a-y-khan

// Create subcontract info
// handling null fields from http://stackoverflow.com/questions/37081842/cant-merge-with-null-values-cannot-merge-node-using-null-property-value-in-n
USING PERIODIC COMMIT 100
LOAD CSV WITH HEADERS FROM "file:///subaward3.csv" AS row
MERGE (p:Primary {name: row.prime_awardee_parent_contractor_name, awardeeParentContractorName: row.prime_awardee_parent_contractor_name})
ON CREATE SET p.awardeeParentDUNS = row.prime_awardee_parent_duns
ON MATCH SET p.awardeeParentDUNS = row.prime_awardee_parent_duns
ON CREATE SET p.awardPrincipalNAICSCode = row.prime_award_principal_naics_code
ON MATCH SET p.awardPrincipalNAICSCode = row.prime_award_principal_naics_code
MERGE (s:Subaward {name: row.subawardee_name, DUNS: row.subawardee_dunsnumber, amount: row.subaward_amount})

a-y-khan

import math
import sys
import ijson
import csv
import argparse

def extract_to_csv(json_filename, new_json_filename, csv_filename):
  # ijson's parser chokes on NaNs, so let's get rid of them
  # NaN containing fields not needed for Adam's analysis?
  # if Circularity and Pixel area are NaN, we're in trouble!!!

a-y-khan

import argparse
import ast
import pandas as pd

from datetime import datetime
from distutils.util import strtobool
from typing import Dict, List, Union


def convert_to_dict_list(string: str) -> Union[List[Dict], None]:

a-y-khan

a-y-khan

a-y-khan

import json
import requests
import subprocess


def query_github_graphql(url: str, api_token: str, owner: str, service: str, pull_request: int):
    headers = {'Authorization': 'bearer {}'.format(api_token), 'Content-Type': 'application/json'}
    payload = {'query': '{repository(owner:\"%s\", name: \"%s\"){pullRequest(number: %d){headRefName,baseRefName}}}' % (owner, service, pull_request)}
    response = requests.post(url=url, json=payload, headers=headers)
    print(response.text)

a-y-khan

a-y-khan

a-y-khan

a-y-khan