def test__bfgs_optimization():
"""
Ensure that the bfgs optimization properly processes the input for one
iteration. The value of 0.4044 was computed by hand for
comparison purposes
"""
X_, y_ = X.reshape(N, J, K), y.reshape(N, J)
betas = np.array([.1, .1])
model = MultinomialLogit()
res = model._bfgs_optimization(betas, X_, y_, None, None, 0)
assert pytest.approx(res['fun'], 0.40443136)
def test_fit():
"""
Ensures the log-likelihood works for a single iterations with the default
initial coefficients. The value of 0.4044 was computed by hand for
comparison purposes
"""
model = MultinomialLogit()
model.fit(X,
y,
varnames=varnames,
alts=alts,
ids=ids,
maxiter=0,
verbose=0)
assert pytest.approx(model.loglikelihood, -0.40443136)
def test_log_likelihood():
"""
Computes the log-likelihood "by hand" for a simple example and ensures
that the one returned by xlogit is the same
"""
X_, y_ = X.reshape(N, J, K), y.reshape(N, J)
betas = np.array([.1, .1])
# Compute log likelihood using xlogit
model = MultinomialLogit()
obtained_loglik, _, _ = model._loglik_and_gradient(betas, X_, y_, None,
None)
# Compute expected log likelihood "by hand"
eXB = np.exp(X_.dot(betas))
expected_loglik = np.sum(
np.log(np.sum(eXB / np.sum(eXB, axis=1, keepdims=True) * y_, axis=1)))
assert pytest.approx(expected_loglik, obtained_loglik)
def example9_run():
df = pd.read_csv(
"https://raw.githubusercontent.com/arteagac/xlogit/master/examples/data/electricity_long.csv"
)
varnames = ["pf", "cl", "loc", "wk", "tod", "seas"]
X = df[varnames].values
y = df['choice'].values
choice_id = df['chid']
alt = [1, 2, 3, 4]
np.random.seed(123)
model = MultinomialLogit()
model.fit(
X=df[varnames],
y=y,
varnames=varnames,
isvars=[],
alts=alt,
fit_intercept=True,
# hess=False,
# grad=False,
# method="L-BFGS-B"
# tol=1e-4,
# scipy_optimisation=True
)
model.summary()
def example10_run():
# df = pd.read_csv("examples_prit/Final_HBW_WC_Long.csv")
df = pd.read_csv("xlogitprit/examples_prit/Final_HBW_WC_Long.csv")
# Accessibility Time (One coefficient per alternative)
df['ACT_PT'] = df['act'] * ((df['alt'] == 'w2pt') | (df['alt'] == 'pr') |
(df['alt'] == 'kr'))
# Waiting Time (One coefficient per alternative)
df['WT_PT'] = df['wt'] * ((df['alt'] == 'w2pt') | (df['alt'] == 'pr') |
(df['alt'] == 'kr'))
df['EMP_DENS'] = df['emp_dens'] * ((df['alt'] == 'w2pt') |
(df['alt'] == 'pr') |
(df['alt'] == 'kr'))
df['ADUL_VEH'] = df['adul_veh'] * ((df['alt'] == 'cad') |
(df['alt'] == 'pr'))
#To be provided by the user
choice_id = df['TRIPID']
ind_id = df['TRIPID']
varnames = ['tt', 'tc', 'ACT_PT', 'WT_PT', 'EMP_DENS', 'ADUL_VEH']
# asvarnames = ['tt','tc','ACT_PT', 'WT_PT', 'EMP_DENS','ADUL_VEH']
isvarnames = []
X = df[varnames].values
y = df['Chosen_Mode'].values
choice_set = ['cad', 'cap', 'w2pt', 'pr', 'kr', 'cycle', 'walk']
