원문 보기 (영어)
Uh oh! There was an error while loading. Please reload this page . xqlsystems / xarray-sql Public Notifications You must be signed in to change notification settings Fork 16 Star 91 Files Expand file tree claude/xarray-sql-mnist-demo / nn.py Copy path Blame More file actions Blame More file actions Latest commit History History History 488 lines (446 loc) · 18.8 KB claude/xarray-sql-mnist-demo / nn.py Copy path Top File metadata and controls Code Blame 488 lines (446 loc) · 18.8 KB Raw Copy raw file Download raw file Open symbols panel Edit and raw actions 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 # /// script # requires-python = ">=3.12" # dependencies = [ # "xarray_sql", # "xarray", # "numpy", # "s3fs", # "zarr<3", # ] # # [tool.uv.sources] # xarray_sql = { path = "..", editable = true } # /// from __future__ import annotations from typing import Callable import numpy as np import xarray as xr import datetime import xarray_sql as xql SIDE = 28 # images are 28x28; flatten index is height * SIDE + width WIDTHS = ( SIDE * SIDE , 196 , 32 , 10 , ) # 784 pixels -> 196 -> 32 tanh -> 10 softmax N_SAMPLES , TRAIN_FRAC = 700 , 0.7 # total samples; fraction used for training LR , STEPS , CHUNK = 0.5 , 60 , 250 # Drop zero-valued pixels from the (dominant) layer-0 contraction. A background # pixel contributes 0 * weight = 0, so skipping those rows shrinks the join # *exactly* — the result is identical, and the speedup scales with the fraction # of zeros (a dark background). On dense inputs it is a no-op. # # Measured ~1.8x on real Fashion-MNIST (~50% zero pixels): 2.56 -> 1.45 s/step. SKIP_ZERO_PIXELS = True def fashion_mnist (): """The whole training set, left lazy so SQL streams and samples it. The real path returns a dask-backed (chunked) Dataset — nothing is pulled into memory here; ``from_dataset`` reads it chunk by chunk on demand, and the random subsample happens later in SQL. The offline fallback is a small synthetic set built in memory. """ try : ds = xr . open_dataset ( "s3://carbonplan-share/xbatcher/fashion-mnist-train.zarr" , engine = "zarr" , chunks = None , backend_kwargs = { "storage_options" : { "anon" : True }}, ) if "channel" in ds . dims : ds = ds . isel ( channel = 0 , drop = True ) # To float64, lazily (no full read). This zarr already stores images # as float in [0, 1]; only integer-encoded sources ([0, 255]) rescale. images = ds [ "images" ]. astype ( "float64" ) if not np . issubdtype ( ds [ "images" ]. dtype , np . floating ): images = images / 255.0 ds = ds . assign ( images = images , labels = ds [ "labels" ]. astype ( "int64" )) except Exception : # Offline fallback: a separable synthetic set (per-class template + # noise), so the same pipeline still learns without the network. A pool # larger than N_SAMPLES so the SQL subsample still has something to pick. rng = np . random . default_rng ( 0 ) n = 3 * N_SAMPLES templates = rng . standard_normal (( 10 , SIDE , SIDE )) labels = rng . integers ( 0 , 10 , n ). astype ( "int64" ) images = templates [ labels ] + 0.6 * rng . standard_normal (( n , SIDE , SIDE )) ds = xr . Dataset ( { "images" : (( "sample" , "height" , "width" ), images ), "labels" : (( "sample" ,), labels ), } ) # Integer index coords are the SQL join keys (sample, height, width). return ds [[ "images" , "labels" ]]. assign_coords ( sample = np . arange ( ds . sizes [ "sample" ]), height = np . arange ( ds . sizes [ "height" ]), width = np . arange ( ds . sizes [ "width" ]), ) def build_model_with_table_names ( init_weight : Callable [[ int , int ], np . ndarray ], init_bias : Callable [[ int ], np . ndarray ], widths = WIDTHS , ) -> tuple [ xr . Dataset , dict [ tuple [ str , ...], str ]]: """The network as one Dataset that splits into tables per layer. Layer ``i`` is a weight matrix ``layer_i (inp_i, out_i)`` and a separate bias vector ``bias_i (out_i,)``. """ weights = { f"layer_ { i } " : (( f"inp_ { i } " , f"out_ { i } " ), init_weight ( inp , out )) for i , ( inp , out ) in enumerate ( zip ( widths [: - 1 ], widths [ 1 :])) } biases = { f"bias_ { i } " : (( f"out_ { i } " ,), init_bias ( out )) for i , out in enumerate ( widths [ 1 :]) } coords = {} coords . update ( { f"inp_ { i } " : np . arange ( inp ) for i , inp in enumerate ( widths [: - 1 ])} ) coords . update ( { f"out_ { i } " : np . arange ( out ) for i , out in enumerate ( widths [ 1 :])} ) ds = xr . Dataset ({ ** weights , ** biases }, coords = coords ) names : dict [ tuple [ str , ...], str ] = {} for i in range ( len ( weights )): names [( f"inp_ { i } " , f"out_ { i } " )] = f"layer { i } " names [( f"out_ { i } " ,)] = f"bias { i } " return ds , names def main (): rng = np . random . default_rng ( 1 ) mnist = fashion_mnist () ctx = xql . XarrayContext () # One Dataset splits into two tables: pixels (sample, height, width) and # labels (sample). The dim names are the join keys. ctx . from_dataset ( "mnist" , mnist , chunks = dict ( sample = CHUNK ), table_names = { ( "sample" , "height" , "width" ): "pixels" , ( "sample" ,): "labels" , }, ) # Draw a random N_SAMPLES subset in SQL (ORDER BY random() LIMIT), carrying # each sample's label and a train/test tag. `data` is the working label # table: cache() pins the chosen subset so every downstream query sees the # same split without rescanning the source. `ORDER BY random()` shuffles the # whole label column, so the subset is order-independent even if the on-disk # samples are class-sorted. data = ctx . sql ( f""" SELECT sample, labels, CASE WHEN random() < { TRAIN_FRAC } THEN 'train' ELSE 'test' END AS split FROM mnist.labels ORDER BY random() LIMIT { N_SAMPLES } """ ). cache () ctx . register_table ( "data" , data ) # Materialise just the sampled images once: a single lazy scan of the full # dataset extracts the ~N_SAMPLES subset into `pixels`, which the per-step # forward joins instead of rescanning the source 60x. Only the subset lives # in memory; the full set stays lazy. pixels = ctx . sql ( """ SELECT p.sample, p.height, p.width, p.images FROM mnist.pixels p JOIN data d ON p.sample = d.sample """ ). cache () ctx . register_table ( "pixels" , pixels ) # The gradient averages over the actual train coun