def test_setup(self):
data = self.data
resp = self.resp
fittedvalues = resp.predict()
formulas = ["apply ~ 1 + pared + public + gpa + C(dummy)",
"apply ~ pared + public + gpa + C(dummy)"]
for formula in formulas:
modf1 = OrderedModel.from_formula(formula, data, distr='logit')
resf1 = modf1.fit(method='bfgs')
summf1 = resf1.summary()
summf1_str = str(summf1)
assert resf1.model.exog_names == resp.model.exog_names
assert resf1.model.data.param_names == resp.model.exog_names
assert all(name in summf1_str for name in
resp.model.data.param_names)
assert_allclose(resf1.predict(data[:5]), fittedvalues[:5])
# test over parameterized model with implicit constant
formula = "apply ~ 0 + pared + public + gpa + C(dummy)"
with pytest.raises(ValueError):
OrderedModel.from_formula(formula, data, distr='logit')
# ignore constant, so we get results without exception
modf2 = OrderedModel.from_formula(formula, data, distr='logit',
hasconst=False)
# we get a warning in some environments
with warnings.catch_warnings():
warnings.simplefilter("ignore", HessianInversionWarning)
resf2 = modf2.fit(method='bfgs')
assert_allclose(resf2.predict(data[:5]), fittedvalues[:5], rtol=1e-4)
def test_formula_categorical(self):
resp = self.resp
data = ds.df
formula = "apply ~ pared + public + gpa - 1"
modf2 = OrderedModel.from_formula(formula, data, distr='probit')
resf2 = modf2.fit(method='bfgs', disp=False)
assert_allclose(resf2.params, resp.params, atol=1e-8)
assert modf2.exog_names == resp.model.exog_names
assert modf2.data.ynames == resp.model.data.ynames
assert hasattr(modf2.data, "frame")
assert not hasattr(modf2, "frame")
with pytest.raises(ValueError):
# only ordered categorical or numerical endog are allowed
# string endog raises ValueError
OrderedModel.from_formula("apply ~ pared + public + gpa - 1",
data={
"apply": np.asarray(data['apply']),
"pared": data['pared'],
"public": data['public'],
"gpa": data['gpa']
},
distr='probit')
def test_offset(self):
resp = self.resp
data = ds.df
offset = np.ones(len(data))
formula = "apply ~ pared + public + gpa - 1"
modf2 = OrderedModel.from_formula(formula, data, offset=offset,
distr='probit')
resf2 = modf2.fit(method='bfgs', disp=False)
assert_allclose(resf2.params[:3], resp.params[:3], atol=2e-4)
assert_allclose(resf2.params[3], resp.params[3] + 1, atol=2e-4)
fitted = resp.predict()
fitted2 = resf2.predict()
assert_allclose(fitted2, fitted, atol=2e-4)
pred_ones = resf2.predict(data[:6], offset=np.ones(6))
assert_allclose(pred_ones, fitted[:6], atol=2e-4)
# check default is 0. if exog provided
pred_zero1 = resf2.predict(data[:6])
pred_zero2 = resf2.predict(data[:6], offset=0)
assert_allclose(pred_zero1, pred_zero2, atol=2e-4)
# compare with equivalent results frp, no-offset model
pred_zero = resp.predict(data[['pared', 'public', 'gpa']].iloc[:6],
offset=-np.ones(6))
assert_allclose(pred_zero1, pred_zero, atol=2e-4)
params_adj = resp.params.copy()
params_adj[3] += 1
fitted_zero = resp.model.predict(params_adj)
assert_allclose(pred_zero1, fitted_zero[:6], atol=2e-4)
def setup_class(cls):
data = ds.df
data_unordered = ds.df_unordered
# a Scipy distribution defined minimally
class CLogLog(stats.rv_continuous):
def _ppf(self, q):
return np.log(-np.log(1 - q))
def _cdf(self, x):
return 1 - np.exp(-np.exp(x))
cloglog = CLogLog()
mod = OrderedModel(data['apply'].values.codes,
np.asarray(data[['pared', 'public', 'gpa']], float),
distr=cloglog)
res = mod.fit(method='bfgs', disp=False)
modp = OrderedModel(data['apply'],
data[['pared', 'public', 'gpa']],
distr=cloglog)
resp = modp.fit(method='bfgs', disp=False)
# with pytest.warns(UserWarning):
modf = OrderedModel.from_formula("apply ~ pared + public + gpa - 1",
data={
"apply":
data['apply'].values.codes,
"pared": data['pared'],
"public": data['public'],
"gpa": data['gpa']
},
distr=cloglog)
resf = modf.fit(method='bfgs', disp=False)
modu = OrderedModel(data_unordered['apply'].values.codes,
np.asarray(
data_unordered[['pared', 'public', 'gpa']],
float),
distr=cloglog)
resu = modu.fit(method='bfgs', disp=False)
from .results.results_ordinal_model import res_ord_cloglog as res2
cls.res2 = res2
cls.res1 = res
cls.resp = resp
cls.resf = resf
cls.resu = resu
def setup_class(cls):
data = ds.df
data_unordered = ds.df_unordered
mod = OrderedModel(data['apply'].values.codes,
np.asarray(data[['pared', 'public', 'gpa']], float),
distr='probit')
