Add popular stocks to ticker reference data

edgar/reference/data/common.py

@@ -32,11 +32,10 @@ def read_pyarrow_from_package(parquet_filename: str):
     return table
 
 
-@lru_cache(maxsize=1)
-def read_csv_from_package(csv_filename: str):
+def read_csv_from_package(csv_filename: str, **pandas_kwargs):
     package_name = 'edgar.reference.data'
 
     with resources.path(package_name, csv_filename) as csv_path:
-        df = pd.read_csv(csv_path)
+        df = pd.read_csv(csv_path, **pandas_kwargs)
 
     return df

edgar/reference/data/popular_us_stocks.csv

@@ -0,0 +1,86 @@
+Ticker,Company,Cik
+AAPL,Apple Inc.,320193
+MSFT,Microsoft Corporation,789019
+AMZN,"Amazon.com, Inc.",1018724
+NVDA,NVIDIA Corporation,1045810
+TSLA,"Tesla, Inc.",1318605
+GOOGL,Alphabet Inc. Class A,1652044
+META,"Meta Platforms, Inc.",1326801
+AMD,"Advanced Micro Devices, Inc.",2488
+NFLX,"Netflix, Inc.",1065280
+BRK.B,Berkshire Hathaway Inc.,1067983
+V,Visa Inc.,1403161
+JNJ,Johnson & Johnson,200406
+PG,Procter & Gamble Co.,80424
+JPM,JPMorgan Chase & Co.,19617
+UNH,UnitedHealth Group Incorporated,731766
+DIS,The Walt Disney Company,1744489
+HD,"Home Depot, Inc.",354950
+XOM,Exxon Mobil Corporation,34088
+KO,Coca-Cola Company,21344
+PEP,"PepsiCo, Inc.",77476
+PFE,Pfizer Inc.,78003
+MA,Mastercard Incorporated,1141391
+ADBE,Adobe Inc.,796343
+CRM,"Salesforce, Inc.",1108524
+INTC,Intel Corporation,50863
+CSCO,"Cisco Systems, Inc.",858877
+NKE,"Nike, Inc.",320187
+T,AT&T Inc.,732717
+CMCSA,Comcast Corporation,1166691
+VZ,Verizon Communications Inc.,732712
+CVX,Chevron Corporation,93410
+ABBV,AbbVie Inc.,1551152
+MRK,"Merck & Co., Inc.",310158
+BMY,Bristol-Myers Squibb Company,14272
+WMT,Walmart Inc.,104169
+MCD,McDonald's Corporation,63908
+SBUX,Starbucks Corporation,829224
+GS,"Goldman Sachs Group, Inc.",886982
+MS,Morgan Stanley,895421
+AXP,American Express Company,4962
+C,Citigroup Inc.,831001
+BA,Boeing Company,12927
+DAL,"Delta Air Lines, Inc.",27904
+LUV,Southwest Airlines Co.,92380
+MAR,"Marriott International, Inc.",1048286
+HLT,Hilton Worldwide Holdings Inc.,1585689
+BKNG,Booking Holdings Inc.,1075531
+PYPL,"PayPal Holdings, Inc.",1633917
+SQ,"Square, Inc.",1512673
+ZM,"Zoom Video Communications, Inc.",1585521
+SNOW,Snowflake Inc.,1640147
+UBER,"Uber Technologies, Inc.",1543151
+LYFT,"Lyft, Inc.",1759509
+ROKU,"Roku, Inc.",1428439
+SPOT,Spotify Technology S.A.,1639920
+SHOP,Shopify Inc.,1594805
+EBAY,eBay Inc.,1065088
+TWTR,"Twitter, Inc.",1418091
+SNAP,Snap Inc.,1564408
+PINS,"Pinterest, Inc.",1506293
+PLTR,Palantir Technologies Inc.,1321655
+ZI,ZoomInfo Technologies Inc.,1794515
+DOCU,"DocuSign, Inc.",1261333
+TWLO,Twilio Inc.,1447669
+CRWD,"CrowdStrike Holdings, Inc.",1535527
+NET,"Cloudflare, Inc.",1477333
+DDOG,"Datadog, Inc.",1561550
+MDB,"MongoDB, Inc.",1441816
+ZS,"Zscaler, Inc.",1713683
+OKTA,"Okta, Inc.",1660134
+DBX,"Dropbox, Inc.",1467623
+SMAR,Smartsheet Inc.,1366561
+ASAN,"Asana, Inc.",1477720
+RNG,"RingCentral, Inc.",1384905
+PTON,"Peloton Interactive, Inc.",1639825
+TTD,"The Trade Desk, Inc.",1671933
+HUBS,"HubSpot, Inc.",1404655
+COUP,Coupa Software Incorporated,1385867
+AYX,"Alteryx, Inc.",1689923
+SPLK,Splunk Inc.,1353283
+NEWR,"New Relic, Inc.",1448056
+DT,"Dynatrace, Inc.",1773383
+NOW,"ServiceNow, Inc.",1373715
+WDAY,"Workday, Inc.",1327811
+ADSK,"Autodesk, Inc.",769397

