filter_jobs.py

# Grab data from https://drive.google.com/open?id=18IVEIp5qn4OnoWerC4f3e9MUwcBnM5U-

df = pd.read_excel('all_data_M_2018.xlsx')

df = df[df['o_group']=='detailed']
# Drop broad occupation groups

df = df[df['area']==99]
# Drop occupations for states, keep only those for the entire US

df = df[df['i_group'] == '4-digit']
# Drop 2 digit NAICS codes

df[pd.isna(df['tot_emp'])]
# Drop NAs in employment numbers

ceoDf = df[df['occ_code'] == '11-1011']
# Focus on CEOs only

ceoDf[ceoDf['naics']=='611100']
# Gives you 3 rows for CEOs in Elementary schools, with different ownerships

'''

naics	naics_title	own_code	tot_emp
118921	611100	Elementary and Secondary Schools	235	9210
118922	611100	Elementary and Secondary Schools	5	930
118923	611100	Elementary and Secondary Schools	3	8270
'''