betterdatascience

from flask import Flask, request, jsonify
from flask_sqlalchemy import SQLAlchemy
from flask_marshmallow import Marshmallow
from flask_restful import Resource, Api


app = Flask(__name__)
api = Api(app)
app.config['SQLALCHEMY_DATABASE_URI'] = 'sqlite:///users.db'
app.config['SQLALCHEMY_TRACK_MODIFICATIONS'] = False

richiefrost

class QueryBuilder:
     def __init__(self):
          self.select_value = ''
          self.from_table_name = ''
          self.where_value = ''
          self.groupby_value = ''

     def select(self, select_arg):
          self.select_value = select_arg
          return self

gecko655

"""A liveness prober dag for monitoring composer.googleapis.com/environment/healthy."""
import airflow
from airflow import DAG
from airflow.operators.bash_operator import BashOperator
from datetime import timedelta

default_args = {
    'start_date': airflow.utils.dates.days_ago(0),
    'retries': 1,
    'retry_delay': timedelta(minutes=5)

lhlong

import cv2, queue, threading, time


class VideoCapture:
    def __init__(self, name):
        self.cap = cv2.VideoCapture(name)
        self.q = queue.Queue()
        t = threading.Thread(target=self._reader)
        t.daemon = True
        t.start()

cmungall

#!/usr/bin/env python3
import os
import re
import logging
import click

# don't index these
excludes = {
    'single_files',
    'Icon',

snakers4

class BertEmbeddingBag(nn.Module):
    """Construct the embeddings from word, position and token_type embeddings.
    """
    def __init__(self, config):
        super(BertEmbeddingBag, self).__init__()

        # self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size)
        ngram_matrix=np.load(config.ngram_matrix_path)

        self.old_bag = config.old_bag

anton-petrov

import re, csv
from time import sleep, time
from random import uniform, randint
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import NoSuchElementException    

J2TEAM

s1 = u'ÀÁÂÃÈÉÊÌÍÒÓÔÕÙÚÝàáâãèéêìíòóôõùúýĂăĐđĨĩŨũƠơƯưẠạẢảẤấẦầẨẩẪẫẬậẮắẰằẲẳẴẵẶặẸẹẺẻẼẽẾếỀềỂểỄễỆệỈỉỊịỌọỎỏỐốỒồỔổỖỗỘộỚớỜờỞởỠỡỢợỤụỦủỨứỪừỬửỮữỰựỲỳỴỵỶỷỸỹ'
s0 = u'AAAAEEEIIOOOOUUYaaaaeeeiioooouuyAaDdIiUuOoUuAaAaAaAaAaAaAaAaAaAaAaAaEeEeEeEeEeEeEeEeIiIiOoOoOoOoOoOoOoOoOoOoOoOoUuUuUuUuUuUuUuYyYyYyYy'
def remove_accents(input_str):
	s = ''
	print input_str.encode('utf-8')
	for c in input_str:
		if c in s1:
			s += s0[s1.index(c)]
		else:
			s += c

joshlk

import pandas as pd

def _map_to_pandas(rdds):
    """ Needs to be here due to pickling issues """
    return [pd.DataFrame(list(rdds))]

def toPandas(df, n_partitions=None):
    """
    Returns the contents of `df` as a local `pandas.DataFrame` in a speedy fashion. The DataFrame is
    repartitioned if `n_partitions` is passed.

bsweger

Useful Pandas Snippets

A personal diary of DataFrame munging over the years.

Data Types and Conversion

Convert Series datatype to numeric (will error if column has non-numeric values)
(h/t @makmanalp)