def fixture_learners_data(breast_cancer_data, boston_data,
boston_survival_data):
"""
Returns:
A list of iterables,
each iterable containing a fitted model and
X data and the predictions for the X_data
"""
models_data = []
X_class_train, _, Y_class_train, _ = breast_cancer_data
ngb = NGBClassifier(verbose=False, n_estimators=10)
ngb.fit(X_class_train, Y_class_train)
models_data.append((ngb, X_class_train, ngb.predict(X_class_train)))
X_reg_train, _, Y_reg_train, _ = boston_data
ngb = NGBRegressor(verbose=False, n_estimators=10)
ngb.fit(X_reg_train, Y_reg_train)
models_data.append((ngb, X_reg_train, ngb.predict(X_reg_train)))
X_surv_train, _, T_surv_train, E_surv_train, _ = boston_survival_data
ngb = NGBSurvival(verbose=False, n_estimators=10)
ngb.fit(X_surv_train, T_surv_train, E_surv_train)
models_data.append((ngb, X_surv_train, ngb.predict(X_surv_train)))
ngb = NGBRegressor(Dist=MultivariateNormal(2), n_estimators=10)
ngb.fit(X_surv_train, np.vstack([T_surv_train, E_surv_train]).T)
models_data.append((ngb, X_surv_train, ngb.predict(X_surv_train)))
return models_data
def estimate_infcens(Y):
res = {}
params = np.array([[0, 0, 1, 0, 1]] * N).T
for _ in range(100000):
D = MultivariateNormal(params)
S = MLE()
grad = np.mean(S.grad(D, Y, natural=True).T, axis=1, keepdims=True)
params = params - 1 * grad
if np.linalg.norm(grad) < 1e-4:
break
print('Jointly Estimated E:', params[0, 0])
res['joint'] = params[0, 0]
params = np.array([[0, 0]] * N).T
for _ in range(100000):
D = LogNormal(params)
S = MLE()
grad = np.mean(S.grad(D, Y, natural=True).T, axis=1, keepdims=True)
params = params - 0.005 * grad
if np.linalg.norm(grad) < 1e-4:
break
print('Estimate E (assume non-inf):', params[0, 0])
res['lognorm'] = params[0, 0]
return res
def mvnorm_mle(Y, max_iter=1e4, lr=0.5, eps=1e-4):
N = Y.shape[0]
params = np.array([[0, 0, 1, 0, 1]] * N).T
for _ in range(max_iter):
D = MultivariateNormal(params)
S = MLE()
grad = np.mean(S.grad(D, Y, natural=True).T, axis=1, keepdims=True)
params = params - lr * grad
if np.linalg.norm(grad) < eps:
break
def test_multivariatenormal(k: 2, learner):
dist = MultivariateNormal(k)
# Generate some sample data
N = 500
X_train = np.random.randn(N, k)
y_fns = [np.sin, np.cos, np.exp]
y_cols = [
fn(X_train[:, num_col]).reshape(-1, 1) + np.random.randn(N, 1)
for num_col, fn in enumerate(y_fns[:k])
]
y_train = np.hstack(y_cols)
X_test = np.random.randn(N, k)
ngb = NGBRegressor(Dist=dist, Score=LogScore, Base=learner, verbose=False)
ngb.fit(X_train, y_train)
y_pred = ngb.predict(X_test)
y_dist = ngb.pred_dist(X_test)
mean = y_dist.mean
sample = y_dist.rv()
scipy_list = y_dist.scipy_distribution()
)
return metric_err
def idfn(dist_score: DistScore):
dist, score = dist_score
return dist.__name__ + "_" + score.__name__
TEST_METRIC: List[DistScore] = [
(Normal, LogScore),
(Normal, CRPScore),
(TFixedDfFixedVar, LogScore),
(Laplace, LogScore),
(Poisson, LogScore),
] + [(MultivariateNormal(i), LogScore) for i in range(2, 5)]
# Fill in the dist, score pair to test the gradient
# Tests all in TEST_METRIC by default
TEST_GRAD: List[DistScore] = TEST_METRIC + [
(Cauchy, LogScore),
(T, LogScore),
(TFixedDf, LogScore),
]
@pytest.mark.parametrize("dist_score_pair", TEST_GRAD, ids=idfn)
def test_dists_grad(dist_score_pair: DistScore):
# Set seed as this test involves randomness
# All errors around 1e-5 mark
np.random.seed(9)
dist, score = dist_score_pair
def Y_join(T, E):
col_event = 'Event'
col_time = 'Time'
y = np.empty(dtype=[(col_event, np.bool), (col_time, np.float64)],
shape=T.shape[0])
y[col_event] = E
y[col_time] = np.exp(T)
return y
Y = Y_join(T, E)
params = np.array([[0, 0, 1, 0, 1]] * N).T
for _ in range(100000):
D = MultivariateNormal(params)
S = MLE()
grad = np.mean(S.grad(D, Y, natural=True).T, axis=1, keepdims=True)
params = params - 1 * grad
if np.linalg.norm(grad) < 1e-4:
break
print('Jointly Estimated E:', params[0, 0])
params = np.array([[0, 0]] * N).T
for _ in range(100000):
D = LogNormal(params)
S = MLE()
grad = np.mean(S.grad(D, Y, natural=True).T, axis=1, keepdims=True)
params = params - 0.1 * grad
if np.linalg.norm(grad) < 1e-4:
sigma: (N,2) numpy array containing the variances
corr: (N,) numpy array the correlation [-1,1] extracted from cov_mat
"""
sigma = np.sqrt(np.diagonal(cov_mat, axis1=1, axis2=2))
corr = cov_mat[:, 0, 1] / (sigma[:, 0] * sigma[:, 1])
return sigma, corr
if __name__ == "__main__":
SEED = 12345
np.random.seed(SEED)
X, Y, true_dist = simulate_data()
X = X.reshape(-1, 1)
dist = MultivariateNormal(2)
data_figure, data_axs = plt.subplots()
data_axs.plot(X, Y[:, 0], label="Dim 1")
data_axs.plot(X, Y[:, 1], label="Dim 2")
data_axs.set_xlabel("X")
data_axs.set_ylabel("Y")
data_axs.set_title("Input Data")
data_axs.legend()
data_figure.show()
X_val, Y_val, _ = simulate_data(500)
X_val = X_val.reshape(-1, 1)
ngb = NGBRegressor(Dist=dist,
verbose=True,
n_estimators=2000,