main.py 19.5 KB
Newer Older
1 2 3 4
from flask import Flask, jsonify, request
import pandas as pd
import numpy as np
from flask_cors import CORS
5
from collections import defaultdict, Counter
6
from time import time
7 8 9
import os.path
import json
from sklearn import preprocessing
10
import orjson
11
import dask.dataframe as dd
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
12 13
import bigwig
import bbi
14 15
from bitarray import bitarray
import _ucrdtw
16 17
import _lsh
from scipy.spatial import distance
18
from scipy.sparse import dia_matrix
19 20 21 22 23
from fastdtw import fastdtw
from scipy.spatial.distance import euclidean
import dtw
import math
from random import sample
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
24

25
reload = False
26 27 28 29

app = Flask(__name__)
CORS(app)

30 31 32 33 34 35 36 37 38 39 40 41 42
def calculate_signatures_random_weights(data, window_size=None, hash_size=None, hash_function=None):
    if hash_function is None:
        hash_function = np.random.uniform(-1, 1, size=(window_size, hash_size))
    signatures_bool = np.dot(data, hash_function) > 0
    if signatures_bool.ndim == 1:
        return ''.join(['1' if x else '0' for x in signatures_bool])
    return [''.join(['1' if x else '0' for x in lst]) for lst in signatures_bool], hash_function


def calculate_signatures_cumsum_weights(data, window_size=None, hash_size=None, hash_function=None):
    if hash_function is None:
        hash_function = np.array([np.cumsum(np.random.uniform(-1, 1, window_size)) for _ in range(hash_size)]).transpose()
    signatures_bool = np.dot(data, hash_function) > 0
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
    if hash_size is None:
        signatures_int = np.packbits(signatures_bool)
    else:
        signatures_int = np.packbits(signatures_bool, axis=1).flatten()
    return signatures_int.tolist(), hash_function

def calculate_signatures_normal_weights(data, window_size=None, hash_size=None, hash_function=None):
    if hash_function is None:
        hash_function = np.array([np.random.normal(0, 1, window_size) for _ in range(hash_size)]).transpose()
    signatures_bool = np.dot(data, hash_function) > 0
    if hash_size is None:
        signatures_int = np.packbits(signatures_bool)
    else:
        signatures_int = np.packbits(signatures_bool, axis=1).flatten()
    return signatures_int.tolist(), hash_function

def calculate_signatures_normal_split_weights(data, window_size=None, hash_size=None, hash_function=None):
    if hash_function is None:
        hash_function = []
        interval = int(window_size / hash_size)
        empty = np.zeros(window_size)
        for i in range(hash_size):
            copy = np.copy(empty)
            copy[i * interval:(i+1) * interval] = np.random.normal(0, 1, interval)
            hash_function.append(copy)
        hash_function = np.array(hash_function).transpose()
    signatures_bool = np.dot(data, hash_function) > 0
    if hash_size is None:
        signatures_int = np.packbits(signatures_bool)
    else:
        signatures_int = np.packbits(signatures_bool, axis=1).flatten()
74 75
    return signatures_int.tolist(), hash_function

76
def calculate_signatures_new(data, window_size=None, hash_size=None, hash_function=None):
77 78
    if hash_function is None:
        hash_function = np.array([np.cumsum(np.random.uniform(-1, 1, window_size)) for _ in range(hash_size)]).transpose()
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
    if len(data) == len(np.array(hash_function)[:, 0]):
        signatures_bool = np.dot(data, hash_function) > 0
        output = signatures_bool.astype(int)[0]
        print(output)
        return output
    print('starting hashing')
    t0 = time()
    all_signatures = []
    batch_size = 20
    data = data.transpose()
    temp = np.zeros((batch_size, window_size + batch_size - 1))
    for h in range(hash_size):
        for i in range(batch_size):
            temp[i, i:i + window_size] = hash_function[:, h]
        print('first: ' + str(time() - t0))
        signatures_bool = [np.dot(temp, data[i:i + window_size + batch_size - 1]) > 0 for i in range(0, len(data) - window_size, batch_size)]
        # signatures_bool = []
        # for i in range(0, len(data) - window_size, batch_size):
        #     if i % 1000000 == 0:
        #         print(i)
        #     signatures_bool.append(np.dot(temp, data[i:i + window_size + batch_size - 1]) > 0)
        print('second: ' + str(time() - t0))
        all_signatures.append(np.array(signatures_bool).flatten().astype(int))
    print('done')
    signatures_int = np.packbits(np.stack(np.array(all_signatures), axis=1), axis=0).flatten()
104 105
    return signatures_int.tolist(), hash_function

