SHL Project

  • simulation module: shl_sm

shl_sm required data feeds:

  • live bidding price, per second, time series

prediction module parameters/csv

  • parm_si.csv (seasonality index per second)

  • parm_month.csv (parameter like alpha, beta, gamma, etc. per month)

SHL Simulation Module: shl_sm

Import useful reference packages


In [1]:
import pandas as pd

Import SHL Prediction Module: shl_pm


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)

shl_sm parameters:


In [ ]:

shl_sm simulated real time per second price ata, fetch from csv:


In [7]:
## 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[shl_sm_data['ccyy-mm'] == shl_sm_parm_ccyy_mm ]


Out[7]:
ccyy-mm time bid-price
1952 2017-09 11:29:00 90100
1953 2017-09 11:29:01 90100
1954 2017-09 11:29:02 90100
1955 2017-09 11:29:03 90100
1956 2017-09 11:29:04 90100
1957 2017-09 11:29:05 90100
1958 2017-09 11:29:06 90100
1959 2017-09 11:29:07 90100
1960 2017-09 11:29:08 90100
1961 2017-09 11:29:09 90100
1962 2017-09 11:29:10 90100
1963 2017-09 11:29:11 90100
1964 2017-09 11:29:12 90100
1965 2017-09 11:29:13 90100
1966 2017-09 11:29:14 90100
1967 2017-09 11:29:15 90200
1968 2017-09 11:29:16 90200
1969 2017-09 11:29:17 90200
1970 2017-09 11:29:18 90300
1971 2017-09 11:29:19 90300
1972 2017-09 11:29:20 90300
1973 2017-09 11:29:21 90300
1974 2017-09 11:29:22 90300
1975 2017-09 11:29:23 90400
1976 2017-09 11:29:24 90400
1977 2017-09 11:29:25 90400
1978 2017-09 11:29:26 90400
1979 2017-09 11:29:27 90400
1980 2017-09 11:29:28 90400
1981 2017-09 11:29:29 90400
... ... ... ...
1983 2017-09 11:29:31 90400
1984 2017-09 11:29:32 90400
1985 2017-09 11:29:33 90400
1986 2017-09 11:29:34 90400
1987 2017-09 11:29:35 90400
1988 2017-09 11:29:36 90400
1989 2017-09 11:29:37 90400
1990 2017-09 11:29:38 90400
1991 2017-09 11:29:39 90400
1992 2017-09 11:29:40 90400
1993 2017-09 11:29:41 90400
1994 2017-09 11:29:42 90400
1995 2017-09 11:29:43 90400
1996 2017-09 11:29:44 90400
1997 2017-09 11:29:45 90400
1998 2017-09 11:29:46 90500
1999 2017-09 11:29:47 90500
2000 2017-09 11:29:48 90700
2001 2017-09 11:29:49 90700
2002 2017-09 11:29:50 90700
2003 2017-09 11:29:51 90700
2004 2017-09 11:29:52 90700
2005 2017-09 11:29:53 90800
2006 2017-09 11:29:54 90800
2007 2017-09 11:29:55 90800
2008 2017-09 11:29:56 90900
2009 2017-09 11:29:57 91000
2010 2017-09 11:29:58 91000
2011 2017-09 11:29:59 91200
2012 2017-09 11:30:00 91300

61 rows × 3 columns

shl_pm Initialization


In [8]:
shl_pm.shl_initialize(shl_sm_parm_ccyy_mm)


+-----------------------------------------------+
| shl_initialize()                              |
+-----------------------------------------------+

shl_global_parm_ccyy_mm           : 2017-09
-------------------------------------------------
shl_global_parm_alpha             : 0.848823804527792
shl_global_parm_beta              : 0.001000000000000
shl_global_parm_gamma             : 0.149949473217226
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 [9]:
# 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.:  1952 >>>>
2017-09
11:29:00
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:00
in_current_price  : 90100.000000
*INFO* At time [ 11:29:00 ] Set shl_global_parm_base_price : 90099 
*INFO* f_current_datetime   : 2017-09 11:29:00 
*INFO* f_current_si         : 0.0023528925 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 425.0087897114 
*INFO* f_1_step_time        : 11:29:01
*INFO* f_1_step_si          : 0.0208894325 
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1953 >>>>
2017-09
11:29:01
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:01
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:01 
*INFO* f_current_si         : 0.0208894325 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 47.8710946610 
*INFO* f_1_step_time        : 11:29:02
*INFO* f_1_step_si          : 0.0355407527 
     previous_pred_les_level  : 425.0087897114
     previous_pred_les_trend  : 0.0000000000
     f_1_step_pred_les_level  : 104.8853365679
     f_1_step_pred_les_trend  : -0.3201234531
     f_1_step_pred_les        : 104.5652131148
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 104.5652131148
     f_1_step_pred_price_inc          : 3.7163263759
     f_1_step_pred_price              : 90102.7163263759
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1954 >>>>
2017-09
11:29:02
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:02
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:02 
*INFO* f_current_si         : 0.0355407527 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 28.1367142004 
*INFO* f_1_step_time        : 11:29:03
*INFO* f_1_step_si          : 0.0418911956 
     previous_pred_les_level  : 104.8853365679
     previous_pred_les_trend  : -0.3201234531
     f_1_step_pred_les_level  : 39.6908838919
     f_1_step_pred_les_trend  : -0.3849977824
     f_1_step_pred_les        : 39.3058861095
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 39.3058861095
     f_1_step_pred_price_inc          : 1.6465705629
     f_1_step_pred_price              : 90100.6465705629
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1955 >>>>
2017-09
11:29:03
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:03
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:03 
*INFO* f_current_si         : 0.0418911956 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 23.8713645170 
*INFO* f_1_step_time        : 11:29:04
*INFO* f_1_step_si          : 0.0492385622 
     previous_pred_les_level  : 39.6908838919
     previous_pred_les_trend  : -0.3849977824
     f_1_step_pred_les_level  : 26.2046967703
     f_1_step_pred_les_trend  : -0.3980989717
     f_1_step_pred_les        : 25.8065977986
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 25.8065977986
     f_1_step_pred_price_inc          : 1.2706797701
     f_1_step_pred_price              : 90100.2706797701
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1956 >>>>
2017-09
11:29:04
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:04
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:04 
*INFO* f_current_si         : 0.0492385622 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 20.3092851604 
*INFO* f_1_step_time        : 11:29:05
*INFO* f_1_step_si          : 0.0488651959 
     previous_pred_les_level  : 26.2046967703
     previous_pred_les_trend  : -0.3980989717
     f_1_step_pred_les_level  : 21.1403479703
     f_1_step_pred_les_trend  : -0.4027652215
     f_1_step_pred_les        : 20.7375827488
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 20.7375827488
     f_1_step_pred_price_inc          : 1.0133460440
     f_1_step_pred_price              : 90100.0133460440
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1957 >>>>
2017-09
11:29:05
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:05
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:05 
*INFO* f_current_si         : 0.0488651959 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 20.4644631225 
*INFO* f_1_step_time        : 11:29:06
*INFO* f_1_step_si          : 0.0817093781 
     previous_pred_les_level  : 21.1403479703
     previous_pred_les_trend  : -0.4027652215
     f_1_step_pred_les_level  : 20.5057523085
     f_1_step_pred_les_trend  : -0.4029970520
     f_1_step_pred_les        : 20.1027552566
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 20.1027552566
     f_1_step_pred_price_inc          : 1.6425836295
     f_1_step_pred_price              : 90100.6425836295
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1958 >>>>
2017-09
11:29:06
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:06
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:06 
*INFO* f_current_si         : 0.0817093781 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 12.2384972645 
*INFO* f_1_step_time        : 11:29:07
*INFO* f_1_step_si          : 0.0981591570 
     previous_pred_les_level  : 20.5057523085
     previous_pred_les_trend  : -0.4029970520
     f_1_step_pred_les_level  : 13.4273858680
     f_1_step_pred_les_trend  : -0.4096724214
     f_1_step_pred_les        : 13.0177134466
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 13.0177134466
     f_1_step_pred_price_inc          : 1.2778077782
     f_1_step_pred_price              : 90100.2778077782
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1959 >>>>
2017-09
11:29:07
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:07
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:07 
*INFO* f_current_si         : 0.0981591570 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 10.1875365517 
*INFO* f_1_step_time        : 11:29:08
*INFO* f_1_step_si          : 0.1399015190 
     previous_pred_les_level  : 13.4273858680
     previous_pred_les_trend  : -0.4096724214
     f_1_step_pred_les_level  : 10.6153919272
     f_1_step_pred_les_trend  : -0.4120747429
     f_1_step_pred_les        : 10.2033171843
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 10.2033171843
     f_1_step_pred_price_inc          : 1.4274595730
     f_1_step_pred_price              : 90100.4274595730
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1960 >>>>
2017-09
11:29:08
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:08
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:08 
*INFO* f_current_si         : 0.1399015190 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 7.1478852204 
*INFO* f_1_step_time        : 11:29:09
*INFO* f_1_step_si          : 0.2029073163 
     previous_pred_les_level  : 10.6153919272
     previous_pred_les_trend  : -0.4120747429
     f_1_step_pred_les_level  : 7.6097938002
     f_1_step_pred_les_trend  : -0.4146682663
     f_1_step_pred_les        : 7.1951255339
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 7.1951255339
     f_1_step_pred_price_inc          : 1.4599436125
     f_1_step_pred_price              : 90100.4599436125
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1961 >>>>
2017-09
11:29:09
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:09
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:09 
*INFO* f_current_si         : 0.2029073163 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 4.9283585149 
*INFO* f_1_step_time        : 11:29:10
*INFO* f_1_step_si          : 0.2371406695 
     previous_pred_les_level  : 7.6097938002
     previous_pred_les_trend  : -0.4146682663
     f_1_step_pred_les_level  : 5.2710397289
     f_1_step_pred_les_trend  : -0.4165923521
     f_1_step_pred_les        : 4.8544473768
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 4.8544473768
     f_1_step_pred_price_inc          : 1.1511869008
     f_1_step_pred_price              : 90100.1511869008
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1962 >>>>
2017-09
11:29:10
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:10
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:10 
*INFO* f_current_si         : 0.2371406695 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 4.2169063716 
*INFO* f_1_step_time        : 11:29:11
*INFO* f_1_step_si          : 0.2926460055 
     previous_pred_les_level  : 5.2710397289
     previous_pred_les_trend  : -0.4165923521
     f_1_step_pred_les_level  : 4.3132873952
     f_1_step_pred_les_trend  : -0.4171335121
     f_1_step_pred_les        : 3.8961538831
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 3.8961538831
     f_1_step_pred_price_inc          : 1.1401938708
     f_1_step_pred_price              : 90100.1401938708
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1963 >>>>
2017-09
11:29:11
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:11
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:11 
*INFO* f_current_si         : 0.2926460055 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 3.4170977260 
*INFO* f_1_step_time        : 11:29:12
*INFO* f_1_step_si          : 0.3408875008 
     previous_pred_les_level  : 4.3132873952
     previous_pred_les_trend  : -0.4171335121
     f_1_step_pred_les_level  : 3.4895196133
     f_1_step_pred_les_trend  : -0.4175401463
     f_1_step_pred_les        : 3.0719794670
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 3.0719794670
     f_1_step_pred_price_inc          : 1.0471994029
     f_1_step_pred_price              : 90100.0471994029
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1964 >>>>
2017-09
11:29:12
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:12
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:12 
*INFO* f_current_si         : 0.3408875008 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 2.9335191163 
*INFO* f_1_step_time        : 11:29:13
*INFO* f_1_step_si          : 0.3574878850 
     previous_pred_les_level  : 3.4895196133
     previous_pred_les_trend  : -0.4175401463
     f_1_step_pred_les_level  : 2.9544510254
     f_1_step_pred_les_trend  : -0.4176576748
     f_1_step_pred_les        : 2.5367933506
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 2.5367933506
     f_1_step_pred_price_inc          : 0.9068728897
     f_1_step_pred_price              : 90099.9068728897
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1965 >>>>
2017-09
11:29:13
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:13
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:13 
*INFO* f_current_si         : 0.3574878850 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 2.7972975921 
*INFO* f_1_step_time        : 11:29:14
*INFO* f_1_step_si          : 0.3755849903 
     previous_pred_les_level  : 2.9544510254
     previous_pred_les_trend  : -0.4176576748
     f_1_step_pred_les_level  : 2.7579155520
     f_1_step_pred_les_trend  : -0.4174365526
     f_1_step_pred_les        : 2.3404789994
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 2.3404789994
     f_1_step_pred_price_inc          : 0.8790487824
     f_1_step_pred_price              : 90099.8790487824
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1966 >>>>
2017-09
11:29:14
90100
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:14
in_current_price  : 90100.000000
*INFO* f_current_datetime   : 2017-09 11:29:14 
*INFO* f_current_si         : 0.3755849903 
*INFO* f_current_price4pm   : 1 
*INFO* f_current_price4pmsi : 2.6625132147 
*INFO* f_1_step_time        : 11:29:15
*INFO* f_1_step_si          : 0.4038575154 
     previous_pred_les_level  : 2.7579155520
     previous_pred_les_trend  : -0.4174365526
     f_1_step_pred_les_level  : 2.6138293072
     f_1_step_pred_les_trend  : -0.4171632023
     f_1_step_pred_les        : 2.1966661050
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 2.1966661050
     f_1_step_pred_price_inc          : 0.8871401154
     f_1_step_pred_price              : 90099.8871401154
     f_1_step_pred_price_rounded      : 90100
     f_1_step_pred_set_price_rounded  : 90400
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90400]
[90400]

