def run_candidate():
print("script begin", datetime.datetime.now())
EPS = 1e-12
model = models.UnrollingHelicesShiftingZ(
djs=[-20, -10, 0, 10, 20],
dbscan_features=["sina1", "cosa1", "z1", "z2", "x_rt", "y_rt"],
dbscan_weight=[0.9, 0.9, 0.35, 0.22, 0.01, 0.01],
coef_rt1=1.33,
coef_rt2=0.0,
niter=150)
nevents = 1
path_to_input = os.path.join(path_to_trackml, "train_1")
path_to_out = "out_{0}".format(sys.argv[0].split(".")[0])
event_id_list = []
hits_list = []
truth_list = []
sys.stderr.write("load data\n")
for event_id, hits, truth in load_dataset(path_to_input,
parts=["hits", "truth"],
skip=0,
nevents=nevents):
print("size(hits) : ", len(hits))
event_id_list.append(event_id)
hits_list.append(hits)
truth_list.append(truth)
sys.stderr.write("scan\n")
for (event_id, hits, truth) in zip(event_id_list, hits_list, truth_list):
truth = truth.merge(hits, on=['hit_id'], how='left')
dfh = truth.copy()
label = model.predict(dfh)
submission = pd.DataFrame(columns=['event_id', 'hit_id', 'track_id'],
data=np.column_stack(([
int(event_id),
] * len(dfh), dfh.hit_id.values,
label))).astype(int)
submission.to_csv("02.csv", index=None)
score = score_event(dfh, submission)
max_score = dfh.weight.sum()
print("score: %0.5f (%0.5f)" % (score * max_score, score))
print("script end", datetime.datetime.now())
def run_candidate():
print("script begin", datetime.datetime.now())
EPS = 1e-12
model = models.UnrollingHelicesShiftingZ(
dbscan_features = ["sina1", "cosa1", "z1", "z2", "x_y", "x_r", "y_r", "rt_r"],
dbscan_weight = [2.7474448671796874, 2.7474448671796874,
1.3649721713529086, 0.7034918842926337,
0.0005549122352940002, 0.023096034747190672,0.04619756315527515,0.2437077420144654],
djs = [-20, -10, 0, 10, 20],
niter = 150,
eps0 = 0.00975)
nevents = 1
path_to_input = os.path.join(path_to_trackml, "train_1")
path_to_out = "out_{0}".format(sys.argv[0].split(".")[0])
event_id_list = []
hits_list = []
truth_list = []
sys.stderr.write("load data\n")
for event_id, hits, truth in load_dataset(path_to_input, parts=["hits", "truth"],
skip=0, nevents=nevents):
print("size(hits) : ", len(hits))
event_id_list.append(event_id)
hits_list.append(hits)
truth_list.append(truth)
sys.stderr.write("scan\n")
for (event_id, hits, truth) in zip(event_id_list, hits_list, truth_list):
truth = truth.merge(hits, on=['hit_id'], how='left')
dfh = truth.copy()
label = model.predict(dfh)
submission = pd.DataFrame(columns=['event_id', 'hit_id', 'track_id'],
data=np.column_stack(([int(event_id),]*len(dfh),
dfh.hit_id.values,
label))).astype(int)
submission.to_csv("05.csv", index=None)
score = score_event(dfh, submission)
max_score = dfh.weight.sum()
print("score: %0.5f (%0.5f)" % (score*max_score, score))
print("script end", datetime.datetime.now())
def run(filename):
print("script begin", datetime.datetime.now())
EPS = 1e-12
model = models.UnrollingHelicesShiftingZ(
djs=np.arange(-20, 20 + EPS, 10),
dbscan_features=["sina1", "cosa1", "z1", "z2"],
dbscan_weight=[1.0, 1.0, 0.75, 0.2],
niter=150)
nevents = 1
path_to_input = os.path.join(path_to_trackml, "train_1")
path_to_out = "out_{0}".format(sys.argv[0].split(".")[0])
event_id_list = []
hits_list = []
truth_list = []
sys.stderr.write("load data\n")
for event_id, hits, truth in load_dataset(path_to_input,
parts=["hits", "truth"],
skip=0,
nevents=nevents):
event_id_list.append(event_id)
hits_list.append(hits)
truth_list.append(truth)
def Fun4BO(w_a1, w_z1, w_z2):
model.dbscan_weight[0] = w_a1
model.dbscan_weight[1] = w_a1
model.dbscan_weight[2] = w_z1
model.dbscan_weight[3] = w_z2
sys.stderr.write("scan\n")
score_list = []
for (event_id, hits, truth) in zip(event_id_list, hits_list,
truth_list):
label = model.predict(hits)
submission = pd.DataFrame(
columns=['event_id', 'hit_id', 'track_id'],
data=np.column_stack(([
int(event_id),
] * len(hits), hits.hit_id.values, label))).astype(int)
score = score_event(truth, submission)
score_list.append(score)
return np.sum(score_list) / len(score_list)
opt = BayesianOptimization(Fun4BO, {
"w_a1": (0.9, 1.2),
"w_z1": (0.3, 0.7),
"w_z2": (0.1, 0.4)
},
verbose=True)
opt.maximize(
init_points=3,
n_iter=30, # 30
kappa=2.576)
# [string]
labels = opt.res["max"]["max_params"].keys()
# [dict(string, [float])]
params = opt.res["all"]["params"]
len_params = len(params)
data_dic = {}
for label in labels:
val = [opt.res["max"]["max_params"][label]]
for i in range(len_params):
val.append(params[i][label])
data_dic[label] = val
data_dic["value"] = [opt.res["max"]["max_val"]] + opt.res["all"]["values"]
data_dic["label"] = ["max"] + [str(x) for x in range(len_params)]
df = pd.DataFrame(data_dic)
df.to_csv(filename, index=None)