def crude_mixedMLbayse(df_merged,
x_feature,
y_feature,
covars='False',
logit=False):
#TODO: Replace covars variable with actual selection of indivdual features
df_merged = df_merged.replace(-9, np.nan).replace('-9', np.nan).replace(
999, np.nan).replace(888, np.nan)
if covars == 'False':
data = df_merged[[x_feature, y_feature,
'CohortType']].dropna(how='any', axis='rows')
fit_string = y_feature + '~' + x_feature
if covars == 'True':
data = add_confound(df_merged, x_feature, y_feature)
## create the model string for
fit_string = y_feature + '~'
cnt = 0
## filter out target, at birth, and reference dummy variables in model
for x in data.columns:
#data.drop(['education'], inplace = True, axis = 0)
if x != 'birthWt' and x !='Outcome_weeks' and x!= 'Outcome' and x != 'PIN_Patient' and x != 'SGA' and x != 'LGA' \
and x !='birthLen' and x != 'CohortType' and x != 'race' and x!='race_1' and x!= 'smoking' and x != 'smoking_3' \
and x != 'education_5' and x != 'education':
if cnt == 0:
fit_string += ' ' + x + ' '
else:
fit_string += ' + ' + x + ' '
cnt += 1
print('mixedML string:')
print(fit_string)
fit_string += '+ (1|CohortType)'
if logit == False:
model = bmb.Model(data)
results = model.fit(fit_string)
else:
model = bmb.Model(data)
results = model.fit(fit_string, family='bernoulli', link='logit')
## miced linear model with group variable = CohortType
mdf = az.summary(results)
return mdf
# # # data.loc[:, ('employment_rate', idx)] = c2emp[(c, y)]
#
# data['foreign_born'][idx] = c2fb[(c, y)]
# data['net_migration'][idx] = c2nm[(c, y)]
# data['expenditures'][idx] = c2ex[(c, y)]
# data['employment_rate'][idx] = c2emp[(c, y)]
# except KeyError:
# pass
# data.to_pickle("data_dump")
data = pd.read_pickle("data_dump")
print(data)
print(data.columns.tolist())
# Table 4. Fit a two-way fixed effects model. Percent foreign born on welfare
# state attitudes, controlling for social welfare expenditures and the
# employment rate.
model = bambi.Model(data, dropna=True)
model.add('deps_jobs ~ 0')
# print(model)
model.add('foreign_born')
model.add('expenditures')
model.add('employment_rate')
results = model.fit(link="logit")
print(results)
print(results.summary())
# results.plot()
# Table 5. Fix a two-way fixed effects model. Net migration on welfare state
# attitudes, controlling for social welfare expenditures, exployment rate,
# and percent foreign born.
'interval': intervals
})
# Read the comma-separated values file containing metadata of our corpus
corpus = pd.read_csv("corpus/corpus.csv")
# Concatenate all data from the corpus into one big pandas DataFrame
# To do so, loop over all rows of the corpus, get the syllable intervals DataFrames, and concatenate them all
data = pd.concat(
[syllable_intervals_data(row) for _, row in corpus.iterrows()])
# Maximum likelihood (ML/REML) estimation of mixed-effects linear model
import statsmodels.formula.api as smf
# Construct and fit the StatsModels model, with 'native' a fixed effect and 'speaker' a random effect
# For details, see http://www.statsmodels.org/devel/mixed_linear.html
model = smf.mixedlm('interval ~ native', data, groups=data['speaker'])
results = model.fit()
# Print the results (or they could be saved, or further queried)
print(results.summary())
# Bayesian estimation of mixed-effects linear model
import bambi
# Construct and fit a Bayesian version of the same mixed-effect model
# For details, see https://github.com/bambinos/bambi#user-guide
model = bambi.Model(data)
results = model.fit('interval ~ native', random=['1|speaker'])
# And again print those results
print(results.summary())
def build_model(self, bids_folder='/data/ds-tmsrisk'):
formula = self.models[self.model_type]
self.model = bmb.Model(formula, self.data[[
'chose_risky', 'x', 'risky_first', 'n_safe']].reset_index(), family="bernoulli", link='probit')
sleep_st.groupby('hour').count()
start_fig = px.histogram(y=sleep_st.hour)
start_fig.show()
## do a random regression just so that you know how
## FIXME: scale values with zscores()
regression = data[[
"duration", "maxAvgHeartRate", "start_time", "wake_time",
"awakeSleepSeconds", "restingHeartRate", "activeKilocalories",
"activeSeconds"
]]
## specify a simple additive model to try to predict
## how many times I spent awake during the night
formula = 'awakeSleepSeconds ~ activeKilocalories + duration + restingHeartRate'
# see if level of exercise affected sleep duration
model = bmb.Model(formula=formula, data=regression, dropna=True)
results = model.fit(draws=2000, chains=4)
model.predict(results, kind="pps", draws=1000)
results.posterior.mean()
az.plot_trace(results)
az.summary(results)
az.plot_ppc(results)
# TODO: to partial r squared correlation