Spaces:
Sleeping
Sleeping
File size: 10,184 Bytes
46e0dd0 97bda4d 46e0dd0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 |
import os
import sys
import numpy as np
import json
import math
import torch
from transformers import RobertaTokenizer, BertTokenizer
from torch.utils.data import Dataset
#sys.path.append('/home/zekun/spatial_bert/spatial_bert/datasets')
#sys.path.append('/content/drive/MyDrive/spaBERT/spabert/datasets')
from models.spabert.datasets.dataset_loader_ver2 import SpatialDataset
#from dataset_loader_ver2 import SpatialDataset
import pdb
class PbfMapDataset(SpatialDataset):
def __init__(self, data_file_path, tokenizer=None, max_token_len = 512, distance_norm_factor = 0.0001, spatial_dist_fill=10,
with_type = True, sep_between_neighbors = False, label_encoder = None, mode = None, num_neighbor_limit = None, random_remove_neighbor = 0.,type_key_str='class'):
if tokenizer is None:
self.tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
else:
self.tokenizer = tokenizer
self.max_token_len = max_token_len
self.spatial_dist_fill = spatial_dist_fill # should be normalized distance fill, larger than all normalized neighbor distance
self.with_type = with_type
self.sep_between_neighbors = sep_between_neighbors
self.label_encoder = label_encoder
self.num_neighbor_limit = num_neighbor_limit
self.read_file(data_file_path, mode)
self.random_remove_neighbor = random_remove_neighbor
self.type_key_str = type_key_str # key name of the class type in the input data dictionary
super(PbfMapDataset, self).__init__(self.tokenizer , max_token_len , distance_norm_factor, sep_between_neighbors )
def read_file(self, data_file_path, mode):
with open(data_file_path, 'r') as f:
data = f.readlines()
if mode == 'train':
data = data[0:int(len(data) * 0.8)]
elif mode == 'test':
data = data[int(len(data) * 0.8):]
elif mode is None: # use the full dataset (for mlm)
pass
else:
raise NotImplementedError
self.len_data = len(data) # updated data length
self.data = data
def load_data(self, index):
spatial_dist_fill = self.spatial_dist_fill
line = self.data[index] # take one line from the input data according to the index
line_data_dict = json.loads(line)
# process pivot
pivot_name = line_data_dict['info']['name']
pivot_pos = line_data_dict['info']['geometry']['coordinates']
neighbor_info = line_data_dict['neighbor_info']
neighbor_name_list = neighbor_info['name_list']
neighbor_geometry_list = neighbor_info['geometry_list']
if self.random_remove_neighbor != 0:
num_neighbors = len(neighbor_name_list)
rand_neighbor = np.random.uniform(size = num_neighbors)
neighbor_keep_arr = (rand_neighbor >= self.random_remove_neighbor) # select the neighbors to be removed
neighbor_keep_arr = np.where(neighbor_keep_arr)[0]
new_neighbor_name_list, new_neighbor_geometry_list = [],[]
for i in range(0, num_neighbors):
if i in neighbor_keep_arr:
new_neighbor_name_list.append(neighbor_name_list[i])
new_neighbor_geometry_list.append(neighbor_geometry_list[i])
neighbor_name_list = new_neighbor_name_list
neighbor_geometry_list = new_neighbor_geometry_list
if self.num_neighbor_limit is not None:
neighbor_name_list = neighbor_name_list[0:self.num_neighbor_limit]
neighbor_geometry_list = neighbor_geometry_list[0:self.num_neighbor_limit]
train_data = self.parse_spatial_context(pivot_name, pivot_pos, neighbor_name_list, neighbor_geometry_list, spatial_dist_fill )
if self.with_type:
pivot_type = line_data_dict['info'][self.type_key_str]
train_data['pivot_type'] = torch.tensor(self.label_encoder.transform([pivot_type])[0]) # scalar, label_id
if 'ogc_fid' in line_data_dict['info']:
train_data['ogc_fid'] = line_data_dict['info']['ogc_fid']
return train_data
def __len__(self):
return self.len_data
def __getitem__(self, index):
return self.load_data(index)
class PbfMapDatasetMarginRanking(SpatialDataset):
def __init__(self, data_file_path, type_list = None, tokenizer=None, max_token_len = 512, distance_norm_factor = 0.0001, spatial_dist_fill=10,
sep_between_neighbors = False, mode = None, num_neighbor_limit = None, random_remove_neighbor = 0., type_key_str='class'):
if tokenizer is None:
self.tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
else:
self.tokenizer = tokenizer
self.type_list = type_list