<<<< Record No.:  1967 >>>>
2017-09
11:29:15
90200
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:15
in_current_price  : 90200.000000
*INFO* f_current_datetime   : 2017-09 11:29:15 
*INFO* f_current_si         : 0.4038575154 
*INFO* f_current_price4pm   : 101 
*INFO* f_current_price4pmsi : 250.0882022419 
*INFO* f_1_step_time        : 11:29:16
*INFO* f_1_step_si          : 0.4231287374 
     previous_pred_les_level  : 2.6138293072
     previous_pred_les_trend  : -0.4171632023
     f_1_step_pred_les_level  : 212.6129029189
     f_1_step_pred_les_trend  : -0.2067469654
     f_1_step_pred_les        : 212.4061559535
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 212.4061559535
     f_1_step_pred_price_inc          : 89.8751485897
     f_1_step_pred_price              : 90188.8751485897
     f_1_step_pred_price_rounded      : 90200
     f_1_step_pred_set_price_rounded  : 90500
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90500]
[90500]

<<<< Record No.:  1968 >>>>
2017-09
11:29:16
90200
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:16
in_current_price  : 90200.000000
*INFO* f_current_datetime   : 2017-09 11:29:16 
*INFO* f_current_si         : 0.4231287374 
*INFO* f_current_price4pm   : 101 
*INFO* f_current_price4pmsi : 238.6980393128 
*INFO* f_1_step_time        : 11:29:17
*INFO* f_1_step_si          : 0.4613990996 
     previous_pred_les_level  : 212.6129029189
     previous_pred_les_trend  : -0.2067469654
     f_1_step_pred_les_level  : 234.7233324147
     f_1_step_pred_les_trend  : -0.1844297890
     f_1_step_pred_les        : 234.5389026257
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 234.5389026257
     f_1_step_pred_price_inc          : 108.2160384941
     f_1_step_pred_price              : 90207.2160384941
     f_1_step_pred_price_rounded      : 90200
     f_1_step_pred_set_price_rounded  : 90500
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90500]
[90500]

<<<< Record No.:  1969 >>>>
2017-09
11:29:17
90200
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:17
in_current_price  : 90200.000000
*INFO* f_current_datetime   : 2017-09 11:29:17 
*INFO* f_current_si         : 0.4613990996 
*INFO* f_current_price4pm   : 101 
*INFO* f_current_price4pmsi : 218.8994302032 
*INFO* f_1_step_time        : 11:29:18
*INFO* f_1_step_si          : 0.4890396813 
     previous_pred_les_level  : 234.7233324147
     previous_pred_les_trend  : -0.1844297890
     f_1_step_pred_les_level  : 221.2637461432
     f_1_step_pred_les_trend  : -0.1977049455
     f_1_step_pred_les        : 221.0660411977
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 221.0660411977
     f_1_step_pred_price_inc          : 108.1100663347
     f_1_step_pred_price              : 90207.1100663347
     f_1_step_pred_price_rounded      : 90200
     f_1_step_pred_set_price_rounded  : 90500
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90500]
[90500]

<<<< Record No.:  1970 >>>>
2017-09
11:29:18
90300
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:18
in_current_price  : 90300.000000
*INFO* f_current_datetime   : 2017-09 11:29:18 
*INFO* f_current_si         : 0.4890396813 
*INFO* f_current_price4pm   : 201 
*INFO* f_current_price4pmsi : 411.0095922351 
*INFO* f_1_step_time        : 11:29:19
*INFO* f_1_step_si          : 0.5080889033 
     previous_pred_les_level  : 221.2637461432
     previous_pred_les_trend  : -0.1977049455
     f_1_step_pred_les_level  : 382.2946488348
     f_1_step_pred_les_trend  : -0.0364763378
     f_1_step_pred_les        : 382.2581724969
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 382.2581724969
     f_1_step_pred_price_inc          : 194.2211356228
     f_1_step_pred_price              : 90293.2211356228
     f_1_step_pred_price_rounded      : 90300
     f_1_step_pred_set_price_rounded  : 90600
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90600]
[90600]

<<<< Record No.:  1971 >>>>
2017-09
11:29:19
90300
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:19
in_current_price  : 90300.000000
*INFO* f_current_datetime   : 2017-09 11:29:19 
*INFO* f_current_si         : 0.5080889033 
*INFO* f_current_price4pm   : 201 
*INFO* f_current_price4pmsi : 395.6000587964 
*INFO* f_1_step_time        : 11:29:20
*INFO* f_1_step_si          : 0.5288548106 
     previous_pred_les_level  : 382.2946488348
     previous_pred_les_trend  : -0.0364763378
     f_1_step_pred_les_level  : 393.5830831852
     f_1_step_pred_les_trend  : -0.0251514271
     f_1_step_pred_les        : 393.5579317581
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 393.5579317581
     f_1_step_pred_price_inc          : 208.1350054453
     f_1_step_pred_price              : 90307.1350054453
     f_1_step_pred_price_rounded      : 90300
     f_1_step_pred_set_price_rounded  : 90600
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90600]
[90600]

<<<< Record No.:  1972 >>>>
2017-09
11:29:20
90300
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:20
in_current_price  : 90300.000000
*INFO* f_current_datetime   : 2017-09 11:29:20 
*INFO* f_current_si         : 0.5288548106 
*INFO* f_current_price4pm   : 201 
*INFO* f_current_price4pmsi : 380.0665059398 
*INFO* f_1_step_time        : 11:29:21
*INFO* f_1_step_si          : 0.5649603971 
     previous_pred_les_level  : 393.5830831852
     previous_pred_les_trend  : -0.0251514271
     f_1_step_pred_les_level  : 382.1060883665
     f_1_step_pred_les_trend  : -0.0366032705
     f_1_step_pred_les        : 382.0694850960
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 382.0694850960
     f_1_step_pred_price_inc          : 215.8541280182
     f_1_step_pred_price              : 90314.8541280182
     f_1_step_pred_price_rounded      : 90300
     f_1_step_pred_set_price_rounded  : 90600
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90600]
[90600]

<<<< Record No.:  1973 >>>>
2017-09
11:29:21
90300
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:21
in_current_price  : 90300.000000
*INFO* f_current_datetime   : 2017-09 11:29:21 
*INFO* f_current_si         : 0.5649603971 
*INFO* f_current_price4pm   : 201 
*INFO* f_current_price4pmsi : 355.7771501030 
*INFO* f_1_step_time        : 11:29:22
*INFO* f_1_step_si          : 0.5754012825 
     previous_pred_les_level  : 382.1060883665
     previous_pred_les_trend  : -0.0366032705
     f_1_step_pred_les_level  : 359.7519252773
     f_1_step_pred_les_trend  : -0.0589208303
     f_1_step_pred_les        : 359.6930044470
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 359.6930044470
     f_1_step_pred_price_inc          : 206.9678160688
     f_1_step_pred_price              : 90305.9678160688
     f_1_step_pred_price_rounded      : 90300
     f_1_step_pred_set_price_rounded  : 90600
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90600]
[90600]

<<<< Record No.:  1974 >>>>
2017-09
11:29:22
90300
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:22
in_current_price  : 90300.000000
*INFO* f_current_datetime   : 2017-09 11:29:22 
*INFO* f_current_si         : 0.5754012825 
*INFO* f_current_price4pm   : 201 
*INFO* f_current_price4pmsi : 349.3214320327 
*INFO* f_1_step_time        : 11:29:23
*INFO* f_1_step_si          : 0.5861877846 
     previous_pred_les_level  : 359.7519252773
     previous_pred_les_trend  : -0.0589208303
     f_1_step_pred_les_level  : 350.8893668914
     f_1_step_pred_les_trend  : -0.0677244679
     f_1_step_pred_les        : 350.8216424235
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 350.8216424235
     f_1_step_pred_price_inc          : 205.6473613678
     f_1_step_pred_price              : 90304.6473613678
     f_1_step_pred_price_rounded      : 90300
     f_1_step_pred_set_price_rounded  : 90600
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90600]
[90600]

