main.py 9.3 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():
26
    t0 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
27
28
29
30
    size = bbi.chromsizes('test.bigWig')['chr1']
    bins = 100000
    data = bigwig.get('test.bigWig', 'chr1', 0, size, bins)
    print(data.shape)
31
    response = {
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
32
33
        "index": list(range(0, size, int(size/(bins)))),
        "values": data.tolist()
34
    }
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
35
    response = orjson.dumps(response)
36
    print('Data read: ' + str(time()-t0))
37
38
39
40
    return response

@app.route('/create-windows', methods=['POST'])
def create_windows():
41
    t0 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
42
43
    if reload:
        size = bbi.chromsizes('test.bigWig')['chr1']
44
45
        raw_data = request.json
        window_size = int(raw_data['parameters']["windowsize"])
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
46
47
48
49
50
51
52
53
54
        data = bigwig.chunk(
            'test.bigWig',
            12000,
            12000 / window_size,
            12000 / 6,
            ['chr1'],
            verbose=True,
        )
        print(data.shape)
55
        np.save('processed-data', data)
56
    print('Windows created: ' + str(time()-t0))
57
    return '1'
58
59
60

@app.route('/create-tables', methods=['POST'])
def create_tables():
61
62
63
    t0 = time()
    print("loading")
    data = np.load('processed-data.npy')
64
    print('Number of tables: ' + str(data.shape))
65
66
67
68
69
70
71
72
    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))
73
    tables_hash_function = [np.random.uniform(-100, 100, size=(window_size, hash_size)) for _ in range(table_size)]
74
75
76
77
78
    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
79
        signatures_bool = np.dot(data, tables_hash_function[index]) > 0
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
        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

97
98
@app.route('/query', methods=['POST'])
def query():
99
    t0 = time()
100
    raw_data = orjson.loads(request.data)
101
    window = raw_data['window']
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
    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]
119
    response = orjson.dumps(output.tolist())
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
120
    print("Query done: " + str(time() - t0))
121
122
123
124
125
126
127
    return response

@app.route('/similarity', methods=['POST'])
def similarity():
    t0 = time()
    raw_data = orjson.loads(request.data)
    window = raw_data['query']
128
129
130
    tables = raw_data["tables"]
    neighbours = []

Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
131
    output = defaultdict(list)
132
133

    for t in tables.values():
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
134
        signature_bool = np.dot(window, t["hash"]) > 0
135
        signature = ''.join(['1' if x else '0' for x in signature_bool])
136
        neighbours.extend(t["entries"][signature])
137
138
    neighbours_with_frequency = dict(Counter(neighbours))
    for index, frequency in neighbours_with_frequency.items():
139
        output[str(frequency)].append(index)
140
    response = orjson.dumps(output)
141
142
143
144
145
146
147
148
149
150
151
    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
152
    print("Starting average progress")
153
154
155
    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
156
        actual_windows.extend(data[windows])
157
158
159
        if len(actual_windows) == 0:
            output.append([])
            continue
160
161
162
        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
163
        output = [({
164
165
166
            'average': average_values,
            'max': max_values,
            'min': min_values
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
167
        })] + output
168
169
170
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
    print("Averages calculated: " + str(time() - t0))
171
172
    return response

173
174
@app.route('/average-table', methods=['POST'])
def average_table():
175
176
177
178
179
    t0 = time()
    raw_data = orjson.loads(request.data)
    all_windows = raw_data['windows']
    data = np.load('processed-data.npy')
    output = []
180
    print("Initialized: " + str(time() - t0))
181
182
    for windows in all_windows:
        t1 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
183
        actual_windows = data[windows]
184
        print(len(actual_windows))
185
186
187
188
189
190
191
        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()
192
        output.append({
193
194
195
            'average': average_values.tolist(),
            'max': max_values.tolist(),
            'min': min_values.tolist()
196
        })
197
198
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
199
    print("Averages calculated: " + str(time() - t0))
200
201
202
203
204
    return response

@app.route('/update', methods=['POST'])
def update():
    t0 = time()
205
    print("Start")
206
    raw_data = orjson.loads(request.data)
207
208
    print("Data loaded: " + str(time() - t0))
    data = np.load('processed-data.npy')
209
210
    label_data = raw_data["labelData"]
    tables = raw_data["tables"]
211
    window = raw_data["query"]
212
213
214
215
216
217

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

218
219
    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]
220

221
    print("Initialized: " + str(time() - t0))
222
223
    for t in tables.values():
        valid = True
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
224
        signature = ''.join((np.dot(window, t["hash"]) > 0).astype('int').astype('str'))
225
        neighbours = t["entries"][signature]
226
227
228
229
230
231
232
233
234
235
        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)
236
237
238
239
240
241
    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
242
            correct_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
243
                                  i in
244
                                  correct_indices]
245
246
            incorrect_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
                                    i
247
248
249
250
251
252
253
                                    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
254
        signatures_bool = np.dot(data, hash_function) > 0
255
256
257
258
259
260
261
262
        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
        })
263

264
265
266
267
268
269
270
271
    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)
272
    return response