US higher education data dump with executive details, private public, 2 or 4 year, state, region, location.

[Jennbrown281]

import requests
import pandas as pd

URL to the IPEDS API for institutions

url = "https://api.data.gov/ed/collegescorecard/v1/schools.json"

Parameters for the API request

params = {
'api_key': 'YOUR_API_KEY', # Replace with your API key
'fields': 'id,school.name,school.state,school.locale,school.control,latest.enrollment.full_time,latest.enrollment.total,latest.programs.cip_4_digit',
'per_page': 100
}

Function to fetch data

def fetch_data(url, params):
response = requests.get(url, params=params)
response.raise_for_status()
return response.json()

Fetch and process data

def get_institutions():
institutions = []
page = 0

while True:
    params['page'] = page
    data = fetch_data(url, params)
    institutions.extend(data['results'])
    
    # Break if there are no more results
    if len(data['results']) < params['per_page']:
        break
    
    page += 1

return institutions

Convert data to DataFrame and save as CSV

def save_to_csv(data):
df = pd.DataFrame(data)
df.to_csv('us_higher_education_institutions.csv', index=False)

if name == "main":
institutions = get_institutions()
save_to_csv(institutions)
print("Data saved to 'us_higher_education_institutions.csv'")