<<<< Record No.:  1975 >>>>
2017-09
11:29:23
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:23
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:23 
*INFO* f_current_si         : 0.5861877846 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 513.4873293152 
*INFO* f_1_step_time        : 11:29:24
*INFO* f_1_step_si          : 0.6135904893 
     previous_pred_les_level  : 350.8893668914
     previous_pred_les_trend  : -0.0677244679
     f_1_step_pred_les_level  : 488.8961496371
     f_1_step_pred_les_trend  : 0.0703500393
     f_1_step_pred_les        : 488.9664996764
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 488.9664996764
     f_1_step_pred_price_inc          : 300.0251937668
     f_1_step_pred_price              : 90399.0251937668
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1976 >>>>
2017-09
11:29:24
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:24
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:24 
*INFO* f_current_si         : 0.6135904893 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 490.5551915650 
*INFO* f_1_step_time        : 11:29:25
*INFO* f_1_step_si          : 0.6521912336 
     previous_pred_les_level  : 488.8961496371
     previous_pred_les_trend  : 0.0703500393
     f_1_step_pred_les_level  : 490.3150191695
     f_1_step_pred_les_trend  : 0.0716985588
     f_1_step_pred_les        : 490.3867177283
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 490.3867177283
     f_1_step_pred_price_inc          : 319.8259183644
     f_1_step_pred_price              : 90418.8259183644
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1977 >>>>
2017-09
11:29:25
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:25
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:25 
*INFO* f_current_si         : 0.6521912336 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 461.5210761876 
*INFO* f_1_step_time        : 11:29:26
*INFO* f_1_step_si          : 0.6684637421 
     previous_pred_les_level  : 490.3150191695
     previous_pred_les_trend  : 0.0716985588
     f_1_step_pred_les_level  : 465.8848740556
     f_1_step_pred_les_trend  : 0.0471967151
     f_1_step_pred_les        : 465.9320707707
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 465.9320707707
     f_1_step_pred_price_inc          : 311.4586956111
     f_1_step_pred_price              : 90410.4586956111
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1978 >>>>
2017-09
11:29:26
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:26
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:26 
*INFO* f_current_si         : 0.6684637421 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 450.2862025631 
*INFO* f_1_step_time        : 11:29:27
*INFO* f_1_step_si          : 0.6877341370 
     previous_pred_les_level  : 465.8848740556
     previous_pred_les_trend  : 0.0471967151
     f_1_step_pred_les_level  : 452.6514853936
     f_1_step_pred_les_trend  : 0.0339161298
     f_1_step_pred_les        : 452.6854015234
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 452.6854015234
     f_1_step_pred_price_inc          : 311.3272039491
     f_1_step_pred_price              : 90410.3272039491
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1979 >>>>
2017-09
11:29:27
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:27
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:27 
*INFO* f_current_si         : 0.6877341370 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 437.6691279469 
*INFO* f_1_step_time        : 11:29:28
*INFO* f_1_step_si          : 0.7187130127 
     previous_pred_les_level  : 452.6514853936
     previous_pred_les_trend  : 0.0339161298
     f_1_step_pred_les_level  : 439.9392310563
     f_1_step_pred_les_trend  : 0.0211699593
     f_1_step_pred_les        : 439.9604010156
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 439.9604010156
     f_1_step_pred_price_inc          : 316.2052652726
     f_1_step_pred_price              : 90415.2052652726
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1980 >>>>
2017-09
11:29:28
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:28
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:28 
*INFO* f_current_si         : 0.7187130127 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 418.8041606187 
*INFO* f_1_step_time        : 11:29:29
*INFO* f_1_step_si          : 0.7326749715 
     previous_pred_les_level  : 439.9392310563
     previous_pred_les_trend  : 0.0211699593
     f_1_step_pred_les_level  : 422.0024805524
     f_1_step_pred_les_trend  : 0.0032120388
     f_1_step_pred_les        : 422.0056925912
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 422.0056925912
     f_1_step_pred_price_inc          : 309.1930087911
     f_1_step_pred_price              : 90408.1930087911
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1981 >>>>
2017-09
11:29:29
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:29
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:29 
*INFO* f_current_si         : 0.7326749715 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 410.8233687644 
*INFO* f_1_step_time        : 11:29:30
*INFO* f_1_step_si          : 0.7733932183 
     previous_pred_les_level  : 422.0024805524
     previous_pred_les_trend  : 0.0032120388
     f_1_step_pred_les_level  : 412.5138699371
     f_1_step_pred_les_trend  : -0.0062797838
     f_1_step_pred_les        : 412.5075901532
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 412.5075901532
     f_1_step_pred_price_inc          : 319.0305727232
     f_1_step_pred_price              : 90418.0305727232
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1982 >>>>
2017-09
11:29:30
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:30
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:30 
*INFO* f_current_si         : 0.7733932183 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 389.1939997357 
*INFO* f_1_step_time        : 11:29:31
*INFO* f_1_step_si          : 0.7887254294 
     previous_pred_les_level  : 412.5138699371
     previous_pred_les_trend  : -0.0062797838
     f_1_step_pred_les_level  : 392.7184596378
     f_1_step_pred_les_trend  : -0.0260689143
     f_1_step_pred_les        : 392.6923907235
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 392.6923907235
     f_1_step_pred_price_inc          : 309.7264745108
     f_1_step_pred_price              : 90408.7264745108
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1983 >>>>
2017-09
11:29:31
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:31
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:31 
*INFO* f_current_si         : 0.7887254294 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 381.6283699818 
*INFO* f_1_step_time        : 11:29:32
*INFO* f_1_step_si          : 0.8130073876 
     previous_pred_les_level  : 392.7184596378
     previous_pred_les_trend  : -0.0260689143
     f_1_step_pred_les_level  : 383.3009865442
     f_1_step_pred_les_trend  : -0.0354603185
     f_1_step_pred_les        : 383.2655262256
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 383.2655262256
     f_1_step_pred_price_inc          : 311.5977042215
     f_1_step_pred_price              : 90410.5977042215
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1984 >>>>
2017-09
11:29:32
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:32
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:32 
*INFO* f_current_si         : 0.8130073876 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 370.2303381283 
*INFO* f_1_step_time        : 11:29:33
*INFO* f_1_step_si          : 0.8322837182 
     previous_pred_les_level  : 383.3009865442
     previous_pred_les_trend  : -0.0354603185
     f_1_step_pred_les_level  : 372.2009482721
     f_1_step_pred_les_trend  : -0.0465248965
     f_1_step_pred_les        : 372.1544233756
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 372.1544233756
     f_1_step_pred_price_inc          : 309.7380672196
     f_1_step_pred_price              : 90408.7380672196
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1985 >>>>
2017-09
11:29:33
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:33
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:33 
*INFO* f_current_si         : 0.8322837182 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 361.6555189409 
*INFO* f_1_step_time        : 11:29:34
*INFO* f_1_step_si          : 0.8619636567 
     previous_pred_les_level  : 372.2009482721
     previous_pred_les_trend  : -0.0465248965
     f_1_step_pred_les_level  : 363.2427033700
     f_1_step_pred_les_trend  : -0.0554366165
     f_1_step_pred_les        : 363.1872667535
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 363.1872667535
     f_1_step_pred_price_inc          : 313.0542245286
     f_1_step_pred_price              : 90412.0542245286
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1986 >>>>
2017-09
11:29:34
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:34
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:34 
*INFO* f_current_si         : 0.8619636567 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 349.2026579658 
*INFO* f_1_step_time        : 11:29:35
*INFO* f_1_step_si          : 0.9193121258 
     previous_pred_les_level  : 363.2427033700
     previous_pred_les_trend  : -0.0554366165
     f_1_step_pred_les_level  : 351.3167979175
     f_1_step_pred_les_trend  : -0.0673070853
     f_1_step_pred_les        : 351.2494908322
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 351.2494908322
     f_1_step_pred_price_inc          : 322.9079160898
     f_1_step_pred_price              : 90421.9079160898
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1987 >>>>
2017-09
11:29:35
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:35
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:35 
*INFO* f_current_si         : 0.9193121258 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 327.4187205466 
*INFO* f_1_step_time        : 11:29:36
*INFO* f_1_step_si          : 0.9493202485 
     previous_pred_les_level  : 351.3167979175
     previous_pred_les_trend  : -0.0673070853
     f_1_step_pred_les_level  : 331.0213657336
     f_1_step_pred_les_trend  : -0.0875352104
     f_1_step_pred_les        : 330.9338305231
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 330.9338305231
     f_1_step_pred_price_inc          : 314.1621862429
     f_1_step_pred_price              : 90413.1621862429
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1988 >>>>
2017-09
11:29:36
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:36
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:36 
*INFO* f_current_si         : 0.9493202485 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 317.0689769470 
*INFO* f_1_step_time        : 11:29:37
*INFO* f_1_step_si          : 0.9783465150 
     previous_pred_les_level  : 331.0213657336
     previous_pred_les_trend  : -0.0875352104
     f_1_step_pred_les_level  : 319.1650127614
     f_1_step_pred_les_trend  : -0.0993040282
     f_1_step_pred_les        : 319.0657087333
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 319.0657087333
     f_1_step_pred_price_inc          : 312.1568242099
     f_1_step_pred_price              : 90411.1568242099
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1989 >>>>
2017-09
11:29:37
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:37
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:37 
*INFO* f_current_si         : 0.9783465150 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 307.6619534806 
*INFO* f_1_step_time        : 11:29:38
*INFO* f_1_step_si          : 0.9994757142 
     previous_pred_les_level  : 319.1650127614
     previous_pred_les_trend  : -0.0993040282
     f_1_step_pred_les_level  : 309.3859298138
     f_1_step_pred_les_trend  : -0.1089838071
     f_1_step_pred_les        : 309.2769460067
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 309.2769460067
     f_1_step_pred_price_inc          : 309.1147964988
     f_1_step_pred_price              : 90408.1147964988
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1990 >>>>
2017-09
11:29:38
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:38
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:38 
*INFO* f_current_si         : 0.9994757142 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 301.1578928036 
*INFO* f_1_step_time        : 11:29:39
*INFO* f_1_step_si          : 1.0355575847 
     previous_pred_les_level  : 309.3859298138
     previous_pred_les_trend  : -0.1089838071
     f_1_step_pred_les_level  : 302.3853003777
     f_1_step_pred_les_trend  : -0.1158754527
     f_1_step_pred_les        : 302.2694249250
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 302.2694249250
     f_1_step_pred_price_inc          : 313.0173956139
     f_1_step_pred_price              : 90412.0173956139
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1991 >>>>
2017-09
11:29:39
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:39
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:39 
*INFO* f_current_si         : 1.0355575847 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 290.6646664924 
*INFO* f_1_step_time        : 11:29:40
*INFO* f_1_step_si          : 1.0759763027 
     previous_pred_les_level  : 302.3853003777
     previous_pred_les_trend  : -0.1158754527
     f_1_step_pred_les_level  : 292.4190297216
     f_1_step_pred_les_trend  : -0.1257258479
     f_1_step_pred_les        : 292.2933038737
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 292.2933038737
     f_1_step_pred_price_inc          : 314.5006684193
     f_1_step_pred_price              : 90413.5006684194
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1992 >>>>
2017-09
11:29:40
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:40
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:40 
*INFO* f_current_si         : 1.0759763027 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 279.7459379280 
*INFO* f_1_step_time        : 11:29:41
*INFO* f_1_step_si          : 1.1108416381 
     previous_pred_les_level  : 292.4190297216
     previous_pred_les_trend  : -0.1257258479
     f_1_step_pred_les_level  : 281.6428009749
     f_1_step_pred_les_trend  : -0.1363763508
     f_1_step_pred_les        : 281.5064246241
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 281.5064246241
     f_1_step_pred_price_inc          : 312.7090578667
     f_1_step_pred_price              : 90411.7090578667
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1993 >>>>
2017-09
11:29:41
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:41
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:41 
*INFO* f_current_si         : 1.1108416381 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 270.9657161513 
*INFO* f_1_step_time        : 11:29:42
*INFO* f_1_step_si          : 1.1660037147 
     previous_pred_les_level  : 281.6428009749
     previous_pred_les_trend  : -0.1363763508
     f_1_step_pred_les_level  : 272.5592203558
     f_1_step_pred_les_trend  : -0.1453235551
     f_1_step_pred_les        : 272.4138968007
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 272.4138968007
     f_1_step_pred_price_inc          : 317.6356156148
     f_1_step_pred_price              : 90416.6356156148
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1994 >>>>
2017-09
11:29:42
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:42
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:42 
*INFO* f_current_si         : 1.1660037147 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 258.1466904406 
*INFO* f_1_step_time        : 11:29:43
*INFO* f_1_step_si          : 1.2765898950 
     previous_pred_les_level  : 272.5592203558
     previous_pred_les_trend  : -0.1453235551
     f_1_step_pred_les_level  : 260.3035524181
     f_1_step_pred_les_trend  : -0.1574338995
     f_1_step_pred_les        : 260.1461185186
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 260.1461185186
     f_1_step_pred_price_inc          : 332.0999061146
     f_1_step_pred_price              : 90431.0999061146
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1995 >>>>
2017-09
11:29:43
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:43
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:43 
*INFO* f_current_si         : 1.2765898950 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 235.7844137634 
*INFO* f_1_step_time        : 11:29:44
*INFO* f_1_step_si          : 1.3892040979 
     previous_pred_les_level  : 260.3035524181
     previous_pred_les_trend  : -0.1574338995
     f_1_step_pred_les_level  : 239.4673236035
     f_1_step_pred_les_trend  : -0.1781126944
     f_1_step_pred_les        : 239.2892109091
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 239.2892109091
     f_1_step_pred_price_inc          : 332.4215523794
     f_1_step_pred_price              : 90431.4215523794
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1996 >>>>
2017-09
11:29:44
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:44
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:44 
*INFO* f_current_si         : 1.3892040979 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 216.6708264494 
*INFO* f_1_step_time        : 11:29:45
*INFO* f_1_step_si          : 1.4455133373 
     previous_pred_les_level  : 239.4673236035
     previous_pred_les_trend  : -0.1781126944
     f_1_step_pred_les_level  : 220.0901877598
     f_1_step_pred_les_trend  : -0.1973117175
     f_1_step_pred_les        : 219.8928760422
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 219.8928760422
     f_1_step_pred_price_inc          : 317.8580850998
     f_1_step_pred_price              : 90416.8580850998
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1997 >>>>
2017-09
11:29:45
90400
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:45
in_current_price  : 90400.000000
*INFO* f_current_datetime   : 2017-09 11:29:45 
*INFO* f_current_si         : 1.4455133373 
*INFO* f_current_price4pm   : 301 
*INFO* f_current_price4pmsi : 208.2305242225 
*INFO* f_1_step_time        : 11:29:46
*INFO* f_1_step_si          : 1.5735144860 
     previous_pred_les_level  : 220.0901877598
     previous_pred_les_trend  : -0.1973117175
     f_1_step_pred_les_level  : 209.9935942009
     f_1_step_pred_les_trend  : -0.2072109994
     f_1_step_pred_les        : 209.7863832015
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 209.7863832015
     f_1_step_pred_price_inc          : 330.1019129355
     f_1_step_pred_price              : 90429.1019129355
     f_1_step_pred_price_rounded      : 90400
     f_1_step_pred_set_price_rounded  : 90700
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90700]
[90700]

<<<< Record No.:  1998 >>>>
2017-09
11:29:46
90500
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:46
in_current_price  : 90500.000000
*INFO* f_current_datetime   : 2017-09 11:29:46 
*INFO* f_current_si         : 1.5735144860 
*INFO* f_current_price4pm   : 401 
*INFO* f_current_price4pmsi : 254.8435388202 
*INFO* f_1_step_time        : 11:29:47
*INFO* f_1_step_si          : 1.6469907093 
     previous_pred_les_level  : 209.9935942009
     previous_pred_les_trend  : -0.2072109994
     f_1_step_pred_les_level  : 248.0319694549
     f_1_step_pred_les_trend  : -0.1689654131
     f_1_step_pred_les        : 247.8630040418
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 247.8630040418
     f_1_step_pred_price_inc          : 408.2280648447
     f_1_step_pred_price              : 90507.2280648447
     f_1_step_pred_price_rounded      : 90500
     f_1_step_pred_set_price_rounded  : 90800
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90800]
[90800]

<<<< Record No.:  1999 >>>>
2017-09
11:29:47
90500
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:47
in_current_price  : 90500.000000
*INFO* f_current_datetime   : 2017-09 11:29:47 
*INFO* f_current_si         : 1.6469907093 
*INFO* f_current_price4pm   : 401 
*INFO* f_current_price4pmsi : 243.4743546076 
*INFO* f_1_step_time        : 11:29:48
*INFO* f_1_step_si          : 1.7528360537 
     previous_pred_les_level  : 248.0319694549
     previous_pred_les_trend  : -0.1689654131
     f_1_step_pred_les_level  : 244.1378139323
     f_1_step_pred_les_trend  : -0.1726906032
     f_1_step_pred_les        : 243.9651233291
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 243.9651233291
     f_1_step_pred_price_inc          : 427.6308640186
     f_1_step_pred_price              : 90526.6308640186
     f_1_step_pred_price_rounded      : 90500
     f_1_step_pred_set_price_rounded  : 90800
-------------------------------------------------
==>> Prediction Restuls in Python List :  [90800]
[90800]

<<<< Record No.:  2000 >>>>
2017-09
11:29:48
90700
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:48
in_current_price  : 90700.000000
*INFO* f_current_datetime   : 2017-09 11:29:48 
*INFO* f_current_si         : 1.7528360537 
*INFO* f_current_price4pm   : 601 
*INFO* f_current_price4pmsi : 342.8729108627 
*INFO* f_1_step_time        : 11:29:49
*INFO* f_1_step_si          : 1.7901007887 
     previous_pred_les_level  : 244.1378139323
     previous_pred_les_trend  : -0.1726906032
     f_1_step_pred_les_level  : 327.9204078408
     f_1_step_pred_les_trend  : -0.0887353187
     f_1_step_pred_les        : 327.8316725221
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 327.8316725221
     f_1_step_pred_price_inc          : 586.8517355400
     f_1_step_pred_price              : 90685.8517355400
     f_1_step_pred_price_rounded      : 90700
     f_1_step_pred_set_price_rounded  : 91000
-------------------------------------------------
==>> Prediction Restuls in Python List :  [91000]
[91000]

<<<< Record No.:  2001 >>>>
2017-09
11:29:49
90700
==>> Forecasting   1 out of next   1 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:49
in_current_price  : 90700.000000
*INFO* f_current_datetime   : 2017-09 11:29:49 
*INFO* f_current_si         : 1.7901007887 
*INFO* f_current_price4pm   : 601 
*INFO* f_current_price4pmsi : 335.7352858546 
*INFO* f_1_step_time        : 11:29:50
*INFO* f_1_step_si          : 1.9291876914 
     previous_pred_les_level  : 327.9204078408
     previous_pred_les_trend  : -0.0887353187
     f_1_step_pred_les_level  : 334.5404476605
     f_1_step_pred_les_trend  : -0.0820265436
     f_1_step_pred_les        : 334.4584211169
     f_1_step_pred_adj_misc   : 0.0000000000
     pred_les + pred_adj_misc : 334.4584211169
     f_1_step_pred_price_inc          : 645.2330692874
     f_1_step_pred_price              : 90744.2330692874
     f_1_step_pred_price_rounded      : 90700
     f_1_step_pred_set_price_rounded  : 91000
-------------------------------------------------
==>> Prediction Restuls in Python List :  [91000]
[91000]

In [10]:
# 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.:  2002 >>>>
2017-09
11:29:50
90700
==>> Forecasting   1 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:50
in_current_price  : 90700.000000
*INFO* f_current_datetime   : 2017-09 11:29:50 
*INFO* f_current_si         : 1.9291876914 
*INFO* f_current_price4pm   : 601 
*INFO* f_current_price4pmsi : 311.5300821659 
*INFO* f_1_step_time        : 11:29:51
*INFO* f_1_step_si          : 1.9989322682 
*INFO* sec50_error          : 44.2330692874
*INFO* sec46_49_error       : -251.1874226613
*INFO* shl_global_parm_short_weight_misc  : -41.3908706748
*INFO* shl_global_parm_short_weight_ratio : 1
     previous_pred_les_level  : 334.5404476605
     previous_pred_les_trend  : -0.0820265436
     f_1_step_pred_les_level  : 314.9963012170
     f_1_step_pred_les_trend  : -0.1014886635
     f_1_step_pred_les        : 314.8948125535
     f_1_step_pred_adj_misc   : -0.7758174067
     pred_les + pred_adj_misc : 314.1189951468
     f_1_step_pred_price_inc          : 627.9025954669
     f_1_step_pred_price              : 90726.9025954669
     f_1_step_pred_price_rounded      : 90700
     f_1_step_pred_set_price_rounded  : 91000
-------------------------------------------------
==>> Forecasting   2 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:51
in_current_price  : 90726.902595
*INFO* f_current_datetime   : 2017-09 11:29:51 
*INFO* f_current_si         : 1.9989322682 
*INFO* f_current_price4pm   : 627 
*INFO* f_current_price4pmsi : 314.1189951468 
*INFO* f_1_step_time        : 11:29:52
*INFO* f_1_step_si          : 2.0656315104 
*INFO* shl_global_parm_short_weight_ratio : 2
     previous_pred_les_level  : 314.9963012170
     previous_pred_les_trend  : -0.1014886635
     f_1_step_pred_les_level  : 314.2362802707
     f_1_step_pred_les_trend  : -0.1021471958
     f_1_step_pred_les        : 314.1341330749
     f_1_step_pred_adj_misc   : -1.5516348134
     pred_les + pred_adj_misc : 312.5824982615
     f_1_step_pred_price_inc          : 645.6802580155
     f_1_step_pred_price              : 90744.6802580155
     f_1_step_pred_price_rounded      : 90700
     f_1_step_pred_set_price_rounded  : 91000
-------------------------------------------------
==>> Forecasting   3 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:52
in_current_price  : 90744.680258
*INFO* f_current_datetime   : 2017-09 11:29:52 
*INFO* f_current_si         : 2.0656315104 
*INFO* f_current_price4pm   : 645 
*INFO* f_current_price4pmsi : 312.5824982615 
*INFO* f_1_step_time        : 11:29:53
*INFO* f_1_step_si          : 2.1762324236 
*INFO* shl_global_parm_short_weight_ratio : 3
     previous_pred_les_level  : 314.2362802707
     previous_pred_les_trend  : -0.1021471958
     f_1_step_pred_les_level  : 312.8170685094
     f_1_step_pred_les_trend  : -0.1034642603
     f_1_step_pred_les        : 312.7136042490
     f_1_step_pred_adj_misc   : -2.3274522201
     pred_les + pred_adj_misc : 310.3861520289
     f_1_step_pred_price_inc          : 675.4724078803
     f_1_step_pred_price              : 90774.4724078803
     f_1_step_pred_price_rounded      : 90800
     f_1_step_pred_set_price_rounded  : 91100
-------------------------------------------------
==>> Forecasting   4 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:53
in_current_price  : 90774.472408
*INFO* f_current_datetime   : 2017-09 11:29:53 
*INFO* f_current_si         : 2.1762324236 
*INFO* f_current_price4pm   : 675 
*INFO* f_current_price4pmsi : 310.3861520289 
*INFO* f_1_step_time        : 11:29:54
*INFO* f_1_step_si          : 2.2959546949 
*INFO* shl_global_parm_short_weight_ratio : 4
     previous_pred_les_level  : 312.8170685094
     previous_pred_les_trend  : -0.1034642603
     f_1_step_pred_les_level  : 310.7380074007
     f_1_step_pred_les_trend  : -0.1054398572
     f_1_step_pred_les        : 310.6325675435
     f_1_step_pred_adj_misc   : -3.1032696268
     pred_les + pred_adj_misc : 307.5292979166
     f_1_step_pred_price_inc          : 706.0733353668
     f_1_step_pred_price              : 90805.0733353668
     f_1_step_pred_price_rounded      : 90800
     f_1_step_pred_set_price_rounded  : 91100
-------------------------------------------------
==>> Forecasting   5 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:54
in_current_price  : 90805.073335
*INFO* f_current_datetime   : 2017-09 11:29:54 
*INFO* f_current_si         : 2.2959546949 
*INFO* f_current_price4pm   : 706 
*INFO* f_current_price4pmsi : 307.5292979166 
*INFO* f_1_step_time        : 11:29:55
*INFO* f_1_step_si          : 2.4167518634 
*INFO* shl_global_parm_short_weight_ratio : 5
     previous_pred_les_level  : 310.7380074007
     previous_pred_les_trend  : -0.1054398572
     f_1_step_pred_les_level  : 307.9984384124
     f_1_step_pred_les_trend  : -0.1080739863
     f_1_step_pred_les        : 307.8903644260
     f_1_step_pred_adj_misc   : -3.8790870336
     pred_les + pred_adj_misc : 304.0112773925
     f_1_step_pred_price_inc          : 734.7198211334
     f_1_step_pred_price              : 90833.7198211334
     f_1_step_pred_price_rounded      : 90800
     f_1_step_pred_set_price_rounded  : 91100
-------------------------------------------------
==>> Forecasting   6 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:55
in_current_price  : 90833.719821
*INFO* f_current_datetime   : 2017-09 11:29:55 
*INFO* f_current_si         : 2.4167518634 
*INFO* f_current_price4pm   : 734 
*INFO* f_current_price4pmsi : 304.0112773925 
*INFO* f_1_step_time        : 11:29:56
*INFO* f_1_step_si          : 2.5507155017 
*INFO* shl_global_parm_short_weight_ratio : 6
     previous_pred_les_level  : 307.9984384124
     previous_pred_les_trend  : -0.1080739863
     f_1_step_pred_les_level  : 304.5977030121
     f_1_step_pred_les_trend  : -0.1113666477
     f_1_step_pred_les        : 304.4863363644
     f_1_step_pred_adj_misc   : -4.6549044403
     pred_les + pred_adj_misc : 299.8314319241
     f_1_step_pred_price_inc          : 764.7846813105
     f_1_step_pred_price              : 90863.7846813105
     f_1_step_pred_price_rounded      : 90900
     f_1_step_pred_set_price_rounded  : 91200
-------------------------------------------------
==>> Forecasting   7 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:56
in_current_price  : 90863.784681
*INFO* f_current_datetime   : 2017-09 11:29:56 
*INFO* f_current_si         : 2.5507155017 
*INFO* f_current_price4pm   : 764 
*INFO* f_current_price4pmsi : 299.8314319241 
*INFO* f_1_step_time        : 11:29:57
*INFO* f_1_step_si          : 2.7036260128 
*INFO* shl_global_parm_short_weight_ratio : 7
     previous_pred_les_level  : 304.5977030121
     previous_pred_les_trend  : -0.1113666477
     f_1_step_pred_les_level  : 300.5351426677
     f_1_step_pred_les_trend  : -0.1153178414
     f_1_step_pred_les        : 300.4198248263
     f_1_step_pred_adj_misc   : -5.4307218470
     pred_les + pred_adj_misc : 294.9891029793
     f_1_step_pred_price_inc          : 797.5402123158
     f_1_step_pred_price              : 90896.5402123158
     f_1_step_pred_price_rounded      : 90900
     f_1_step_pred_set_price_rounded  : 91200
-------------------------------------------------
==>> Forecasting   8 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:57
in_current_price  : 90896.540212
*INFO* f_current_datetime   : 2017-09 11:29:57 
*INFO* f_current_si         : 2.7036260128 
*INFO* f_current_price4pm   : 797 
*INFO* f_current_price4pmsi : 294.9891029793 
*INFO* f_1_step_time        : 11:29:58
*INFO* f_1_step_si          : 2.7679954159 
*INFO* shl_global_parm_short_weight_ratio : 8
     previous_pred_les_level  : 300.5351426677
     previous_pred_les_trend  : -0.1153178414
     f_1_step_pred_les_level  : 295.8100988468
     f_1_step_pred_les_trend  : -0.1199275674
     f_1_step_pred_les        : 295.6901712794
     f_1_step_pred_adj_misc   : -6.2065392537
     pred_les + pred_adj_misc : 289.4836320257
     f_1_step_pred_price_inc          : 801.2893664356
     f_1_step_pred_price              : 90900.2893664356
     f_1_step_pred_price_rounded      : 90900
     f_1_step_pred_set_price_rounded  : 91200
-------------------------------------------------
==>> Forecasting   9 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:58
in_current_price  : 90900.289366
*INFO* f_current_datetime   : 2017-09 11:29:58 
*INFO* f_current_si         : 2.7679954159 
*INFO* f_current_price4pm   : 801 
*INFO* f_current_price4pmsi : 289.4836320257 
*INFO* f_1_step_time        : 11:29:59
*INFO* f_1_step_si          : 2.9179195994 
*INFO* shl_global_parm_short_weight_ratio : 9
     previous_pred_les_level  : 295.8100988468
     previous_pred_les_trend  : -0.1199275674
     f_1_step_pred_les_level  : 290.4219130171
     f_1_step_pred_les_trend  : -0.1251958257
     f_1_step_pred_les        : 290.2967171914
     f_1_step_pred_adj_misc   : -6.9823566604
     pred_les + pred_adj_misc : 283.3143605310
     f_1_step_pred_price_inc          : 826.6885253928
     f_1_step_pred_price              : 90925.6885253928
     f_1_step_pred_price_rounded      : 90900
     f_1_step_pred_set_price_rounded  : 91200
-------------------------------------------------
==>> Forecasting  10 out of next  10 seconds/steps... 

+-----------------------------------------------+
| shl_predict_price_1_step()                    |
+-----------------------------------------------+
current_ccyy_mm   : 2017-09
in_current_time   : 11:29:59
in_current_price  : 90925.688525
*INFO* f_current_datetime   : 2017-09 11:29:59 
*INFO* f_current_si         : 2.9179195994 
*INFO* f_current_price4pm   : 826 
*INFO* f_current_price4pmsi : 283.3143605310 
*INFO* f_1_step_time        : 11:30:00
*INFO* f_1_step_si          : 3.0586081454 
*INFO* shl_global_parm_short_weight_ratio : 10
     previous_pred_les_level  : 290.4219130171
     previous_pred_les_trend  : -0.1251958257
     f_1_step_pred_les_level  : 284.3699266464
     f_1_step_pred_les_trend  : -0.1311226162
     f_1_step_pred_les        : 284.2388040302
     f_1_step_pred_adj_misc   : -7.7581740671
     pred_les + pred_adj_misc : 276.4806299631
     f_1_step_pred_price_inc          : 845.6459068442
     f_1_step_pred_price              : 90944.6459068442
     f_1_step_pred_price_rounded      : 90900
     f_1_step_pred_set_price_rounded  : 91200
-------------------------------------------------
==>> Prediction Restuls in Python List :  [91000, 91000, 91100, 91100, 91100, 91200, 91200, 91200, 91200, 91200]
[91000, 91000, 91100, 91100, 91100, 91200, 91200, 91200, 91200, 91200]

In [11]:
print(shl_sm_prediction_list_local_k)


[91000, 91000, 91100, 91100, 91100, 91200, 91200, 91200, 91200, 91200]

In [12]:
shl_pm.shl_data_pm_1_step.tail(11)


Out[12]:
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 2017-09 0.000000 281.506425 281.642801 -0.136376 90411.709058 312.709058 90400.0 90700.0 1.110842 11:29:41 90400.0 2017-09 11:29:40 301.0 279.745938 1.075976
41 2017-09 0.000000 272.413897 272.559220 -0.145324 90416.635616 317.635616 90400.0 90700.0 1.166004 11:29:42 90400.0 2017-09 11:29:41 301.0 270.965716 1.110842
42 2017-09 0.000000 260.146119 260.303552 -0.157434 90431.099906 332.099906 90400.0 90700.0 1.276590 11:29:43 90400.0 2017-09 11:29:42 301.0 258.146690 1.166004
43 2017-09 0.000000 239.289211 239.467324 -0.178113 90431.421552 332.421552 90400.0 90700.0 1.389204 11:29:44 90400.0 2017-09 11:29:43 301.0 235.784414 1.276590
44 2017-09 0.000000 219.892876 220.090188 -0.197312 90416.858085 317.858085 90400.0 90700.0 1.445513 11:29:45 90400.0 2017-09 11:29:44 301.0 216.670826 1.389204
45 2017-09 0.000000 209.786383 209.993594 -0.207211 90429.101913 330.101913 90400.0 90700.0 1.573514 11:29:46 90400.0 2017-09 11:29:45 301.0 208.230524 1.445513
46 2017-09 0.000000 247.863004 248.031969 -0.168965 90507.228065 408.228065 90500.0 90800.0 1.646991 11:29:47 90500.0 2017-09 11:29:46 401.0 254.843539 1.573514
47 2017-09 0.000000 243.965123 244.137814 -0.172691 90526.630864 427.630864 90500.0 90800.0 1.752836 11:29:48 90500.0 2017-09 11:29:47 401.0 243.474355 1.646991
48 2017-09 0.000000 327.831673 327.920408 -0.088735 90685.851736 586.851736 90700.0 91000.0 1.790101 11:29:49 90700.0 2017-09 11:29:48 601.0 342.872911 1.752836
49 2017-09 0.000000 334.458421 334.540448 -0.082027 90744.233069 645.233069 90700.0 91000.0 1.929188 11:29:50 90700.0 2017-09 11:29:49 601.0 335.735286 1.790101
50 2017-09 -0.775817 314.894813 314.996301 -0.101489 90726.902595 627.902595 90700.0 91000.0 1.998932 11:29:51 90700.0 2017-09 11:29:50 601.0 311.530082 1.929188

In [13]:
shl_pm.shl_data_pm_k_step.tail(20)


