def load_daily_factor(self, file_name):
load_path = f'{self.root_path}/EM_Funda/daily/'
tmp_df = bt.AZ_Load_csv(os.path.join(load_path, file_name + '.csv'))
if self.xinx[-1] not in tmp_df.index:
send_email.send_email(file_name + self.sector_name,
['*****@*****.**'], [], '[LOADDATA]error')
tmp_df = tmp_df.reindex(index=self.xinx, columns=self.xnms)
target_df = self.row_extre(tmp_df, self.sector_df, 0.3)
if self.if_only_long:
target_df = target_df[target_df > 0]
return target_df
def load_tech_factor(self, file_name):
load_path = os.path.join('/media/hdd1/DAT_PreCalc/PreCalc_whs/' +
self.sector_name)
target_df = pd.read_pickle(os.path.join(load_path, file_name + '.pkl'))
if self.xinx[-1] not in target_df.index:
send_email.send_email(file_name + self.sector_name,
['*****@*****.**'], [], '[LOADDATA]error')
target_df = target_df.reindex(index=self.xinx, columns=self.xnms)
if self.if_only_long:
target_df = target_df[target_df > 0]
return target_df
def plot_send_result(pnl_df, sharpe_ratio, subject):
figure_save_path = '/mnt/mfs/dat_whs/tmp_figure'
plt.figure(figsize=[16, 8])
plt.plot(pnl_df.index,
pnl_df.cumsum(),
label='sharpe_ratio={}'.format(sharpe_ratio))
plt.legend()
plt.savefig(os.path.join(figure_save_path, '{}.png'.format(subject)))
text = ''
to = ['*****@*****.**']
filepath = [os.path.join(figure_save_path, '{}.png'.format(subject))]
send_email.send_email(text, to, filepath, subject)
def check_factor(self, name_list, file_name, check_path=None):
if check_path is None:
load_path = os.path.join('/mnt/mfs/dat_whs/data/new_factor_data/' + self.sector_name)
else:
load_path = check_path
exist_factor = set([x[:-4] for x in os.listdir(load_path)])
print()
use_factor = set(name_list)
a = use_factor - exist_factor
if len(a) != 0:
print('factor not enough!')
print(a)
print(len(a))
send_email.send_email(f'{file_name} factor not enough!', ['*****@*****.**'], [], 'Factor Test Warning!')
def load_remy_factor(self, file_name):
load_path = f'{self.root_path}/EM_Funda/DERIVED_F1'
raw_df = bt.AZ_Load_csv(f'{load_path}/{file_name}')
a = list(set(raw_df.iloc[-1, :100].dropna().values))
if self.xinx[-1] not in raw_df.index:
send_email.send_email(file_name + self.sector_name,
['*****@*****.**'], [], '[LOADDATA]error')
tmp_df = raw_df.reindex(index=self.xinx, columns=self.xnms)
if len(a) > 5:
target_df = self.row_extre(tmp_df, self.sector_df, 0.3)
else:
target_df = tmp_df
pass
if self.if_only_long:
target_df = target_df[target_df > 0]
return target_df
if hasattr(algorithm, 'labels_'):
y_pred = algorithm.labels_.astype(np.int)
else:
y_pred = algorithm.predict(X)
plt.subplot(len(datasets), len(clustering_algorithms), plot_num)
if i_dataset == 0:
plt.title(name, size=18)
colors = np.array(list(islice(cycle(['#377eb8', '#ff7f00', '#4daf4a',
'#f781bf', '#a65628', '#984ea3',
'#999999', '#e41a1c', '#dede00']),
int(max(y_pred) + 1))))
plt.scatter(X[:, 0], X[:, 1], s=10, color=colors[y_pred])
plt.xlim(-2.5, 2.5)
plt.ylim(-2.5, 2.5)
plt.xticks(())
plt.yticks(())
plt.text(.99, .01, ('%.2fs' % (t1 - t0)).lstrip('0'),
transform=plt.gca().transAxes, size=15,
horizontalalignment='right')
plot_num += 1
plt.savefig('/mnt/mfs/dat_whs/tmp_figure/cluster.png')
text = 'cluster figure'
to = ['*****@*****.**']
filepath = ['/mnt/mfs/dat_whs/tmp_figure/cluster.png']
subject = 'haha'
send_email.send_email(text, to, filepath, subject)