hostname = "VIEWSHOST"
connectstring = dbutils.make_connectstring(prefix, db, uname, hostname, port)
rf_500 = RandomForestClassifier(n_estimators = 500, n_jobs=10)
scaler = StandardScaler()
pipe_rf_500 = Pipeline([
('scaler', scaler),
('rf', rf_500)])
output_schema = "landed_test"
output_table = "osa_pgm_acled_meanhist_fcast_calib_sb"
models = [
{
"dir_pickles": "$SNIC_TMP/osa/pickles/osa_pgm_acled_meanhist_fcast_calib_sb/pgm_acled_meanhist_fcast_calib_logit_fullsample_sb",
"estimator": SMLogit(),
"features": [
"l2_ged_dummy_sb",
"l3_ged_dummy_sb",
"l4_ged_dummy_sb",
"l5_ged_dummy_sb",
"l6_ged_dummy_sb",
"l7_ged_dummy_sb",
"l8_ged_dummy_sb",
"l9_ged_dummy_sb",
"l10_ged_dummy_sb",
"l11_ged_dummy_sb",
"l12_ged_dummy_sb",
"q_1_1_l2_ged_dummy_sb",
"q_1_1_l3_ged_dummy_sb",
"l1_ged_dummy_sb",
port = "5432"
hostname = "VIEWSHOST"
connectstring = dbutils.make_connectstring(prefix, db, uname, hostname, port)
rf_500 = RandomForestClassifier(n_estimators=500, n_jobs=10)
scaler = StandardScaler()
pipe_rf_500 = Pipeline([('scaler', scaler), ('rf', rf_500)])
output_schema = "landed_test"
output_table = "osa_cm_acled_base_fcast_test_os"
models = [{
"dir_pickles":
"$SNIC_TMP/osa/pickles/osa_cm_acled_base_fcast_test_os/cm_acled_base_fcast_test_logit_fullsample_os",
"estimator":
SMLogit(),
"features": [
"l2_ged_dummy_os", "l3_ged_dummy_os", "l4_ged_dummy_os",
"l5_ged_dummy_os", "l6_ged_dummy_os", "l7_ged_dummy_os",
"l8_ged_dummy_os", "l9_ged_dummy_os", "l10_ged_dummy_os",
"l11_ged_dummy_os", "l12_ged_dummy_os", "l1_ged_dummy_sb",
"l1_ged_dummy_ns", "l1_ged_dummy_os", "l1_acled_dummy_pr",
"decay_12_cw_ged_dummy_sb_0", "decay_12_cw_ged_dummy_ns_0",
"decay_12_cw_ged_dummy_os_0", "decay_12_cw_acled_dummy_pr_0",
"fvp_lngdpcap_nonoilrent", "fvp_lngdpcap_oilrent",
"fvp_grgdpcap_oilrent", "fvp_grgdpcap_nonoilrent", "ln_fvp_timeindep",
"ln_fvp_timesincepreindepwar", "ln_fvp_timesinceregimechange",
"fvp_demo", "fvp_semi", "fvp_prop_excluded", "ln_fvp_population200",
"ssp2_edu_sec_15_24_prop", "ssp2_urban_share_iiasa"
],
"forecast_end":
"l11_acled_count_pr", "l12_acled_count_pr", "decay_12_cw_ged_dummy_sb_0",
"decay_12_cw_ged_dummy_ns_0", "decay_12_cw_ged_dummy_os_0",
"l1_ged_dummy_os", "l2_ged_dummy_os", "l3_ged_dummy_os", "l4_ged_dummy_os",
"l5_ged_dummy_os", "l6_ged_dummy_os", "l7_ged_dummy_os", "l8_ged_dummy_os",
"l9_ged_dummy_os", "l10_ged_dummy_os", "l11_ged_dummy_os",
"l12_ged_dummy_os", "q_1_1_l1_ged_dummy_sb", "q_1_1_l1_ged_dummy_ns",
"q_1_1_l1_ged_dummy_os", "q_1_1_l2_ged_dummy_os", "q_1_1_l3_ged_dummy_os",
"ln_bdist3", "ln_ttime", "ln_capdist", "ln_pop", "ln_dist_diamsec",
"ln_dist_petroleum", "gcp_li_mer", "imr_mean", "mountains_mean",
"urban_ih_li", "excluded_dummy_li", "agri_ih_li", "barren_ih_li",
"forest_ih_li", "savanna_ih_li", "shrub_ih_li", "pasture_ih_li"
]
logit_canon_full_train_sb = {
'name': 'logit_canon_full_train_sb',
'estimator': SMLogit(),
'outcome': 'ged_dummy_sb',
'features': features_canon_sb,
'steps': steps,
'share_zeros_keep': share_zeros_full,
'share_ones_keep': share_ones_full,
'train_start': train_start_canon,
'train_end': train_end_train,
'forecast_start': predict_start_train,
'forecast_end': predict_end_train,
'table': table_input
}
logit_canon_full_calib_sb = {
'name': 'logit_canon_full_calib_sb',
'estimator': SMLogit(),
