KalebNyquist

import pandas as pd
import numpy as np

def strange_zeroes(dataset, drop_columns = None, zero = 0):
    """Exploratory Data Analysis function that looks to see if there is any correlation between '0' values occurerence,
        which would suggest a relationship between the instruments used and their non-detection of a value."""
    
    # Find all zeroes (can be altered to including other common missing / non-response values as well)
    zeroes = (dataset == zero)
    

KalebNyquist

import requests

headers = {"Authorization" : "Bearer [INSERT AIRTABLE API KEY HERE]"}
params = (
    ('maxRecords', '100'),
    ('view', 'Grid view'))
URL = 'https://api.airtable.com/v0/appgaUkvDLKnYOmdA/URLS%20to%20Process'

response = requests.get(URL, params = params, headers = headers)

KalebNyquist

import newspaper

article = newspaper.Article(urls[0])
article.download()
article.parse()
article.nlp()

KalebNyquist

upload_dict = {
        "fields": {
            "URL" : article.url,
            "Title" : article.title,
            "Date" : publish_date(article),
            "Author(s)" : article.authors,
            "Site Name" : article.meta_data['og']['site_name'],
            "Media" : determine_media(article),
            "Opinion" : determine_opinion(article),
            "Keywords" : article.keywords,

KalebNyquist

author_dict = create_author_dict()

for author in article.authors:
    if author in list(author_dict.keys()):
        print("Author already exists")
    else:
        print(add_new_author(author))
        
author_dict = create_author_dict()

KalebNyquist

def convert_authors_to_ids(authors):
    author_ids = []
    for author in authors:
        author_ids.append(author_dict[author])
    return author_ids

upload_dict = {
        "fields": {
            "URL" : article.url,
            "Title" : article.title,

KalebNyquist

import json
upload_data = json.dumps(upload_dict)
headers = {
    "Authorization" : "Bearer INSERT AIRTABLE USER API KEY HERE",
    'Content-Type': 'application/json',
}
URL = 'https://api.airtable.com/v0/INSERT AIRTABLE DOC KEY HERE/Online%20Media%20Hits'
response = requests.post(URL, headers=headers, data=upload_data)

KalebNyquist

def find_locations_in_pandas_dataframe(dataframe, search_term, starts_with_search_term=False):
    """ Returns an ordered list of (dataframe column, dataframe row, specific string) index values where `search_term` is 
    found in Pandas `dataframe` string data.
    
    Keyword arguments:
    starts_with_search_term: if set to True, then returns only strings that start with `search_term` 
      i.e., "Re" in "Rebecca" but not "González, Rebecca"
      
    Source: https://gist.github.com/KalebNyquist/6781634b4ad307576046352696d2d194
    """

KalebNyquist

import requests
import json
import pandas as pd


def airtable_download(table, params_dict={}, api_key=None, base_id=None, record_id=None):
    """Makes a request to Airtable for all records from a single table.
        Returns data in dictionary format.

    Keyword Arguments:

KalebNyquist

import requests
import pandas as pd
from bs4 import BeautifulSoup

# List of States
# source: https://gist.github.com/mshafrir/2646763#gistcomment-1583853
states = {"al":"alabama","ak":"alaska","az":"arizona","ar":"arkansas","ca":"california","co":"colorado","ct":"connecticut","dc":"district of columbia","de":"delaware","fl":"florida","ga":"georgia","hi":"hawaii","id":"idaho","il":"illinois","in":"indiana","ia":"iowa","ks":"kansas","ky":"kentucky","la":"louisiana","me":"maine","md":"maryland","ma":"massachusetts","mi":"michigan","mn":"minnesota","ms":"mississippi","mo":"missouri","mt":"montana","ne":"nebraska","nv":"nevada","nh":"new hampshire","nj":"new jersey","nm":"new mexico","ny":"new york","nc":"north carolina","nd":"north dakota","oh":"ohio","ok":"oklahoma","or":"oregon","pa":"pennsylvania","ri":"rhode island","sc":"south carolina","sd":"south dakota","tn":"tennessee","tx":"texas","ut":"utah","vt":"vermont","va":"virginia","wa":"washington","wv":"west virginia","wi":"wisconsin","wy":"wyoming"}
states =