choice_var = df['Chosen_Mode']
alt_var = df['alt']
randvars = {'EMP_DENS': 'n', 'WT_PT': 'u'}
R = 200
Tol = 1e-6
model = MultinomialLogit()
# init_coeff = [-2, -4, -3, -2, -1, -1, 0, 0, -0, -0.01, 0.0001, -1.15]
model.fit(
X=df[varnames],
y=choice_var,
varnames=varnames, # init_coeff=np.repeat(.1, 11),
isvars=isvarnames,
alts=alt_var,
ids=choice_id, # gtol=1e-1,
# randvars=randvars,
fit_intercept=True,
hess=False,
gtol=1e-1,
# weights=[1, 1, 10, 10, 10, 100, 1]
) #, init_coeff=init_coeff, tol=1e-2) #hess=False, grad=False)
model.summary()
def example6_run():
df = pd.read_csv("https://raw.githubusercontent.com/arteagac/xlogit/master/examples/data/fishing_long.csv")
varnames = ['price', 'catch', 'income']
X = df[varnames].values
y = df['choice'].values
asvarnames = ['price']
isvarnames = ['income', 'catch']
rand_vars = {'price': 'n'}
alts = [1, 2, 3, 4]
# choice_id = df['chid']
model = MultinomialLogit()
# N, _ = Xd
N = len(np.unique(df['id'].values))
training_size = int(0.8*N)
ids = np.random.choice(N, training_size, replace=False)
train_idx = [ii for ii, id_val in enumerate(df['id']) if id_val in ids]
test_idx = [ii for ii, id_val in enumerate(df['id']) if id_val not in ids]
X_train = X[train_idx]
y_train = y[train_idx]
X_test = X[test_idx]
y_test = y[test_idx]
model.fit(X_train, y_train, varnames=varnames, alts=alts,
fit_intercept=True,
isvars=isvarnames
# scipy_optimisation=False,
# isvars=isvarnames, #transvars=['price', 'catch'], # randvars=rand_vars, #transvars=['price', 'catch'],
#, hess=False, grad=False
)
model.summary()
model.validation_loglik(X_test, y_test)
def example4_run():
df = pd.read_csv("https://raw.githubusercontent.com/arteagac/xlogit/master/examples/data/electricity_long.csv")
varnames = ["pf", "cl", "loc", "wk", "tod", "seas"]
X = df[varnames].values
y = df['choice'].values
# df['seas'] = -df
choice_id = df['chid']
alts = [1, 2, 3, 4]
np.random.seed(123)
model = MultinomialLogit()
maxiter = 1000
model.fit(X=X, y=y, varnames=varnames, isvars=[], alts=alts, fit_intercept=True,
transformation="boxcox", maxiter=maxiter, gtol=1e-3)
model.summary()
def example5_run():
df = pd.read_csv("https://raw.githubusercontent.com/arteagac/xlogit/master/examples/data/electricity_long.csv")
varnames = ["pf", "cl", "loc", "wk", "tod", "seas"]
# df['tod'] = -df['tod']
# df['seas'] = -df['seas']
# print('sum', sum(np.where(df)))
# print("df['seas']", df['seas'])
# print(1/0)
X = df[varnames].values
y = df['choice'].values
choice_id = df['chid']
alt = [1, 2, 3, 4]
np.random.seed(123)
print('covariance', np.cov(np.transpose(X)))
# print(1/0)
model = MultinomialLogit()
model.fit(X, y,
varnames,
alts=alt,
# randvars={'seas': 'ln', 'wk': 'n', 'pf': 'n', 'loc': 'n'},
fit_intercept=True,
# transformation="boxcox",
# transvars=['wk', 'seas'],
# correlation=True,
# ids=choice_id,
# panels=df.id.values,
# tol=1e-4,
# grad=False,
# hess=False,
isvars=[],
