def main(df):
df = df.reset_index("date", drop = True)
df = base1.main(df)
for each in ["ta_ROC_5","ta_WILLR_2", "ta_ROC_7", "ta_WILLR_7", "ta_WILLR_5", "ta_STOCHRSI_slowd_28_5_3", "ta_NATR_28"]:
for i in [1, 2, 5, 7, 14]:
df["%s-shift-%d" % (each, i)] = df[each].shift(i)
return df
def main(df):
df = base1.main(df)
lipt = get_lipt()
df = df[lipt]
sym = df['sym'].values[0]
vol = pd.read_csv(os.path.join(base.dir_vol(), sym + ".csv"))
d = {'Date': 'date'}
for each in vol.columns[1:]:
d[each] = 'ta_' + each
vol = vol.rename(columns=d)
vol = vol.fillna(0)
dfDate = df[["date"]]
vol = pd.merge(how='left',
left=dfDate,
right=vol,
left_on='date',
right_on='date')
vol = vol.fillna(0)
print df.shape[1]
df = pd.merge(how='left',
left=df,
right=vol,
left_on="date",
right_on="date")
print df.shape[1]
return df
def main(df):
df = df.reset_index("date", drop=True)
df = base1.main(df)
df = sig_123recall.main(df)
df = sig_adx.main(df)
#df = sig_upbreak.main(df)
#assert 40 == df.shape[1]
return df
def main(df):
df = df.reset_index("date", drop=True)
df = base1.main(df)
df = sig_123recall.main(df)
df = sig_adx.main(df)
df = sig_upbreak.main(df)
# assert 40 == df.shape[1]
return df
def main(df):
df.reset_index(drop=True, inplace=True)
df = base1.main(df)
lipt = get_lipt()
df = df[lipt]
df = sig_adx(df)
df.reset_index(drop=True, inplace=True)
assert 38 == df.shape[1]
return df
def main(df):
df = df.reset_index("date", drop=True)
df = base1.main(df)
lipt = get_lipt()
df = df[lipt]
del df["ta_ADX_7"]
df = adx_sig(df)
df = df.eset_index()
assert 37 == df.shape[1]
return df
def main(df):
df = df.reset_index("date", drop=True)
df = base1.main(df)
for each in [
"ta_ROC_5", "ta_WILLR_2", "ta_ROC_7", "ta_WILLR_7", "ta_WILLR_5",
"ta_STOCHRSI_slowd_28_5_3", "ta_NATR_28"
]:
for i in [1, 2, 5, 7, 14]:
df["%s-shift-%d" % (each, i)] = df[each].shift(i)
return df
def main(df):
df = df.reset_index("date", drop=True)
df = base1.main(df)
df = sig_123recall.main(df)
df = sig_adx.main(df)
df = sig_upbreak.main(df)
df = sig_ta_PLUS_DM_28.main(df)
del df["ta_PLUS_DM_28"]
#assert 40 == df.shape[1]
return df
def main(df):
df = base1.main(df)
lipt = get_lipt()
df = df[lipt]
df["shift"] = df['close'].shift(5)
df["trend"] = df['close'] / df['shift']
df = df[df["trend"] < 1.0]
del df["trend"]
del df["shift"]
assert 37 == df.shape[1]
return df
def main(df):
df = df.reset_index("date", drop = True)
df = base1.main(df)
df = sig_123recall.main(df)
df = sig_adx.main(df)
df = sig_upbreak.main(df)
df = sig_ta_PLUS_DM_28.main(df)
del df["ta_PLUS_DM_28"]
#assert 40 == df.shape[1]
return df
def main(df):
df['closer'] = df['close'] / df['close'].shift(1)
closes=df['closer'].values
df = base1.main(df)
for tri in [(6,13,8),(12, 26, 9), (24, 52, 18)]:
macd = talib.MACD(closes, tri[0], tri[1], tri[2])
df['ta_MACD_macd_%d_%d_%d'%(tri[0],tri[1],tri[2])] = macd[0]
df['ta_MACD_macdsignal_%d_%d_%d'%(tri[0],tri[1],tri[2])] = macd[1]
df['ta_MACD_macdhist_%d_%d_%d'%(tri[0],tri[1],tri[2])] = macd[2]
print df.shape
return df
def main(df):
df['closer'] = df['close'] / df['close'].shift(1)
closes = df['closer'].values
df = base1.main(df)
for tri in [(6, 13, 8), (12, 26, 9), (24, 52, 18)]:
macd = talib.MACD(closes, tri[0], tri[1], tri[2])
df['ta_MACD_macd_%d_%d_%d' % (tri[0], tri[1], tri[2])] = macd[0]
df['ta_MACD_macdsignal_%d_%d_%d' % (tri[0], tri[1], tri[2])] = macd[1]
df['ta_MACD_macdhist_%d_%d_%d' % (tri[0], tri[1], tri[2])] = macd[2]
print df.shape
return df
def main(df):
df = base1.main(df)
df.reset_index(inplace=True,drop=True)
orig_feats = base.get_feat_names(df)
df = merge(df, 1)
df = merge(df, 2)
df = merge(df, 3)
for each in orig_feats:
if not each.startswith("ta_ADX"):
del df[each]
print list(df.columns)
return df
def main(df):
df = base1.main(df)
lipt = get_lipt()
df = df[lipt]
df["shift"] = df['close'].shift(5)
df["trend"] = df['close'] / df['shift']
#print df[['date','sym','close',"shift", 'trend']].tail(10)
df = df[df["trend"] > 1.0]
del df["trend"]
del df["shift"]
assert 37 == df.shape[1]