self.type_key_str = type_key_str # key name of the class type in the input data dictionary
self.max_token_len = max_token_len
self.spatial_dist_fill = spatial_dist_fill # should be normalized distance fill, larger than all normalized neighbor distance
self.sep_between_neighbors = sep_between_neighbors
# self.label_encoder = label_encoder
self.num_neighbor_limit = num_neighbor_limit
self.read_file(data_file_path, mode)
self.random_remove_neighbor = random_remove_neighbor
self.mode = mode
super(PbfMapDatasetMarginRanking, self).__init__(self.tokenizer , max_token_len , distance_norm_factor, sep_between_neighbors )
def read_file(self, data_file_path, mode):
with open(data_file_path, 'r') as f:
data = f.readlines()
if mode == 'train':
data = data[0:int(len(data) * 0.8)]
elif mode == 'test':
data = data[int(len(data) * 0.8):]
self.all_types_data = self.prepare_all_types_data()
elif mode is None: # use the full dataset (for mlm)
pass
else:
raise NotImplementedError
self.len_data = len(data) # updated data length
self.data = data
def prepare_all_types_data(self):
type_list = self.type_list
spatial_dist_fill = self.spatial_dist_fill
type_data_dict = dict()
for type_name in type_list:
type_pos = [None, None] # use filler values
type_data = self.parse_spatial_context(type_name, type_pos, pivot_dist_fill = 0.,
neighbor_name_list = [], neighbor_geometry_list=[], spatial_dist_fill= spatial_dist_fill)
type_data_dict[type_name] = type_data
return type_data_dict
def load_data(self, index):
spatial_dist_fill = self.spatial_dist_fill
line = self.data[index] # take one line from the input data according to the index
line_data_dict = json.loads(line)
# process pivot
pivot_name = line_data_dict['info']['name']
pivot_pos = line_data_dict['info']['geometry']['coordinates']
neighbor_info = line_data_dict['neighbor_info']
neighbor_name_list = neighbor_info['name_list']
neighbor_geometry_list = neighbor_info['geometry_list']
if self.random_remove_neighbor != 0:
num_neighbors = len(neighbor_name_list)
rand_neighbor = np.random.uniform(size = num_neighbors)
neighbor_keep_arr = (rand_neighbor >= self.random_remove_neighbor) # select the neighbors to be removed
neighbor_keep_arr = np.where(neighbor_keep_arr)[0]
new_neighbor_name_list, new_neighbor_geometry_list = [],[]
for i in range(0, num_neighbors):
if i in neighbor_keep_arr:
new_neighbor_name_list.append(neighbor_name_list[i])
new_neighbor_geometry_list.append(neighbor_geometry_list[i])
neighbor_name_list = new_neighbor_name_list
neighbor_geometry_list = new_neighbor_geometry_list
if self.num_neighbor_limit is not None:
neighbor_name_list = neighbor_name_list[0:self.num_neighbor_limit]
neighbor_geometry_list = neighbor_geometry_list[0:self.num_neighbor_limit]
train_data = self.parse_spatial_context(pivot_name, pivot_pos, neighbor_name_list, neighbor_geometry_list, spatial_dist_fill )
if 'ogc_fid' in line_data_dict['info']:
train_data['ogc_fid'] = line_data_dict['info']['ogc_fid']
# train_data['pivot_type'] = torch.tensor(self.label_encoder.transform([pivot_type])[0]) # scalar, label_id
pivot_type = line_data_dict['info'][self.type_key_str]
train_data['pivot_type'] = pivot_type
if self.mode == 'train':
# postive class
postive_name = pivot_type # class type string as input to tokenizer
positive_pos = [None, None] # use filler values
postive_type_data = self.parse_spatial_context(postive_name, positive_pos, pivot_dist_fill = 0.,
neighbor_name_list = [], neighbor_geometry_list=[], spatial_dist_fill= spatial_dist_fill)
train_data['positive_type_data'] = postive_type_data
# negative class
other_type_list = self.type_list.copy()
other_type_list.remove(pivot_type)
other_type = np.random.choice(other_type_list)
negative_name = other_type
negative_pos = [None, None] # use filler values
negative_type_data = self.parse_spatial_context(negative_name, negative_pos, pivot_dist_fill = 0.,
neighbor_name_list = [], neighbor_geometry_list=[], spatial_dist_fill= spatial_dist_fill)
train_data['negative_type_data'] = negative_type_data
elif self.mode == 'test':
# return data for all class types in type_list
train_data['all_types_data'] = self.all_types_data
else:
raise NotImplementedError
return train_data
def __len__(self):
return self.len_data
def __getitem__(self, index):
return self.load_data(index)
|