106

107
lsh_function = calculate_signatures_normal_weights
108

109 110 111 112 113 114
@app.route('/', methods=['GET'])
def index():
    return "hi"

@app.route('/read-data', methods=['GET'])
def read_data():
115
    t0 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
116 117 118 119
    size = bbi.chromsizes('test.bigWig')['chr1']
    bins = 100000
    data = bigwig.get('test.bigWig', 'chr1', 0, size, bins)
    print(data.shape)
120
    response = {
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
121 122
        "index": list(range(0, size, int(size/(bins)))),
        "values": data.tolist()
123
    }
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
124
    response = orjson.dumps(response)
125
    print('Data read: ' + str(time()-t0))
126 127 128 129
    return response

@app.route('/create-windows', methods=['POST'])
def create_windows():
130
    t0 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
131
    if reload:
132 133 134
        # raw_data = request.json
        # window_size = int(raw_data['parameters']["windowsize"])
        window_size = 120
135
        chromsize = bbi.chromsizes('test.bigWig')['chr1']
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
        step_size = int(12000 / 6)
        start_bps = np.arange(0, chromsize - 12000 + step_size, step_size)
        end_bps = np.arange(12000, chromsize + step_size, step_size)
        data = bigwig.chunk(
            'test.bigWig',
            12000,
            int(12000 / window_size),
            int(12000 / 6),
            ['chr1'],
            verbose=True,
        )
        # data = bbi.stackup(
        #     'test.bigWig',
        #     ['chr1'] * start_bps.size,
        #     start_bps,
        #     end_bps,
        #     bins=window_size,
        #     missing=0.0,
        #     oob=0.0,
        # )
        # data = (data - np.min(data))/np.ptp(data)
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
157
        print(data.shape)
158
        np.save('processed-data', data)
159
        np.savetxt('processed-data', data, delimiter=' ', fmt='%f')
160
    print('Windows created: ' + str(time()-t0))
161
    return '1'
162 163 164

@app.route('/create-tables', methods=['POST'])
def create_tables():
165 166 167 168 169
    data = np.load('processed-data.npy')
    raw_data = orjson.loads(request.data)
    window_size = int(raw_data['parameters']["windowsize"])
    hash_size = int(raw_data['parameters']["hashsize"])
    table_size = int(raw_data['parameters']["tablesize"])
170

171
    t0 = time()
172 173
    r, a, sd = preprocess()
    lsh_method(r, a, sd)
174 175 176 177 178 179 180 181
    hash_functions, tables = lsh(data, window_size, hash_size, table_size)

    response = {}
    for table_index in range(table_size):
        response[str(table_index)] = {
            "hash": hash_functions[table_index],
            "entries": tables[table_index]
        }
182 183
    response = jsonify(response)
    print('done: ' + str(time()-t0))
184 185 186 187 188
    return response


def lsh(data, window_size, hash_size, table_size):
    tables_hash_function = []
189
    tables = []
190 191
    print(data.shape)

192
    for index in range(table_size):
193
        signatures, hash_function = lsh_function(data, window_size=window_size, hash_size=hash_size)
194
        print(index)
195 196 197
        table = defaultdict(list)
        for v, k in enumerate(signatures):
            table[k].append(v)
198
        tables.append(table)
199
        tables_hash_function.append(hash_function.tolist())
200

201 202 203 204 205 206 207 208 209 210 211 212
    hash_functions = tables_hash_function
    return hash_functions, tables


@app.route('/similarity', methods=['POST'])
def similarity():
    t0 = time()
    raw_data = orjson.loads(request.data)
    window = raw_data['query']
    tables = raw_data["tables"]
    neighbours = []
    output = defaultdict(list)
213
    i = 0
214
    for t in tables.values():
215 216 217 218
        print(i)
        signatures, _ = lsh_function(window, hash_function=t["hash"])
        neighbours.extend(t["entries"][str(signatures[0])])
        i = i+1
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
    neighbours_with_frequency = dict(Counter(neighbours))
    for index, frequency in neighbours_with_frequency.items():
        output[str(frequency)].append(index)

    response = orjson.dumps(output)
    print("Similarity done: " + str(time()-t0))
    return response

