def create_rows_CG(depth, segments_set):
global TARGETS
global constraint_indicators
constraint_indicators = []
row_value = 0
row_names = []
row_values = []
row_right_sides = []
row_senses = ""
num_features = get_num_features()
data_size = get_data_size()
num_leafs = 2**depth
num_nodes = num_leafs - 1
big_M = get_max_value() - get_min_value()
constraint_indicators.append(row_value)
for i in range(num_features): #constraint (15), indicator 0
for j in range(num_nodes):
for l in get_left_leafs(j, num_nodes):
col_names = [
"segment_leaf_" + str(s) + "_" + str(l)
for s in range(len(segments_set[l]))
] #x_{l,s}
col_values = [
max([get_feature_value(r, i) for r in s])
for s in segments_set[l]
] #mu^{i,s} max
col_names.extend([
"node_feature_" + str(j) + "_" + str(i),
"node_constant_" + str(j)
])
col_values.extend([big_M, -1])
row_names.append("constraint_15_" + str(i) + "_" + str(j) +
"_" + str(l))
row_values.append([col_names, col_values])
row_right_sides.append(big_M)
row_senses = row_senses + "L"
row_value = row_value + 1
constraint_indicators.append(row_value)
for i in range(num_features): #constraint (16), indicator 1
for j in range(num_nodes):
for l in get_right_leafs(j, num_nodes):
col_names = [
"segment_leaf_" + str(s) + "_" + str(l)
for s in range(len(segments_set[l]))
] #x_{l,s}
col_values = [
-min([get_feature_value(r, i) for r in s])
for s in segments_set[l]
] #mu^{i,s} min
col_names.extend([
"node_feature_" + str(j) + "_" + str(i),
"node_constant_" + str(j)
])
col_values.extend([big_M, 1])
row_names.append("constraint_16_" + str(i) + "_" + str(j) +
"_" + str(l))
row_values.append([col_names, col_values])
row_right_sides.append(big_M + 0.01)
row_senses = row_senses + "L"
row_value = row_value + 1
constraint_indicators.append(row_value)
for r in range(data_size): #constraint (17), indicator 2
col_names, col_values = [], []
for l in range(num_leafs):
for s in range(len(segments_set[l])):
if r in segments_set[l][s]:
col_names.extend(["segment_leaf_" + str(s) + "_" + str(l)
]) #x_{l,s}
col_values.extend([1])
row_names.append("constraint_17_" + str(r))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "E"
row_value = row_value + 1
constraint_indicators.append(row_value)
for l in range(num_leafs): #constraint (18), indicator 3
col_names = [
"segment_leaf_" + str(s) + "_" + str(l)
for s in range(len(segments_set[l]))
] #x_{l,s}
col_values = [1 for s in range(len(segments_set[l]))] #x_{l,s}
row_names.append("constraint_18_" + str(l))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "E"
row_value = row_value + 1
constraint_indicators.append(row_value)
for r in range(data_size): #constraint (19), indicator 4
for l in range(num_leafs):
col_names, col_values = [], []
for s in range(len(segments_set[l])):
if r in segments_set[l][s]:
col_names.extend(["segment_leaf_" + str(s) + "_" + str(l)
]) #x_{l,s}
col_values.extend([1])
for t in range(get_num_targets()):
if TARGETS[t] != get_target(r):
col_names.extend(
["prediction_type_" + str(t) + "_" + str(l)])
col_values.extend([1])
col_names.extend(["row_error_" + str(r)])
col_values.extend([-1])
row_names.append("constraint_19_" + str(r) + "_" + str(l))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "L"
row_value = row_value + 1
constraint_indicators.append(row_value)
for l in range(num_leafs): #constraint (20), indicator 5
col_names = [
"prediction_type_" + str(s) + "_" + str(l)
for s in range(get_num_targets())
]
col_values = [1 for s in range(get_num_targets())]
row_names.append("constraint_20_" + str(l))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "E"
row_value = row_value + 1
constraint_indicators.append(row_value)
for j in range(num_nodes): #constraint (21), indicator 6
col_names = [
"node_feature_" + str(j) + "_" + str(i)
for i in range(num_features)
]
col_values = [1 for i in range(num_features)]
row_names.append("constraint_21_" + str(j))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "E"
row_value = row_value + 1
return row_names, row_values, row_right_sides, row_senses
def create_variables(depth, prob):
global VARS
var_value = 0
var_names = []
var_types = ""
var_lb = []
var_ub = []
var_obj = []
num_features = get_num_features()
data_size = get_data_size()
num_leafs = 2**depth
num_nodes = num_leafs - 1
# node n had a boolean test on feature f, boolean. On the paper: f_{i,j}
for j in range(num_nodes):
for i in range(num_features):