res = mod.fit(method='bfgs', disp=False)
modp = OrderedModel(data['apply'],
data[['pared', 'public', 'gpa']],
distr='probit')
resp = modp.fit(method='bfgs', disp=False)
modf = OrderedModel.from_formula("apply ~ pared + public + gpa - 1",
data={
"apply":
data['apply'].values.codes,
"pared": data['pared'],
"public": data['public'],
"gpa": data['gpa']
},
distr='probit')
resf = modf.fit(method='bfgs', disp=False)
modu = OrderedModel(data_unordered['apply'].values.codes,
np.asarray(
data_unordered[['pared', 'public', 'gpa']],
float),
distr='probit')
resu = modu.fit(method='bfgs', disp=False)
from .results.results_ordinal_model import res_ord_probit as res2
cls.res2 = res2
cls.res1 = res
cls.resp = resp
cls.resf = resf
cls.resu = resu
# regression numbers
cls.pred_table = np.array(
[
[202, 18, 0, 220],
[112, 28, 0, 140],
[27, 13, 0, 40], # noqa
[341, 59, 0, 400]
],
dtype=np.int64)
def setup_class(cls):
data = ds.df
data_unordered = ds.df_unordered
# standard fit
mod = OrderedModel(data['apply'].values.codes,
np.asarray(data[['pared', 'public', 'gpa']], float),
distr='logit')
res = mod.fit(method='bfgs', disp=False)
# standard fit with pandas input
modp = OrderedModel(data['apply'],
data[['pared', 'public', 'gpa']],
distr='logit')
resp = modp.fit(method='bfgs', disp=False)
# fit with formula
modf = OrderedModel.from_formula("apply ~ pared + public + gpa - 1",
data={
"apply":
data['apply'].values.codes,
"pared": data['pared'],
"public": data['public'],
"gpa": data['gpa']
},
distr='logit')
resf = modf.fit(method='bfgs', disp=False)
# fit on data with ordered=False
modu = OrderedModel(data_unordered['apply'].values.codes,
np.asarray(
data_unordered[['pared', 'public', 'gpa']],
float),
distr='logit')
resu = modu.fit(method='bfgs', disp=False)
from .results.results_ordinal_model import res_ord_logit as res2
cls.res2 = res2
cls.res1 = res
cls.resp = resp
cls.resf = resf
cls.resu = resu
def ordinal_regression_formula(data, formula, distr="probit"):
model = OrderedModel.from_formula(formula=formula, data=data, distr=distr)
result = model.fit(method="bfgs")
summary = result.summary()
odds_radio = get_odds_radio(result)
return result, summary, odds_radio
data = pd.read_csv(r"D:/书籍资料整理/属性数据分析/政治意识与党派.csv")
# data['意识形态']=data['意识形态'].replace({'很自由':1,'有点自由':2,'中等':3,'有点保守':4,'很保守':5})
data['政治党派'] = data['政治党派'].replace({'民主党人': 1, '共和党人': 0})
tmp = pd.DataFrame()
for i in range(0, 20):
tmp = tmp.append([data.loc[i]] * data.iloc[i]['值'])
tmp = tmp.reset_index()
del tmp['值']
del tmp['index']
# tmp.to_csv(r'D:/书籍资料整理/属性数据分析/政治意识与党派_整理数据.csv')
#得到的结果显示,自变量参数是反的.这个可以解释,因为使用的是α-βx展示
#书中的结果是α+βx
#但是截距从第二个开始就相去甚远很难找到解释理由,OrderedModel这个功能
#并非包内本身带的,文档也几乎没有提到.
#这个是将要被statsmodels带入的功能并没有完善待后续.
tmp['意识形态'] = tmp['意识形态'].astype('category')
s = pd.Series(["a", "b", "c", "a", "d", "e"])
cat_type = CategoricalDtype(categories=['很自由', '有点自由', '中等', '有点保守', '很保守'],
ordered=True) #categories必须是一个列表
tmp['意识形态'] = tmp['意识形态'].astype(cat_type)
modf_logit = OrderedModel.from_formula("意识形态~政治党派", tmp, distr='logit')
resf_logit = modf_logit.fit(method='bfgs')
print(resf_logit.summary())
data = pd.read_csv(r"D:/书籍资料整理/属性数据分析/心灵伤害与SES.csv")
data['心理伤害'] = data['心理伤害'].replace({'健康': 0, '轻度': 1, '中等': 2, '受损': 3})
modf_logit = OrderedModel.from_formula("心理伤害~SES+生活事件", data, distr='logit')
resf_logit = modf_logit.fit()
resf_logit.summary()
cloglog = CLogLog()
# definition of the model and fitting
res_cloglog = OrderedModel(data_student['apply'],
data_student[['pared', 'public', 'gpa']],
distr=cloglog).fit(method='bfgs', disp=False)
res_cloglog.summary()
# ### Using formulas - treatment of endog
#
# Pandas' ordered categorical and numeric values are supported as
# dependent variable in formulas. Other types will raise a ValueError.
modf_logit = OrderedModel.from_formula("apply ~ 0 + pared + public + gpa",
data_student,
distr='logit')
resf_logit = modf_logit.fit(method='bfgs')
resf_logit.summary()
# Using numerical codes for the dependent variable is supported but loses
# the names of the category levels. The levels and names correspond to the
# unique values of the dependent variable sorted in alphanumeric order as in
# the case without using formulas.
data_student["apply_codes"] = data_student['apply'].cat.codes * 2 + 5
data_student["apply_codes"].head()
OrderedModel.from_formula("apply_codes ~ 0 + pared + public + gpa",
data_student,
distr='logit').fit().summary()