# verbose=1,
# halton=False,
# method='L-BFGS-B',
# n_draws=600
)
model.summary()
def example13_run():
df = pd.read_csv("xlogitprit/examples_prit/Final_HBW_WC_Long.csv")
# Accessibility Time (One coefficient per alternative)
df['ACT_PT'] = df['act'] * ((df['alt'] == 'w2pt') | (df['alt'] == 'pr') |
(df['alt'] == 'kr'))
# Waiting Time (One coefficient per alternative)
df['WT_PT'] = df['wt'] * ((df['alt'] == 'w2pt') | (df['alt'] == 'pr') |
(df['alt'] == 'kr'))
df['EMP_DENS'] = df['emp_dens'] * ((df['alt'] == 'w2pt') |
(df['alt'] == 'pr') |
(df['alt'] == 'kr'))
df['ADUL_VEH'] = df['adul_veh'] * ((df['alt'] == 'cad') |
(df['alt'] == 'pr'))
#To be provided by the user
choice_id = df['TRIPID']
ind_id = df['TRIPID']
varnames = ['tt', 'tc', 'ACT_PT', 'WT_PT', 'EMP_DENS', 'ADUL_VEH']
# asvarnames = ['tt','tc','ACT_PT', 'WT_PT', 'EMP_DENS','ADUL_VEH']
isvarnames = []
X = df[varnames].values
y = df['Chosen_Mode'].values
choice_set = ['cad', 'cap', 'w2pt', 'pr', 'kr', 'cycle', 'walk']
choice_var = df['Chosen_Mode']
alt_var = df['alt']
randvars = {'EMP_DENS': 'n', 'WT_PT': 'u'}
R = 200
Tol = 1e-6
def df_coeff_col(seed, dataframe, names_asvars, choiceset, var_alt):
np.random.seed(seed)
random_matrix = np.random.randint(1,
len(choiceset) + 1,
(len(choiceset), len(names_asvars)))
#print(random_matrix)
## Finding coefficients type (alt-specific or generic) for corresponding variables
alt_spec_pos = []
for i in range(random_matrix.shape[1]):
pos_freq = pd.Series(range(len(random_matrix[:, i]))).groupby(
random_matrix[:, i], sort=False).apply(list).tolist()
alt_spec_pos.append(pos_freq)
for i in range(len(alt_spec_pos)):
for j in range(len(alt_spec_pos[i])):
for k in range(len(alt_spec_pos[i][j])):
alt_spec_pos[i][j][k] = choiceset[alt_spec_pos[i][j][k]]
## creating dummy columns based on the coefficient type
asvars_new = []
for i in range(len(alt_spec_pos)):
for j in range(len(alt_spec_pos[i])):
if len(alt_spec_pos[i][j]) < len(choiceset):
dataframe[names_asvars[i] + '_' +
'_'.join(alt_spec_pos[i][j])] = dataframe[
names_asvars[i]] * np.isin(
var_alt, alt_spec_pos[i][j])
asvars_new.append(names_asvars[i] + '_' +
'_'.join(alt_spec_pos[i][j]))
else:
asvars_new.append(names_asvars[i])
return (asvars_new)
new_asvars = df_coeff_col(1, df, varnames, choice_set, alt_var)
varnames = new_asvars
model = MultinomialLogit()
# init_coeff = [-2, -4, -3, -2, -1, -1, 0, 0, -0, -0.01, 0.0001, -1.15]
model.fit(
X=df[varnames],
y=choice_var,
varnames=varnames, # init_coeff=np.repeat(.1, 11),
isvars=[],
alts=alt_var,
ids=choice_id, # gtol=1e-1,
# randvars=randvars,
fit_intercept=True,
# hess=False,
# gtol=1e-1,
# weights=[1, 1, 10, 10, 10, 100, 1]
) #, init_coeff=init_coeff, tol=1e-2) #hess=False, grad=False)
model.summary()