VARS["node_feature_" + str(j) + "_" + str(i)] = var_value
var_names.append("#" + str(var_value))
var_types = var_types + "B"
var_lb.append(0)
var_ub.append(1)
var_obj.append(0)
var_value = var_value + 1
# value used in the boolean test in node n, integer. On the paper: c_{j}
for j in range(num_nodes):
VARS["node_constant_" + str(j)] = var_value
var_names.append("#" + str(var_value))
if continuousconstant == 1:
var_types = var_types + "C"
else:
var_types = var_types + "I"
var_lb.append(get_min_value())
var_ub.append(get_max_value())
var_obj.append(0)
var_value = var_value + 1
# leaf l predicts type t, boolean. On the paper: p_{l,t}
for l in range(num_leafs):
for t in range(get_num_targets()):
VARS["prediction_type_" + str(t) + "_" + str(l)] = var_value
var_names.append("#" + str(var_value))
var_types = var_types + "B"
var_lb.append(0)
var_ub.append(1)
var_obj.append(0)
var_value = var_value + 1
# row error, variables to minimize. On the paper: e_{r}
for r in range(data_size):
VARS["row_error_" + str(r)] = var_value
var_names.append("#" + str(var_value))
var_types = var_types + "C"
var_lb.append(0)
var_ub.append(1)
var_obj.append(1)
var_value = var_value + 1
# indicates that data row r passes node j when executed in decision tree. Careful, leafs are included. On the paper: pt_{r,j}
for r in range(data_size):
for j in range(num_nodes):
VARS["path_node_" + str(j) + "_" + str(r)] = var_value
var_names.append("#" + str(var_value))
var_types = var_types + "B"
var_lb.append(0)
var_ub.append(1)
var_obj.append(0)
var_value = var_value + 1
for l in range(num_leafs):
VARS["path_leaf_" + str(l) + "_" + str(r)] = var_value
var_names.append("#" + str(var_value))
var_types = var_types + "B"
var_lb.append(0)
var_ub.append(1)
var_obj.append(0)
var_value = var_value + 1
return var_names, var_types, var_lb, var_ub, var_obj
def create_variables_CG(depth, segments_set):
var_value = 0
var_names = []
var_types = ""
var_lb = []
var_ub = []
var_obj = []
num_features = get_num_features()
data_size = get_data_size()
num_leafs = 2**depth
num_nodes = num_leafs - 1
# node n had a boolean test on feature f, boolean. On the paper: f_{i,j}
for j in range(num_nodes):
for i in range(num_features):
var_names.append("node_feature_" + str(j) + "_" + str(i))
var_types = var_types + "C"
var_lb.append(0)
var_ub.append(1)
var_obj.append(0)
var_value = var_value + 1
# value used in the boolean test in node n, integer. On the paper: c_{j}
for j in range(num_nodes):
var_names.append("node_constant_" + str(j))
var_types = var_types + "C"
var_lb.append(get_min_value())
var_ub.append(get_max_value())
var_obj.append(0)
var_value = var_value + 1
# leaf l predicts type t, boolean. On the paper: p_{l,t}
for l in range(num_leafs):
for t in range(get_num_targets()):
var_names.append("prediction_type_" + str(t) + "_" + str(l))
var_types = var_types + "C"
var_lb.append(0)
var_ub.append(1)
var_obj.append(0)
var_value = var_value + 1
# row error, variables to minimize. On the paper: e_{r}
for r in range(data_size):
var_names.append("row_error_" + str(r))
var_types = var_types + "C"
var_lb.append(0)
var_ub.append(1)
var_obj.append(1)
var_value = var_value + 1
for l in range(num_leafs): # x_{l,s}
for s in range(len(segments_set[l])):
var_names.append("segment_leaf_" + str(s) + "_" + str(l))
var_types = var_types + "C"
var_lb.append(0)
var_ub.append(1)
var_obj.append(0)
var_value = var_value + 1
return var_names, var_types, var_lb, var_ub, var_obj
def create_rows(depth):
global VARS
global TARGETS
row_value = 0
row_names = []
row_values = []
row_right_sides = []
row_senses = ""
num_features = get_num_features()
data_size = get_data_size()
num_leafs = 2**depth
num_nodes = num_leafs - 1
big_M = get_max_value() - get_min_value()
big_M = 10 * big_M + 10
for r in range(data_size): #constraint (2)
for j in range(num_nodes):
col_names = [
VARS["node_feature_" + str(j) + "_" + str(i)]
for i in range(num_features)
] #f_{i,j}
col_values = [
get_feature_value(r, i) for i in range(num_features)
] #mu^{i,r}
left_node = get_left_node(j, num_nodes)
if int(left_node) != -1: #if not a leaf
col_names.extend(
[
VARS["path_node_" + str(j) + "_" + str(r)],
VARS["path_node_" + str(left_node) + "_" + str(r)]
]
) #VARS["depth_true_" + str(r) + "_" + str(get_depth(j,num_nodes)-1)]])
else:
col_names.extend([
VARS["path_node_" + str(j) + "_" + str(r)],
VARS["path_leaf_" + str(j) + "_" + str(r)]
