def getDic():
# temp=pickle.load(open('data2/delx,y', 'rb'))
# x=temp['x']
# y=temp['y']
# r={}
# for i,yi in enumerate(y):
# if yi in r:
# r[yi].append(x.getrow(i))
# else:
# r[yi]=[x.getrow(i)]
# result={k:{"matrix":vstack(r[k])} for k in r}
# pickle.dump(result, open('data2/class_mat', 'wb'))
# result={}
# for k in r:
# result[k]={"matrix":vstack(r[k])}
result = pickle.load(open('data2/class_mat', 'rb'))
rv = rv_continuous()
for k in result:
print(
str(k) + ":" +
time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())))
list = []
for i in range(result[k]["matrix"].shape[1]):
stds = np.std(result[k]["matrix"].getcol(i).todense(), axis=0)
list.append(stds[0][0])
if i % 10000 == 0:
print("i:" + str(i) + ":" + time.strftime(
'%Y-%m-%d %H:%M:%S', time.localtime(time.time())))
print(str(k) + ":" + str(len(list)))
pickle.dump(list, open('data2/std_' + str(k), 'wb'))
def __init__(self,
name=None,
type=None,
mean=None,
stdv=None,
startpoint=None,
p1=None,
p2=None,
p3=None,
p4=None,
input_type=None):
self.name = name
self.type = type
self.mean = mean
self.stdv = stdv
self.startpoint = None
self.setStartPoint(startpoint)
self.p1 = p1
self.p2 = p2
self.p3 = p3
self.p4 = p4
self.input_type = input_type
self.rv = stats.rv_continuous()
def __init__(self, name=None,type=None,mean=None,stdv=None,startpoint=None,p1=None,p2=None,p3=None,p4=None,input_type=None):
self.name = name
self.type = type
self.mean = mean
self.stdv = stdv
self.startpoint = None
self.setStartPoint(startpoint)
self.p1 = p1
self.p2 = p2
self.p3 = p3
self.p4 = p4
self.input_type = input_type
self.rv = stats.rv_continuous()
month_demand.groupby('month', as_index=False).sum())
week_demand['demand'] = week_demand['demand'] * 10
month_demand['demand'] = month_demand['demand'] * 10
#month_demand.drop(month_demand.tail(1).index, axis = 0, inplace = True)
#month_demand.drop(month_demand.head(1).index, axis = 0, inplace = True)
history_data = Biweek_demand[
'demand'].values #[140,130,120,110,100,100,90,90,90,70,60,60,60,60,60,40,40,40,40]
#history_data = [10,30,150,90,120,320,40,410,170,170,60,60,150,90,150,330,100,60,70,60,100,90,210,130,140,40,40,110,60,40,20,20]
#history_data = [i for i in history_data if i >=300]
history_data = history_data[history_data > 100]
#history_data = history_data[history_data>200]
params = gamma.fit(history_data)
params = rv_continuous(gamma, history_data)
statistic, pvalue = kstest(history_data, gamma.cdf, params)
print('gamma: %f %f' % (statistic, pvalue))
print(params)
params = norm.fit(history_data)
statistic, pvalue = kstest(history_data, "norm", params)
print('norm: %f %f' % (statistic, pvalue))
params = exponweib.fit(history_data)
statistic, pvalue = kstest(history_data, "exponweib", params)
print('weibull: %f %f' % (statistic, pvalue))
params = expon.fit(history_data)
statistic, pvalue = kstest(history_data, "expon", params)
print('expon: %f %f' % (statistic, pvalue))
def test_no_name_arg(self):
"""If name is not given, construction shouldn't fail. See #1508."""
stats.rv_continuous()
stats.rv_discrete()
}
parameters_k_nearest_neighbors_classifier = {
"algorithm": ["auto", "ball_tree", "kd_tree", "brute"],
"leaf_size": sp_randint(15, 45),
"metric": ["euclidean", "manhattan", "minkowski"],
"n_neighbors": sp_randint(2, 8),
"p": [1, 2],
"weights": ["uniform", "distance"],
}
parameters_radius_neighbors_classifier = {
"algorithm": ["auto", "ball_tree", "kd_tree", "brute"],
"leaf_size": sp_randint(15, 45),
"metric": ["euclidean", "manhattan", "minkowski"],
"outlier_label": ["Unknown"],
"p": [1, 2],
"radius": rv_continuous(1.0, 3.0),
"weights": ["uniform", "distance"],
}
parameters_gaussian_naive_bayes = {}
parameters_never_functional = []
parameters_support_vector_classifier = [{
'kernel': ['rbf'],
'gamma': [1e-3, 1e-4],
'C': [1, 10, 100, 1000]
}, {
'kernel': ['linear'],
'C': [1, 10, 100, 1000]
}]
#
# names = [
