-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy path17lognormalMixtureIntegral.py
92 lines (69 loc) · 3.15 KB
/
17lognormalMixtureIntegral.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
import pandas as pd
import biogeme.database as db
import biogeme.biogeme as bio
import biogeme.distributions as dist
import biogeme.models as models
#from biogeme.expressions import *
pandas = pd.read_table("swissmetro.dat")
database = db.Database("swissmetro",pandas)
# The Pandas data structure is available as database.data. Use all the
# Pandas functions to invesigate the database
#print(database.data.describe())
from headers import *
# Removing some observations can be done directly using pandas.
#remove = (((database.data.PURPOSE != 1) & (database.data.PURPOSE != 3)) | (database.data.CHOICE == 0))
#database.data.drop(database.data[remove].index,inplace=True)
# Here we use the "biogeme" way for backward compatibility
exclude = (( PURPOSE != 1 ) * ( PURPOSE != 3 ) + ( CHOICE == 0 )) > 0
database.remove(exclude)
ASC_CAR = Beta('ASC_CAR',0,None,None,0)
ASC_TRAIN = Beta('ASC_TRAIN',0,None,None,0)
ASC_SM = Beta('ASC_SM',0,None,None,1)
B_TIME = Beta('B_TIME',0,None,None,0)
B_TIME_S = Beta('B_TIME_S',1,None,None,0)
B_COST = Beta('B_COST',0,None,None,0)
# Define a random parameter, normally distirbuted, designed to be used
# for Monte-Carlo simulation
omega = RandomVariable('omega')
B_TIME_RND = -exp(B_TIME + B_TIME_S * omega)
density = dist.normalpdf(omega)
# Utility functions
#If the person has a GA (season ticket) her incremental cost is actually 0
#rather than the cost value gathered from the
# network data.
SM_COST = SM_CO * ( GA == 0 )
TRAIN_COST = TRAIN_CO * ( GA == 0 )
# For numerical reasons, it is good practice to scale the data to
# that the values of the parameters are around 1.0.
# A previous estimation with the unscaled data has generated
# parameters around -0.01 for both cost and time. Therefore, time and
# cost are multipled my 0.01.
TRAIN_TT_SCALED = DefineVariable('TRAIN_TT_SCALED',\
TRAIN_TT / 100.0,database)
TRAIN_COST_SCALED = DefineVariable('TRAIN_COST_SCALED',\
TRAIN_COST / 100,database)
SM_TT_SCALED = DefineVariable('SM_TT_SCALED', SM_TT / 100.0,database)
SM_COST_SCALED = DefineVariable('SM_COST_SCALED', SM_COST / 100,database)
CAR_TT_SCALED = DefineVariable('CAR_TT_SCALED', CAR_TT / 100,database)
CAR_CO_SCALED = DefineVariable('CAR_CO_SCALED', CAR_CO / 100,database)
V1 = ASC_TRAIN + B_TIME_RND * TRAIN_TT_SCALED + B_COST * TRAIN_COST_SCALED
V2 = ASC_SM + B_TIME_RND * SM_TT_SCALED + B_COST * SM_COST_SCALED
V3 = ASC_CAR + B_TIME_RND * CAR_TT_SCALED + B_COST * CAR_CO_SCALED
# Associate utility functions with the numbering of alternatives
V = {1: V1,
2: V2,
3: V3}
# Associate the availability conditions with the alternatives
CAR_AV_SP = DefineVariable('CAR_AV_SP',CAR_AV * ( SP != 0 ),database)
TRAIN_AV_SP = DefineVariable('TRAIN_AV_SP',TRAIN_AV * ( SP != 0 ),database)
av = {1: TRAIN_AV_SP,
2: SM_AV,
3: CAR_AV_SP}
# The choice model is a logit, with availability conditions
condprob = models.logit(V,av,CHOICE)
prob = Integrate(condprob * density,'omega')
logprob = log(prob)
biogeme = bio.BIOGEME(database,logprob)
biogeme.modelName = '17lognormalMixtureIntegral'
results = biogeme.estimate()
print(results)