main.py 7.39 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
    query = raw_data['query']
102 103
    tables = raw_data["tables"]
    neighbours = []
104 105
    data = np.load('processed-data.npy')
    window = data[query]
106

Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
107
    output = defaultdict(list)
108 109

    for t in tables.values():
110 111
        signature = ''.join((np.dot(window, t["hash"]) > 0).astype('int').astype('str'))
        neighbours.extend(t["entries"][signature])
112 113
    neighbours_with_frequency = dict(Counter(neighbours))
    for index, frequency in neighbours_with_frequency.items():
114
        output[str(frequency)].append(index)
115
    response = orjson.dumps(output)
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133
    print("Query done: " + str(time()-t0))
    return response

@app.route('/average', methods=['POST'])
def average():
    t0 = time()
    raw_data = orjson.loads(request.data)
    all_windows = raw_data['windows']
    data = np.load('processed-data.npy')
    output = []
    for windows in all_windows:
        t1 = time()
        actual_windows = data[windows]
        output.append((np.sum(actual_windows, 0)/len(actual_windows)).tolist())
        #output.append([(sum(x)/len(actual_windows)).item() for x in zip(*actual_windows)])
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
    print("Average calculated: " + str(time() - t0))
134 135 136 137 138
    return response

@app.route('/update', methods=['POST'])
def update():
    t0 = time()
139
    print("Start")
140
    raw_data = orjson.loads(request.data)
141 142
    print("Data loaded: " + str(time() - t0))
    data = np.load('processed-data.npy')
143 144 145 146 147 148 149 150
    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 = []

151 152
    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]
153 154

    window = data[correct_indices[0]]
155
    print("Initialized: " + str(time() - t0))
156 157
    for t in tables.values():
        valid = True
158 159
        signature = ''.join((np.dot(window, t["hash"]) > 0).astype('int').astype('str'))
        neighbours = t["entries"][signature]
160 161 162 163 164 165 166 167 168 169
        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)
170 171 172 173 174 175
    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)
176 177
            correct_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
                                  i in
178
                                  correct_indices]
179 180
            incorrect_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
                                    i
181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196
                                    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
        })
197

198 199 200 201 202 203 204 205
    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)
206
    return response