def validated(self, val):
"Accepts datetime, string, or list of 6 ints. Returns a datetime."
if isinstance(val, _dt):
return val
if self._format and isinstance(val, basestring):
return _dt.strptime(val, self._format)
try:
return _dt.utcfromtimestamp(float(val))
except TypeError:
pass # it was not a number
if len(val) > 2:
return _dt(*val[:6])
raise TypeError("value %r isn't a datetime" % val)
def validated(self, val):
"Accepts datetime, string, or list of 6 ints. Returns a datetime."
if isinstance(val,_dt):
return val
if self._format and isinstance(val,basestring):
return _dt.strptime(val,self._format)
try:
return _dt.utcfromtimestamp(float(val))
except TypeError:
pass # it was not a number
if len(val) > 2:
return _dt(*val[:6])
raise TypeError("value %r isn't a datetime"%val)
def get_most_recent_docs(db_name):
try:
db = _get_authentication("normal")[db_name]
checked_types = _config["checked_types"]
rec_list = [(t, db.design('document_type').view('document_type').get(
params=dict(limit=1,reduce=False,endkey=[t], startkey=[t,{}], descending=True)).result().json()['rows'])
for t in checked_types
]
for t, r in rec_list:
if len(r) == 0: continue
# Months in JS begin with 0, in python with 1!
r[0]["key"][2] += 1
doc = dict(id=db_name + ":" + str(t), refid=r[0]['id'],
timestamp=_dt(*r[0]["key"][1:]).strftime("%a, %d %b %Y %H:%M:%S GMT"))
_post_doc_to_aggregate(doc)
except:
error("Error while posting to aggregate DB ({})".format(traceback.format_exc()))
async def _get_newest(self, *, item):
logger.debug(f'{self._name} type:{type(item)} {item}')
l_newest_item = None
l_newest_ts = _dt(1970, 1, 1, tzinfo=timezone.utc)
if isinstance(item, list):
for l_item in item:
l_time = l_item.get('time', None)
if l_time:
l_ts = ciso8601.parse_datetime(l_time).replace(
tzinfo=timezone.utc)
if l_ts > l_newest_ts:
l_newest_item = l_item
l_newest_ts = l_ts
else:
l_newest_item = item
logger.debug(f'{self._name} item: {l_newest_item}')
return l_newest_item
def metrics(returns,
benchmark=None,
rf=0.,
display=True,
mode='basic',
sep=False,
compounded=True,
periods_per_year=252,
prepare_returns=True,
match_dates=False,
**kwargs):
win_year, _ = _get_trading_periods(periods_per_year)
if benchmark is not None \
and isinstance(benchmark, _pd.DataFrame) and len(benchmark.columns) > 1:
raise ValueError("`benchmark` must be a pandas Series, "
"but a multi-column DataFrame was passed")
blank = ['']
if isinstance(returns, _pd.DataFrame):
if len(returns.columns) > 1:
raise ValueError(
"`returns` needs to be a Pandas Series or one column DataFrame. multi colums DataFrame was passed"
)
returns = returns[returns.columns[0]]
if prepare_returns:
returns = _utils._prepare_returns(returns)
df = _pd.DataFrame({"returns": returns})
if benchmark is not None:
blank = ['', '']
benchmark = _utils._prepare_benchmark(benchmark, returns.index, rf)
if match_dates is True:
returns, benchmark = _match_dates(returns, benchmark)
df["returns"] = returns
df["benchmark"] = benchmark
df = df.fillna(0)
# pct multiplier
pct = 100 if display or "internal" in kwargs else 1
if kwargs.get("as_pct", False):
pct = 100
# return df
dd = _calc_dd(df,
display=(display or "internal" in kwargs),
as_pct=kwargs.get("as_pct", False))
metrics = _pd.DataFrame()
s_start = {'returns': df['returns'].index.strftime('%Y-%m-%d')[0]}
s_end = {'returns': df['returns'].index.strftime('%Y-%m-%d')[-1]}
