vannguyen3007

def load_ecg(file):
    # load the ecg
    # example file: 'mit-bih-arrhythmia-database-1.0.0/101'
    
    # load the ecg
    record = wfdb.rdrecord(file)
    # load the annotation
    annotation = wfdb.rdann(file, 'atr')
    
    # extract the signal

vannguyen3007

os.makedirs("annotated_results", exist_ok=True)
test_image_paths = test_df.file_name.unique()


for clothing_image in test_image_paths:
  file_path = f'{IMAGES_PATH}/{clothing_image}'
  im = cv2.imread(file_path)
  outputs = predictor(im)
  v = Visualizer(
    im[:, :, ::-1],

vannguyen3007

os.makedirs("faces", exist_ok=True)

dataset = []

for index, row in tqdm(faces_df.iterrows(), total=faces_df.shape[0]):
    img = urllib.request.urlopen(row["content"])
    img = Image.open(img)
    img = img.convert('RGB')

    image_name = f'face_{index}.jpeg'

vannguyen3007

!pip install -U torch==1.5 torchvision==0.6 -f https://download.pytorch.org/whl/cu101/torch_stable.html 
!pip install cython pyyaml==5.1
!pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
import torch, torchvision
print(torch.__version__, torch.cuda.is_available())
!gcc --version

vannguyen3007

def cal_shap(num, m = 150000):
    x_sample = numpy_sample(valx, m, 1)
    features_permute = np.array([np.random.permutation(i) for i in np.tile(np.array(list(range(25))),(m,1))])
    shap_values = []

    for i,f in enumerate(features):
        b1 = [np.concatenate([instance[:,:,:i+1],x_sample[:,j:j+1,fts[i+1:]]],axis=2) for j, fts in enumerate(features_permute)]
        b1 = np.concatenate(b1,axis=1)

        b2 = [np.concatenate([instance[:,:,:i],x_sample[:,j:j+1,fts[i:]]],axis=2) for j, fts in enumerate(features_permute)]

vannguyen3007

fig = plt.figure(figsize=(10,10))

for f, feature in enumerate(features):
    print(feature_dict[feature]['meaning'], end="\r")    
    Min, _, _, _, Max, _ = boxnwhisker_value(np.reshape(x_transpose[:,:,f:f+1],-1))
    mean = feature_dict[feature]['mean']                                   
    std = feature_dict[feature]['std']
    x = np.linspace(Min, Max, num_space)
    X, Y = np.meshgrid(x, time_range)
    preds = []    

vannguyen3007

class attention_block(nn.Module):
    def __init__(self, input_sz = 64, hidden_sz = 64, tp = 'fea'):
        super().__init__()
        self.tp = tp
        self.ln_h = linear_block(hidden_sz, input_sz)
        self.ln_i = linear_block(input_sz, input_sz)
        self.ln_w = linear_block(input_sz, input_sz)
        self.v = self.rand_p(input_sz, input_sz)
    
    @staticmethod

vannguyen3007

{
    "count": 23,
    "data": {
        "address_city_district": "Chau Thanh District",
        "address_country": "Vietnam",
        "address_full": "Village 9, Tan Thach Commune, Chau Thanh District, Ben Tre Province",
        "address_full_en": "Village 9, Tan Thach Commune, Chau Thanh District, Ben Tre Province",
        "address_province": "Ben Tre Province",
        "address_street": "Village 9",
        "auditing_company": [

vannguyen3007

# -*- coding: utf-8 -*-
from flask import Flask

from module.company.model_crawler import db_crawler
from module.company.view import module_company
from module.home.view import module_home

def create_app():
    app = Flask(__name__)
    # setup config

vannguyen3007

import datetime
import json

from flask import Blueprint, jsonify, request

from module.company.model_crawler import Company, db_crawler
from module.company.vietnammarkets.VietnamMarkets import VietnamMarkets

module_company = Blueprint('module_scrap_news', __name__, template_folder='templates')