def test_companyDF(self):
from pyEX import companyDF
with patch('requests.get') as mock:
mock.return_value = MagicMock()
mock.return_value.status_code = 200
mock.return_value.json = MagicMock(return_value={'test': [4], 'symbol': ['test']})
companyDF('test')
def test_companyDF(self):
from pyEX import companyDF
with patch("requests.get") as mock, patch("pickle.dump"):
mock.return_value = MagicMock()
mock.return_value.status_code = 200
mock.return_value.json = MagicMock(
return_value={"test": [4], "symbol": ["test"]}
)
companyDF("test")
def get_co_sector_industry_tags(self, row):
ticker = row.symbol
self.logger.info(
"IEXTradingApi.get_co_sector_industry_tags(): getting sector, industry, tags for ticker %s",
ticker)
df = pyex.companyDF(symbol=ticker)
co_sector_industry_tags = (
df.loc[ticker,
['sector', 'industry', 'tags', 'companyName', 'website']])
co_sector_industry_tags['symbol'] = ticker
# co_sector_industry_tags is a pandas Series
# access the symbol (ticker) by using ".name" of pd.Series object co_sector_industry_tags
alt_industries = co_sector_industry_tags['tags']
rows_to_insert = []
for alt_industry in alt_industries:
if alt_industry != co_sector_industry_tags['sector'] and \
alt_industry != co_sector_industry_tags['industry']:
rows_to_insert.append(
[co_sector_industry_tags['sector'], alt_industry])
rows_to_insert.append([
co_sector_industry_tags['sector'],
co_sector_industry_tags['industry']
])
for sector_industry in rows_to_insert:
if self.master_sector_indusry_df.index.size == 0:
next_index = 0
else:
next_index = self.master_sector_indusry_df.index[-1] + 1
if sector_industry[0] != '' and sector_industry[1] != '':
self.master_sector_indusry_df.loc[next_index] = sector_industry
print(self.master_sector_indusry_df)
def refetch(field, symbol):
if field == 'TICK':
return p.chartDF(symbol, '1d')
if field == 'FINANCIALS':
return p.financialsDF(symbol)
elif field == 'DAILY':
return p.chartDF(symbol, '5y')
elif field == 'COMPANY':
return p.companyDF(symbol)
elif field == 'EARNINGS':
return p.earningsDF(symbol)
elif field == 'DIVIDENDS':
return p.dividendsDF(symbol)
elif field == 'NEWS':
return p.newsDF(symbol)
elif field == 'STATS':
return p.stockStatsDF(symbol)
elif field == 'COMPOSITION':
return _fetchComposition(symbol)
elif field == 'PEERS':
return p.peersDF(symbol)
raise NotImplementedError('%s - %s' % (field, symbol))
def test_companyDF(self):
from pyEX import companyDF
companyDF(C)
companies = {company: {} for company in companies}
for company in topCompanies:
companies[company['name']]['symbol'] = company['symbol']
companies[company['name']]['industry_id'] = company['industry_id']
arbSymbol = 'AAPL'
# arbitrarily create df object
# get stock history for last month
arbChart = p.chartDF(arbSymbol, timeframe='1m')
# add stock symbol to df to act as a foreign key for company table
arbChart['symbol'] = "Arbitrary"
arbChart['industry_id'] = 0
# get company info
arbCompany = p.companyDF(arbSymbol)
# join the 2 tables and add to rest of stocks df
stocks_df = pd.merge(arbChart, arbCompany, how='left', on=['symbol'])
for company in companies.values():
symbol = company['symbol']
industry_id = company['industry_id']
# get stock history for last 1 month
chart_df = p.chartDF(symbol, timeframe='1y')
# add stock symbol to df to act as a foreign key for company table
chart_df['symbol'] = symbol
# add our unique identifier for industry to the table
chart_df['industry_id'] = industry_id
# get company info
company_df = p.companyDF(symbol)
# join the 2 tables and add to rest of stocks df
def test_companyDF(self):
from pyEX import companyDF
with patch('requests.get') as mock:
mock.return_value = MagicMock()
mock.return_value.status_code = 200
companyDF('test')
def fetchDF(self, key, field, _ret=True):