s_rf = {'returns': rf}
if "benchmark" in df:
s_start['benchmark'] = df['benchmark'].index.strftime('%Y-%m-%d')[0]
s_end['benchmark'] = df['benchmark'].index.strftime('%Y-%m-%d')[-1]
s_rf['benchmark'] = rf
metrics['Start Period'] = _pd.Series(s_start)
metrics['End Period'] = _pd.Series(s_end)
metrics['Risk-Free Rate %'] = _pd.Series(s_rf)
metrics['Time in Market %'] = _stats.exposure(df,
prepare_returns=False) * pct
metrics['~'] = blank
if compounded:
metrics['Cumulative Return %'] = (_stats.comp(df) * pct).map(
'{:,.2f}'.format)
else:
metrics['Total Return %'] = (df.sum() * pct).map('{:,.2f}'.format)
metrics['CAGR﹪%'] = _stats.cagr(df, rf, compounded) * pct
metrics['~~~~~~~~~~~~~~'] = blank
metrics['Sharpe'] = _stats.sharpe(df, rf, win_year, True)
if mode.lower() == 'full':
metrics['Smart Sharpe'] = _stats.smart_sharpe(df, rf, win_year, True)
metrics['Sortino'] = _stats.sortino(df, rf, win_year, True)
if mode.lower() == 'full':
metrics['Smart Sortino'] = _stats.smart_sortino(df, rf, win_year, True)
metrics['Sortino/√2'] = metrics['Sortino'] / _sqrt(2)
if mode.lower() == 'full':
metrics['Smart Sortino/√2'] = metrics['Smart Sortino'] / _sqrt(2)
metrics['Omega'] = _stats.omega(df, rf, 0., win_year)
metrics['~~~~~~~~'] = blank
metrics['Max Drawdown %'] = blank
metrics['Longest DD Days'] = blank
if mode.lower() == 'full':
ret_vol = _stats.volatility(
df['returns'], win_year, True, prepare_returns=False) * pct
if "benchmark" in df:
bench_vol = _stats.volatility(
df['benchmark'], win_year, True, prepare_returns=False) * pct
metrics['Volatility (ann.) %'] = [ret_vol, bench_vol]
metrics['R^2'] = _stats.r_squared(df['returns'],
df['benchmark'],
prepare_returns=False)
else:
metrics['Volatility (ann.) %'] = [ret_vol]
metrics['Calmar'] = _stats.calmar(df, prepare_returns=False)
metrics['Skew'] = _stats.skew(df, prepare_returns=False)
metrics['Kurtosis'] = _stats.kurtosis(df, prepare_returns=False)
metrics['~~~~~~~~~~'] = blank
metrics['Expected Daily %%'] = _stats.expected_return(
df, prepare_returns=False) * pct
metrics['Expected Monthly %%'] = _stats.expected_return(
df, aggregate='M', prepare_returns=False) * pct
metrics['Expected Yearly %%'] = _stats.expected_return(
df, aggregate='A', prepare_returns=False) * pct
metrics['Kelly Criterion %'] = _stats.kelly_criterion(
df, prepare_returns=False) * pct
metrics['Risk of Ruin %'] = _stats.risk_of_ruin(df,
prepare_returns=False)
metrics['Daily Value-at-Risk %'] = -abs(
_stats.var(df, prepare_returns=False) * pct)
metrics['Expected Shortfall (cVaR) %'] = -abs(
_stats.cvar(df, prepare_returns=False) * pct)
metrics['~~~~~~'] = blank
metrics['Gain/Pain Ratio'] = _stats.gain_to_pain_ratio(df, rf)
metrics['Gain/Pain (1M)'] = _stats.gain_to_pain_ratio(df, rf, "M")
# if mode.lower() == 'full':
# metrics['GPR (3M)'] = _stats.gain_to_pain_ratio(df, rf, "Q")
# metrics['GPR (6M)'] = _stats.gain_to_pain_ratio(df, rf, "2Q")
# metrics['GPR (1Y)'] = _stats.gain_to_pain_ratio(df, rf, "A")
metrics['~~~~~~~'] = blank
metrics['Payoff Ratio'] = _stats.payoff_ratio(df, prepare_returns=False)
metrics['Profit Factor'] = _stats.profit_factor(df, prepare_returns=False)
metrics['Common Sense Ratio'] = _stats.common_sense_ratio(
df, prepare_returns=False)
metrics['CPC Index'] = _stats.cpc_index(df, prepare_returns=False)
metrics['Tail Ratio'] = _stats.tail_ratio(df, prepare_returns=False)
