def fc_update_nav(ctx, optid):
lookback_days = 365
blacklist = [24, 32, 40]
factor_ids = [
'1200000%02d' % i for i in range(1, 40) if i not in blacklist
]
trade_dates = ATradeDate.month_trade_date(begin_date='2018-01-01')
date = trade_dates[-1]
start_date = (date -
datetime.timedelta(lookback_days)).strftime('%Y-%m-%d')
end_date = date.strftime('%Y-%m-%d')
corr0 = load_ind(factor_ids, start_date, end_date)
res = clusterKMeansBase(corr0, maxNumClusters=10, n_init=100)
asset_cluster = res[1]
asset_cluster = dict(
zip(sorted(asset_cluster), sorted(asset_cluster.values())))
factor_name = base_ra_index.load()
for k, v in asset_cluster.iteritems():
v = np.array(v).astype('int')
print factor_name.loc[v]
assets = {}
for factor_id in factor_ids:
assets[factor_id] = Asset.load_nav_series(factor_id)
df_assets = pd.DataFrame(assets)
db = database.connection('asset')
metadata = MetaData(bind=db)
t = Table('ra_composite_asset_nav', metadata, autoload=True)
for layer in asset_cluster.keys():
layer_id = 'FC.000001.%d' % (layer + 1)
layer_assets = asset_cluster[layer]
layer_nav = df_assets.loc[:, layer_assets]
layer_ret = layer_nav.pct_change().dropna()
layer_ret = layer_ret.mean(1)
layer_ret = layer_ret.reset_index()
layer_ret.columns = ['ra_date', 'ra_inc']
layer_ret['ra_nav'] = (1 + layer_ret['ra_inc']).cumprod()
layer_ret['ra_asset_id'] = layer_id
df_new = layer_ret.set_index(['ra_asset_id', 'ra_date'])
df_old = asset_ra_composite_asset_nav.load_nav(layer_id)
df_new = df_new.reindex(columns=['ra_nav', 'ra_inc'])
database.batch(db, t, df_new, df_old, timestamp=False)
def fc_rolling(ctx, optid):
lookback_days = 365
blacklist = [24, 32, 40]
factor_ids = [
'1200000%02d' % i for i in range(1, 40) if i not in blacklist
]
trade_dates = ATradeDate.month_trade_date(begin_date='2018-01-01')
for date in trade_dates:
start_date = (date -
datetime.timedelta(lookback_days)).strftime('%Y-%m-%d')
end_date = date.strftime('%Y-%m-%d')
print start_date, end_date
corr0 = load_ind(factor_ids, start_date, end_date)
factor_name = base_ra_index.load()
res = clusterKMeansBase(corr0, maxNumClusters=10, n_init=100)
asset_cluster = res[1]
asset_cluster = dict(
zip(sorted(asset_cluster), sorted(asset_cluster.values())))
for k, v in asset_cluster.iteritems():
v = np.array(v).astype('int')
print factor_name.loc[v]
print
def fc_rolling(ctx, optid):
engine = database.connection('asset')
Session = sessionmaker(bind=engine)
session = Session()
blacklist = [24, 40]
asset_ids = ['1200000%02d' % i for i in range(1, 40) if i not in blacklist]
assets = {}
for asset_id in asset_ids:
# assets[asset_id] = load_nav_series(asset_id)
assets[asset_id] = Asset.load_nav_series(asset_id)
layer_result = {}
layer_result['date'] = []
layer_result['layer'] = []
layer_result['factor'] = []
lookback_days = 365
forecast_days = 90
df_result = pd.DataFrame(columns=['date', 'factor_id', 'layer'])
start_date = '2017-01-01'
trade_dates = ATradeDate.month_trade_date(begin_date=start_date)
for date in trade_dates:
print date
sdate = (date - datetime.timedelta(lookback_days)).strftime('%Y-%m-%d')
edate = date.strftime('%Y-%m-%d')
fdate = (date + datetime.timedelta(forecast_days)).strftime('%Y-%m-%d')
'''
init_num = 5
fc = FactorCluster(assets, init_num, sdate, edate, fdate)
fc.handle()
while fc.inner_score < 0.88:
init_num += 1
fc = FactorCluster(assets, init_num, sdate, edate, fdate)
fc.handle()
'''
method = 'beta'
scores = {}
models = {}
for i in range(7, 12):
fc = FactorCluster(assets,
i,
sdate,
edate,
fdate,
method=method,
bf_ids=None)
fc.handle()
print i, 'silhouette_samples_value:', fc.silhouette_samples_value
score = fc.silhouette_samples_value
scores[score] = i
models[score] = fc
best_score = np.max(scores.keys())
best_model = models[best_score]
fc = best_model
print 'best cluster num:', fc.n_clusters
factor_name = base_ra_index.load()
for k, v in fc.asset_cluster.iteritems():
v = np.array(v).astype('int')
print factor_name.loc[v]
for vv in v:
df_result.loc[len(df_result)] = [date, vv, k]
print
session.commit()
session.close()
blacklist = [24, 32, 40]
factor_ids = [
'1200000%02d' % i for i in range(1, 40) if i not in blacklist
]
trade_dates = ATradeDate.month_trade_date(begin_date='2018-01-01')
for date in trade_dates:
# start_date = '%d-%02d-01'%(year, month)
# end_date = '%d-%02d-01'%(year+1, month)
start_date = (date -
datetime.timedelta(lookback_days)).strftime('%Y-%m-%d')
end_date = date.strftime('%Y-%m-%d')
print start_date, end_date
# corr0 = load_fund(start_date, end_date)
corr0 = load_ind(factor_ids, start_date, end_date)
# corr1, clstrs, silh = clusterKMeansBase(corr0,maxNumClusters=10,n_init=1)
factor_name = base_ra_index.load()
# df_fund = base_ra_fund.load()
# df_fund.index = df_fund.ra_code.astype('int')
# df_fund = df_fund.set_index('ra_code')
# factor_name = df_fund.ra_name
res = None
while res is None:
try:
# res = clusterKMeansTop(corr0, maxNumClusters=10, n_init=1)
res = clusterKMeansBase(corr0, maxNumClusters=10, n_init=10)
except:
pass
for k, v in res[1].iteritems():
v = np.array(v).astype('int')
print factor_name.loc[v]