def _gen_sgdcls(self):
coef_path = "%s/%s" % (CSV_DIR, self.coef_csv)
intercept_path = "%s/%s" % (CSV_DIR, self.coef_intercept)
coef = None
if os.path.exists(coef_path):
coef = np.array(f.csv2arr(coef_path))
intercept = None
if os.path.exists(intercept_path):
coef = np.array(f.csv2arr(intercept_path))
sgdcls = SGDClassifier(alpha=0.0001, average=False, class_weight=None, epsilon=0.1,
eta0=0.0, fit_intercept=True, l1_ratio=0.15,
learning_rate='optimal', loss='hinge', n_iter=5, n_jobs=N_JOBS,
penalty='l2', power_t=0.5, random_state=None, shuffle=True,
verbose=0, warm_start=False)
if coef is not None:
sgdcls.coef_ = coef
sgdcls.intercept_ = intercept
self.sgdcls = sgdcls
def gen_km(meigaras=[], cluster_centers_csv = ""):
strsql = "select count(*) from trade.kabuka "
if len(meigaras) > 0:
strsql = strsql + kf.where_col_in(meigaras, "code")
cnt = sql.exec_selsql(strsql, 0)
km = MiniBatchKMeans(
n_clusters=np.sqrt(cnt*SAMPLE_RATE),
batch_size=1000)
if cluster_centers_csv != "":
path = "%s/%s" % (CSV_DIR, cluster_centers_csv)
if os.path.exists(path):
cluster_centers = f.csv2arr(path)
km.cluster_centers_ = cluster_centers
return km
def _gen_km(self, bolverbose=False):
strsql = "select count(*) from trade.kabuka "
if len(self.meigaras) > 0:
strsql = strsql + " where " + kf.where_col_in(self.meigaras, "code")
cnt = sql.exec_selsql(strsql, 0)[0]
path = "%s/%s" % (CSV_DIR, self.cluster_centers_csv)
X = None
if os.path.exists(path):
X = np.array(f.csv2arr(path))
if X is None:
km = MiniBatchKMeans(n_clusters=int(np.sqrt(cnt * SAMPLE_RATE)), batch_size=1000, verbose=bolverbose)
else:
km = MiniBatchKMeans(
n_clusters=int(np.sqrt(cnt * SAMPLE_RATE)), batch_size=1000, init=X, verbose=bolverbose
)
km.cluster_centers_ = X
self.km = km