metrics['Outlier Win Ratio'] = _stats.outlier_win_ratio(
df, prepare_returns=False)
metrics['Outlier Loss Ratio'] = _stats.outlier_loss_ratio(
df, prepare_returns=False)
# returns
metrics['~~'] = blank
comp_func = _stats.comp if compounded else _np.sum
today = df.index[-1] # _dt.today()
metrics['MTD %'] = comp_func(
df[df.index >= _dt(today.year, today.month, 1)]) * pct
d = today - _td(3 * 365 / 12)
metrics['3M %'] = comp_func(
df[df.index >= _dt(d.year, d.month, d.day)]) * pct
d = today - _td(6 * 365 / 12)
metrics['6M %'] = comp_func(
df[df.index >= _dt(d.year, d.month, d.day)]) * pct
metrics['YTD %'] = comp_func(df[df.index >= _dt(today.year, 1, 1)]) * pct
d = today - _td(12 * 365 / 12)
metrics['1Y %'] = comp_func(
df[df.index >= _dt(d.year, d.month, d.day)]) * pct
d = today - _td(3 * 365)
metrics['3Y (ann.) %'] = _stats.cagr(
df[df.index >= _dt(d.year, d.month, d.day)], 0., compounded) * pct
d = today - _td(5 * 365)
metrics['5Y (ann.) %'] = _stats.cagr(
df[df.index >= _dt(d.year, d.month, d.day)], 0., compounded) * pct
d = today - _td(10 * 365)
metrics['10Y (ann.) %'] = _stats.cagr(
df[df.index >= _dt(d.year, d.month, d.day)], 0., compounded) * pct
metrics['All-time (ann.) %'] = _stats.cagr(df, 0., compounded) * pct
# best/worst
if mode.lower() == 'full':
metrics['~~~'] = blank
metrics['Best Day %'] = _stats.best(df, prepare_returns=False) * pct
metrics['Worst Day %'] = _stats.worst(df, prepare_returns=False) * pct
metrics['Best Month %'] = _stats.best(
df, aggregate='M', prepare_returns=False) * pct
metrics['Worst Month %'] = _stats.worst(
df, aggregate='M', prepare_returns=False) * pct
metrics['Best Year %'] = _stats.best(
df, aggregate='A', prepare_returns=False) * pct
metrics['Worst Year %'] = _stats.worst(
df, aggregate='A', prepare_returns=False) * pct
# dd
metrics['~~~~'] = blank
for ix, row in dd.iterrows():
metrics[ix] = row
metrics['Recovery Factor'] = _stats.recovery_factor(df)
metrics['Ulcer Index'] = _stats.ulcer_index(df)
metrics['Serenity Index'] = _stats.serenity_index(df, rf)
# win rate
if mode.lower() == 'full':
metrics['~~~~~'] = blank
metrics['Avg. Up Month %'] = _stats.avg_win(
df, aggregate='M', prepare_returns=False) * pct
metrics['Avg. Down Month %'] = _stats.avg_loss(
df, aggregate='M', prepare_returns=False) * pct
metrics['Win Days %%'] = _stats.win_rate(df,
prepare_returns=False) * pct
metrics['Win Month %%'] = _stats.win_rate(
df, aggregate='M', prepare_returns=False) * pct
metrics['Win Quarter %%'] = _stats.win_rate(
df, aggregate='Q', prepare_returns=False) * pct
metrics['Win Year %%'] = _stats.win_rate(
df, aggregate='A', prepare_returns=False) * pct
if "benchmark" in df:
metrics['~~~~~~~'] = blank
greeks = _stats.greeks(df['returns'],
df['benchmark'],
win_year,
prepare_returns=False)
metrics['Beta'] = [str(round(greeks['beta'], 2)), '-']
metrics['Alpha'] = [str(round(greeks['alpha'], 2)), '-']
# prepare for display
for col in metrics.columns:
try:
metrics[col] = metrics[col].astype(float).round(2)
if display or "internal" in kwargs:
metrics[col] = metrics[col].astype(str)
except Exception:
pass
if (display or "internal" in kwargs) and "%" in col:
metrics[col] = metrics[col] + '%'
try:
metrics['Longest DD Days'] = _pd.to_numeric(
metrics['Longest DD Days']).astype('int')
metrics['Avg. Drawdown Days'] = _pd.to_numeric(
metrics['Avg. Drawdown Days']).astype('int')
if display or "internal" in kwargs:
metrics['Longest DD Days'] = metrics['Longest DD Days'].astype(str)
metrics['Avg. Drawdown Days'] = metrics[
'Avg. Drawdown Days'].astype(str)
except Exception:
metrics['Longest DD Days'] = '-'
metrics['Avg. Drawdown Days'] = '-'
if display or "internal" in kwargs:
metrics['Longest DD Days'] = '-'
metrics['Avg. Drawdown Days'] = '-'
metrics.columns = [
col if '~' not in col else '' for col in metrics.columns
]
metrics.columns = [
col[:-1] if '%' in col else col for col in metrics.columns
]
metrics = metrics.T
if "benchmark" in df:
metrics.columns = ['Strategy', 'Benchmark']
else:
metrics.columns = ['Strategy']
if display:
print(_tabulate(metrics, headers="keys", tablefmt='simple'))
return None
if not sep:
metrics = metrics[metrics.index != '']
return metrics
def __init__(self, uvfitsfile, telescope=None, vsys=0, distance=0, endian=None, **kwargs):
"""
Reads the uvfits and calculates useful things, e.g. u,v,w,
phase and amplitude
.byteswap().newbyteorder() is applied in various places to
convert to little endian
"""
f = pfopen(uvfitsfile, **kwargs)
self.loadendian = endian
if f[0].header['NAXIS1'] != 0:
print "error: this file may not be a UV FITS."
raise FileError('File format error.')
#~ f.info()
try:
self.hdu = f[0]
except:
print "error: cannot open uv data HDU."
self.hdr = self.hdu.header
self.data = self.hdu.data
if self.hdr['NAXIS4'] > 1:
self.datatype = ('CUBE', 3)
else:
self.datatype = ('IMAGE', 2)
# find spectral axis
axis_types = self.WCS.get_axis_types()
ax_types = np.array([i['coordinate_type'] for i in axis_types])
try:
spec_axis = ('spectral' == ax_types).nonzero()[0][0]
freq = self.hdu.header['CRVAL{0}'.format(spec_axis+1)]
# assumes the frequency given in Hz
self.freq = freq * un.Hz
except (IndexError):
print('No spectral axis in header.')
spec_axis = -1
self.freq = None
if 'RESTFREQ' in self.hdu.header.keys():
self.restfreq = self.hdu.header['RESTFREQ']
self.restfreq_unit = self.hdu.header['RESTFREQ'] * u.Hz
else:
raise StandardError('No restfrequency found, NEED it!')
#TODO : Read in velocity and frequency array if present
"""
The standard unit is to give UU and VV in seconds (??!?)
So we have to convert to whatever we want.
"""
# standard storing unit here is kilo-lambdas
# save a million lines of code!
u.add_enabled_equivalencies(lambdas_equivalencies(self.restfreq_unit))
self.u = (self.data.par('UU') * u.s).to(klambdas)
self.v = (self.data.par('VV') * u.s).to(klambdas)
self.w = (self.data.par('WW') * u.s).to(klambdas)
self.uvdist = sqrt(self.u.value**2 + self.v.value**2) * klambdas
# BASELINE
self.baseline = self.hdu.data.par('BASELINE').byteswap().newbyteorder()
# DATES
self.jdate = self.hdu.data.par('DATE')
# set date to 1900, Jan, 01, 01:00:00 if date before before this
self.jdate =self.jdate.clip(2415020.5)
self.date = _sp.array([jd2gd(i) for i in self.jdate])
self.date0 = self.date.transpose()
fields = ['year', 'month', 'day', 'hour', 'minute', 'sec']
self.date1 = {key:value for key,value in zip(fields, self.date0)}
# convert to datetime objects
# LOSES the sub-second resolution
self.date2 = [_dt(int(i[0]), int(i[1]), int(i[2]), int(i[3]), int(i[4]), int(i[5])) for i in self.date]
# get number of tracks
# TODO : rough hack, separate track if diff day is >1
tmp = _sp.where(_sp.diff(_sp.unique(self.jdate.round(0)))>1)[0]
