In [21]:

# Load schools from salesforce
account_df = get_cysh_df('Account', ['Id', 'Name'])
account_df.rename(columns={'Id':'Organization__c', 'Name':'School'}, inplace=True)

d = []
for folder_name in set(heatmaps_df['Folder']):
    match = process.extract(folder_name, set(account_df['School']), scorer=fuzz.token_set_ratio, limit=1)
    match = [folder_name] + [x for tup in match for x in tup]
    d.append(match)
df = pd.DataFrame(d, columns=['Folder', 'School', 'Match_Score'])
df.head()

Out[21]:

	Folder	School	Match_Score
0	Gage Park	Gage Park High School	100
1	Johnson	Johnson School of Excellence	100
2	Phillips	Wendell Phillips Academy	100
3	Langford	Anna R. Langford Community Academy	100
4	Jordan	Jordan Elementary Community School	100