
0.927857
37
2017-06
0.000000
416.055258
421.606078
-5.550820
88806.209935
407.209935
88800.0
89100.0
0.978740
11:29:37
88800.000000
2017-06 11:29:36
401.000000
416.999387
0.961632
38
2017-06
0.000000
404.690487
411.124647
-6.434161
88798.450494
399.450494
88800.0
89100.0
0.987052
11:29:38
88800.000000
2017-06 11:29:37
401.000000
409.710432
0.978740
39
2017-06
0.000000
399.694810
405.910415
-6.215605
88809.777840
410.777840
88800.0
89100.0
1.027729
11:29:39
88800.000000
2017-06 11:29:38
401.000000
406.260319
0.987052
40
2017-06
0.000000
384.761219
392.301389
-7.540169
88811.957223
412.957223
88800.0
89100.0
1.073282
11:29:40
88800.000000
2017-06 11:29:39
401.000000
390.180781
1.027729
41
2017-06
0.000000
367.012402
376.103618
-9.091217
88803.238913
404.238913
88800.0
89100.0
1.101431
11:29:41
88800.000000
2017-06 11:29:40
401.000000
373.620415
1.073282
42
2017-06
0.000000
438.421029
435.281530
3.139499
88909.165294
510.165294
88900.0
89200.0
1.163642
11:29:42
88900.000000
2017-06 11:29:41
501.000000
454.862724
1.101431
43
2017-06
0.000000
434.343166
432.300234
2.042932
88953.661244
554.661244
89000.0
89300.0
1.277012
11:29:43
88900.000000
2017-06 11:29:42
501.000000
430.544646
1.163642
44
2017-06
0.000000
469.636830
462.541960
7.094870
89051.096407
652.096407
89100.0
89400.0
1.388512
11:29:44
89000.000000
2017-06 11:29:43
601.000000
470.630038
1.277012
45
2017-06
0.000000
443.011326
441.039749
1.971577
89037.325751
638.325751
89000.0
89300.0
1.440879
11:29:45
89000.000000
2017-06 11:29:44
601.000000
432.837433
1.388512
46
2017-06
0.000000
484.840699
476.813342
8.027357
89159.936034
760.936034
89200.0
89500.0
1.569456
11:29:46
89100.000000
2017-06 11:29:45
701.000000
486.508556
1.440879
47
2017-06
0.000000
457.874298
455.163705
2.710593
89152.141453
753.141453
89200.0
89500.0
1.644865
11:29:47
89100.000000
2017-06 11:29:46
701.000000
446.651644
1.569456
48
2017-06
0.000000
431.537674
433.240360
-1.702686
89153.510464
754.510464
89200.0
89500.0
1.748423
11:29:48
89100.000000
2017-06 11:29:47
701.000000
426.174766
1.644865
49
2017-06
0.000000
401.790737
407.754317
-5.963580
89118.331439
719.331439
89100.0
89400.0
1.790314
11:29:49
89100.000000
2017-06 11:29:48
701.000000
400.932689
1.748423
50
2017-06
0.000000
386.444646
393.833754
-7.389108
89145.216218
746.216218
89100.0
89400.0
1.930978
11:29:50
89100.000000
2017-06 11:29:49
701.000000
391.551504
1.790314
51
2017-06
0.690837
357.598562
368.247728
-10.649166
89116.233014
717.233014
89100.0
89400.0
2.001826
11:29:51
89100.000000
2017-06 11:29:50
701.000000
363.028423
1.930978
52
2017-06
1.381674
347.582430
358.135416
-10.552987
89118.159518
719.159518
89100.0
89400.0
2.060841
11:29:52
89116.233014
2017-06 11:29:51
717.233014
358.289399
2.001826
53
2017-06
2.072511
338.295512
348.656139
-10.360627
89136.554118
737.554118
89100.0
89400.0
2.166931
11:29:53
89118.159518
2017-06 11:29:52
719.159518
348.964104
2.060841
54
2017-06
2.763349
329.833989
339.906076
-10.072087
89159.145617
760.145617
89200.0
89500.0
