import pandas as pd # Keys key_all = "All R&D expenditures" key_federal = "Federal government" key_state = "State and local government" key_inst = "Institution funds" key_business = "Business" key_nonprofit = "Nonprofit organizations" key_other = "All other sources" keys = [key_federal, key_state, key_inst, key_business, key_nonprofit, key_other] percent_suffix = " Percent" def read_excel(file): # Read excel df = pd.read_excel(file, header=3) # Remove fluff df = df[:-4][[field for field in df[:-4] if 'Unnamed' not in field]] # Add percent for key in keys: key_percent = key + percent_suffix df[key_percent] = df[key] / df[key_all] * 100 return df def print_data(data): print(data)