self.ntracks = len(tmp)+1
################################################################
# NB : need to streamline this.
# only load the complex visibilities, into a complex array
# AND then work on that
# COMPLEX VISIBILITY
visi_index = len(self.data.parnames)
if self.hdu.header['NAXIS'] == 7:
self.visdata = self.data.par(visi_index)[:,0,0,0,0,0,:].byteswap().newbyteorder()
#~ self.visdata = self.hdu.data.data[:,0,0,0,0,0,:]
elif self.hdu.header['NAXIS'] == 6:
self.visdata = self.data.par(visi_index)[:,0,0,0,0,:].byteswap().newbyteorder()
# load the re, im and weight arrays
self.re, self.im, self.wt = self.visdata[:,:].T
#~ self.re = self.visdata[:,0][:]
#~ self.im = self.visdata[:,1][:]
#~ self.wt = self.visdata[:,2][:]
# complex numbers
#~ self.comp = self.visdata[:,:2].astype(_np.float64).view(_np.complexfloating)
#~ self.comp = 1j*self.visdata[:,1][:]
#~ self.comp += self.visdata[:,0][:]
#~ self.comp = self.visdata[:,:2].astype(_np.float).view(_np.complex)
# below seems a bit dependent...
self.cvisi = self.visdata[:,:2].astype(_np.float).view(_np.complex).T[0]
"""
with complex array, you can do
amp = np.abs(vis)
np.angle(vis)
vis.real
vis.imag
"""
# the data is not shifted
self.isshifted = (False, [0,0])
# AMPLITUDE
self.amp = sqrt(self.re**2 + self.im**2)
# PHASE
self.pha = arctan2(self.im, self.re)
self.pha_deg = self.pha / pi * 180.
# ERROR / SIGMA
#TODO : check
# following 1.0e6 is just for GILDAS, change if needed
#~ print('NB : Error calculated from weights assuming GILDAS '
#~ 'data (i.e. frequencies in MHz).')
self.sigma_alt = 1/sqrt(self.wt*1.0e6)
# Daniels way of calculating sigma
# test this first
self.sigma = _sp.sqrt(0.5 / ( self.wt * float(self.amp.shape[0]) ) )
def test_timezone_defaults(self, Sample):
when = _dt(2001, 9, 1)
instance = Sample(when)
assert instance['field'].tzinfo == utc
assert instance.field.tzinfo == utc
def test_basic_tzinfo_use(self, Sample):
now = _dt(1902, 4, 24)
instance = Sample(now)
assert instance.field.tzinfo.tzname(instance.field) in ('PST', 'Canada/Pacific')
def test_basic_tzinfo_use(self, Sample):
now = _dt(1902, 4, 24)
instance = Sample(now)
assert instance.field.tzinfo.tzname(
instance.field) in ('PST', 'Canada/Pacific')
def test_date_like_oid(self, Sample):
oid = ObjectId('586846800000000000000000')
assert Sample(oid).field == _dt(2017, 1, 1, tzinfo=utc)
def test_naive_explicit(self, Sample):
tz = pytz.timezone('America/Chicago')
when = _dt(1992, 1, 12) # Prod. #3
instance = Sample(when)
assert tz.normalize(instance['field'].astimezone(tz)).replace(tzinfo=None) == when
def test_timezone_defaults(self, Sample): when = _dt(2001, 9, 1) instance = Sample(when) assert instance['field'].tzinfo == utc assert instance.field.tzinfo == utc
def test_date_like_oid(self, Sample):
oid = ObjectId('586846800000000000000000')
assert Sample(oid).field == _dt(2017, 1, 1, tzinfo=utc)
def datetime(*args, **kwargs):
return _dt(*args, **kwargs)
def test_naive_explicit(self, Sample):
tz = pytz.timezone('America/Chicago')
when = _dt(1992, 1, 12) # Prod. #3
instance = Sample(when)
assert tz.normalize(
instance['field'].astimezone(tz)).replace(tzinfo=None) == when
def metrics(returns,
benchmark=None,
rf=0.,
display=True,
mode='basic',
sep=False,
**kwargs):
if isinstance(returns, _pd.DataFrame) and len(returns.columns) > 1:
