main.py 9.15 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
14
15
import bigwig
import bbi

reload = False
16
17
18
19
20
21
22
23
24
25

app = Flask(__name__)
CORS(app)

@app.route('/', methods=['GET'])
def index():
    return "hi"

@app.route('/read-data', methods=['GET'])
def read_data():
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
26
27
28
29
    size = bbi.chromsizes('test.bigWig')['chr1']
    bins = 100000
    data = bigwig.get('test.bigWig', 'chr1', 0, size, bins)
    print(data.shape)
30
    response = {
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
31
32
        "index": list(range(0, size, int(size/(bins)))),
        "values": data.tolist()
33
    }
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
34
    response = orjson.dumps(response)
35
36
37
38
    return response

@app.route('/create-windows', methods=['POST'])
def create_windows():
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
39
40
    if reload:
        size = bbi.chromsizes('test.bigWig')['chr1']
41
42
        raw_data = request.json
        window_size = int(raw_data['parameters']["windowsize"])
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
43
44
45
46
47
48
49
50
51
        data = bigwig.chunk(
            'test.bigWig',
            12000,
            12000 / window_size,
            12000 / 6,
            ['chr1'],
            verbose=True,
        )
        print(data.shape)
52
53
        np.save('processed-data', data)
    return '1'
54
55
56

@app.route('/create-tables', methods=['POST'])
def create_tables():
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
    t0 = time()
    print("loading")
    data = np.load('processed-data.npy')
    print(time()-t0)
    raw_data = orjson.loads(request.data)
    print(time()-t0)
    window_size = int(raw_data['parameters']["windowsize"])
    hash_size = int(raw_data['parameters']["hashsize"])
    table_size = int(raw_data['parameters']["tablesize"])
    data = np.array(data)
    print('Starting: ' + str(time()-t0))
    tables_hash_function = [np.random.uniform(-1, 1, size=(window_size, hash_size)) for _ in range(table_size)]
    print('Init time: ' + str(time() - t0))
    tables = []
    for index in range(table_size):
        t1 = time()
        table = defaultdict(list)
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
74
        signatures_bool = np.dot(data, tables_hash_function[index]) > 0
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
        signatures = [''.join(['1' if x else '0' for x in lst]) for lst in signatures_bool]
        for i in range(len(signatures)):
            table[signatures[i]].append(i)
        print(time()-t1)
        tables.append(table)

    print('Creation time: ' + str(time() - t0))
    hash_functions = np.array(tables_hash_function).tolist()
    response = {}
    for table_index in range(table_size):
        response[str(table_index)] = {
            "hash": hash_functions[table_index],
            "entries": tables[table_index]
        }
    response = orjson.dumps(response)
    return response

92
93
@app.route('/query', methods=['POST'])
def query():
94
    t0 = time()
95
    raw_data = orjson.loads(request.data)
96
    window = raw_data['window']
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
    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]
114
    response = orjson.dumps(output.tolist())
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
115
116
    print(output)
    print("Query done: " + str(time() - t0))
117
118
119
120
121
122
123
    return response

@app.route('/similarity', methods=['POST'])
def similarity():
    t0 = time()
    raw_data = orjson.loads(request.data)
    window = raw_data['query']
124
125
126
    tables = raw_data["tables"]
    neighbours = []

Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
127
    output = defaultdict(list)
128
129

    for t in tables.values():
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
130
        signature_bool = np.dot(window, t["hash"]) > 0
131
        signature = ''.join(['1' if x else '0' for x in signature_bool])
132
        neighbours.extend(t["entries"][signature])
133
134
    neighbours_with_frequency = dict(Counter(neighbours))
    for index, frequency in neighbours_with_frequency.items():
135
        output[str(frequency)].append(index)
136
    response = orjson.dumps(output)
137
138
139
140
141
142
143
144
145
146
147
    print("Similarity done: " + str(time()-t0))
    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
148
    print("Starting average progress")
149
150
151
    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
152
        actual_windows.extend(data[windows])
153
154
155
        if len(actual_windows) == 0:
            output.append([])
            continue
156
157
158
        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
159
        output = [({
160
161
162
            'average': average_values,
            'max': max_values,
            'min': min_values
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
163
        })] + output
164
165
166
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
    print("Averages calculated: " + str(time() - t0))
167
168
    return response

169
170
@app.route('/average-table', methods=['POST'])
def average_table():
171
172
173
174
175
    t0 = time()
    raw_data = orjson.loads(request.data)
    all_windows = raw_data['windows']
    data = np.load('processed-data.npy')
    output = []
176
    print("Initialized: " + str(time() - t0))
177
178
    for windows in all_windows:
        t1 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
179
        actual_windows = data[windows]
180
        print(len(actual_windows))
181
182
183
184
185
186
187
        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()
188
        output.append({
189
190
191
            'average': average_values.tolist(),
            'max': max_values.tolist(),
            'min': min_values.tolist()
192
        })
193
194
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
195
    print("Averages calculated: " + str(time() - t0))
196
197
198
199
200
    return response

@app.route('/update', methods=['POST'])
def update():
    t0 = time()
201
    print("Start")
202
    raw_data = orjson.loads(request.data)
203
204
    print("Data loaded: " + str(time() - t0))
    data = np.load('processed-data.npy')
205
206
    label_data = raw_data["labelData"]
    tables = raw_data["tables"]
207
    window = raw_data["query"]
208
209
210
211
212
213

    window_size = int(raw_data['parameters']["windowsize"])
    hash_size = int(raw_data['parameters']["hashsize"])
    table_size = int(raw_data['parameters']["tablesize"])
    new_tables = []

214
215
    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]
216

217
    print("Initialized: " + str(time() - t0))
218
219
    for t in tables.values():
        valid = True
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
220
        signature = ''.join((np.dot(window, t["hash"]) > 0).astype('int').astype('str'))
221
        neighbours = t["entries"][signature]
222
223
224
225
226
227
228
229
230
231
        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)
232
233
234
235
236
237
    print("Filtered good tables: " + str(time() - t0))
    for index in range(table_size - len(new_tables)):
        entries = defaultdict(list)
        t1 = time()
        while True:
            hash_function = np.random.randn(window_size, hash_size)
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
238
            correct_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
239
                                  i in
240
                                  correct_indices]
241
242
            incorrect_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
                                    i
243
244
245
246
247
248
249
                                    in incorrect_indices]
            if correct_signatures.count(correct_signatures[0]) == len(
                    correct_signatures) and incorrect_signatures.count(
                    correct_signatures[0]) == 0:
                break
        print("first: " + str(time() - t1))
        t2 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
250
        signatures_bool = np.dot(data, hash_function) > 0
251
252
253
254
255
256
257
258
        signatures = [''.join(['1' if x else '0' for x in lst]) for lst in signatures_bool]
        for i in range(len(signatures)):
            entries[signatures[i]].append(i)
        print("second: " + str(time() - t2))
        new_tables.append({
            "hash": hash_function.tolist(),
            "entries": entries
        })
259

260
261
262
263
264
265
266
267
    print('Update time: ' + str(time() - t0))
    response = {}
    for table_index in range(len(new_tables)):
        response[table_index] = {
            "hash": new_tables[table_index]["hash"],
            "entries": new_tables[table_index]["entries"]
        }
    response = jsonify(response)
268
    return response