def wls(x):
'''
Performs weighted least squares on the numpy array x of shape
(N,3), where the three components are indep variable, dep variable,
dep variable errors. Returns log(likelihood).
'''
wls_model = WLS(x[:, 1], sm.add_constant(x[:, 0]), weights=1 / x[:, 2]**2)
result = wls_model.fit()
return -np.sum(
(x[:, 1] - wls_model.predict(result.params))**2 / x[:, 2]**
2), result.params[1], x[:, 1] - wls_model.predict(result.params)
def fit(self, x, y1, y2, cens, w, verbose=False):
"""
Fit a maximum-likelihood Tobit regression
:param x: Pandas DataFrame (n_samples, n_features): Data
:param y: Pandas Series (n_samples,): Target
:param cens: Pandas Series (n_samples,): -1 indicates left-censored samples, 0 for uncensored, 1 for right-censored
:param verbose: boolean, show info from minimization
:return:
"""
x_copy = x.copy()
if self.fit_intercept:
x_copy = np.insert(x_copy, 0, 1, axis=1)
else:
x_copy = skl.scale(x_copy,
with_mean=True,
with_std=False,
copy=False)
## qui gen double `z' = cond(`y1'<.&`y2'<.,(`y1'+`y2')/2, /*
## */ cond(`y1'<.,`y1',`y2')) `moff' if `doit'
y = []
counts = cens.value_counts()
for value in [-1, 0, 1]:
if value in counts:
if value == -1:
split = cens == value
y_l = np.squeeze(y2[split].values)
y.append(y_l)
elif value == 1:
split = cens == value
y_r = np.squeeze(y1[split].values)
y.append(y_r)
elif value == 0:
split = cens == value
y_int = np.squeeze(
(y1[split].values + y2[split].values) / 2)
y.append(y_int)
y = np.concatenate(y, axis=0)
init_reg = WLS(y, x_copy, weights=w).fit()
b0 = init_reg.params
print(b0)
y_pred = init_reg.predict(x_copy)
resid = y - y_pred
resid_var = np.var(resid)
s0 = np.sqrt(resid_var)
params0 = np.append(b0, s0)
xs, ys, ys1, ys2, ws = split_left_right_censored(
x_copy, y1, y2, cens, w)
result = minimize(lambda params: tobit_neg_log_likelihood(
xs, ys, ys1, ys2, ws, params),
params0,
jac=None,
method='Powell',
tol=0.000001,
options={
'disp': verbose,
'maxiter': 10000000,
'fatol': 0.00000001
})
if verbose:
print(result)
# self.ols_coef_ = b0[1:]
# self.ols_intercept = b0[0]
if self.fit_intercept:
self.intercept_ = result.x[0]
self.coef_ = result.x[1:-1]
else:
self.coef_ = result.x[:-1]
self.intercept_ = 0
self.sigma_ = result.x[-1]
return self
