jaklinger

import requests
import json
import time 

'''Decorator for retrying up to 10 times'''
def retry(exception):
	def outer_retry(f):
		def inner_retry(*args,attempt=0):
			n=0
			while True:

jaklinger

focus_areas = ['Education Innovation and Technology',
               'Health Information Technology and Bioinformatics',               
               'Public Health, Non-Communicable Diseases and Wellness', 
               'Biotechnology and Genomics',
               'Water Management and Economics', 
               'Solar and Alternative Energy Technology Systems',                                            
               'Space Sciences', 
               'Cubesats and Nanosatellites', 
               'Cybersecurity',
               'Semiconductor Process Development',

jaklinger

# Geometry, shapefiles and projections
import fiona
from shapely.geometry import shape
from shapely.geometry import Point
import pyproj

# Generate a function to create a UK East/North point from Lon/Lat
wgs84 = pyproj.Proj(init = 'epsg:4326')
ukgrid = pyproj.Proj(init = 'epsg:27700')
EnPoint = lambda lon, lat : Point(*pyproj.transform(wgs84, ukgrid, lon, lat))

jaklinger

# Python tools
from matplotlib import pyplot as plt
import pandas as pd
import math
import numpy as np
from collections import defaultdict
from functools import partial
from mpl_toolkits.axes_grid1.inset_locator import inset_axes
import matplotlib as mpl

jaklinger

# Uncomment this for notebooks
# %matplotlib inline

import matplotlib as mpl
from matplotlib.patches import Polygon
from matplotlib.collections import PatchCollection
from mpl_toolkits.basemap import Basemap
import numpy as np

# Country codes --> alpha

jaklinger

import gender_guesser.detector as gender
import pandas as pd

path_to_file = "~/Downloads/test_names.xlsx"

d = gender.Detector()
data = pd.read_excel(path_to_file)

for name in data["names"].values:
    print(d.get_gender(name))

jaklinger

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions
import os
import time


def wait_and_find(driver, element_id, load_time):
    time.sleep(load_time/3)

jaklinger

# Note superfuzz can be found here: https://github.com/jaklinger/nesta_toolbox/blob/master/sandbox/jaklinger/superfuzz/superfuzz.py

import requests
from retrying import retry
import re
import time
from collections import Counter
from superfuzz.superfuzz import superfuzz
from fuzzywuzzy import fuzz
from fuzzywuzzy import process as fuzzy_process

jaklinger

-- Selecting nested elements (e.g. author names)
select author -> 'name' as author_name 
from microsoft_academic_graph 
cross join jsonb_array_elements(microsoft_academic_graph.paper -> 'authors') author 
limit 1;

-- Finding specific papers by author
select paper->'title', paper->'authors' 
from microsoft_academic_graph 
where paper->'authors' @> '[{"name":"John Smith"}]' 

jaklinger

from sqlalchemy import create_engine
from sqlalchemy import text as sql_text

# Stolen from https://stackoverflow.com/a/434328/1571593
def chunker(seq, size):
    return (seq[pos:pos + size] for pos in range(0, len(seq), size))

# Execute {SELECT ... IN ...} in chunks
'''Notes: 
1) query has to be of the form: