def simqso_test():
# --------------------------------------------------------------------------
# Preparing the feature matrix
# --------------------------------------------------------------------------
df_train = pd.read_hdf('../class_photoz/data/brightqsos_sim_2k_new.hdf5',
'data')
passband_names = [\
'SDSS_u','SDSS_g','SDSS_r','SDSS_i','SDSS_z', \
# 'TMASS_j','TMASS_h','TMASS_k', \
'WISE_w1','WISE_w2', \
# 'WISE_w3' \
]
for name in passband_names:
df_train.rename(columns={'obsFlux_' + name: name}, inplace=True)
df_train.rename(columns={'obsFluxErr_' + name: 'sigma_' + name},
inplace=True)
df_train.replace(np.inf, np.nan, inplace=True)
# df_train.query('obsMag_SDSS_i <= 18.5',inplace=True)
df_train, features = qs.prepare_flux_ratio_catalog(df_train,
passband_names)
# --------------------------------------------------------------------------
# Random Forest Regression Grid Search
# --------------------------------------------------------------------------
features = ['SDSS_i', 'WISE_w1', 'ug', 'gr', 'ri', 'iz', 'zw1', 'w1w2']
# features = ['SDSS_i','ug','gr','ri','iz']
label = 'z'
rand_state = 1
params = {
'n_estimators': 300,
'max_depth': 20,
'min_samples_split': 4,
'n_jobs': 2,
'random_state': rand_state
}
rf.rf_reg_example(df_train,
features,
label,
params,
rand_state,
save=True,
save_filename='rf_sim_sdssw1w2')
def dr7dr12_test():
# --------------------------------------------------------------------------
# Preparing the feature matrix
# --------------------------------------------------------------------------
df_train = pd.read_hdf('../class_photoz/data/DR7DR12Q_clean_flux_cat.hdf5',
'data')
passband_names = [\
'SDSS_u','SDSS_g','SDSS_r','SDSS_i','SDSS_z', \
# 'TMASS_j','TMASS_h','TMASS_k', \
'WISE_w1','WISE_w2', \
# 'WISE_w3' \
]
df_train.replace(np.inf, np.nan, inplace=True)
df_train = df_train.query('0 < Z_VI < 10')
# df_train.query('SDSS_mag_i <= 18.5',inplace=True)
df_train, features = qs.prepare_flux_ratio_catalog(df_train,
passband_names)
# --------------------------------------------------------------------------
# Random Forest Regression Grid Search
# --------------------------------------------------------------------------
features = ['SDSS_i', 'WISE_w1', 'ug', 'gr', 'ri', 'iz', 'zw1', 'w1w2']
# features = ['SDSS_i','ug','gr','ri','iz']
label = 'Z_VI'
rand_state = 1
params = {
'n_estimators': 300,
'max_depth': 20,
'min_samples_split': 2,
'n_jobs': 2,
'random_state': rand_state
}
print df_train.shape[0]
rf.rf_reg_example(df_train,
features,
label,
params,
rand_state,
save=True,
save_filename='rf_sdssw1w2')
def test_example():
# --------------------------------------------------------------------------
# Preparing the feature matrix
# --------------------------------------------------------------------------
df_train = pd.read_hdf('../class_photoz/data/DR7DR12Q_clean_flux_cat.hdf5',
'data')
# df_train = pd.read_hdf('../class_photoz/data/brightqsos_sim_2k.hdf5','data')
passband_names = [\
'SDSS_u','SDSS_g','SDSS_r','SDSS_i','SDSS_z', \
# 'TMASS_j','TMASS_h','TMASS_k', \
'WISE_w1','WISE_w2', \
# 'WISE_w3' \
]
df_train.replace(np.inf, np.nan, inplace=True)
df_train.query('10 > Z_VI > 0.0 and PSFMAG_I < 18.5', inplace=True)
df_train, features = qs.prepare_flux_ratio_catalog(df_train,
passband_names)
# df_train = df_train.sample(frac=0.5)
# --------------------------------------------------------------------------
# Random Forest Regression Grid Search
# --------------------------------------------------------------------------
features = ['SDSS_i', 'WISE_w1', 'ug', 'gr', 'ri', 'iz', 'zw1', 'w1w2']
# features = ['SDSS_i','WISE_w1','TMASS_j','ug','gr','ri','iz','zj','jh', 'hk', 'kw1', 'w1w2']
label = 'z'
rand_state = 1
params = {
'n_estimators': 200,
'max_depth': 25,
'min_samples_split': 2,
'n_jobs': 2,
'random_state': rand_state,
}
rf.rf_reg_example(df_train,
features,
label,
params,
rand_state,
save=True,
save_filename='test')