2.285483
11:29:54
89136.554118
2017-06 11:29:53
737.554118
340.368024
2.166931
55
2017-06
3.454186
322.294039
331.981407
-9.687368
89182.469462
783.469462
89200.0
89500.0
2.405138
11:29:55
89159.145617
2017-06 11:29:54
760.145617
332.597337
2.285483
56
2017-06
4.145023
315.771844
324.978312
-9.206468
89211.444759
812.444759
89200.0
89500.0
2.539550
11:29:56
89182.469462
2017-06 11:29:55
783.469462
325.748225
2.405138
57
2017-06
4.835860
310.363583
318.992972
-8.629389
89247.611095
848.611095
89200.0
89500.0
2.692299
11:29:57
89211.444759
2017-06 11:29:56
812.444759
319.916867
2.539550
58
2017-06
5.526697
306.165435
314.121565
-7.956130
89257.998993
858.998993
89300.0
89600.0
2.755921
11:29:58
89247.611095
2017-06 11:29:57
848.611095
315.199443
2.692299
59
2017-06
6.217534
303.273581
310.460272
-7.186691
89301.800158
902.800158
89300.0
89600.0
2.917047
11:29:59
89257.998993
2017-06 11:29:58
858.998993
311.692132
2.755921
60
2017-06
6.908371
301.784200
308.105272
-6.321072
89345.100054
946.100054
89300.0
89600.0
3.064862
11:30:00
89301.800158
2017-06 11:29:59
902.800158
309.491115
2.917047
In [12]:
# bid is predicted bid-price from shl_pm
plt.figure(figsize=(12,6))
plt.plot(shl_pm.shl_data_pm_k_step['f_current_bid'])
# plt.plot(shl_data_pm_1_step_k_step['f_1_step_pred_price'].shift(1))
plt.plot(shl_data_pm_k_step_local['f_1_step_pred_price'])
# bid is actual bid-price from raw dataset
shl_data_actual_bid_local = shl_sm_data[shl_sm_parm_ccyy_mm_offset:shl_sm_parm_ccyy_mm_offset+61].copy()
shl_data_actual_bid_local.reset_index(inplace=True)
plt.figure(figsize=(12,6))
plt.plot(shl_data_actual_bid_local['bid-price'])
plt.plot(shl_data_pm_k_step_local['f_1_step_pred_price'])
plt.figure(figsize=(12,6))
plt.plot(shl_data_actual_bid_local['bid-price'])
plt.plot(shl_data_pm_k_step_local['f_1_step_pred_price_rounded'])
plt.plot(shl_data_pm_k_step_local['f_1_step_pred_set_price_rounded'])
Out[12]:
[<matplotlib.lines.Line2D at 0x7fa15f26e400>]
In [13]:
print('Dynamic Increment : +%d' % shl_pm.shl_global_parm_dynamic_increment)
Dynamic Increment : +300
In [14]:
# pd.concat([shl_data_actual_bid_local['bid-price'], shl_data_pm_k_step_local['f_1_step_pred_price'], shl_data_pm_k_step_local['f_1_step_pred_price'] - shl_data_actual_bid_local['bid-price']], axis=1, join='inner')
pd.concat([shl_data_actual_bid_local['bid-price'].tail(11), shl_data_pm_k_step_local['f_1_step_pred_price'].tail(11), shl_data_pm_k_step_local['f_1_step_pred_price'].tail(11) - shl_data_actual_bid_local['bid-price'].tail(11)], axis=1, join='inner')
Out[14]:
bid-price
f_1_step_pred_price
0
50
89100
89145.216218
45.216218
51
89100
89116.233014
16.233014
52
89100
89118.159518
18.159518
53
89200
89136.554118
-63.445882
54
89200
89159.145617
-40.854383
55
89200
89182.469462
-17.530538
56
89200
89211.444759
11.444759
57
89300
89247.611095
-52.388905
58
89300
89257.998993
-42.001007
59
89300
89301.800158
1.800158
60
89400
89345.100054
-54.899946
Content source: telescopeuser/uat_shl
Similar notebooks: