notebook.community

Edit and run 





In [1]:



    


import smv
from pandas import *
pandas.set_option('display.max_columns', None)
pandas.set_option('display.max_rows', 20)

import numpy as np
src_path = "/Users/xingyuwu/Documents/Datasense/Product/Demo_Output/"
proj_nm = "com.datasenseanalytics.pluto.airlinedemo."

DM Scenario 1





In [3]:



    


corp_raw = ddf(proj_nm+"feature.CorpQuarterFeature")
corp_df = corp_raw.toPandas()
corp_df.head(10)



    


















    
Out[3]:










  
    

      
      CORP_ACC_NO
      smvTime
      corpcnt_tvl_seg_per_qt
      corpcnt_cm_tvl_per_qt
      corpcnt_cm_dly2hr_per_qt
      corpcnt_cm_dly2hr_p1q
      corpcnt_cm_total
    

  
  
    

      0
      5540324
      Q201104
      0
      0
      0
      NaN
      14
    

    

      1
      5540324
      Q201201
      155
      2
      1
      0.0
      14
    

    

      2
      5540324
      Q201202
      404
      4
      1
      1.0
      14
    

    

      3
      5540324
      Q201203
      364
      3
      1
      1.0
      14
    

    

      4
      5540324
      Q201204
      631
      7
      1
      1.0
      14
    

    

      5
      5540324
      Q201301
      444
      6
      1
      1.0
      14
    

    

      6
      5540324
      Q201302
      632
      3
      1
      1.0
      14
    

    

      7
      5540324
      Q201303
      323
      5
      1
      1.0
      14
    

    

      8
      5540324
      Q201304
      484
      9
      1
      1.0
      14
    

    

      9
      5540324
      Q201401
      415
      5
      1
      1.0
      14
Feature Descriptipn
corpcnt_tvl_seg_per_qt count travelled segments of a corporate account per quarter
corpcnt_cm_tvl_per_qt count distinct # of travelled customers of a corporate account per quarter
corpcnt_cm_dly2hr_per_qt count distinct # of customers with >2hr delay of a corporate account per quarter
corpcnt_seg_dly2hr_per_qt count segments with >2hr delay of a corporate account per quarter

DM Scenario 3





In [7]:



    


leg_df = pd.read_csv(src_path+"LegOrgStnFeature.csv")
leg_df[leg_df.SCH_LEG_ORIG_CD == """JFK"""]



    


















    
Out[7]:










  
    

      
      SCH_LEG_ORIG_CD
      flt_leg_dprt_hr
      orgavg_0_web_upd_rate_per_hr
      orgavg_1_web_upd_rate_per_hr
      orgavg_2_web_upd_rate_per_hr
      orgavg_3_web_upd_rate_per_hr
      orgavg_4_web_upd_rate_per_hr
      orgavg_5_web_upd_rate_per_hr
      orgavg_0_CC_upd_rate_per_hr
      orgavg_1_CC_upd_rate_per_hr
      orgavg_2_CC_upd_rate_per_hr
      orgavg_3_CC_upd_rate_per_hr
      orgavg_4_CC_upd_rate_per_hr
      orgavg_5_CC_upd_rate_per_hr
      orgavg_0_Airport_upd_rate_per_hr
      orgavg_1_Airport_upd_rate_per_hr
      orgavg_2_Airport_upd_rate_per_hr
      orgavg_3_Airport_upd_rate_per_hr
      orgavg_4_Airport_upd_rate_per_hr
      orgavg_5_Airport_upd_rate_per_hr
      orgavg_0_upd_rate_per_hr
      orgavg_1_upd_rate_per_hr
      orgavg_2_upd_rate_per_hr
      orgavg_3_upd_rate_per_hr
      orgavg_4_upd_rate_per_hr
      orgavg_5_upd_rate_per_hr
      orgavg_upd_rate_per_hr
      orgavg_grd_stf_per_hr
      org_rto_pax_grd_stf_per_hr
    

  
  
    

      258
      JFK
      0
      0.056180
      0.037383
      0.098765
      0.081633
      0.0
      0.0
      0.033708
      0.037383
      0.049383
      0.081633
      0.0
      0.0
      0.044944
      0.046729
      0.037037
      0.040816
      0.0
      0.0
      0.134831
      0.121495
      0.185185
      0.204082
      0.0
      0.0
      0.109630
      5.000000
      45.000000
    

    

      262
      JFK
      1
      0.031496
      0.173913
      0.027778
      0.045455
      0.0
      0.0
      0.023622
      0.086957
      0.055556
      0.000000
      0.0
      0.0
      0.023622
      0.021739
      0.055556
      0.045455
      0.0
      0.0
      0.078740
      0.282609
      0.138889
      0.090909
      0.0
      0.0
      0.100671
      4.000000
      37.250000
    

    

      332
      JFK
      10
      0.085859
      0.196970
      0.029412
      0.055556
      0.0
      0.0
      0.015152
      0.090909
      0.058824
      0.055556
      0.0
      0.0
      0.010101
      0.075758
      0.029412
      0.083333
      0.0
      0.0
      0.111111
      0.363636
      0.117647
      0.194444
      0.0
      0.0
      0.129787
      11.500000
      20.434783
    

    

      335
      JFK
      11
      0.057692
      0.175000
      0.085714
      0.045455
      0.0
      0.0
      0.057692
      0.000000
      0.028571
      0.000000
      0.0
      0.0
      0.000000
      0.025000
      0.057143
      0.000000
      0.0
      0.0
      0.115385
      0.200000
      0.171429
      0.045455
      0.0
      0.0
      0.112500
      12.000000
      20.000000
    

    

      338
      JFK
      12
      0.078603
      0.151163
      0.073529
      0.022727
      0.0
      0.0
      0.048035
      0.034884
      0.044118
      0.068182
      0.0
      0.0
      0.026201
      0.034884
      0.044118
      0.022727
      0.0
      0.0
      0.152838
      0.220930
      0.161765
      0.113636
      0.0
      0.0
      0.122592
      11.000000
      12.977273
    

    

      342
      JFK
      13
      0.061224
      0.058824
      0.066667
      0.000000
      0.0
      0.0
      0.020408
      0.117647
      0.066667
      0.000000
      0.0
      0.0
      0.020408
      0.058824
      0.066667
      0.000000
      0.0
      0.0
      0.102041
      0.235294
      0.200000
      0.000000
      0.0
      0.0
      0.113208
      9.000000
      11.777778
    

    

      348
      JFK
      15
      0.072254
      0.142857
      0.074766
      0.015625
      0.0
      0.0
      0.020231
      0.042017
      0.037383
      0.031250
      0.0
      0.0
      0.011561
      0.042017
      0.046729
      0.046875
      0.0
      0.0
      0.104046
      0.226891
      0.158879
      0.093750
      0.0
      0.0
      0.105006
      12.000000
      17.062500
    

    

      350
      JFK
      16
      0.034091
      0.085714
      0.068966
      0.052632
      0.0
      0.0
      0.034091
      0.057143
      0.068966
      0.052632
      0.0
      0.0
      0.011364
      0.028571
      0.000000
      0.052632
      0.0
      0.0
      0.079545
      0.171429
      0.137931
      0.157895
      0.0
      0.0
      0.091324
      10.500000
      10.428571
    

    

      354
      JFK
      17
      0.055046
      0.097561
      0.028571
      0.000000
      0.0
      0.0
      0.036697
      0.048780
      0.057143
      0.050000
      0.0
      0.0
      0.027523
      0.024390
      0.028571
      0.000000
      0.0
      0.0
      0.119266
      0.170732
      0.114286
      0.050000
      0.0
      0.0
      0.092593
      9.500000
      14.210526
    

    

      356
      JFK
      18
      0.026596
      0.090909
      0.115385
      0.088235
      0.0
      0.0
      0.026596
      0.060606
      0.038462
      0.058824
      0.0
      0.0
      0.000000
      0.045455
      0.038462
      0.000000
      0.0
      0.0
      0.053191
      0.196970
      0.192308
      0.147059
      0.0
      0.0
      0.092010
      9.333333
      14.750000
    

    

      357
      JFK
      19
      0.078385
      0.061728
      0.081967
      0.094595
      0.0
      0.0
      0.033254
      0.074074
      0.049180
      0.027027
      0.0
      0.0
      0.019002
      0.043210
      0.032787
      0.040541
      0.0
      0.0
      0.130641
      0.179012
      0.163934
      0.162162
      0.0
      0.0
      0.119342
      8.200000
      23.707317
    

    

      397
      JFK
      20
      0.007407
      0.160000
      0.051282
      0.041667
      0.0
      0.0
      0.022222
      0.040000
      0.076923
      0.083333
      0.0
      0.0
      0.037037
      0.040000
      0.025641
      0.000000
      0.0
      0.0
      0.066667
      0.240000
      0.153846
      0.125000
      0.0
      0.0
      0.099668
      8.000000
      18.812500
    

    

      398
      JFK
      21
      0.067829
      0.089474
      0.074074
      0.071429
      0.0
      0.0
      0.029070
      0.068421
      0.049383
      0.071429
      0.0
      0.0
      0.027132
      0.031579
      0.030864
      0.030612
      0.0
      0.0
      0.124031
      0.189474
      0.154321
      0.173469
      0.0
      0.0
      0.113691
      5.571429
      32.025641
    

    

      402
      JFK
      22
      0.076087
      0.065574
      0.090909
      0.100000
      0.0
      0.0
      0.043478
      0.049180
      0.072727
      0.066667
      0.0
      0.0
      0.016304
      0.049180
      0.018182
      0.033333
      0.0
      0.0
      0.135870
      0.163934
      0.181818
      0.200000
      0.0
      0.0
      0.121718
      4.333333
      32.230769

Comments:

  • The output is calculated from dummy data at flight level (dummied passenger counts, ancillary purchases, etc.), assuming there are 6 tiers (0-5) and 3 channels to purchase upgrade (Web, Call Centre, and Airport).
  • The features are at the level of departure origin station x departure hour. For example, orgavg_1_Airport_upd_rate_per_hr is the average upgrade purchase rate of tier 1 customers of all flights per origin station per departure hour.

DM Scenario 2





In [8]:



    


leg_df = pd.read_csv(src_path+"DemandLastMile.csv")
leg_df.head(10)



    


















    
Out[8]:










  
    

      
      SCH_LEG_ORIG_CD
      SCH_LEG_DEST_CD
      FLT_MONTH
      DELTA_MONTH
      prediction
      TGT_AMT
      opportunity
    

  
  
    

      0
      LAX
      JFK
      2016-07
      1.0
      22764.020251
      22414.0
      -350.020251
    

    

      1
      LAX
      JFK
      2016-08
      2.0
      24187.356299
      28498.0
      4310.643701
    

    

      2
      LAX
      JFK
      2016-09
      3.0
      25618.868157
      23918.0
      -1700.868157
    

    

      3
      LAX
      JFK
      2016-10
      4.0
      25268.401609
      32324.0
      7055.598391
    

    

      4
      LAX
      JFK
      2016-11
      5.0
      22362.378033
      27862.0
      5499.621967
    

    

      5
      LAX
      JFK
      2016-12
      6.0
      22890.492109
      24830.0
      1939.507891

Comment: assume we stand at 2016-06 to predict future demand by month





In [ ]:

Content source: DataSenseAnalytics/AirlineApp

Similar notebooks:

notebook.community | gallery | about