raise ValueError("`returns` must be a pandas Series, "
"but a multi-column DataFrame was passed")
if benchmark is not None:
if isinstance(returns, _pd.DataFrame) and len(returns.columns) > 1:
raise ValueError("`benchmark` must be a pandas Series, "
"but a multi-column DataFrame was passed")
blank = ['']
df = _pd.DataFrame({"returns": _utils._prepare_returns(returns, rf)})
if benchmark is not None:
blank = ['', '']
df["benchmark"] = _utils._prepare_benchmark(benchmark, returns.index,
rf)
df = df.dropna()
# pct multiplier
pct = 100 if display or "internal" in kwargs else 1
# return df
dd = _calc_dd(df, display=(display or "internal" in kwargs))
metrics = _pd.DataFrame()
s_start = {'returns': df['returns'].index.strftime('%Y-%m-%d')[0]}
s_end = {'returns': df['returns'].index.strftime('%Y-%m-%d')[-1]}
s_rf = {'returns': rf}
if "benchmark" in df:
s_start['benchmark'] = df['benchmark'].index.strftime('%Y-%m-%d')[0]
s_end['benchmark'] = df['benchmark'].index.strftime('%Y-%m-%d')[-1]
s_rf['benchmark'] = rf
metrics['Start Period'] = _pd.Series(s_start)
metrics['End Period'] = _pd.Series(s_end)
metrics['Risk-free rate %'] = _pd.Series(s_rf)
metrics['Exposure %%'] = _stats.exposure(df) * pct
metrics['~'] = blank
metrics['Cumulative Return %'] = _stats.comp(df) * pct
metrics['CAGR%%'] = _stats.cagr(df, rf) * pct
metrics['Sharpe'] = _stats.sharpe(df, rf)
metrics['Sortino'] = _stats.sortino(df, rf)
metrics['Max Drawdown %'] = blank
metrics['Longest DD Days'] = blank
if mode.lower() == 'full':
ret_vol = _stats.volatility(df['returns']) * pct
if "benchmark" in df:
bench_vol = _stats.volatility(df['benchmark']) * pct
metrics['Volatility (ann.) %'] = [ret_vol, bench_vol]
metrics['R^2'] = _stats.r_squared(df['returns'], df['benchmark'])
else:
metrics['Volatility (ann.) %'] = [ret_vol]
metrics['Calmar'] = _stats.calmar(df)
metrics['Skew'] = _stats.skew(df)
metrics['Kurtosis'] = _stats.kurtosis(df)
if mode.lower() == 'full':
metrics['~~~~~~~~~~'] = blank
metrics['Expected Daily %%'] = _stats.expected_return(df) * pct
metrics['Expected Monthly %%'] = _stats.expected_return(
df, aggregate='M') * pct
metrics['Expected Yearly %%'] = _stats.expected_return(
df, aggregate='A') * pct
metrics['Kelly Criterion %'] = _stats.kelly_criterion(df) * pct
metrics['Risk of Ruin %'] = _stats.risk_of_ruin(df)
metrics['Daily Value-at-Risk %'] = -abs(_stats.var(df) * pct)
metrics['Expected Shortfall (cVaR) %'] = -abs(_stats.cvar(df) * pct)
metrics['~~~~~~'] = blank
metrics['Payoff Ratio'] = _stats.payoff_ratio(df)
metrics['Profit Factor'] = _stats.profit_factor(df)
metrics['Common Sense Ratio'] = _stats.common_sense_ratio(df)
metrics['CPC Index'] = _stats.cpc_index(df)
metrics['Tail Ratio'] = _stats.tail_ratio(df)
metrics['Outlier Win Ratio'] = _stats.outlier_win_ratio(df)
metrics['Outlier Loss Ratio'] = _stats.outlier_loss_ratio(df)
# returns
metrics['~~'] = blank
today = _dt.today()
metrics['MTD %'] = _stats.comp(
df[df.index >= _dt(today.year, today.month, 1)]) * pct
d = today - _td(3 * 365 / 12)
metrics['3M %'] = _stats.comp(
df[df.index >= _dt(d.year, d.month, d.day)]) * pct
d = today - _td(6 * 365 / 12)
metrics['6M %'] = _stats.comp(
df[df.index >= _dt(d.year, d.month, d.day)]) * pct
metrics['YTD %'] = _stats.comp(df[df.index >= _dt(today.year, 1, 1)]) * pct