edgar/reference/tickers.py

@@ -1,6 +1,6 @@
-import re
-import os
 import json
+import os
+import re
 from functools import lru_cache
 from io import StringIO
 from pathlib import Path
@@ -10,12 +10,12 @@
 import pyarrow as pa
 from httpx import HTTPStatusError
 
-from edgar.httprequests import download_file, download_json, download_datafile
-from edgar.reference.data.common import read_parquet_from_package
 from edgar.core import log, get_edgar_data_directory
+from edgar.httprequests import download_file, download_json, download_datafile
+from edgar.reference.data.common import read_parquet_from_package, read_csv_from_package
 
 __all__ = ['cusip_ticker_mapping', 'get_ticker_from_cusip', 'get_company_tickers', 'get_icon_from_ticker', 'find_cik',
-           'get_cik_tickers', 'get_company_ticker_name_exchange', 'get_companies_by_exchange',
+           'get_cik_tickers', 'get_company_ticker_name_exchange', 'get_companies_by_exchange', 'popular_us_stocks',
            'get_mutual_fund_tickers', 'find_mutual_fund_cik', 'list_all_tickers']
 
 ticker_txt_url = "https://www.sec.gov/include/ticker.txt"
@@ -380,6 +380,13 @@ def get_icon_from_ticker(ticker: str) -> Optional[bytes]:
         else:
             raise
 
+def popular_us_stocks():
+    df = (read_csv_from_package('popular_us_stocks.csv', dtype={'Cik': int})
+          .set_index('Cik')
+          )
+    return df
+
+
 
 def download_ticker_data(reference_data_directory: Path):
     """

tests/batch/batch_management_discussions.py

@@ -0,0 +1,18 @@
+from edgar.reference.tickers import popular_us_stocks
+from edgar import *
+from tqdm.auto import tqdm
+
+def load_management_discussions():
+    for cik in tqdm(popular_us_stocks().index):
+        company = Company(cik)
+        tenk = company.latest_tenk
+        if tenk:
+            mda = tenk['Item 7']
+            if not mda:
+                print(f"No MDA found for {company.tickers}")
+                print(tenk.items)
+
+if __name__ == '__main__':
+    load_management_discussions()
+
+

tests/test_tickers.py

@@ -1,5 +1,5 @@
 
-from edgar.reference.tickers import cusip_ticker_mapping, get_ticker_from_cusip, get_company_tickers, get_icon_from_ticker, clean_company_suffix
+from edgar.reference.tickers import popular_us_stocks, get_ticker_from_cusip, get_company_tickers, get_icon_from_ticker, clean_company_suffix
 import pandas as pd
 import pyarrow as pa
 import pytest
@@ -49,3 +49,9 @@ def test_get_icon_bad_ticker():
 
     with pytest.raises(ValueError):
         icon = get_icon_from_ticker(123)
+
+
+def test_popular_us_stocks():
+    stocks = popular_us_stocks()
+    assert not stocks.empty
+    assert stocks[stocks.Ticker=='WDAY'].index.item() ==1327811