main.py 8.34 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
12
13
14
15
16
17
18
19
20
21

app = Flask(__name__)
CORS(app)

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

@app.route('/read-data', methods=['GET'])
def read_data():
22
23
24
25
26
27
28
29
30
31
    filename = 'data.pkl'
    if (not os.path.isfile(filename)):
        print("start")
        df = dd.read_csv("NW_Ground_Stations_2016.csv", usecols=['number_sta', 'date', 't'])
        print("read file")
        df = df.loc[df['number_sta'] == 14066001]
        print("split rows")
        df = df.compute()
        df.to_pickle(filename)
        print("to_pandas")
32
33
    df = pd.read_pickle(filename)
    df.dropna(subset=['t'], inplace=True)
34
    response = {
35
36
        "index": json.dumps(df.loc[:, 'date'].values.astype(str).tolist()),
        "values": json.dumps(df.loc[:, 't'].values.astype(str).tolist())
37
    }
38
    print("response ready")
39
40
41
42
43
    response = jsonify(response)
    return response

@app.route('/create-windows', methods=['POST'])
def create_windows():
44
    t0 = time()
45
46
47
48
49
50
51
52
53
54
55
56
    if (not os.path.isfile('processed-data.npy')):
        filename = 'data.pkl'
        df = pd.read_pickle(filename)
        values = df.loc[:, 't'].values.astype(str).tolist()
        print("Data read: " + str(time()-t0))
        raw_data = request.json
        window_size = int(raw_data['parameters']["windowsize"])
        print("Processing: " + str(time()-t0))
        data = [values[i:i+window_size] for i in range(len(values) - window_size)]
        data = preprocessing.minmax_scale(data, (-1, 1), axis=1)
        print("Preprocessed: " + str(time()-t0))
        np.save('processed-data', data)
57
    print("Sending response: " + str(time()-t0))
58
    return '1'
59
60
61
62

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

86
87
88
89
    print('Creation time: ' + str(time() - t0))
    hash_functions = np.array(tables_hash_function).tolist()
    response = {}
    for table_index in range(table_size):
90
        response[str(table_index)] = {
91
92
93
            "hash": hash_functions[table_index],
            "entries": tables[table_index]
        }
94
    response = orjson.dumps(response)
95
96
97
98
    return response

@app.route('/query', methods=['POST'])
def query():
99
    t0 = time()
100
    raw_data = orjson.loads(request.data)
101
102
103
104
105
106
107
108
109
110
111
    window = raw_data['window']
    output = preprocessing.minmax_scale(window, (-1, 1))
    response = orjson.dumps(output.tolist())
    print("Query done: " + str(time()-t0))
    return response

@app.route('/similarity', methods=['POST'])
def similarity():
    t0 = time()
    raw_data = orjson.loads(request.data)
    window = raw_data['query']
112
113
114
    tables = raw_data["tables"]
    neighbours = []

Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
115
    output = defaultdict(list)
116
117

    for t in tables.values():
118
119
        signature_bool = np.dot(window, t["hash"]) > 0
        signature = ''.join(['1' if x else '0' for x in signature_bool])
120
        neighbours.extend(t["entries"][signature])
121
122
    neighbours_with_frequency = dict(Counter(neighbours))
    for index, frequency in neighbours_with_frequency.items():
123
        output[str(frequency)].append(index)
124
    response = orjson.dumps(output)
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
    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 = []
    print("Initialized: " + str(time() - t0))
    for windows in all_windows:
        t1 = time()
        actual_windows.extend(data[windows])
        print(len(actual_windows))
        output.append((np.sum(actual_windows, 0)/len(actual_windows)).tolist())
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
    print("Averages calculated: " + str(time() - t0))
145
146
    return response

147
148
@app.route('/average-table', methods=['POST'])
def average_table():
149
150
151
152
153
    t0 = time()
    raw_data = orjson.loads(request.data)
    all_windows = raw_data['windows']
    data = np.load('processed-data.npy')
    output = []
154
    print("Initialized: " + str(time() - t0))
155
156
157
    for windows in all_windows:
        t1 = time()
        actual_windows = data[windows]
158
        print(len(actual_windows))
159
160
161
        output.append((np.sum(actual_windows, 0)/len(actual_windows)).tolist())
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
162
    print("Averages calculated: " + str(time() - t0))
163
164
165
166
167
    return response

@app.route('/update', methods=['POST'])
def update():
    t0 = time()
168
    print("Start")
169
    raw_data = orjson.loads(request.data)
170
171
    print("Data loaded: " + str(time() - t0))
    data = np.load('processed-data.npy')
172
173
174
175
176
177
178
179
    label_data = raw_data["labelData"]
    tables = raw_data["tables"]

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

180
181
    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]
182
183

    window = data[correct_indices[0]]
184
    print("Initialized: " + str(time() - t0))
185
186
    for t in tables.values():
        valid = True
187
188
        signature = ''.join((np.dot(window, t["hash"]) > 0).astype('int').astype('str'))
        neighbours = t["entries"][signature]
189
190
191
192
193
194
195
196
197
198
        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)
199
200
201
202
203
204
    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)
205
206
            correct_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
                                  i in
207
                                  correct_indices]
208
209
            incorrect_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
                                    i
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
                                    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()
        signatures_bool = np.dot(data, hash_function) > 0
        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
        })
226

227
228
229
230
231
232
233
234
    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)
235
    return response