d = today - _td(12 * 365 / 12)
metrics['1Y %'] = _stats.comp(
df[df.index >= _dt(d.year, d.month, d.day)]) * pct
metrics['3Y (ann.) %'] = _stats.cagr(
df[df.index >= _dt(today.year - 3, today.month, today.day)]) * pct
metrics['5Y (ann.) %'] = _stats.cagr(
df[df.index >= _dt(today.year - 5, today.month, today.day)]) * pct
metrics['10Y (ann.) %'] = _stats.cagr(
df[df.index >= _dt(today.year - 10, today.month, today.day)]) * pct
metrics['All-time (ann.) %'] = _stats.cagr(df) * pct
# best/worst
if mode.lower() == 'full':
metrics['~~~'] = blank
metrics['Best Day %'] = _stats.best(df) * pct
metrics['Worst Day %'] = _stats.worst(df) * pct
metrics['Best Month %'] = _stats.best(df, aggregate='M') * pct
metrics['Worst Month %'] = _stats.worst(df, aggregate='M') * pct
metrics['Best Year %'] = _stats.best(df, aggregate='A') * pct
metrics['Worst Year %'] = _stats.worst(df, aggregate='A') * pct
# dd
metrics['~~~~'] = blank
for ix, row in dd.iterrows():
metrics[ix] = row
metrics['Recovery Factor'] = _stats.recovery_factor(df)
metrics['Ulcer Index'] = _stats.ulcer_index(df, rf)
# win rate
if mode.lower() == 'full':
metrics['~~~~~'] = blank
metrics['Avg. Up Month %'] = _stats.avg_win(df, aggregate='M') * pct
metrics['Avg. Down Month %'] = _stats.avg_loss(df, aggregate='M') * pct
metrics['Win Days %%'] = _stats.win_rate(df) * pct
metrics['Win Month %%'] = _stats.win_rate(df, aggregate='M') * pct
metrics['Win Quarter %%'] = _stats.win_rate(df, aggregate='Q') * pct
metrics['Win Year %%'] = _stats.win_rate(df, aggregate='A') * pct
if mode.lower() == "full" and "benchmark" in df:
metrics['~~~~~~~'] = blank
greeks = _stats.greeks(df['returns'], df['benchmark'])
metrics['Beta'] = [str(round(greeks['beta'], 2)), '-']
metrics['Alpha'] = [str(round(greeks['alpha'], 2)), '-']
# prepare for display
for col in metrics.columns:
try:
metrics[col] = metrics[col].astype(float).round(2)
if display or "internal" in kwargs:
metrics[col] = metrics[col].astype(str)
except Exception:
pass
if (display or "internal" in kwargs) and "%" in col:
metrics[col] = metrics[col] + '%'
metrics['Longest DD Days'] = _pd.to_numeric(
metrics['Longest DD Days']).astype('int')
metrics['Avg. Drawdown Days'] = _pd.to_numeric(
metrics['Avg. Drawdown Days']).astype('int')
if display or "internal" in kwargs:
metrics['Longest DD Days'] = metrics['Longest DD Days'].astype(str)
metrics['Avg. Drawdown Days'] = metrics[
'Avg. Drawdown Days'].astype(str)
metrics.columns = [
col if '~' not in col else '' for col in metrics.columns
]
metrics.columns = [
col[:-1] if '%' in col else col for col in metrics.columns
]
metrics = metrics.T
if "benchmark" in df:
metrics.columns = ['Strategy', 'Benchmark']
else:
metrics.columns = ['Strategy']
if display:
print(_tabulate(metrics, headers="keys", tablefmt='simple'))
return
if not sep:
metrics = metrics[metrics.index != '']
return metrics
def __init__(self,
uvfitsfile,
telescope=None,
vsys=0,
distance=0,
endian=None,
**kwargs):
"""
Reads the uvfits and calculates useful things, e.g. u,v,w,
phase and amplitude
.byteswap().newbyteorder() is applied in various places to
convert to little endian
"""
f = pfopen(uvfitsfile, **kwargs)
self.loadendian = endian
if f[0].header['NAXIS1'] != 0:
print "error: this file may not be a UV FITS."
raise FileError('File format error.')
