parser.add_argument('--sep_cb_type', action='store_true', default=False) parser.add_argument('--sep_name', action='store_true', default=False) parser.add_argument('--granular', action='store_true', default=False) parser.add_argument('--sep_lr', action='store_true', default=False) parser.add_argument('--all_algos', action='store_true', default=False) parser.add_argument('--keep_datasets', action='store_true', default=False, help='keeps comparing on all datasets at each iteration') parser.add_argument('--reduce_algo', action='store_true', default=False) parser.add_argument('--filter_algos', default=None) parser.add_argument('--interactive', action='store_true', default=False) parser.add_argument('--interactive_norank', action='store_true', default=False) args = parser.parse_args() if not args.reload: df = load_names(args.names.split(','), min_actions=None, ty='all' if args.sep_lr else 'best') # df = df.loc[df.algo.map(lambda x: x.startswith('epsilon:') or x.startswith('bag:'))] # df = df.loc[df.algo.map(lambda x: x in algo_list)].copy() # df = df.loc[df.na * df.nf > 200] if args.granular: df = preprocess_df_granular(df, sep_name=args.sep_name, sep_lr=args.sep_lr, all_algos=args.all_algos) else: df = preprocess_df(df, sep_reduction=args.sep_cb_type, sep_name=args.sep_name, reduce_algo=args.reduce_algo, filter_algos=args.filter_algos.split(',') if args.filter_algos else None) ds_ids = df.ds.unique() ds_to_sz = pickle.load(open('ds_sz.pkl')) if args.interactive_norank: sys.exit(0)
parser.add_argument('--opt_b', action='store_true', default=False) parser.add_argument('--enc', default='neg10') parser.add_argument('--b', default=None) parser.add_argument('--alpha', type=float, default=0.05) parser.add_argument('--seed', type=int, default=1337) parser.add_argument('--base_name', default='allrandfix') args = parser.parse_args() set_base_name(args.base_name) print(base_name()) names = [ '{}{}'.format(base_name(), name) for name in ['01', '01b', 'neg10', 'neg10b'] ] df = load_names(names, min_actions=None, min_size=None) df = preprocess_df_granular(df, all_algos=True, sep_enc=True, sep_b=not args.opt_b) enc_b_str = args.enc if not args.opt_b: if args.b is not None: enc_b_str += ':' + args.b else: enc_b_str += ':(b|nb)' ds_ids = df.ds.unique() np.random.seed(args.seed)
parser.add_argument('--noval', action='store_true', default=False) parser.add_argument('--uci', action='store_true', default=False) parser.add_argument('--base_name', default='allrandfix') args = parser.parse_args() set_base_name(args.base_name) print((base_name())) if args.avg_std_name and args.base_name.startswith('rcv1'): names = ['{}01'.format(base_name())] else: names = [ '{}{}'.format(base_name(), name) for name in ['01', '01b', 'neg10', 'neg10b'] ] df = load_names(names, use_cs=args.use_cs) # filters if args.min_actions is not None: df = df[df.na >= args.min_actions] if args.max_actions is not None: df = df[df.na <= args.max_actions] if args.min_features is not None: df = df[df.nf >= args.min_features] if args.max_features is not None: df = df[df.nf <= args.max_features] if args.min_size is not None: df = df[df.sz >= args.min_size] if args.max_size is not None: df = df[df.sz <= args.max_size] if args.min_refloss is not None:
parser.add_argument('--sep_name', action='store_true', default=False) parser.add_argument('--sep_enc', action='store_true', default=False) parser.add_argument('--sep_b', action='store_true', default=False) parser.add_argument('--algo', default=None) parser.add_argument('--name', default=None) parser.add_argument('--enc', default=None) parser.add_argument('--b', default=None) parser.add_argument('--cb_type', default=None) parser.add_argument('--alpha', default=0.05) parser.add_argument('--min_size', type=int, default=None) parser.add_argument('--diff', action='store_true', default=True) parser.add_argument('--nodiff', dest='diff', action='store_false') args = parser.parse_args() names = ['disagree01', 'disagree01b', 'disagreeneg10', 'disagreeneg10b'] df = load_names(names, min_actions=None, min_size=args.min_size) psi = '0.1' if args.granular_opt or args.all: df_all = preprocess_df_granular(df, all_algos=True) # optimized name print 'optimized over encoding/baseline' algs = [ 'epsilon:0:mtr', 'epsilon:0:dr', 'cover:16:psi:{}:nounif:dr'.format(psi), 'bag:16:mtr', 'bag:16:greedify:mtr', 'epsilon:0.02:mtr', 'cover:16:psi:{}:dr'.format(psi), 'epsilon:1:nounifa:c0:1e-06:dr' ] labels = [ 'G-{}'.format(MTR_LABEL), 'G-dr', 'C-nu', 'B', 'B-g',
args = parser.parse_args() set_base_name(args.base_name) if args.noval: val_dss = np.load('ds_val_list.npy') def filter_heldout(df): if args.noval: return df.loc[df.ds.map(lambda s: s not in val_dss)] else: return df if args.enc_910 or args.all: names = ['disagree910', 'disagree910b'] df = load_names(names, min_actions=None, use_cs=args.use_cs) df = filter_heldout(df) algs = [ 'epsilon:0:mtr', 'cover:4:psi:0.1:nounif:dr', 'bag:4:greedify:mtr' ] labels = ['G', 'C-nu', 'B-g'] df = preprocess_df_granular(df, algos=algs, sep_name=True) for i in range(3): scatterplot(df, [algs[i] + ':910', algs[i] + ':910b'], [labels[i] + ', 9/10', labels[i] + ', 9/10 + b'], args=args, fname='robust910_' + labels[i].lower()) if args.comp_granular or args.all: names = [
parser.add_argument('--all', action='store_true', default=False) parser.add_argument('--enc_910', action='store_true', default=False) parser.add_argument('--comp_granular', action='store_true', default=False) parser.add_argument('--bag_greedy', action='store_true', default=False) parser.add_argument('--baseline', action='store_true', default=False) parser.add_argument('--cover_nu', action='store_true', default=False) parser.add_argument('--active', action='store_true', default=False) parser.add_argument('--active_mtr', action='store_true', default=False) parser.add_argument('--greedy', action='store_true', default=False) parser.add_argument('--psi', default='0.1') parser.add_argument('--alpha', type=float, default=0.05) args = parser.parse_args() if args.enc_910 or args.all: names = ['disagree910', 'disagree910b'] df = load_names(names, min_actions=None) algs = [ 'epsilon:0:mtr', 'cover:16:psi:{}:nounif:dr'.format(args.psi), 'bag:16:greedify:mtr' ] labels = ['G-{}'.format(MTR_LABEL), 'C-nu', 'B-g'] df = preprocess_df_granular(df, algos=algs, sep_name=True) for i in range(3): scatterplot(df, [algs[i] + ':910b', algs[i] + ':910'], [labels[i] + ', 9/10 + b', labels[i] + ', 9/10'], args=args, fname='robust910_' + labels[i].lower()) if args.comp_granular or args.all: names = [