def _correct(self, df, cache=True):
"""
This function is called by convert_measured_to_actual and is NOT meant to be called directly!
It takes a pandas dataframe that all have the same star
"""
# Group by instrument and addmode, and get the PDF for the actual temperature for each
df = df.dropna(subset=['Tmeas'])
if len(df) == 0:
df['Corrected_Temperature'] = np.nan
df['T_uperr'] = np.nan
df['T_lowerr'] = np.nan
return df[['Star', 'Corrected_Temperature', 'T_uperr', 'T_lowerr']].copy()
groups = df.groupby(('Instrument', 'addmode'))
Probabilities = []
for (inst, addmode), group in groups:
# Make a fitter instance
d = {'instrument': inst,
'directory': self._caldir[inst],
'addmode': addmode}
key = (inst, addmode)
fitter = self._fitters[inst]()
# get/set the cache
if key in self._chainCache:
chain, probs = self._chainCache[key]
Tpredictions = self._predictionCache[key]
fitter.spoof_sampler(chain, probs)
else:
chain = np.loadtxt(self._flatchain_format.format(**d))
probs = np.loadtxt(self._flatlnprob_format.format(**d))
fitter.spoof_sampler(chain, probs)
Ta_arr = np.arange(2000, 12000, 2.0)
Tmeas_pred = fitter.predict(Ta_arr, N=10000)
Tpredictions = pd.DataFrame(Tmeas_pred, columns=Ta_arr)
if cache:
self._chainCache[key] = (chain, probs)
self._predictionCache[key] = Tpredictions
# Get the PDF (probability distribution function)
Tmeas = group['Tmeas'].values
Tmeas_err = group['Tmeas_err'].values
for Tm, Tm_err in zip(Tmeas, Tmeas_err):
temperature, probability = CCF_Systematics.get_actual_temperature(fitter, Tm, Tm_err,
cache=Tpredictions,
summarize=False)
Probabilities.append(probability / probability.sum())
# Multiply all the PDFs
Prob = np.array(Probabilities).prod(axis=0)
# Summarize the PDF (similar interface to np.percentile)
l, m, h = integral(temperature, Prob, [0.16, 0.5, 0.84], k=0)
# Save in a Pandas DataFrame and return
return pd.DataFrame(data={'Star': df['Star'].values[0], 'Corrected_Temperature': m,
'T_uperr': h - m, 'T_lowerr': m - l}, index=[0])
def get_measured_temperature(self, starname, date, Tmax, instrument=None,
N=7, addmode='simple', feh=None, vsini=None):
"""
Get the measured temperature by doing a weighted sum over temperatures
near the given one (which I find by hand)
Parameters:
===========
- starname: string
The name of the star
- date: string
The date the observation was taken
- Tmax: float
The temperature to search near
- instrument: string
The instrument used (this function automatically finds it if not given)
- N: integer
The number of temperature points to take
- addmode: string
The way the individual order CCFs were co-added.
- feh: float
The metallicity to use. If not given, it finds whatever gives the highest ccf peak.
- vsini: float
The vsini to use. If not given, it finds whatever gives the highest ccf peak.
Returns:
========
A pandas DataFrame with the starname, date, instrument, and
model parameters for the temperatures near the requested one.
"""
if instrument is None:
# Find this star/date in all of the interfaces
found = False
df_list = []
for inst in self._interfaces.keys():
interface = self._interfaces[inst]
if starname in interface.list_stars() and date in interface.list_dates(starname):
found = True
df = self.get_measured_temperature(starname, date, Tmax, instrument=inst, N=N)
df_list.append(df)
if not found:
warnings.warn('Star ({}) not found for date ({}) in any CCF interfaces!'.format(starname, date))
return None
return pd.concat(df_list, ignore_index=True)
# Check that the star/date combination are in the requested interface
if starname not in self._interfaces[instrument].list_stars():
raise KeyError('Star ({}) not in instrument ({})'.format(starname, instrument))
if date not in self._interfaces[instrument].list_dates(starname):
# Try date +/- 1 before failing (in case of civil/UT date mismatch or something)
from datetime import datetime, timedelta
year, month, day = [int(s) for s in date.split('-')]
for inc in [-1, 1]:
t = datetime(year, month, day) + timedelta(inc)
test_date = '{}-{:02d}-{:02d}'.format(t.year, t.month, t.day)
if test_date in self._interfaces[instrument].list_dates(starname):
return self.get_measured_temperature(starname, test_date, Tmax,
instrument=instrument, N=N, addmode=addmode)
raise KeyError(
'Date ({}) not in CCF interface for star {} and instrument {}'.format(date, starname, instrument))
# Get CCF information from the requested instrument/star/date combo
interface = self._interfaces[instrument]
logging.info('{}, {}, {}, {}'.format(starname, date, instrument, addmode))
df = interface._compile_data(starname=starname, date=date, addmode=addmode, read_ccf=True)
#df['ccf_max'] = df.ccf.map(np.max) Already done now
# Get the parameters and RV of the CCF with the highest peak (which has temperature = Tmax)
requested = df.loc[df['T'] == Tmax]
if feh is not None:
requested = requested.loc[requested['[Fe/H]'] == feh]
if vsini is not None:
requested = requested.loc[requested['vsini'] == vsini]
i = np.argmax(requested.ccf_max)
vsini = requested.loc[i, 'vsini'].item()
metal = requested.loc[i, '[Fe/H]'].item()
logg = requested.loc[i, 'logg'].item()
idx = requested.loc[i, 'ccf'].argmax()
rv = interface.velocities[idx]
# Now, get the CCF height for the N/2 temperatures on either side of Tmax
N = roundodd(N)
d = defaultdict(list)
for T in np.arange(Tmax - 100 * (N - 1) / 2, Tmax + 100 * (N - 1) / 2 + 1, 100):
requested = df.loc[(df['T'] == T) & (df.vsini == vsini) &
(df['[Fe/H]'] == metal) & (df.logg == logg)]
if len(requested) == 0:
warnings.warn('No matches for T = {} with star/date = {}/{}!'.format(T, starname, date))
d['Star'].append(starname)
d['Date'].append(date)
d['Instrument'].append(instrument)
d['Temperature'].append(T)
d['vsini'].append(vsini)
d['logg'].append(logg)
d['[Fe/H]'].append(metal)
d['rv'].append(rv)
d['CCF'].append(np.nan)
d['significance'].append(np.nan)
continue
if len(requested) > 1:
requested = requested.sort_values(by='ccf_max').tail(1)
# Save the best parameters for this temperature
d['Star'].append(starname)
d['Date'].append(date)
d['Instrument'].append(instrument)
d['Temperature'].append(T)
d['vsini'].append(requested['vsini'].item())
d['logg'].append(requested['logg'].item())
d['[Fe/H]'].append(requested['[Fe/H]'].item())
idx = np.argmin(np.abs(interface.velocities - rv))
d['rv'].append(rv)
ccf = requested['ccf'].item()
d['CCF'].append(ccf[idx])
# Measure the detection significance
std = mad(ccf)
mean = np.median(ccf)
d['significance'].append((d['CCF'][-1] - mean) / std)
# Do the weighted sum.
summary = CCF_Systematics.get_Tmeas(pd.DataFrame(data=d), include_actual=False)
# Put the star, date, and instrument back in the dataframe before returning
summary['Star'] = starname
summary['Date'] = date
summary['Instrument'] = instrument
summary['addmode'] = addmode
return summary