main.py 6.98 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
10
import dask.dataframe as dd
import os.path
import json
from sklearn import preprocessing
11
import orjson
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
32
33
    filename = 'processed-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")
    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
    response = jsonify(response)
    return response

42
43
44
45
46
47
48
49
50
51
52
53
# @app.route('/read-data', methods=['GET'])
# def read_data():
#     df = pd.read_csv("1.csv", index_col=3)
#     df.index = pd.to_datetime(df.index)
#     df.sort_index(inplace=True)
#     meantemp = df.loc[:, 7].copy()
#     response = {
#         "index": meantemp.index.values.astype(str).tolist(),
#         "values": meantemp.values.tolist()
#     }
#     response = jsonify(response)
#     return response
54
55
56

@app.route('/create-windows', methods=['POST'])
def create_windows():
57
    t0 = time()
58
59
    raw_data = request.json
    values = raw_data["values"]
60
    window_size = int(raw_data['parameters']["windowsize"])
61
62
    data = [values[i:i+window_size] for i in range(len(values) - window_size)]
    data = preprocessing.minmax_scale(data, (-1, 1), axis=1)
63
64
65
66
67
68
69
    print("Created windows: " + str(time()-t0))
    data = data.tolist()
    print("data converted: " + str(time()-t0))
    # response = {'data': data}
    print("Sending response: " + str(time()-t0))
    response = orjson.dumps(data)
    print("Sending response: " + str(time()-t0))
70
71
72
73
74
    return response

@app.route('/create-tables', methods=['POST'])
def create_tables():
    t0 = time()
75
76
77
    raw_data = orjson.loads(request.data)
    print(time()-t0)
    global data
78
    data = raw_data["windows"]
79
80
81
    window_size = int(raw_data['parameters']["windowsize"])
    hash_size = int(raw_data['parameters']["hashsize"])
    table_size = int(raw_data['parameters']["tablesize"])
82
    data = np.array(data)
83
84
    print('Starting: ' + str(time()-t0))
    global tables_hash_function
85
86
    tables_hash_function = [np.random.uniform(-1, 1, size=(window_size, hash_size)) for _ in range(table_size)]
    print('Init time: ' + str(time() - t0))
87
88
89
90
    tables = []
    for index in range(table_size):
        t1 = time()
        table = defaultdict(list)
91
92
        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]
93
94
95
96
        for i in range(len(signatures)):
            table[signatures[i]].append(i)
        print(time()-t1)
        tables.append(table)
97

98
99
100
101
    print('Creation time: ' + str(time() - t0))
    hash_functions = np.array(tables_hash_function).tolist()
    response = {}
    for table_index in range(table_size):
102
        response[str(table_index)] = {
103
104
105
            "hash": hash_functions[table_index],
            "entries": tables[table_index]
        }
106
    response = orjson.dumps(response)
107
108
109
110
    return response

@app.route('/query', methods=['POST'])
def query():
111
    raw_data = orjson.loads(request.data)
112
113
114
115
    window = raw_data["window"]
    tables = raw_data["tables"]
    neighbours = []

116
117
118
    output = {}

    for t in tables.values():
119
120
        signature = ''.join((np.dot(window, t["hash"]) > 0).astype('int').astype('str'))
        neighbours.extend(t["entries"][signature])
121
122
123
    neighbours_with_frequency = dict(Counter(neighbours))
    for index, frequency in neighbours_with_frequency.items():
        if not frequency in output:
124
125
            output[str(frequency)] = []
        output[str(frequency)].append(index)
126
    response = orjson.dumps(output)
127
128
129
130
131
    return response

@app.route('/update', methods=['POST'])
def update():
    t0 = time()
132
    raw_data = orjson.loads(request.data)
133

134
135
136
137
138
139
140
141
142
143
    data = raw_data["windows"]
    data = np.array(data)
    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 = []

144
145
    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]
146
147

    window = data[correct_indices[0]]
148
    print("Initialized: " + str(time() - t0))
149
150
    for t in tables.values():
        valid = True
151
152
        signature = ''.join((np.dot(window, t["hash"]) > 0).astype('int').astype('str'))
        neighbours = t["entries"][signature]
153
154
155
156
157
158
159
160
161
162
        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)
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
    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)
            correct_signatures = [''.join((np.dot(data[index], hash_function) > 0).astype('int').astype('str')) for
                                  index in
                                  correct_indices]
            incorrect_signatures = [''.join((np.dot(data[index], hash_function) > 0).astype('int').astype('str')) for
                                    index
                                    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
        })
190

191
192
193
194
195
196
197
198
    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)
199
    return response