Out[13]:
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 2017-09 0.000000 281.506425 281.642801 -0.136376 90411.709058 312.709058 90400.0 90700.0 1.110842 11:29:41 90400.000000 2017-09 11:29:40 301.000000 279.745938 1.075976
41 2017-09 0.000000 272.413897 272.559220 -0.145324 90416.635616 317.635616 90400.0 90700.0 1.166004 11:29:42 90400.000000 2017-09 11:29:41 301.000000 270.965716 1.110842
42 2017-09 0.000000 260.146119 260.303552 -0.157434 90431.099906 332.099906 90400.0 90700.0 1.276590 11:29:43 90400.000000 2017-09 11:29:42 301.000000 258.146690 1.166004
43 2017-09 0.000000 239.289211 239.467324 -0.178113 90431.421552 332.421552 90400.0 90700.0 1.389204 11:29:44 90400.000000 2017-09 11:29:43 301.000000 235.784414 1.276590
44 2017-09 0.000000 219.892876 220.090188 -0.197312 90416.858085 317.858085 90400.0 90700.0 1.445513 11:29:45 90400.000000 2017-09 11:29:44 301.000000 216.670826 1.389204
45 2017-09 0.000000 209.786383 209.993594 -0.207211 90429.101913 330.101913 90400.0 90700.0 1.573514 11:29:46 90400.000000 2017-09 11:29:45 301.000000 208.230524 1.445513
46 2017-09 0.000000 247.863004 248.031969 -0.168965 90507.228065 408.228065 90500.0 90800.0 1.646991 11:29:47 90500.000000 2017-09 11:29:46 401.000000 254.843539 1.573514
47 2017-09 0.000000 243.965123 244.137814 -0.172691 90526.630864 427.630864 90500.0 90800.0 1.752836 11:29:48 90500.000000 2017-09 11:29:47 401.000000 243.474355 1.646991
48 2017-09 0.000000 327.831673 327.920408 -0.088735 90685.851736 586.851736 90700.0 91000.0 1.790101 11:29:49 90700.000000 2017-09 11:29:48 601.000000 342.872911 1.752836
49 2017-09 0.000000 334.458421 334.540448 -0.082027 90744.233069 645.233069 90700.0 91000.0 1.929188 11:29:50 90700.000000 2017-09 11:29:49 601.000000 335.735286 1.790101
50 2017-09 -0.775817 314.894813 314.996301 -0.101489 90726.902595 627.902595 90700.0 91000.0 1.998932 11:29:51 90700.000000 2017-09 11:29:50 601.000000 311.530082 1.929188
51 2017-09 -1.551635 314.134133 314.236280 -0.102147 90744.680258 645.680258 90700.0 91000.0 2.065632 11:29:52 90726.902595 2017-09 11:29:51 627.902595 314.118995 1.998932
52 2017-09 -2.327452 312.713604 312.817069 -0.103464 90774.472408 675.472408 90800.0 91100.0 2.176232 11:29:53 90744.680258 2017-09 11:29:52 645.680258 312.582498 2.065632
53 2017-09 -3.103270 310.632568 310.738007 -0.105440 90805.073335 706.073335 90800.0 91100.0 2.295955 11:29:54 90774.472408 2017-09 11:29:53 675.472408 310.386152 2.176232
54 2017-09 -3.879087 307.890364 307.998438 -0.108074 90833.719821 734.719821 90800.0 91100.0 2.416752 11:29:55 90805.073335 2017-09 11:29:54 706.073335 307.529298 2.295955
55 2017-09 -4.654904 304.486336 304.597703 -0.111367 90863.784681 764.784681 90900.0 91200.0 2.550716 11:29:56 90833.719821 2017-09 11:29:55 734.719821 304.011277 2.416752
56 2017-09 -5.430722 300.419825 300.535143 -0.115318 90896.540212 797.540212 90900.0 91200.0 2.703626 11:29:57 90863.784681 2017-09 11:29:56 764.784681 299.831432 2.550716
57 2017-09 -6.206539 295.690171 295.810099 -0.119928 90900.289366 801.289366 90900.0 91200.0 2.767995 11:29:58 90896.540212 2017-09 11:29:57 797.540212 294.989103 2.703626
58 2017-09 -6.982357 290.296717 290.421913 -0.125196 90925.688525 826.688525 90900.0 91200.0 2.917920 11:29:59 90900.289366 2017-09 11:29:58 801.289366 289.483632 2.767995
59 2017-09 -7.758174 284.238804 284.369927 -0.131123 90944.645907 845.645907 90900.0 91200.0 3.058608 11:30:00 90925.688525 2017-09 11:29:59 826.688525 283.314361 2.917920

In [ ]:

