import pandas as pd
import biogeme.database as db
import biogeme.biogeme as bio
import biogeme.models as models

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',0,None,None,0)
B_COST = Beta('B_COST',0,None,None,0)

# Define a random parameter, normally distributed, designed to be used
# for Monte-Carlo simulation
B_TIME_RND = B_TIME + B_TIME_S * bioDraws('B_TIME_RND','NORMAL')

# 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
prob = models.logit(V,av,CHOICE)
logprob = log(MonteCarlo(prob))


biogeme = bio.BIOGEME(database,logprob,numberOfDraws=1000)

biogeme.modelName = '05normalMixture'
results = biogeme.estimate()
print(results)