institutions using cik and tags

uw_token = os.environ['UW_TOKEN']
headers = {'Accept': 'application/json, text/plain', 'Authorization': uw_token}
url = f'https://api.unusualwhales.com/api/institutions'
responses = []
for i in range(0, 20):
    params = {'limit': 500, 'page': i}
    rsp = requests.get(url, headers=headers, params=params)
    if len(rsp.json()['data']) > 0:
        responses.append(rsp.json()['data'])
        time.sleep(1) # rate limit
    else:
        break

flat_list_of_institutions = [item for sublist in responses for item in sublist]
rprint(f'Example institution data:')
rprint(flat_list_of_institutions[0])
rprint(f'Total number of institutions found: {len(flat_list_of_institutions)}')

institutes = []
for inst in flat_list_of_institutions:
    institutes.append(
        {
            'cik': inst.get('cik', None),
            'name': inst.get('name', None),
            'people': inst.get('people', None),
            'is_hedge_fund': inst.get('is_hedge_fund', None),
            'tags': inst.get('tags', None),
            'total_value': inst.get('total_value', None),
            'filing_date': inst.get('filing_date', None),
            'logo_url': inst.get('logo_url', None),
            'founder_img_url': inst.get('founder_img_url', None),
        }
    )
raw_df = pl.DataFrame(institutes)
distinct_institutions_df = (
    raw_df
    .unique(subset=['cik'], keep='first')
    .with_columns(
        pl.col('total_value').cast(pl.Float64).cast(pl.Int64),
        pl.col('filing_date').str.strptime(pl.Date, '%Y-%m-%d'),
    )
    .sort('total_value', descending=True)
)
distinct_institutions_df

target_tags = [
    '13d_activist', 'activist', 'value_investor', 'small_cap', 'biotech',
    'credit', 'technology', 'tiger_club', 'energy', 'esg', 'event'
]
high_priority_institutions_df = (
    distinct_institutions_df
    .filter(
        pl.col('tags').list.eval(pl.element().is_in(target_tags)).list.any()
    )
)
high_priority_institutions_df