constants.py

from enum import Enum
import socket

class Method(Enum):
    PERFECT = 8
    TRIVIAL = 0
    # ORIGINAL = 1       #full ipd
    SM_GREEDY_TOPK = 2
    SM_HET_GREEDY_TOPK = 3
    SM_BEST_FIRST = 4
    SM_BEAM_SEARCH = 5
    SM_HET_BEAM_SEARCH = 6
    # PREDEFINED = 7     #subspaces up to optimal

    PREDEFINED_SUBSPACESETS = 9 # # the subspace sets gradually increase number of dimensions in one of the subspaces chosen randomly; subspace sets are chosen with a step of 2
    PREDEFINED_SUBSPACESETS_SYNCHRONOUS_GREEDY = 13 # the subspace sets gradually increase number of dimensions in all the subspaces; if a subspace has been used up, it extends to irrelevant dimensions
    PREDEFINED_SUBSPACESETS_SYNCHRONOUS_OPTIMAL = 14 # the subspace sets gradually increase number of dimensions in all the subspaces; if a subspace has been used up, it stays the same
    PREDEFINED_SUBSPACESETS_NAIVE = 15

    PREDEFINED_OPTIMAL_SUBSPACESET = 10
    PREDEFINED_OPTIMAL_SUBSPACESET_AND_IRRELEVANT = 11
    FULL = 12


class CorrelationMeasure(Enum):
    UDS = 1
    CMI = 2
    MAC = 3


class DistanceMeasure(Enum):
    ID = 1
    CJS = 2


class InteractionType(Enum):
    CUBES = 1
    XOR = 2


ID_THRESHOLD_QUANTILE = 0.3
ID_SLIDING_WINDOW = 40

NORMALIZATION_RADIUS = 1

FILE_DATA_OUTPUT = "out.arff"
FILE_DATA_CUTS = 'cut.txt'
FILE_NAME_PATTERN = '(?:.*/)*(.*)$'

# subspace mining parameters
MAX_SUBSPACE_SIZE = 5
HETEROGENEOUS_THRESHOLD=0.8
BEAM_WIDTH=4

# cjs
CLUMP = 2
MAXMAX = 5

SUBSPACE_SET_STEP = 2

# class Environment(Enum):
#     TEST = 1
#     PRODUCTION = 2
#
# ENVIRONMENT = Environment.TEST

# todo change later
TRIVIAL_BINS_COUNT = 5

# old settings
IRRELEVANT_FEATURES = 4 if socket.gethostname() != 'push' else 100

RELEVANT_FEATURES_UPPER_BOUND=3 if socket.gethostname() != 'push' else 31
RELEVANT_FEATURES_LOWER_BOUND=2

INTERACTIONS_UPPER_BOUND=4 if socket.gethostname() != 'push' else 11
INTERACTIONS_LOWER_BOUND=3 if socket.gethostname() != 'push' else 1

# new settings (more constrained)
INTERACTION_TYPE_RANGE_LIST=[InteractionType.CUBES, InteractionType.XOR]
IRRELEVANT_FEATURES_RANGE_LIST = [0, 1, 2, 4, 8, 16, 32, 64, 99, 3, 6, 12, 24, 48, 82] if socket.gethostname() != 'push' else [0, 1, 2, 3]
RELEVANT_FEATURES_RANGE_LIST = [2, 3, 4, 6, 8, 12, 16, 23, 30] if socket.gethostname() == 'push' else [7]
INTERACTION_NUMBER_RANGE_LIST = [1, 2, 4, 8, 10] if socket.gethostname() == 'push' else [3]
PARTITION_TYPES_RANGE_LIST=["c", 'i', "io"] if socket.gethostname() == 'push' else ['i']
CUBES_LOWER_BOUND=1
CUBES_UPPER_BOUND=3
NAIVE_CHUNKS_NUMBER_RANGE_LIST = [2, 3, 4, 5, 10, 20, 30]
XOR_SIGMA=0.1


BASE = '/local/tmp/ipd_extended_experiments2/' if socket.gethostname() == 'push' \
    else '/Users/tatyanadembelova/Documents/study/thesis/ipd_extended/'

DATA_DIR = BASE + 'new_cubes/'
PERFECT_DISCRETIZATIONS_DIR = BASE + 'ideal_disc/'
PERFECT_SUBSPACES_JSON = BASE + 'ideal_subspaces.json'

SLIM_BASE = ("/Users/tatyanadembelova/Documents/study/thesis/" if socket.gethostname() != 'push' else BASE) + "code-fic/"
SLIM_DATA_DIR = SLIM_BASE + "data/"
SLIM_BIN = SLIM_BASE + "branches/slim/trunk/fic"
SLIM_COMPRESS_CONF = SLIM_BASE + "branches/slim/trunk/compress.conf"
SLIM_CONVERT_CONF = SLIM_BASE + "branches/slim/trunk/convertdb.conf"

PRECISION_RECALL_FILENAME = "Precision_recall_runtime.csv"
COMPRESSION_FILENAME = "Compression.csv"

WEKA_BIN = "/local/tmp/ipd_extended_experiments2/weka/weka-3-9-1/weka.jar" if socket.gethostname() == 'push' else "/Users/tatyanadembelova/Downloads/weka-3-9-1/weka.jar"