main.py 9.13 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

@app.route('/create-tables', methods=['POST'])
def create_tables():
62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78
    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
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
    output = preprocessing.minmax_scale(window, (-1, 1))
103 104 105 106 107 108 109 110 111
    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():
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
118
        signature_bool = np.dot(window, t["hash"]) > 0
119
        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
    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()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
139
        actual_windows.extend(data[windows])
140 141 142
        if len(actual_windows) == 0:
            output.append([])
            continue
143 144 145 146 147 148 149 150
        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()
        output.append({
            'average': average_values,
            'max': max_values,
            'min': min_values
        })
151 152 153
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
    print("Averages calculated: " + str(time() - t0))
154 155
    return response

156 157
@app.route('/average-table', methods=['POST'])
def average_table():
158 159 160 161 162
    t0 = time()
    raw_data = orjson.loads(request.data)
    all_windows = raw_data['windows']
    data = np.load('processed-data.npy')
    output = []
163
    print("Initialized: " + str(time() - t0))
164 165
    for windows in all_windows:
        t1 = time()
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
166
        actual_windows = data[windows]
167
        print(len(actual_windows))
168 169 170 171 172 173 174
        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()
175
        output.append({
176 177 178
            'average': average_values.tolist(),
            'max': max_values.tolist(),
            'min': min_values.tolist()
179
        })
180 181
        print("Average calculated: " + str(time() - t1))
    response = orjson.dumps(output)
182
    print("Averages calculated: " + str(time() - t0))
183 184 185 186 187
    return response

@app.route('/update', methods=['POST'])
def update():
    t0 = time()
188
    print("Start")
189
    raw_data = orjson.loads(request.data)
190 191
    print("Data loaded: " + str(time() - t0))
    data = np.load('processed-data.npy')
192 193
    label_data = raw_data["labelData"]
    tables = raw_data["tables"]
194
    window = raw_data["query"]
195 196 197 198 199 200

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

201 202
    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]
203

204
    print("Initialized: " + str(time() - t0))
205 206
    for t in tables.values():
        valid = True
Kruyff,D.L.W. (Dylan)'s avatar
Kruyff,D.L.W. (Dylan) committed
207
        signature = ''.join((np.dot(window, t["hash"]) > 0).astype('int').astype('str'))
208
        neighbours = t["entries"][signature]
209 210 211 212 213 214 215 216 217 218
        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)
219 220 221 222 223 224
    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
225
            correct_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
226
                                  i in
227
                                  correct_indices]
228 229
            incorrect_signatures = [''.join((np.dot(data[i], hash_function) > 0).astype('int').astype('str')) for
                                    i
230 231 232 233 234 235 236
                                    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
237
        signatures_bool = np.dot(data, hash_function) > 0
238 239 240 241 242 243 244 245
        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
        })
246

247 248 249 250 251 252 253 254
    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)
255
    return response