@app.route('/update', methods=['POST'])
def update():
    t0 = time()
    raw_data = orjson.loads(request.data)
    data = np.load('processed-data.npy')
    label_data = raw_data["labelData"]
    tables = raw_data["tables"]
    window = raw_data["query"]
    window_size = int(raw_data['parameters']["windowsize"])
    hash_size = int(raw_data['parameters']["hashsize"])
    table_size = int(raw_data['parameters']["tablesize"])
    new_tables = []

    correct_indices = [int(index) for index, value in label_data.items() if value is True]
    incorrect_indices = [int(index) for index, value in label_data.items() if value is False]

    for t in tables.values():
        valid = True
245 246
        signatures, _ = lsh_function(window, hash_function=t['hash'])
        neighbours = t["entries"][str(signatures[0])]
247 248 249 250 251 252 253 254 255 256 257 258 259 260 261
        for index in correct_indices:
            if index not in neighbours:
                valid = False
                break
        for index in incorrect_indices:
            if index in neighbours:
                valid = False
                break
        if valid:
            new_tables.append(t)

    for index in range(table_size - len(new_tables)):
        entries = defaultdict(list)
        t1 = time()
        while True:
262 263
            correct_signatures, hash_function = lsh_function(data[correct_indices], window_size=window_size, hash_size=hash_size)
            incorrect_signatures, _ = lsh_function(data[incorrect_indices], hash_function=hash_function)
264 265
            if correct_signatures.count(correct_signatures[0]) == len(correct_signatures) and incorrect_signatures.count(correct_signatures[0]) == 0:
                break
266
        signatures, _ = lsh_function(data, hash_function=hash_function)
267 268 269 270 271 272 273 274 275
        for i in range(len(signatures)):
            entries[signatures[i]].append(i)
        print(str(index) + ": " + str(time() - t1))
        new_tables.append({
            "hash": hash_function.tolist(),
            "entries": entries
        })

    print('Update time: ' + str(time() - t0))
276
    response = {}
277 278 279 280
    for table_index in range(len(new_tables)):
        response[table_index] = {
            "hash": new_tables[table_index]["hash"],
            "entries": new_tables[table_index]["entries"]
281
        }
282
    response = jsonify(response)
283 284
    return response

285 286
@app.route('/query', methods=['POST'])
def query():
287
    t0 = time()
288
    raw_data = orjson.loads(request.data)
289
    window = raw_data['window']
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
290
    if isinstance(window, int):
291
        output = np.load('processed-data.npy')[window]
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
292 293 294
        response = orjson.dumps(output.tolist())
        print("Query done: " + str(time() - t0))
        return response
295 296 297
    else:
        print("OOOOOOOOOOOOOOOO")
        output = (window - np.min(window))/np.ptp(window)
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
298 299 300 301 302 303 304 305 306 307
        response = orjson.dumps(output.tolist())
        print("Query done: " + str(time()-t0))
        return response

@app.route('/window', methods=['POST'])
def window():
    t0 = time()
    raw_data = orjson.loads(request.data)
    indices = raw_data['indices']
    output = np.load('processed-data.npy')[indices]
308
    response = orjson.dumps(output.tolist())
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
309
    print("Query done: " + str(time() - t0))
310 311 312 313 314 315 316 317 318 319
    return response

@app.route('/average-progress', methods=['POST'])
def average_progress():
    t0 = time()
    raw_data = orjson.loads(request.data)
    all_windows = raw_data['windows']
    data = np.load('processed-data.npy')
    output = []
    actual_windows = []
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
320
    print("Starting average progress")
321 322 323
    print("Initialized: " + str(time() - t0))
    for windows in all_windows:
        t1 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
324
        actual_windows.extend(data[windows])
325 326 327
        if len(actual_windows) == 0:
            output.append([])
            continue
328 329 330
        max_values = np.maximum.reduce(actual_windows).tolist()
        min_values = np.minimum.reduce(actual_windows).tolist()
        average_values = (np.sum(actual_windows, 0)/len(actual_windows)).tolist()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
331
        output = [({
332 333 334
            'average': average_values,
            'max': max_values,
            'min': min_values
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
335
        })] + output
336 337 338
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
    print("Averages calculated: " + str(time() - t0))
339 340
    return response