])
col_values.extend([big_M, big_M])
col_names.extend([VARS["node_constant_" + str(j)]])
col_values.extend([-1])
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(2 * big_M)
row_senses = row_senses + "L"
row_value = row_value + 1
for r in range(data_size): #constraint (3)
for j in range(num_nodes):
col_names = [
VARS["node_feature_" + str(j) + "_" + str(i)]
for i in range(num_features)
] #f_{i,j}
col_values = [
-get_feature_value(r, i) for i in range(num_features)
] #mu^{i,r}
right_node = get_right_node(j, num_nodes)
if int(right_node) != -1: #if not a leaf
col_names.extend(
[
VARS["path_node_" + str(j) + "_" + str(r)],
VARS["path_node_" + str(right_node) + "_" + str(r)]
]
) #VARS["depth_true_" + str(r) + "_" + str(get_depth(j,num_nodes)-1)]])
else:
col_names.extend([
VARS["path_node_" + str(j) + "_" + str(r)],
VARS["path_leaf_" + str(j + 1) + "_" + str(r)]
])
#col_names.extend([VARS["path_node_" + str(j) + "_" + str(r)], VARS["depth_true_" + str(r) + "_" + str(get_depth(j,num_nodes)-1)]])
col_values.extend([big_M, big_M])
col_names.extend([VARS["node_constant_" + str(j)]])
col_values.extend([1])
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(2 * big_M - eps)
row_senses = row_senses + "L"
row_value = row_value + 1
for l in range(num_leafs): #constraint (4)
col_names = [
VARS["prediction_type_" + str(s) + "_" + str(l)]
for s in range(get_num_targets())
]
col_values = [1 for s in range(get_num_targets())]
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "E"
row_value = row_value + 1
for j in range(num_nodes): #constraint (5)
col_names = [
VARS["node_feature_" + str(j) + "_" + str(i)]
for i in range(num_features)
]
col_values = [1 for i in range(num_features)]
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "E"
row_value = row_value + 1
for r in range(data_size): # constraint (6)
col_names = [
VARS["path_leaf_" + str(l) + "_" + str(r)]
for l in range(num_leafs)
]
col_values = [1 for l in range(num_leafs)]
col_names.extend([
VARS["path_node_" + str(j) + "_" + str(r)]
for j in range(num_nodes)
])
col_values.extend([1 for j in range(num_nodes)])
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(depth + 1)
row_senses = row_senses + "E"
row_value = row_value + 1
for r in range(data_size): # contraint (7)
col_names = []
col_values = []
for l in range(num_leafs):
col_names.extend([VARS["path_leaf_" + str(l) + "_" + str(r)]])
col_values.extend([1])
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "E"
row_value = row_value + 1
for r in range(data_size): # constraint (8) for internal nodes
for j in range(num_nodes):
if j != (num_nodes - 1) / 2:
col_names = [VARS["path_node_" + str(j) + "_" + str(r)]]
col_values = [1]
col_names.extend([
VARS["path_node_" + str(get_parent(j, depth)) + "_" +
str(r)]
])
col_values.extend([-1])
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(0)
row_senses = row_senses + "L"
row_value = row_value + 1
for r in range(data_size): # constraint (8) for leaves
for l in range(num_leafs):
col_names = [VARS["path_leaf_" + str(l) + "_" + str(r)]]
col_values = [1]
col_names.extend(
[VARS["path_node_" + str(l - l % 2) + "_" + str(r)]])
col_values.extend([-1])
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(0)
row_senses = row_senses + "L"
row_value = row_value + 1
for r in range(data_size): #constraint (9)
for l in range(num_leafs):
col_names = [VARS["path_leaf_" + str(l) + "_" + str(r)]]
col_values = [1]
for s in range(get_num_targets()):
if TARGETS[s] != get_target(r):
col_names.extend(
[VARS["prediction_type_" + str(s) + "_" + str(l)]])
col_values.extend([1])
col_names.extend([VARS["row_error_" + str(r)]])
col_values.extend([-1])
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "L"
row_value = row_value + 1
if inputsym == 1: #valid inequalties ?
for n in range(num_nodes):
left_leaf = get_left_leafs(n, num_nodes)
right_leaf = get_right_leafs(n, num_nodes)
if len(left_leaf) != 1:
continue
for s in range(get_num_targets()):
col_names = [
VARS["prediction_type_" + str(s) + "_" + str(left_leaf[0])]
]
col_values = [1]
col_names.extend([
VARS["prediction_type_" + str(s) + "_" +
str(right_leaf[0])]
])
col_values.extend([1])
row_names.append("#" + str(row_value))
row_values.append([col_names, col_values])
row_right_sides.append(1)
row_senses = row_senses + "L"
row_value = row_value + 1
return row_names, row_values, row_right_sides, row_senses