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
|
#!/usr/bin/env python
# coding: utf-8
# DO NOT EDIT
# Autogenerated from the notebook glm_formula.ipynb.
# Edit the notebook and then sync the output with this file.
#
# flake8: noqa
# DO NOT EDIT
# # Generalized Linear Models (Formula)
# This notebook illustrates how you can use R-style formulas to fit
# Generalized Linear Models.
#
# To begin, we load the ``Star98`` dataset and we construct a formula and
# pre-process the data:
import statsmodels.api as sm
import statsmodels.formula.api as smf
star98 = sm.datasets.star98.load_pandas().data
formula = "SUCCESS ~ LOWINC + PERASIAN + PERBLACK + PERHISP + PCTCHRT + \
PCTYRRND + PERMINTE*AVYRSEXP*AVSALK + PERSPENK*PTRATIO*PCTAF"
dta = star98[[
"NABOVE",
"NBELOW",
"LOWINC",
"PERASIAN",
"PERBLACK",
"PERHISP",
"PCTCHRT",
"PCTYRRND",
"PERMINTE",
"AVYRSEXP",
"AVSALK",
"PERSPENK",
"PTRATIO",
"PCTAF",
]].copy()
endog = dta["NABOVE"] / (dta["NABOVE"] + dta.pop("NBELOW"))
del dta["NABOVE"]
dta["SUCCESS"] = endog
# Then, we fit the GLM model:
mod1 = smf.glm(formula=formula, data=dta, family=sm.families.Binomial()).fit()
print(mod1.summary())
# Finally, we define a function to operate customized data transformation
# using the formula framework:
def double_it(x):
return 2 * x
formula = "SUCCESS ~ double_it(LOWINC) + PERASIAN + PERBLACK + PERHISP + PCTCHRT + \
PCTYRRND + PERMINTE*AVYRSEXP*AVSALK + PERSPENK*PTRATIO*PCTAF"
mod2 = smf.glm(formula=formula, data=dta, family=sm.families.Binomial()).fit()
print(mod2.summary())
# As expected, the coefficient for ``double_it(LOWINC)`` in the second
# model is half the size of the ``LOWINC`` coefficient from the first model:
print(mod1.params.iloc[1])
print(mod2.params.iloc[1] * 2)
|
