def test_MICE1(self):
df = gendat()
imp_data = mice.MICEData(df)
mi = mice.MICE("y ~ x1 + x2 + x1:x2", sm.OLS, imp_data)
from statsmodels.regression.linear_model import RegressionResultsWrapper
for j in range(3):
x = mi.next_sample()
assert (issubclass(x.__class__, RegressionResultsWrapper))
def test_MICE(self):
df = gendat()
imp_data = mice.MICEData(df)
mi = mice.MICE("y ~ x1 + x2 + x1:x2", sm.OLS, imp_data)
result = mi.fit(1, 3)
assert (issubclass(result.__class__, mice.MICEResults))
# Smoke test for results
smr = result.summary()
def test_MICE2(self):
from statsmodels.genmod.generalized_linear_model import GLMResultsWrapper
df = gendat()
imp_data = mice.MICEData(df)
mi = mice.MICE("x3 ~ x1 + x2", sm.GLM, imp_data,
init_kwds={"family": sm.families.Binomial()})
for j in range(3):
x = mi.next_sample()
assert(isinstance(x, GLMResultsWrapper))
assert(isinstance(x.family, sm.families.Binomial))
def imputation_mice(self, var_name, reddy_mice, reddy_info):
# not sure if this var_data is doing anything
var_data = reddy_mice.copy()
print("How many null values in " + var_name + " to change? " + str(reddy_info[var_name].isnull().sum()))
imp_var = mice.MICEData(var_data)
# create formula: var_name ~ sum(other_vars)
other_vars = reddy_mice.loc[:, reddy_mice.columns != var_name].columns
fml_var = var_name + ' ~' + ' +'.join(' {0}'.format(var) for var in other_vars)
# perform mice imputation
mice_var = mice.MICE(fml_var, lm.OLS, imp_var)
results = mice_var.fit(10,10) # fit(#cycles to skip, #datasets to impute)
reddy_info[var_name] = mice_var.data.data[var_name].values
if reddy_info[var_name].isnull().sum() != 0:
raise AssertionError ("All values could not be imputed.")
else:
#print(reddy_info[var_name].isnull().sum())
print(var_name + " successfully imputed")
return reddy_info
def test_combine(self):
np.random.seed(3897)
x1 = np.random.normal(size=300)
x2 = np.random.normal(size=300)
y = x1 + x2 + np.random.normal(size=300)
x1[0:100] = np.nan
x2[250:] = np.nan
df = pd.DataFrame({"x1": x1, "x2": x2, "y": y})
idata = mice.MICEData(df)
mi = mice.MICE("y ~ x1 + x2", sm.OLS, idata, n_skip=20)
result = mi.fit(10, 20)
fmi = np.asarray([0.1920533, 0.1587287, 0.33174032])
assert_allclose(result.frac_miss_info, fmi, atol=1e-5)
params = np.asarray([-0.05397474, 0.97273307, 1.01652293])
assert_allclose(result.params, params, atol=1e-5)
tvalues = np.asarray([-0.84781698, 15.10491582, 13.59998039])
assert_allclose(result.tvalues, tvalues, atol=1e-5)
def test_combine(self):
np.random.seed(3897)
x1 = np.random.normal(size=300)
x2 = np.random.normal(size=300)
y = x1 + x2 + np.random.normal(size=300)
x1[0:100] = np.nan
x2[250:] = np.nan
df = pd.DataFrame({"x1": x1, "x2": x2, "y": y})
idata = mice.MICEData(df)
mi = mice.MICE("y ~ x1 + x2", sm.OLS, idata, n_skip=20)
result = mi.fit(10, 20)
fmi = np.asarray([0.1778143, 0.11057262, 0.29626521])
assert_allclose(result.frac_miss_info, fmi, atol=1e-5)
params = np.asarray([-0.03486102, 0.96236808, 0.9970371])
assert_allclose(result.params, params, atol=1e-5)
tvalues = np.asarray([-0.54674776, 15.28091069, 13.61359403])
assert_allclose(result.tvalues, tvalues, atol=1e-5)
def Interpolation_mice(df: pd.DataFrame) -> pd.DataFrame:
imp = mice.MICEData(df)
fml = df.columns[0] + " ~ " + df.columns[1]
for i in range(2, len(df.columns)):
fml += " + " + df.columns[i]
# fml = 'y ~ x1 + x2 + x3 + x4'
mi = mice.MICE(fml, sm.OLS, imp)
results = mi.fit(10, 10)
dm = imp.next_sample()
# dm.to_csv("data_mice_10.csv")
# results = []
# for k in range(10):
# x = mi.next_sample()
# results.append(x)
# TODO:
# results到底怎么个结果？
# FINISHED
return dm
chmiss).fit()
(ilogit(lmodr.predict(chmiss))*100)[mv]
#
chredlin.race.iloc[np.where(chmiss.race.isna())]
# ## Multiple Imputation
#
import statsmodels.imputation.mice as smi
imp = smi.MICEData(chmiss)
fm = 'involact ~ race + fire + theft + age + np.log(income)'
mmod = smi.MICE(fm, sm.OLS, imp)
results = mmod.fit(10, 50)
print(results.summary())
# ## Discussion
# ## Exercises
# ## Packages Used
import sys
import matplotlib
import statsmodels as sm
import seaborn as sns
print("Python version:{}".format(sys.version))
print("matplotlib version: {}".format(matplotlib.__version__))
# -*- coding: utf-8 -*- """ Created on Sun Sep 1 23:39:09 2019 @author: 92156 """ from statsmodels.imputation import mice imp = mice.MICEData(data) >>> fml = 'y ~ x1 + x2 + x3 + x4' >>> mice = mice.MICE(fml, sm.OLS, imp) >>> results = mice.fit(10, 10) >>> print(results.summary())
