main.py 9.88 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
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
16
17

reload = False
18
19
20
21

app = Flask(__name__)
CORS(app)

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
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
    signatures_int = np.packbits(signatures_bool)
    return signatures_int.tolist(), 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
    signatures_int = np.packbits(signatures_bool)
    return signatures_int.tolist(), hash_function

lsh_function = calculate_signatures_cumsum_weights

47
48
49
50
51
52
@app.route('/', methods=['GET'])
def index():
    return "hi"

@app.route('/read-data', methods=['GET'])
def read_data():
53
    t0 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
54
55
56
57
    size = bbi.chromsizes('test.bigWig')['chr1']
    bins = 100000
    data = bigwig.get('test.bigWig', 'chr1', 0, size, bins)
    print(data.shape)
58
    response = {
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
59
60
        "index": list(range(0, size, int(size/(bins)))),
        "values": data.tolist()
61
    }
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
62
    response = orjson.dumps(response)
63
    print('Data read: ' + str(time()-t0))
64
65
66
67
68
    query = data[10000:11200]
    print(query)
    loc, dist = _ucrdtw.ucrdtw(data, query, 0.05, True)
    print(data[loc:loc+120])
    print('found query: ' + str(loc) + '[' + str(time()-t0) + ']')
69
70
71
72
    return response

@app.route('/create-windows', methods=['POST'])
def create_windows():
73
    t0 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
74
    if reload:
75
76
        raw_data = request.json
        window_size = int(raw_data['parameters']["windowsize"])
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
77
78
79
        data = bigwig.chunk(
            'test.bigWig',
            12000,
80
81
            int(12000 / window_size),
            int(12000 / 6),
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
82
83
84
85
            ['chr1'],
            verbose=True,
        )
        print(data.shape)
86
        np.save('processed-data', data)
87
    print('Windows created: ' + str(time()-t0))
88
    return '1'
89
90
91

@app.route('/create-tables', methods=['POST'])
def create_tables():
92
93
94
95
96
    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"])
97

98
    t0 = time()
99
100
101
102
103
104
105
106
    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]
        }
107
108
    response = jsonify(response)
    print('done: ' + str(time()-t0))
109
110
111
112
113
    return response


def lsh(data, window_size, hash_size, table_size):
    tables_hash_function = []
114
    tables = []
115
116
    print(data.shape)

117
    for index in range(table_size):
118
119
        signatures, hash_function = lsh_function(data, window_size=window_size, hash_size=hash_size)
        table = {k: v for v, k in enumerate(signatures)}
120
        tables.append(table)
121
        tables_hash_function.append(hash_function.tolist())
122

123
124
125
126
127
128
129
130
131
132
133
134
135
136
    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)

    for t in tables.values():
137
        signature = lsh_function(window, hash_function=t["hash"])
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
        neighbours.extend(t["entries"][signature])
    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
165
        signature = lsh_function(window, hash_function=t['hash'])
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
        neighbours = t["entries"][signature]
        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:
182
183
            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)
184
185
            if correct_signatures.count(correct_signatures[0]) == len(correct_signatures) and incorrect_signatures.count(correct_signatures[0]) == 0:
                break
186
        signatures, _ = lsh_function(data, hash_function=hash_function)
187
188
189
190
191
192
193
194
195
        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))
196
    response = {}
197
198
199
200
    for table_index in range(len(new_tables)):
        response[table_index] = {
            "hash": new_tables[table_index]["hash"],
            "entries": new_tables[table_index]["entries"]
201
        }
202
    response = jsonify(response)
203
204
    return response

205
206
@app.route('/query', methods=['POST'])
def query():
207
    t0 = time()
208
    raw_data = orjson.loads(request.data)
209
    window = raw_data['window']
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
    if isinstance(window, int):
        output = np.load('processed-data.npy')[window]
        response = orjson.dumps(output.tolist())
        print("Query done: " + str(time() - t0))
        return response
    else :
        output = preprocessing.minmax_scale(window, (-1, 1))
        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]
227
    response = orjson.dumps(output.tolist())
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
228
    print("Query done: " + str(time() - t0))
229
230
231
232
233
234
235
236
237
238
    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
239
    print("Starting average progress")
240
241
242
    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
243
        actual_windows.extend(data[windows])
244
245
246
        if len(actual_windows) == 0:
            output.append([])
            continue
247
248
249
        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
250
        output = [({
251
252
253
            'average': average_values,
            'max': max_values,
            'min': min_values
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
254
        })] + output
255
256
257
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
    print("Averages calculated: " + str(time() - t0))
258
259
    return response

260
261
@app.route('/average-table', methods=['POST'])
def average_table():
262
263
264
265
266
    t0 = time()
    raw_data = orjson.loads(request.data)
    all_windows = raw_data['windows']
    data = np.load('processed-data.npy')
    output = []
267
    print("Initialized: " + str(time() - t0))
268
269
    for windows in all_windows:
        t1 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
270
        actual_windows = data[windows]
271
        print(len(actual_windows))
272
273
274
275
276
277
278
        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()
279
        output.append({
280
281
282
            'average': average_values.tolist(),
            'max': max_values.tolist(),
            'min': min_values.tolist()
283
        })
284
285
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
286
    print("Averages calculated: " + str(time() - t0))
287
    return response