return df
def main(df):
df = base1.main(df)
df.reset_index(inplace=True,drop=True)
orig_feats = base.get_feat_names(df)
print df.shape
df = merge(df, 1)
print df.shape
df = merge(df, 2)
print df.shape
for each in orig_feats:
del df[each]
print df.shape
return df
def main(df):
df = base1.main(df)
df.reset_index(inplace=True, drop=True)
orig_feats = base.get_feat_names(df)
print df.shape
df = merge(df, 1)
print df.shape
df = merge(df, 2)
print df.shape
for each in orig_feats:
del df[each]
print df.shape
return df
def main(df):
df = base1.main(df)
lipt = get_lipt()
df = df[lipt]
df.reset_index(drop=True)
print df.shape
for i in range(14, 28):
df = df.join(pta.PDM(df, i))
print df.shape
#for i in (28,):
# ma = pta.MA(df, i)
# df["ta_MA_diff_%d" % i] = 100 * df["close"] / ma
#for d in [(5, 7), (7,14), (14,21), (21,28), (7,21), (7,28)]:
# df["ta_MA_diff_%d_%d"%(d[0],d[1])] = 100 * pta.MA(df,d[1])/pta.MA(df,d[0])
return df
def main(df):
df = base1.main(df)
df.reset_index(inplace=True,drop=True)
dfStable = pd.read_pickle(os.path.join(dataroot,
"phase1_dump",
"sp500_base1_stable.pkl"))
dfStable = dfStable[dfStable.direct != 0]
tobe = []
for i, each in dfStable.iterrows():
name = each["name"]
fname = each["fname"]
start = each["start"]
end = each["end"]
#df.loc[:,name] = df.apply(lambda row:
# 1 if ((row[fname] >= start) and (row[fname] < end)) else 0, axis=1)
new = df.apply(lambda row:
1 if ((row[fname] >= start) and (row[fname] < end)) else 0, axis=1)
tobe.append(pd.Series(new, name = name))
df = df.join(pd.DataFrame(tobe).transpose())
return df
def main(df):
df = base1.main(df)
df.reset_index(inplace=True, drop=True)
dfStable = pd.read_pickle(
os.path.join(dataroot, "phase1_dump", "sp500_base1_stable.pkl"))
dfStable = dfStable[dfStable.direct != 0]
tobe = []
for i, each in dfStable.iterrows():
name = each["name"]
fname = each["fname"]
start = each["start"]
end = each["end"]
#df.loc[:,name] = df.apply(lambda row:
# 1 if ((row[fname] >= start) and (row[fname] < end)) else 0, axis=1)
new = df.apply(lambda row: 1 if
((row[fname] >= start) and (row[fname] < end)) else 0,
axis=1)
tobe.append(pd.Series(new, name=name))
df = df.join(pd.DataFrame(tobe).transpose())
return df
def main(df):
df1 = base1.main(df)
df1.reset_index(drop=True, inplace=True)
df2 = stable_3.main(df)
df2.reset_index(drop=True, inplace=True)
l = [
'ta_CMO_14', 'ta_RSI_14', 'ta_CMO_7', 'ta_RSI_7', 'ta_CMO_10',
'ta_RSI_10', 'ta_TRIX_2', 'ta_RSI_28', 'ta_CMO_28', 'ta_RSI_5',
'ta_STOCHRSI_slowd_5_20_12', 'ta_ROC_7', 'ta_ROCR100_7', 'ta_ROCP_7',
'ta_ROCR_7', 'ta_STOCHRSI_slowd_7_20_12', 'ta_RSI_2', 'ta_ROC_5',
'ta_ROCR100_5', 'ta_ROCR_5', 'ta_ROCP_5', 'ta_WILLR_10', 'ta_WILLR_14',
'ta_ROC_2', 'ta_ROCR100_2', 'ta_ROCP_2', 'ta_ROCR_2', 'ta_WILLR_7'
]
df1 = feat_select.append_deep_feats(df1, l)
df1 = df1[base.get_feat_names(df1).extend(["date"])]
print df2.shape
df2 = df2.merge(df1, left_on='date', right_on="date", how='inner')
print df2.shape
return df2
def main(df):
df1 = base1.main(df)
df1.reset_index(drop=True, inplace=True)
df2 = stable_3.main(df)
df2.reset_index(drop=True, inplace=True)
l = ['ta_CMO_14', 'ta_RSI_14','ta_CMO_7','ta_RSI_7','ta_CMO_10',
'ta_RSI_10',
'ta_TRIX_2',
'ta_RSI_28',
'ta_CMO_28',
'ta_RSI_5',
'ta_STOCHRSI_slowd_5_20_12',
'ta_ROC_7',
'ta_ROCR100_7',
'ta_ROCP_7',
'ta_ROCR_7',
'ta_STOCHRSI_slowd_7_20_12',
'ta_RSI_2',
'ta_ROC_5',
'ta_ROCR100_5',
'ta_ROCR_5',
'ta_ROCP_5',
'ta_WILLR_10',
'ta_WILLR_14',
'ta_ROC_2',
'ta_ROCR100_2',
'ta_ROCP_2',
'ta_ROCR_2',
'ta_WILLR_7']
df1 = feat_select.append_deep_feats(df1,l)
df1 = df1[base.get_feat_names(df1).extend(["date"])]
print df2.shape
df2 = df2.merge(df1, left_on='date', right_on="date", how='inner')
print df2.shape
return df2
def main(df):
df = base1.main(df)
lipt = get_lipt()
df = df[lipt]
assert 37 == df.shape[1]
return df
def main(df):
df = base1.main(df)
df = cdl.main(df)
return df
def main(df):
df = base1.main(df)
df = cdl.main(df)
print df.shape
return df
def main(df):
df = base1.main(df)
df = cdl.main(df)
return df