#~ f.info()
try:
self.hdu = f[0]
except:
print "error: cannot open uv data HDU."
self.hdr = self.hdu.header
self.data = self.hdu.data
if self.hdr['NAXIS4'] > 1:
self.datatype = ('CUBE', 3)
else:
self.datatype = ('IMAGE', 2)
# find spectral axis
axis_types = self.WCS.get_axis_types()
ax_types = np.array([i['coordinate_type'] for i in axis_types])
try:
spec_axis = ('spectral' == ax_types).nonzero()[0][0]
freq = self.hdu.header['CRVAL{0}'.format(spec_axis + 1)]
# assumes the frequency given in Hz
self.freq = freq * un.Hz
except (IndexError):
print('No spectral axis in header.')
spec_axis = -1
self.freq = None
if 'RESTFREQ' in self.hdu.header.keys():
self.restfreq = self.hdu.header['RESTFREQ']
self.restfreq_unit = self.hdu.header['RESTFREQ'] * u.Hz
else:
raise StandardError('No restfrequency found, NEED it!')
#TODO : Read in velocity and frequency array if present
"""
The standard unit is to give UU and VV in seconds (??!?)
So we have to convert to whatever we want.
"""
# standard storing unit here is kilo-lambdas
# save a million lines of code!
u.add_enabled_equivalencies(lambdas_equivalencies(self.restfreq_unit))
self.u = (self.data.par('UU') * u.s).to(klambdas)
self.v = (self.data.par('VV') * u.s).to(klambdas)
self.w = (self.data.par('WW') * u.s).to(klambdas)
self.uvdist = sqrt(self.u.value**2 + self.v.value**2) * klambdas
# BASELINE
self.baseline = self.hdu.data.par('BASELINE').byteswap().newbyteorder()
# DATES
self.jdate = self.hdu.data.par('DATE')
# set date to 1900, Jan, 01, 01:00:00 if date before before this
self.jdate = self.jdate.clip(2415020.5)
self.date = _sp.array([jd2gd(i) for i in self.jdate])
self.date0 = self.date.transpose()
fields = ['year', 'month', 'day', 'hour', 'minute', 'sec']
self.date1 = {key: value for key, value in zip(fields, self.date0)}
# convert to datetime objects
# LOSES the sub-second resolution
self.date2 = [
_dt(int(i[0]), int(i[1]), int(i[2]), int(i[3]), int(i[4]),
int(i[5])) for i in self.date
]
# get number of tracks
# TODO : rough hack, separate track if diff day is >1
tmp = _sp.where(_sp.diff(_sp.unique(self.jdate.round(0))) > 1)[0]
self.ntracks = len(tmp) + 1
################################################################
# NB : need to streamline this.
# only load the complex visibilities, into a complex array
# AND then work on that
# COMPLEX VISIBILITY
visi_index = len(self.data.parnames)
if self.hdu.header['NAXIS'] == 7:
self.visdata = self.data.par(
visi_index)[:, 0, 0, 0, 0, 0, :].byteswap().newbyteorder()
#~ self.visdata = self.hdu.data.data[:,0,0,0,0,0,:]
elif self.hdu.header['NAXIS'] == 6:
self.visdata = self.data.par(
visi_index)[:, 0, 0, 0, 0, :].byteswap().newbyteorder()
# load the re, im and weight arrays
self.re, self.im, self.wt = self.visdata[:, :].T
#~ self.re = self.visdata[:,0][:]
#~ self.im = self.visdata[:,1][:]
#~ self.wt = self.visdata[:,2][:]
# complex numbers
#~ self.comp = self.visdata[:,:2].astype(_np.float64).view(_np.complexfloating)
#~ self.comp = 1j*self.visdata[:,1][:]
#~ self.comp += self.visdata[:,0][:]
#~ self.comp = self.visdata[:,:2].astype(_np.float).view(_np.complex)
# below seems a bit dependent...
self.cvisi = self.visdata[:, :2].astype(_np.float).view(
_np.complex).T[0]
"""
with complex array, you can do
amp = np.abs(vis)
np.angle(vis)
vis.real
vis.imag
"""
# the data is not shifted
self.isshifted = (False, [0, 0])
# AMPLITUDE
self.amp = sqrt(self.re**2 + self.im**2)
# PHASE
self.pha = arctan2(self.im, self.re)
self.pha_deg = self.pha / pi * 180.
# ERROR / SIGMA
#TODO : check
# following 1.0e6 is just for GILDAS, change if needed
#~ print('NB : Error calculated from weights assuming GILDAS '
#~ 'data (i.e. frequencies in MHz).')
self.sigma_alt = 1 / sqrt(self.wt * 1.0e6)
# Daniels way of calculating sigma
# test this first
self.sigma = _sp.sqrt(0.5 / (self.wt * float(self.amp.shape[0])))