341 342
@app.route('/average-table', methods=['POST'])
def average_table():
343 344 345 346 347
    t0 = time()
    raw_data = orjson.loads(request.data)
    all_windows = raw_data['windows']
    data = np.load('processed-data.npy')
    output = []
348
    print("Initialized: " + str(time() - t0))
349 350
    for windows in all_windows:
        t1 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
351
        actual_windows = data[windows]
352
        print(len(actual_windows))
353 354 355 356 357 358 359
        average_values = np.average(actual_windows, 0)
        # average_values = (np.sum(actual_windows, 0) / len(actual_windows))
        std_values = np.std(actual_windows, 0)
        max_values = average_values + std_values
        min_values = average_values - std_values
        # max_values = np.maximum.reduce(actual_windows).tolist()
        # min_values = np.minimum.reduce(actual_windows).tolist()
360
        output.append({
361 362 363
            'average': average_values.tolist(),
            'max': max_values.tolist(),
            'min': min_values.tolist()
364
        })
365 366
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
367
    print("Averages calculated: " + str(time() - t0))
368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584
    return response

def preprocess():
    data = np.load('processed-data.npy')
    # data = np.array(data, dtype='double')
    # data = np.reshape(data, (int(len(data) / 1), 1, len(data[0])))
    # data = np.repeat(data, repeats=1, axis=1)
    subset = []
    # query = data[80503]
    t0 = time()
    # for i, window in enumerate(data):
    #     print(i)
    #     a = dtw.dtw(window, query, dist_method="Euclidean").distance
    # print(time() - t0)
    # print("done")

    r = 3
    for i, window in enumerate(data):
        if i % 10000 == 0:
            print(str(i) + ':' + str(len(subset)))
        state = 1
        for s in subset:
            if np.linalg.norm(window - data[s]) < r:
                state = 0
                break
        if state == 1:
            subset.append(i)

    #
    # subset = sample(list(range(len(data))), 50)
    # print(subset)
    dtw_distances = []
    eq_distances = []
    for i, index_1 in enumerate(subset):
        print(i)
        for j, index_2 in enumerate(subset):
            if index_1 == index_2:
                continue
            e = distance.euclidean(data[index_1], data[index_2])
            eq_distances.append(e)
            # d = dtw.dtw(data[index_1], data[index_2], dist_method="Euclidean", window_type="sakoechiba", window_args={"window_size": 6}).distance
            # print(d-e)
            # if (e != 0):
            #     dtw_distances.append(d)#(dtw.dtw(data[index_1], data[index_2], keep_internals=True).distance)
            #     eq_distances.append(e)
            # else:
            #     dtw_distances.append(0)
            #     eq_distances.append(1)
    # ratios = np.array(dtw_distances)/np.array(eq_distances)
    # mean_dtw = np.mean(dtw_distances)
    # sd_dtw = np.std(dtw_distances)
    mean_eq = np.mean(eq_distances)
    sd_eq = np.std(eq_distances)
    a=1
    sd=1
    # a = np.mean(ratios)
    # sd = np.std(ratios)
    # theta = mean_dtw + -2.58 * sd_dtw
    theta = mean_eq + -2.58 * sd_eq
    # r = theta / ((a-sd)*math.sqrt(120))
    r = theta / (math.sqrt(120))
    # print(mean_dtw)
    # print(sd_dtw)
    print(a)
    print(sd)
    print(theta)
    print(r)
    print(time() - t0)
    return r, a, sd

def dtw_query():
    data = np.load('processed-data.npy')
    data= np.array(data, dtype='double')
    data = np.repeat(data, repeats=1, axis=0)
    data = np.reshape(data, (int(len(data)/1), 1, len(data[0])))
    query = data[80503]
    t0 = time()
    for i, window in enumerate(data):
        print(i)
        alignment = dtw.dtw(query, window, keep_internals=True)
    print(time() - t0)

def lsh_method(r, a, sd):
    create_windows()
    query_n = 80503
    dim = 10
    data = np.load('processed-data.npy')
    data= np.array(data, dtype='double')
    data = np.reshape(data, (len(data), len(data[0]), 1))
    data = np.repeat(data, repeats=1, axis=2)
    query = data[query_n]
    candidates, hf = _lsh.lsh(data, query, r, a, sd)
    print(repr(candidates[0:10]))