# tickers always caps
key = key.upper()
# fields always lower
field = field.lower()
if not (self._tickers['symbol'] == key).any():
# FIXME
return pd.DataFrame()
if key not in self._cache:
# initialize cache
self._cache[key] = {}
self._cache[key]['timestamp'] = {}
if field in ('financials', 'all'):
if 'financials' not in self._cache[key] or self._check_timestamp(
key, 'financials'):
try:
self._cache[key]['financials'] = p.financialsDF(key)
except KeyError:
self._cache[key]['financials'] = pd.DataFrame()
self._cache[key]['timestamp']['financials'] = datetime.now()
if field in ('chart', 'all'):
if 'chart' not in self._cache[key] or self._check_timestamp(
key, 'chart'):
try:
self._cache[key]['chart'] = p.chartDF(key, '1y')
except KeyError:
self._cache[key]['chart'] = pd.DataFrame()
self._cache[key]['timestamp']['chart'] = datetime.now()
if field in ('company', 'all'):
if 'company' not in self._cache[key] or self._check_timestamp(
key, 'company'):
self._cache[key]['company'] = p.companyDF(key)
self._cache[key]['timestamp']['company'] = datetime.now()
if field in ('quote', 'all'):
# always update
self._cache[key]['quote'] = p.quoteDF(key)
if field in ('dividends', 'all'):
if 'dividends' not in self._cache[key] or self._check_timestamp(
key, 'dividends'):
try:
self._cache[key]['dividends'] = p.dividendsDF(key)
except KeyError:
self._cache[key]['dividends'] = pd.DataFrame()
self._cache[key]['timestamp']['dividends'] = datetime.now()
if field in ('earnings', 'all'):
if 'earnings' not in self._cache[key] or self._check_timestamp(
key, 'earnings'):
try:
self._cache[key]['earnings'] = p.earningsDF(key)
except KeyError:
self._cache[key]['earnings'] = pd.DataFrame()
self._cache[key]['timestamp']['earnings'] = datetime.now()
if field in ('news', 'all'):
if 'news' not in self._cache[key] or self._check_timestamp(
key, 'news'):
try:
self._cache[key]['news'] = p.newsDF(key)
except KeyError:
self._cache[key]['news'] = pd.DataFrame()
self._cache[key]['timestamp']['news'] = datetime.now()
if field in ('peers', 'all'):
if 'peers' not in self._cache[key] or self._check_timestamp(
key, 'peers'):
try:
peers = p.peersDF(key)
except KeyError:
peers = pd.DataFrame()
if peers is not None and not peers.empty:
peers = peers.replace({np.nan: None})
infos = pd.concat(
[p.companyDF(item) for item in peers['symbol'].values])
self._cache[key]['peers'] = infos
else:
self._cache[key]['peers'] = pd.DataFrame()
self._cache[key]['timestamp']['peers'] = datetime.now()
if field in ('stats', 'all'):
if 'stats' not in self._cache[key] or self._check_timestamp(
key, 'stats'):
try:
self._cache[key]['stats'] = p.stockStatsDF(key)
except KeyError:
self._cache[key]['stats'] = pd.DataFrame()
self._cache[key]['timestamp']['stats'] = datetime.now()
if field in ('composition', 'all'):
if 'company' not in self._cache[key]:
self.fetchDF(key, 'company', _ret=False)
try:
self._cache[key]['composition'] = pd.read_html(
ETF_URL % key, attrs={'id': 'etfs-that-own'})[0]
self._cache[key]['composition']['% of Total'] = self._cache[
key]['composition']['% of Total'].str.rstrip('%').astype(
float) / 100.0
self._cache[key]['composition'].columns = [
'Symbol', 'Name', 'Percent'
]
self._cache[key]['composition'] = self._cache[key][
'composition'][['Symbol', 'Percent', 'Name']]
except (IndexError, requests.HTTPError, ValueError, HTTPError):
self._cache[key]['composition'] = pd.DataFrame()
self._cache[key]['timestamp']['composition'] = datetime.now()
if _ret:
# pull data
if field == 'all':
ret = copy.deepcopy(self._cache[key])
del ret['timestamp']
ret = pd.concat(ret)
elif field in self._cache[key]:
# or i have that field
ret = pd.concat({field: self._cache[key][field]})
else:
raise Exception('No ticker provided!')
return ret