#To be provided by the user
choice_id = df['TRIPID']
ind_id = df['TRIPID']
varnames = ['tt', 'tc', 'ACT_PT', 'WT_PT', 'EMP_DENS', 'ADUL_VEH']
# asvarnames = ['tt','tc','ACT_PT', 'WT_PT', 'EMP_DENS','ADUL_VEH']
isvarnames = []
X = df[varnames].values
y = df['Chosen_Mode'].values
choice_set = ['cad', 'cap', 'w2pt', 'pr', 'kr', 'cycle', 'walk']
choice_var = df['Chosen_Mode']
alt_var = df['alt']
randvars = {'EMP_DENS': 'n', 'WT_PT': 'u'}
R = 200
Tol = 1e-6
model = MultinomialLogit()
# init_coeff = [-2, -4, -3, -2, -1, -1, 0, 0, -0, -0.01, 0.0001, -1.15]
model.fit(
X=df[varnames],
y=choice_var,
varnames=varnames, # init_coeff=np.repeat(.1, 11),
isvars=isvarnames,
alts=alt_var,
ids=choice_id, # gtol=1e-1,
# randvars=randvars,
fit_intercept=True,
hess=False
# gtol=1e-1,
# weights=[1, 1, 10, 10, 10, 100, 1]
) #, init_coeff=init_coeff, tol=1e-2) #hess=False, grad=False)
model.summary()
(df['alt'] == 'sm'))
# Coefficient Age for train
df['age_train'] = df['AGE'] * (df['alt'] == 'train')
# Coefficient Luggage for car
df['luggage_car'] = df['LUGGAGE'] * (df['alt'] == 'car')
# Coefficient seatsconfig for car
df['seats'] = df['seatconf'] * (df['alt'] == 'sm')
varnames = [
'asc_train', 'asc_car', 'cost', 'time', 'luggage_car', 'he_sm_train',
'seats', 'ga_sm_train', 'age_train'
]
model = MultinomialLogit()
model.fit(
X=df[varnames],
y=df['CHOICE'],
varnames=varnames,
alts=df['alt'],
ids=df['custom_id'],
avail=df['av'],
weights=np.ones(2)
# randvars={'cost': 'n'},
# transvars=['luggage_car']
# init_coeff=np.random.normal(0, 1, 9)
# scipy_optimisation=False
# method="L-BFGS-B"
# tol=1e-3
)
# df['tod'] = -df['tod']
# df['seas'] = -df['seas']
# print('sum', sum(np.where(df)))
# print("df['seas']", df['seas'])
# print(1/0)
X = df[varnames].values
y = df['choice'].values
choice_id = df['chid']
alt = [1, 2, 3, 4]
np.random.seed(123)
print('covariance', np.cov(np.transpose(X)))
# print(1/0)
model = MultinomialLogit()
model.fit(
X,
y,
varnames,
alts=alt,
# randvars={'seas': 'ln', 'wk': 'n', 'pf': 'n', 'loc': 'n'},
fit_intercept=True,
# transformation="boxcox",
# transvars=['wk', 'seas'],
# correlation=True,
# ids=choice_id,
# panels=df.id.values,
# tol=1e-4,
# grad=False,
# hess=False,
def example11_run():
# df_wide = pd.read_csv("examples/data/swissmetro_training.csv")
df_wide = pd.read_csv("xlogitprit/examples/data/swissmetro_training.csv")
df_wide['custom_id'] = np.arange(len(df_wide)) # Add unique identifier
#Let's rename some columns for convenient reshaping using pandas
df_wide.rename(columns={
"TRAIN_TT": "time_train",
"SM_TT": "time_sm",
"CAR_TT": "time_car",
"TRAIN_CO": "cost_train",
"SM_CO": "cost_sm",
"CAR_CO": "cost_car",
"TRAIN_HE": "headway_train",
"SM_HE": "headway_sm",
"SM_SEATS": "seatconf_sm",
"TRAIN_AV": "av_train",
"SM_AV": "av_sm",
"CAR_AV": "av_car"
},
inplace=True)