    # data = np.load('processed-data.npy')
    # query = data[query_n]
    # distances = [_ucrdtw.ucrdtw(window, query, 0.05, False)[1] for window in data]
    # topk_dtw = sorted(range(len(distances)), key=lambda k: distances[k])
    # print(topk_dtw[0:10])

    distances_ed = [distance.euclidean(query, window) for window in data]
    topk_ed = sorted(range(len(distances_ed)), key=lambda k: distances_ed[k])

    accuracy = 0
    # for index in topk_dtw[0:50]:
    #     if index in candidates[0:50]:
    #         accuracy += 1
    # print(accuracy)

    accuracy = 0
    for index in topk_ed[0:20]:
        if index in candidates[0:20]:
            accuracy += 1
    print(accuracy)

    accuracy = 0
    for index in topk_ed[0:50]:
        if index in candidates[0:50]:
            accuracy += 1
    print(accuracy)

    # accuracy = 0
    # for index in topk_dtw[0:50]:
    #     if index in candidates[0:1000]:
    #         accuracy += 1
    # print(accuracy)
    #
    # accuracy = 0
    # for index in topk_dtw[0:50]:
    #     if index in candidates[0:5000]:
    #         accuracy += 1
    # print(accuracy)
    #
    # accuracy = 0
    # for index in topk_dtw[0:50]:
    #     if index in candidates[0:10000]:
    #         accuracy += 1
    # print(accuracy)
    #
    # accuracy = 0
    # for index in topk_dtw[0:50]:
    #     if index in candidates[0:50000]:
    #         accuracy += 1
    # print(accuracy)
    #
    # accuracy = 0
    # for index in topk_dtw[0:50]:
    #     if index in candidates:
    #         accuracy += 1
    # print(accuracy)

# r, a, sd = preprocess()
# lsh_method(r, a, sd)
# create_windows()
# query_n = 80503
# data = np.load('processed-data.npy')
# data= np.array(data, dtype='double')
# data = np.reshape(data, (len(data), len(data[0]), 1))
# data = np.repeat(data, repeats=10, axis=2)
# query = data[query_n]
# # candidates, hf = _lsh.lsh(data, query)
# # data = np.load('processed-data.npy')
# # query = data[query_n]
#
# data = np.load('processed-data.npy')
# print(_ucrdtw.ucrdtw(data[query_n], data[0], 0.05, False)[1])
#
# # l2_norm = lambda x, y: (x - y) ** 2
#
# data = np.load('processed-data.npy')
# data= np.array(data, dtype='double')
# data = np.repeat(data, repeats=1, axis=0)
# data = np.reshape(data, (int(len(data)/1), 1, len(data[0])))
# query = data[query_n]
# # distances = [_ucrdtw.ucrdtw(window, query, 0.05, False)[1] for window in data]
# # topk_dtw = sorted(range(len(distances)), key=lambda k: distances[k])
# # print(topk_dtw[0:10])
#
# # Generate our data
# template = data[query_n]
# rt,ct = template.shape
# rq,cq = query.shape
# t0 = time()
# # Calculate the alignment vector and corresponding distance
# alignment = dtw.dtw(query, template, keep_internals=True)
# print(alignment.distance)
#
# print(time()-t0)
# np.save('topk', np.array(topk_dtw))
print('done')
# topk_dtw = np.load('topk.npy')
# distances_ed = [distance.euclidean(query, window) for window in data]
# topk_ed = sorted(range(len(distances_ed)), key=lambda k: distances_ed[k])

#
#
# accuracy = 0
# for index in topk_dtw[0:50]:
#     if index in candidates[0:50]:
#         accuracy += 1
# print(accuracy)
# accuracy = 0
# output = []
# for index in topk_ed[0:50]:
#     if index in candidates:
#         accuracy += 1
# print(accuracy)
# accuracy = 0
# for index in topk_ed[0:50]:
#     if index in candidates[0:50]:
#         accuracy += 1
# print(accuracy)
# accuracy = 0
# for index in topk_ed[0:20]:
#     if index in candidates[0:20]:
#         accuracy += 1
# print(accuracy)