MISC - Validation


In [14]:
%matplotlib inline
import matplotlib.pyplot as plt

In [15]:
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[15]:
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 2017-09 0.000000 425.008790 425.008790 0.000000 90107.878192 8.878192 90100.0 90400.0 0.020889 11:29:01 90100.000000 2017-09 11:29:00 1.000000 425.008790 0.002353
2 2017-09 0.000000 104.565213 104.885337 -0.320123 90102.716326 3.716326 90100.0 90400.0 0.035541 11:29:02 90100.000000 2017-09 11:29:01 1.000000 47.871095 0.020889
3 2017-09 0.000000 39.305886 39.690884 -0.384998 90100.646571 1.646571 90100.0 90400.0 0.041891 11:29:03 90100.000000 2017-09 11:29:02 1.000000 28.136714 0.035541
4 2017-09 0.000000 25.806598 26.204697 -0.398099 90100.270680 1.270680 90100.0 90400.0 0.049239 11:29:04 90100.000000 2017-09 11:29:03 1.000000 23.871365 0.041891
5 2017-09 0.000000 20.737583 21.140348 -0.402765 90100.013346 1.013346 90100.0 90400.0 0.048865 11:29:05 90100.000000 2017-09 11:29:04 1.000000 20.309285 0.049239
6 2017-09 0.000000 20.102755 20.505752 -0.402997 90100.642584 1.642584 90100.0 90400.0 0.081709 11:29:06 90100.000000 2017-09 11:29:05 1.000000 20.464463 0.048865
7 2017-09 0.000000 13.017713 13.427386 -0.409672 90100.277808 1.277808 90100.0 90400.0 0.098159 11:29:07 90100.000000 2017-09 11:29:06 1.000000 12.238497 0.081709
8 2017-09 0.000000 10.203317 10.615392 -0.412075 90100.427460 1.427460 90100.0 90400.0 0.139902 11:29:08 90100.000000 2017-09 11:29:07 1.000000 10.187537 0.098159
9 2017-09 0.000000 7.195126 7.609794 -0.414668 90100.459944 1.459944 90100.0 90400.0 0.202907 11:29:09 90100.000000 2017-09 11:29:08 1.000000 7.147885 0.139902
10 2017-09 0.000000 4.854447 5.271040 -0.416592 90100.151187 1.151187 90100.0 90400.0 0.237141 11:29:10 90100.000000 2017-09 11:29:09 1.000000 4.928359 0.202907
11 2017-09 0.000000 3.896154 4.313287 -0.417134 90100.140194 1.140194 90100.0 90400.0 0.292646 11:29:11 90100.000000 2017-09 11:29:10 1.000000 4.216906 0.237141
12 2017-09 0.000000 3.071979 3.489520 -0.417540 90100.047199 1.047199 90100.0 90400.0 0.340888 11:29:12 90100.000000 2017-09 11:29:11 1.000000 3.417098 0.292646
13 2017-09 0.000000 2.536793 2.954451 -0.417658 90099.906873 0.906873 90100.0 90400.0 0.357488 11:29:13 90100.000000 2017-09 11:29:12 1.000000 2.933519 0.340888
14 2017-09 0.000000 2.340479 2.757916 -0.417437 90099.879049 0.879049 90100.0 90400.0 0.375585 11:29:14 90100.000000 2017-09 11:29:13 1.000000 2.797298 0.357488
15 2017-09 0.000000 2.196666 2.613829 -0.417163 90099.887140 0.887140 90100.0 90400.0 0.403858 11:29:15 90100.000000 2017-09 11:29:14 1.000000 2.662513 0.375585
16 2017-09 0.000000 212.406156 212.612903 -0.206747 90188.875149 89.875149 90200.0 90500.0 0.423129 11:29:16 90200.000000 2017-09 11:29:15 101.000000 250.088202 0.403858
17 2017-09 0.000000 234.538903 234.723332 -0.184430 90207.216038 108.216038 90200.0 90500.0 0.461399 11:29:17 90200.000000 2017-09 11:29:16 101.000000 238.698039 0.423129
18 2017-09 0.000000 221.066041 221.263746 -0.197705 90207.110066 108.110066 90200.0 90500.0 0.489040 11:29:18 90200.000000 2017-09 11:29:17 101.000000 218.899430 0.461399
19 2017-09 0.000000 382.258172 382.294649 -0.036476 90293.221136 194.221136 90300.0 90600.0 0.508089 11:29:19 90300.000000 2017-09 11:29:18 201.000000 411.009592 0.489040
20 2017-09 0.000000 393.557932 393.583083 -0.025151 90307.135005 208.135005 90300.0 90600.0 0.528855 11:29:20 90300.000000 2017-09 11:29:19 201.000000 395.600059 0.508089
21 2017-09 0.000000 382.069485 382.106088 -0.036603 90314.854128 215.854128 90300.0 90600.0 0.564960 11:29:21 90300.000000 2017-09 11:29:20 201.000000 380.066506 0.528855
22 2017-09 0.000000 359.693004 359.751925 -0.058921 90305.967816 206.967816 90300.0 90600.0 0.575401 11:29:22 90300.000000 2017-09 11:29:21 201.000000 355.777150 0.564960
23 2017-09 0.000000 350.821642 350.889367 -0.067724 90304.647361 205.647361 90300.0 90600.0 0.586188 11:29:23 90300.000000 2017-09 11:29:22 201.000000 349.321432 0.575401
24 2017-09 0.000000 488.966500 488.896150 0.070350 90399.025194 300.025194 90400.0 90700.0 0.613590 11:29:24 90400.000000 2017-09 11:29:23 301.000000 513.487329 0.586188
25 2017-09 0.000000 490.386718 490.315019 0.071699 90418.825918 319.825918 90400.0 90700.0 0.652191 11:29:25 90400.000000 2017-09 11:29:24 301.000000 490.555192 0.613590
26 2017-09 0.000000 465.932071 465.884874 0.047197 90410.458696 311.458696 90400.0 90700.0 0.668464 11:29:26 90400.000000 2017-09 11:29:25 301.000000 461.521076 0.652191
27 2017-09 0.000000 452.685402 452.651485 0.033916 90410.327204 311.327204 90400.0 90700.0 0.687734 11:29:27 90400.000000 2017-09 11:29:26 301.000000 450.286203 0.668464
28 2017-09 0.000000 439.960401 439.939231 0.021170 90415.205265 316.205265 90400.0 90700.0 0.718713 11:29:28 90400.000000 2017-09 11:29:27 301.000000 437.669128 0.687734
29 2017-09 0.000000 422.005693 422.002481 0.003212 90408.193009 309.193009 90400.0 90700.0 0.732675 11:29:29 90400.000000 2017-09 11:29:28 301.000000 418.804161 0.718713
30 2017-09 0.000000 412.507590 412.513870 -0.006280 90418.030573 319.030573 90400.0 90700.0 0.773393 11:29:30 90400.000000 2017-09 11:29:29 301.000000 410.823369 0.732675
31 2017-09 0.000000 392.692391 392.718460 -0.026069 90408.726475 309.726475 90400.0 90700.0 0.788725 11:29:31 90400.000000 2017-09 11:29:30 301.000000 389.194000 0.773393
32 2017-09 0.000000 383.265526 383.300987 -0.035460 90410.597704 311.597704 90400.0 90700.0 0.813007 11:29:32 90400.000000 2017-09 11:29:31 301.000000 381.628370 0.788725
33 2017-09 0.000000 372.154423 372.200948 -0.046525 90408.738067 309.738067 90400.0 90700.0 0.832284 11:29:33 90400.000000 2017-09 11:29:32 301.000000 370.230338 0.813007
34 2017-09 0.000000 363.187267 363.242703 -0.055437 90412.054225 313.054225 90400.0 90700.0 0.861964 11:29:34 90400.000000 2017-09 11:29:33 301.000000 361.655519 0.832284
35 2017-09 0.000000 351.249491 351.316798 -0.067307 90421.907916 322.907916 90400.0 90700.0 0.919312 11:29:35 90400.000000 2017-09 11:29:34 301.000000 349.202658 0.861964
36 2017-09 0.000000 330.933831 331.021366 -0.087535 90413.162186 314.162186 90400.0 90700.0 0.949320 11:29:36 90400.000000 2017-09 11:29:35 301.000000 327.418721 0.919312
37 2017-09 0.000000 319.065709 319.165013 -0.099304 90411.156824 312.156824 90400.0 90700.0 0.978347 11:29:37 90400.000000 2017-09 11:29:36 301.000000 317.068977 0.949320
38 2017-09 0.000000 309.276946 309.385930 -0.108984 90408.114796 309.114796 90400.0 90700.0 0.999476 11:29:38 90400.000000 2017-09 11:29:37 301.000000 307.661953 0.978347
39 2017-09 0.000000 302.269425 302.385300 -0.115875 90412.017396 313.017396 90400.0 90700.0 1.035558 11:29:39 90400.000000 2017-09 11:29:38 301.000000 301.157893 0.999476
40 2017-09 0.000000 292.293304 292.419030 -0.125726 90413.500668 314.500668 90400.0 90700.0 1.075976 11:29:40 90400.000000 2017-09 11:29:39 301.000000 290.664666 1.035558
41 2017-09 0.000000 281.506425 281.642801 -0.136376 90411.709058 312.709058 90400.0 90700.0 1.110842 11:29:41 90400.000000 2017-09 11:29:40 301.000000 279.745938 1.075976
42 2017-09 0.000000 272.413897 272.559220 -0.145324 90416.635616 317.635616 90400.0 90700.0 1.166004 11:29:42 90400.000000 2017-09 11:29:41 301.000000 270.965716 1.110842
43 2017-09 0.000000 260.146119 260.303552 -0.157434 90431.099906 332.099906 90400.0 90700.0 1.276590 11:29:43 90400.000000 2017-09 11:29:42 301.000000 258.146690 1.166004
44 2017-09 0.000000 239.289211 239.467324 -0.178113 90431.421552 332.421552 90400.0 90700.0 1.389204 11:29:44 90400.000000 2017-09 11:29:43 301.000000 235.784414 1.276590
45 2017-09 0.000000 219.892876 220.090188 -0.197312 90416.858085 317.858085 90400.0 90700.0 1.445513 11:29:45 90400.000000 2017-09 11:29:44 301.000000 216.670826 1.389204
46 2017-09 0.000000 209.786383 209.993594 -0.207211 90429.101913 330.101913 90400.0 90700.0 1.573514 11:29:46 90400.000000 2017-09 11:29:45 301.000000 208.230524 1.445513
47 2017-09 0.000000 247.863004 248.031969 -0.168965 90507.228065 408.228065 90500.0 90800.0 1.646991 11:29:47 90500.000000 2017-09 11:29:46 401.000000 254.843539 1.573514
48 2017-09 0.000000 243.965123 244.137814 -0.172691 90526.630864 427.630864 90500.0 90800.0 1.752836 11:29:48 90500.000000 2017-09 11:29:47 401.000000 243.474355 1.646991
49 2017-09 0.000000 327.831673 327.920408 -0.088735 90685.851736 586.851736 90700.0 91000.0 1.790101 11:29:49 90700.000000 2017-09 11:29:48 601.000000 342.872911 1.752836
50 2017-09 0.000000 334.458421 334.540448 -0.082027 90744.233069 645.233069 90700.0 91000.0 1.929188 11:29:50 90700.000000 2017-09 11:29:49 601.000000 335.735286 1.790101
51 2017-09 -0.775817 314.894813 314.996301 -0.101489 90726.902595 627.902595 90700.0 91000.0 1.998932 11:29:51 90700.000000 2017-09 11:29:50 601.000000 311.530082 1.929188
52 2017-09 -1.551635 314.134133 314.236280 -0.102147 90744.680258 645.680258 90700.0 91000.0 2.065632 11:29:52 90726.902595 2017-09 11:29:51 627.902595 314.118995 1.998932
53 2017-09 -2.327452 312.713604 312.817069 -0.103464 90774.472408 675.472408 90800.0 91100.0 2.176232 11:29:53 90744.680258 2017-09 11:29:52 645.680258 312.582498 2.065632
54 2017-09 -3.103270 310.632568 310.738007 -0.105440 90805.073335 706.073335 90800.0 91100.0 2.295955 11:29:54 90774.472408 2017-09 11:29:53 675.472408 310.386152 2.176232
55 2017-09 -3.879087 307.890364 307.998438 -0.108074 90833.719821 734.719821 90800.0 91100.0 2.416752 11:29:55 90805.073335 2017-09 11:29:54 706.073335 307.529298 2.295955
56 2017-09 -4.654904 304.486336 304.597703 -0.111367 90863.784681 764.784681 90900.0 91200.0 2.550716 11:29:56 90833.719821 2017-09 11:29:55 734.719821 304.011277 2.416752
57 2017-09 -5.430722 300.419825 300.535143 -0.115318 90896.540212 797.540212 90900.0 91200.0 2.703626 11:29:57 90863.784681 2017-09 11:29:56 764.784681 299.831432 2.550716
58 2017-09 -6.206539 295.690171 295.810099 -0.119928 90900.289366 801.289366 90900.0 91200.0 2.767995 11:29:58 90896.540212 2017-09 11:29:57 797.540212 294.989103 2.703626
59 2017-09 -6.982357 290.296717 290.421913 -0.125196 90925.688525 826.688525 90900.0 91200.0 2.917920 11:29:59 90900.289366 2017-09 11:29:58 801.289366 289.483632 2.767995
60 2017-09 -7.758174 284.238804 284.369927 -0.131123 90944.645907 845.645907 90900.0 91200.0 3.058608 11:30:00 90925.688525 2017-09 11:29:59 826.688525 283.314361 2.917920

In [16]:
# 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[16]:
[<matplotlib.lines.Line2D at 0x7f31066f5240>]

In [17]:
print('Dynamic Increment : +%d' % shl_pm.shl_global_parm_dynamic_increment)


Dynamic Increment : +300

In [18]:
# 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[18]:
bid-price f_1_step_pred_price 0
50 90700 90744.233069 44.233069
51 90700 90726.902595 26.902595
52 90700 90744.680258 44.680258
53 90800 90774.472408 -25.527592
54 90800 90805.073335 5.073335
55 90800 90833.719821 33.719821
56 90900 90863.784681 -36.215319
57 91000 90896.540212 -103.459788
58 91000 90900.289366 -99.710634
59 91200 90925.688525 -274.311475
60 91300 90944.645907 -355.354093

The End