# Convert from wide to long format using pandas.
df = pd.wide_to_long(
df_wide, ["time", "cost", "headway", "seatconf", "av"],
i="custom_id",
j="alt",
sep="_",
suffix='\w+').sort_values(by=['custom_id', 'alt']).reset_index()
df = df.fillna(0) # Fill unexisting values for some alternatives
# Format the outcome variable approapriately
df["CHOICE"] = df["CHOICE"].map({1: 'train', 2: 'sm', 3: 'car'})
# Convert CHOICE to True if alternative was selected; False otherwise
df["CHOICE"] = df["CHOICE"] == df["alt"]
# Create model specification
# Alternative Specific Constants
df['asc_train'] = np.ones(len(df)) * (df['alt'] == 'train')
df['asc_car'] = np.ones(len(df)) * (df['alt'] == 'car')
# Coefficient GA for swissmetro and train
df['ga_sm_train'] = df['GA'] * ((df['alt'] == 'train') |
(df['alt'] == 'sm'))
# Coefficient headway for swissmetro and train
df['he_sm_train'] = df['headway'] * ((df['alt'] == 'train') |
(df['alt'] == 'sm'))
# Coefficient Age for train
df['age_train'] = df['AGE'] * (df['alt'] == 'train')
# Coefficient Luggage for car
df['luggage_car'] = df['LUGGAGE'] * (df['alt'] == 'car')
# Coefficient seatsconfig for car
df['seats'] = df['seatconf'] * (df['alt'] == 'sm')
varnames = [
'asc_train', 'asc_car', 'cost', 'time', 'luggage_car', 'he_sm_train',
'seats', 'ga_sm_train', 'age_train'
]
model = MultinomialLogit()
model.fit(
X=df[varnames],
y=df['CHOICE'],
varnames=varnames,
alts=df['alt'],
ids=df['custom_id'],
avail=df['av'],
# randvars={'cost': 'n'},
# transvars=['luggage_car']
# init_coeff=np.random.normal(0, 1, 9)
# scipy_optimisation=False
# method="L-BFGS-B"
# tol=1e-3
)
model.summary()
import pandas as pd
import numpy as np
from xlogitprit import MultinomialLogit
df = pd.read_csv(
"https://raw.githubusercontent.com/arteagac/xlogit/master/examples/data/fishing_long.csv"
)
varnames = ['price', 'catch']
X = df[varnames]
y = df['choice']
asvarnames = ['price', 'catch']
isvarnames = []
rand_vars = {'price': 'n'}
alts = [1, 2, 3, 4]
# choice_id = df['chid']
model = MultinomialLogit()
model.fit(
X,
y,
varnames=varnames,
alts=alts,
isvars=isvarnames,
transvars=['price',
'catch'], # randvars=rand_vars, #transvars=['price', 'catch'],
fit_intercept=False #, hess=False, grad=False
)
model.summary()
sep="_",
suffix='\w+').sort_values(by=['custom_id', 'alt']).reset_index()
# Fill unexisting values for some alternatives
df = df.fillna(0)
# Format the outcome variable approapriatly
df["CHOICE"] = df["CHOICE"].map({1: 'train', 2: 'sm', 3: 'car'})
# Convert CHOICE to True if alternative was selected; False otherwise
df["CHOICE"] = df["CHOICE"] == df["alt"]
# Scale variables
df['time'] = df['time'] / 100
train_pass = ((df["GA"] == 1) & (df["alt"].isin(['train', 'sm']))).astype(int)
df['cost'] = df['cost'] * (train_pass == 0) / 100
# Create alternative specific constants
df['asc_train'] = np.ones(len(df)) * (df['alt'] == 'train')
df['asc_car'] = np.ones(len(df)) * (df['alt'] == 'car')
varnames = [
'asc_car', 'asc_train', 'cost', 'time', 'luggage_car', 'he_sm_train',
'seats', 'ga_sm_train', 'age_train'
]
model = MultinomialLogit()
model.fit(X=df[varnames], y=df['CHOICE'], varnames=varnames, alts=df['alt'])
# model = MixedLogit()
# model.fit(X=df[varnames], y=df['CHOICE'], varnames=varnames, alts=df['alt'],
# # transvars=['cost'],
# ids=df['custom_id'], avail=df['av'], randvars={'time': 'n'}, n_draws=2000,
# # tol=1e-10
# )
model.summary()
import pandas as pd
import time
import matplotlib.pyplot as plt
#To be provided by the user
df = pd.read_csv(
"https://raw.githubusercontent.com/timothyb0912/pylogit/master/examples/data/electricity_r_data_long.csv"
)
choice_id = df['chid']
ind_id = df['id']
varnames = ['cl', 'loc', 'wk', 'tod', 'seas']
# asvarnames = ['pf','cl','loc','wk','tod', 'seas']
# isvarnames = []
alternatives = [1, 2, 3, 4]
choice_var = df['choice']
alt_var = df['alt']
R = 200
dist = ['n', 'ln', 'tn', 'u', 't', 'f']
#dist = ['n', 'ln', 'u', 'f']
model = MultinomialLogit()
# init_coeffs = np.repeat(.0, 6)
model.fit(X=df[varnames],
y=choice_var,
varnames=varnames,
alts=alt_var,
ids=choice_id,
transformation="boxcox",
transvars=['cl'],
fit_intercept=False)
model.summary()