/
master_sim.py
195 lines (126 loc) · 5.12 KB
/
master_sim.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
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
import numpy as np
import pandas as pd
import pickle
import tracemalloc
import itertools
import sys, os
import time
from scipy import stats
from scipy import interpolate
import matplotlib.pyplot as plt
import statsmodels.api as sm
import xlsxwriter
#sys.path.append("/Users/jorge-home/Dropbox/Research/DN-early/structural/child-care-welfare")
sys.path.append("/Users/antoniaaguilera/Desktop/AY-INV/python/sim-anto/currently working")
#call py scripts
import utility as util
import parameters as parameters
import simdata as simdata
import estimate as est
import bootstrap as bstr
np.random.seed(123)
#------------ PREP DATA ------------#
data = pd.read_stata('data/data_python.dta')
N = len(data)
data['constant']=np.ones((N,1))
#------------ REG WITH DATA ------------#
#wage
regw=sm.OLS(endog=data['ln_w'], exog=data[['constant', 'm_sch']], missing='drop').fit()
betasw = regw.params
sigma2w_reg = np.var(regw.resid)
#test score vs d_cc
regtd=sm.OLS(endog=data['TVIP_age_3'], exog=data[['constant', 'd_cc_34']], missing='drop').fit()
betastd = regtd.params
sigma2td= np.var(regtd.resid)
#d_cc vs commute
regdz=sm.OLS(endog=data['d_cc_34'], exog=data[['constant', 'commute2cc']], missing='drop').fit()
betasdz = regdz.params
#test score vs commute
regtz = sm.OLS(endog=data['TVIP_age_3'], exog=data[['constant', 'commute2cc']], missing='drop').fit()
betastz = regtz.params
#non-labor income
regn = sm.OLS(endog = data['ln_nli'], exog = data[['constant', 'married34', 'd_work', 'tot_kids', 'm_sch']], missing='drop').fit()
betasn = regn.params
sigma2n = np.var(regn.resid)
#------------ PARAMETERS ------------#
#betas = [beta1 , beta0]
betas = [0.0992312, 0.0084627]
sigma2w_estr = 0.5869
meanshocks = [0,0.5]
rho = 0.9
sigma1 = 1#constante
sigma2 = 0.9
cov12 = (sigma1**(1/2))*(sigma2**(1/2))*rho
covshocks = [[sigma1,cov12],[cov12,sigma2]]
T = (24-8)*20 #monthly waking hours
Lc = 8*20 #monthly cc hours
alpha = -0.1
gamma = 0.4
w_matrix = np.identity(10)
times = 20
#------------ CALL CLASSES, ESTIMATION SIM & BOOTSTRAP ------------#
param0 = parameters.Parameters(betas, betasw, betastd, betasn, sigma2w_estr, sigma2w_reg, meanshocks, covshocks, T, Lc, alpha, gamma, times)
model = util.Utility(param0, N, data)
model_sim = simdata.SimData(N, model)
model_boot= bstr.bootstrap(N, data)
moments_boot = model_boot.boostr(times)
model_est = est.estimate(N, data, param0, moments_boot, w_matrix)
results_estimate = model_est.simulation(model_sim)
#------------ DATA SIMULATION ------------#
workbook = xlsxwriter.Workbook('data/labor_choice.xlsx')
worksheet = workbook.add_worksheet()
worksheet.write('B2', 'parameter')
worksheet.write('B3', 'labor choice')
worksheet.write('B4', 'cc choice')
worksheet.write('B5', 'test score')
worksheet.write('B6', 'wage ec: beta_0')
worksheet.write('B7', 'wage ec: beta_1')
worksheet.write('B8', 'sigma^2_{varepsilon}')
worksheet.write('B9', 'beta1_td')
worksheet.write('B10', 'beta1_tz')
worksheet.write('B11', 'beta1_dz')
worksheet.write('B12', 'resid var score')
worksheet.write('C2', 'sim')
worksheet.write('C3', results_estimate['Labor Choice'])
worksheet.write('C4', results_estimate['CC Choice'])
worksheet.write('C5', results_estimate['Test Score'])
worksheet.write('C6', results_estimate['beta0_w'])
worksheet.write('C7', results_estimate['beta1_w'])
worksheet.write('C8', results_estimate['resid_var_w'])
worksheet.write('C9', results_estimate['beta1_td'])
worksheet.write('C10', results_estimate['beta1_tz'])
worksheet.write('C11', results_estimate['beta1_dz'])
worksheet.write('C12', results_estimate['resid_var_td'])
worksheet.write('D2', 'data')
worksheet.write('D3', moments_boot['Labor Choice'])
worksheet.write('D4', moments_boot['CC Choice'])
worksheet.write('D5', moments_boot['Test Score'])
worksheet.write('D6', moments_boot['beta0_w'])
worksheet.write('D7', moments_boot['beta1_w'])
worksheet.write('D8', moments_boot['resid_var_w'])
worksheet.write('D9', moments_boot['beta1_td'])
worksheet.write('D10', moments_boot['beta1_tz'])
worksheet.write('D11', moments_boot['beta1_dz'])
worksheet.write('D12', moments_boot['resid_var_td'])
worksheet.write('E2', 'SE')
worksheet.write('E3', moments_boot['SE Labor Choice'])
worksheet.write('E4', moments_boot['SE CC Choice'])
worksheet.write('E5', moments_boot['SE Test Score'])
worksheet.write('E6', moments_boot['SE beta0_w'])
worksheet.write('E7', moments_boot['SE beta1_w'])
worksheet.write('E8', moments_boot['SE resid_var_w'])
worksheet.write('E9', moments_boot['SE beta1_td'])
worksheet.write('E10', moments_boot['SE beta1_tz'])
worksheet.write('E11', moments_boot['SE beta1_dz'])
worksheet.write('E12', moments_boot['SE resid_var_td'])
workbook.close()
#----------------- OPTIMIZER -----------------#
start_time = time.time()
opt = model_est.optimizer()
#------------ END TIME ------------#
time_opt=time.time() - start_time
print ('Done in')
print("--- %s seconds ---" % (time_opt))
#results:
#[-0.278902, 0.122961, 0.245317, -0.0992151, -0.00317576, 0.713988,
#0.891685, -0.000487114, 0.356655, 0.857309, 0.903501, 0.838664, 0.855367]