def gen_fit_df(ts_start, ts_end, varnames, timeshifts, pointcode=71699):
""" timeshifts must be integer number of hours. Posetive values only,
dataframe contains columns with the variables minus their value
'timeshift' hours before. """
df = pd.DataFrame()
df['prod'] = sq.fetch_production(ts_start, ts_end)
for timeshift in timeshifts:
df['prod%ihbefore'%timeshift] = sq.fetch_production(h_hoursbefore(ts_start, timeshift),\
h_hoursbefore(ts_end, timeshift))
for v in varnames:
ens_mean = ens.load_ens_mean_avail_at10_series(v, ts_start, ts_end, pointcode=71699)
ens_mean_before = ens.load_ens_mean_avail_at10_series(v,\
h_hoursbefore(ts_start, timeshift),\
h_hoursbefore(ts_end, timeshift),\
pointcode=71699)
df['%s%ihdiff'%(v,timeshift)] = ens_mean - ens_mean_before
return df
def gen_fit_df(ts_start, ts_end, varnames, timeshifts, pointcode=71699):
""" timeshifts must be integer number of hours. Posetive values only,
dataframe contains columns with the variables minus their value
'timeshift' hours before. """
df = pd.DataFrame()
df['prod'] = sq.fetch_production(ts_start, ts_end)
for timeshift in timeshifts:
df['prod%ihbefore'%timeshift] = sq.fetch_production(h_hoursbefore(ts_start, timeshift),\
h_hoursbefore(ts_end, timeshift))
for v in varnames:
ens_mean = ens.load_ens_mean_avail_at10_series(v,
ts_start,
ts_end,
pointcode=71699)
ens_mean_before = ens.load_ens_mean_avail_at10_series(v,\
h_hoursbefore(ts_start, timeshift),\
h_hoursbefore(ts_end, timeshift),\
pointcode=71699)
df['%s%ihdiff' % (v, timeshift)] = ens_mean - ens_mean_before
return df
from model_selection import gen_all_combinations, rmse, mae, mape
import sql_tools as sq
import ensemble_tools as ens
#%% SVR experinment
ts = ens.gen_hourly_timesteps(dt.datetime(2016,1,26,1), dt.datetime(2016,4,1,0))
X = pd.read_pickle('48h60h168h_lagged_X.pkl') # run model_selection_ext_horizon to generate these files
y = pd.read_pickle('prod_to_gowith.pkl')
# add more predictor data:
for v in ['Tout', 'vWind', 'hum', 'sunRad']:
X[v] = ens.load_ens_mean_avail_at10_series(v, ts[0], ts[-1], pointcode=71699)
#X['weekdays'] = [t.weekday() for t in ts]
def h_hoursbefore(timestamp, h):
return timestamp + dt.timedelta(hours=-h)
most_recent_avail_prod = sq.fetch_production(h_hoursbefore(ts[0], 24),\
h_hoursbefore(ts[-1], 24))
for i, t, p48 in zip(range(len(most_recent_avail_prod)), ts, X['prod48hbefore']):
if t.hour > 8 or t.hour == 0:
most_recent_avail_prod[i] = p48
X['prod24or48hbefore'] = most_recent_avail_prod
##
from model_selection import gen_all_combinations, rmse, mae, mape
import sql_tools as sq
import ensemble_tools as ens
#%% SVR experinment
ts = ens.gen_hourly_timesteps(dt.datetime(2016, 1, 26, 1),
dt.datetime(2016, 4, 1, 0))
X = pd.read_pickle('48h60h168h_lagged_X.pkl'
) # run model_selection_ext_horizon to generate these files
y = pd.read_pickle('prod_to_gowith.pkl')
# add more predictor data:
for v in ['Tout', 'vWind', 'hum', 'sunRad']:
X[v] = ens.load_ens_mean_avail_at10_series(v,
ts[0],
ts[-1],
pointcode=71699)
#X['weekdays'] = [t.weekday() for t in ts]
def h_hoursbefore(timestamp, h):
return timestamp + dt.timedelta(hours=-h)
most_recent_avail_prod = sq.fetch_production(h_hoursbefore(ts[0], 24),\
h_hoursbefore(ts[-1], 24))
for i, t, p48 in zip(range(len(most_recent_avail_prod)), ts,
X['prod48hbefore']):
if t.hour > 8 or t.hour == 0:
most_recent_avail_prod[i] = p48
X['prod24or48hbefore'] = most_recent_avail_prod
