def main(args):
lsym = getattr(yeod, "get_%s" % args.setname)()
if args.start is None:
args.start = base.last_trade_date()
args.end = args.start
cls = joblib.load(os.path.join(base.dir_model(), args.model))
ta = base.get_merged_with_na(args.taname, lsym)
ta = ta[(ta['date'] >= args.start) & (ta['date'] <= args.end)]
dfFeat = ta.loc[:, base.get_feat_names(ta)]
dfFeat = dfFeat.replace([np.inf,-np.inf],np.nan)\
.dropna()
npFeat = dfFeat.values
npPred = cls.predict_proba(npFeat)
#for i, npPred in enumerate(cls.staged_predict_proba(npFeat)):
# if i == args.stage:
# break
ta["pred"] = npPred[:, 1]
ta.sort("pred", inplace=True, ascending=False)
freport, fcsv = base.file_pred(args)
ta.to_csv(fcsv)
#ta[["date", "sym", "pred", label]].to_csv(os.path.join(out_dir, 'pred.s.csv'))
with open(freport, 'w') as fout:
print >> fout, ta[["date", "sym", "pred"]].head(10)
def main(argv):
yeod.main(["sp500", 5])
build.main(["sp500", 'call1s1', 5])
last_date = base.last_trade_date()
pred.main([
'call1s1_sp500_GBCv1n322md3lr001_l5_s1700e2009', 'call1s1_sp500',
last_date, last_date, 'label5'
])
def main(argv):
#shutil.rmtree(os.path.join(root, "data", "yeod_batch", "%s-%d" % (eod, batch)), ignore_errors=False)
yeod.main(["index_dow", 1])
yeod_b.main([eod, batch, 10])
build_b.main([eod, batch ,ta,10])
paper_b.main([model, 600, "%s-%s" % (ta,eod), batch, "2010-06-01", "2016-06-31", 2, 400])
last_date = base.last_trade_date()
pred_b.main([model, 600, "%s-%s-%d" % (ta, eod, batch),
last_date, last_date, "label5"])
def transfer():
df_pred = pd.read_pickle(os.path.join(root, "data", "cross", "pred%s.pkl" % base.last_trade_date()))
df_pred = df_pred[df_pred.date >= "2010-01-01"]
index = df_pred[df_pred.sym == "MSFT"]["date"].unique(); index.sort()
index = pd.to_datetime(index)
columns = df_pred["sym"].unique(); columns.sort()
df_price = pd.DataFrame(index = index, columns = columns)
df_thred = pd.DataFrame(index = index, columns = columns)
for i, each in df_pred.iterrows():
if each["date"] not in df_price.index:
continue
df_price.set_value(each["date"], each["sym"], each["close"])
df_thred.set_value(each["date"], each["sym"], each["pred"])
# assert
assert_cotinue(df_price)
assert_cotinue(df_thred)
return (df_price, df_thred)