def one_work(cls, taName, label, date_range, th):
df = base.get_merged(base.dir_ta(taName))
df = get_range(df, date_range[0], date_range[1])
m = joblib.load(
os.path.join(root, 'data', 'models', "model_" + cls + ".pkl"))
s = joblib.load(
os.path.join(root, 'data', 'models', "scaler_" + cls + ".pkl"))
feat_names = base.get_feat_names(df)
npFeat = df.loc[:, feat_names].values
#npPred = cls.predict_proba(npFeat)[:,1]
#prent npPred
res = ""
for i, npPred in enumerate(m.staged_predict_proba(s.transform(npFeat))):
#if i % 1 != 0:
# continue
re = "%s\t%s\t%s\t%s\t%s\t%f\t" % (cls, taName, label, date_range[0],
date_range[1], th)
df["pred"] = npPred[:, 1]
dacc = accu(df, label, th)
re += "%d\t%d\t%d\t" % (i, dacc["trueInPos"], dacc["pos"])
if dacc["pos"] > 0:
re += "%f" % (dacc["trueInPos"] * 1.0 / dacc["pos"])
else:
re += "0.0"
re += "\n"
print re
res += re
return re
def one_work(cls, taName, label, date_range, th):
df = base.get_merged(base.dir_ta(taName))
df = get_range(df, date_range[0], date_range[1])
m = joblib.load(os.path.join(root, 'data', 'models',"model_" + cls + ".pkl"))
s = joblib.load(os.path.join(root, 'data', 'models',"scaler_" + cls + ".pkl"))
feat_names = base.get_feat_names(df)
npFeat = df.loc[:,feat_names].values
#npPred = cls.predict_proba(npFeat)[:,1]
#prent npPred
res = ""
for i, npPred in enumerate(m.staged_predict_proba(s.transform(npFeat))):
#if i % 1 != 0:
# continue
re = "%s\t%s\t%s\t%s\t%s\t%f\t" % (cls, taName, label, date_range[0], date_range[1],th)
df["pred"] = npPred[:,1]
dacc = accu(df, label, th)
re += "%d\t%d\t%d\t" % (i, dacc["trueInPos"], dacc["pos"])
if dacc["pos"] > 0:
re += "%f" % (dacc["trueInPos"]*1.0 / dacc["pos"])
else :
re += "0.0"
re += "\n"
print re
res += re
return re
def _one_work2(sym, tafunc):
exec "import main.pandas_talib.sig_%s as conf" % tafunc
df = pd.read_csv(os.path.join(base.dir_eod(), sym + ".csv"))
if df is None:
print sym
return
df = judge(df)
if 'ta_index_hdiff_close_1' in df.columns:
df = judge2(df)
df["sym"] = sym
df = conf.main(df)
df.to_pickle(os.path.join(base.dir_ta(conf.__name__), sym + ".pkl"))
def _one_work(sym, taname):
impstr = "import ta_%s as conf" % taname
exec impstr
df = pd.read_csv(os.path.join(base.dir_eod(), sym + ".csv"))
if df is None:
print sym
return
df = judge(df)
if 'ta_index_hdiff_close_1' in df.columns:
df = judge2(df)
df["sym"] = sym
df = conf.main(df)
df.to_pickle(os.path.join(base.dir_ta(taname), sym + ".pkl"))
def _one_work(sym, ta, confer):
try:
df = pd.read_csv(os.path.join(base.dir_eod(), sym + ".csv"))
df = df[["date", "open", "high", "low", "close", "volume"]]
df[["volume"]] = df[["volume"]].astype(float)
if df is None:
print(sym)
return
df["sym"] = sym
if TEST:
print("TEST")
df = df[df.date >= "2000-01-01"]
df = ta.get_ta(df, confer)
df.to_pickle(os.path.join(base.dir_ta(ta.get_name()), sym + ".pkl"))
return df
except:
traceback.print_exc()
assert False
def one_work(clsName, taName, labelName, start, end, top):
df = base.get_merged(base.dir_ta(taName))
df = get_range(df, start, end)
m = joblib.load(os.path.join(root, 'data', 'models',"model_" + clsName + ".pkl"))
if isscaler:
s = joblib.load(os.path.join(root, 'data', 'models',"scaler_" + clsName + ".pkl"))
feat_names = base.get_feat_names(df)
npFeat = df.loc[:,feat_names].values
res = ""
if isscaler :
npFeat = s.transform(npFeat)
topscore = None
l = []
for i, npPred in enumerate(m.staged_predict_proba(npFeat)):
df.loc[:,"pred"] = npPred[:,1]
dacc = accu(df, labelName, top)
acc = 0.0
if dacc["pos"] > 0:
acc = (dacc["trueInPos"]*1.0 / dacc["pos"])
print i, acc
l.append([i, acc])
return pd.DataFrame(np.asarray(l), columns=["idx", "acc"])
