def fit(self, results, train_true):
x = []
y = []
count = 0
missing = []
for idx, row in train_true.iterrows():
res = results.get(row['Id'])
if res is None:
missing.append(row['Id'])
continue
count += 1
x.extend(res)
y.extend([row['Systole'], row['Diastole']])
print(("{} cases are used to fit the model".format(count)))
if len(missing) > 0:
print(
("cases are missing: " + ','.join([str(_x)
for _x in missing])))
x = np.asarray(x).reshape((-1, 4))
y = np.asarray(y)
ff = minimize(lambda p: analysis.crps_score(self._get_result(x, p), y),
self.p0,
bounds=self.bounds,
options={
'gtol': 1e-6,
'maxiter': 500,
'eps': 1e-5
})
self.p = ff.x
print(("fitting parameters " + str(self.p)))
print(("fitting score " + str(ff.fun)))
def fit(self,preds,train_true):
N = len(preds);
print("combine # predictions:" + ','.join([str(len(x)) for x in preds]));
self.p0 = np.ones(N)*np.sqrt(N);
X = np.zeros((train_true.shape[0]*2,N*2));
X[:] = np.nan;
y = [];
i = 0;
for idx,row in train_true.iterrows():
case = row['Id'];
y.extend([row['Systole'],row['Diastole']]);
for j in range(N):
sede = preds[j].get(case);
if sede is not None:
X[i*2,2*j:2*j+2] = sede[0:2];
X[i*2+1,2*j:2*j+2] = sede[2:4];
i += 1;
y = np.asarray(y);
print("init score :{}".format(analysis.crps_score(self._get_result(X,self.p0),y)));
ff = minimize(lambda p:analysis.crps_score(self._get_result(X,p),y) + self.ll*np.var(p), self.p0, options={'gtol':1e-5,'eps':1e-4,'maxiter':500});
self.p = ff.x;
print("fitting parameters " + str(self.p));
print("fitting score " + str(ff.fun));
def fit(self, results,train_true):
x = [];
y = [];
count = 0;
missing = [];
for idx,row in train_true.iterrows():
res = results.get(row['Id']);
if res is None:
missing.append(row['Id']);
continue
count+=1;
x.extend(res);
y.extend([row['Systole'],row['Diastole']]);
print("{} cases are used to fit the model".format(count));
if len(missing)>0:
print("cases are missing: " + ','.join([str(_x) for _x in missing]));
x = np.asarray(x).reshape((-1,4));
y = np.asarray(y);
ff = minimize(lambda p:analysis.crps_score(self._get_result(x,p),y), self.p0, bounds=self.bounds, options={'gtol':1e-6,'maxiter':500,'eps':1e-5});
self.p = ff.x;
print("fitting parameters " + str(self.p));
print("fitting score " + str(ff.fun));
class AverageModel(BaseModel):
def __init__(self, ll=9.5e-5):
self.p = None
self.ll = ll
def _get_result(self, X, p):
"""
how to deal with nans???
this code treat them as missing use the same coefficients
ideally, it should fit another model use only the rest of models
"""
NR = X.shape[0]
y = np.zeros((NR, 2))
p = np.asarray(p)
for i in range(NR):
preds = np.copy(X[i]).reshape((-1, 2))
err0 = np.copy(preds[:, 1])
preds[:, 1] = err0 * p
preds = preds[~np.isnan(preds[:, 0])]
if preds.shape[0] == 0:
y[i] = [np.nan, np.nan]
continue
me = np.sum(preds[:, 0] / preds[:, 1]**2)
err = np.sum(1.0 / preds[:, 1]**2)
me /= err
err = 1.0 / np.sqrt(err)
err = np.minimum(np.nanmin(err0), err)
err *= (1.0 + np.std(preds[:, 0]) / np.max(preds[:, 1]) / 3)**0.5
y[i] = [me, err]
return y
def fit(self, preds, train_true):
N = len(preds)
print(
("combine # predictions:" + ','.join([str(len(x))
for x in preds])))
self.p0 = np.ones(N) * np.sqrt(N)
X = np.zeros((train_true.shape[0] * 2, N * 2))
X[:] = np.nan
y = []
i = 0
for idx, row in train_true.iterrows():
case = row['Id']
y.extend([row['Systole'], row['Diastole']])
for j in range(N):
sede = preds[j].get(case)
if sede is not None:
X[i * 2, 2 * j:2 * j + 2] = sede[0:2]
X[i * 2 + 1, 2 * j:2 * j + 2] = sede[2:4]
i += 1
y = np.asarray(y)
print(("init score :{}".format(
analysis.crps_score(self._get_result(X, self.p0), y))))
ff = minimize(lambda p: analysis.crps_score(self._get_result(X, p), y)
+ self.ll * np.var(p),
self.p0,
options={
'gtol': 1e-5,
'eps': 1e-4,
'maxiter': 500
})
self.p = ff.x
print(("fitting parameters " + str(self.p)))
print(("fitting score " + str(ff.fun)))