def insert_financials(self):
print( "Insert new financials" )
mdb_query = Query()
iex = Iex()
#Get all symbols in MongoDB
mdb_symbols = mdb_query.get_active_companies()
#Get current date
currDate = datetime.datetime.now().strftime("%Y-%m-%d")
#Get latest financials in MongoDB for each symbol
mdb_financials = mdb_query.get_financials( mdb_symbols.tolist(), currDate, "latest" )
#Initial call to print 0% progress
printProgressBar(0, len(mdb_symbols.index), prefix = 'Progress:', suffix = '', length = 50)
#Loop through symbols
for index, mdb_symbol in mdb_symbols.iteritems():
#Get financials from IEX
iex_financials = iex.get_financials( mdb_symbol )
#Get matching financial in MongoDB
mdb_financial = mdb_financials[ mdb_financials['symbol'] == mdb_symbol ]
#Select financials more recent than MongoDB
if not mdb_financial.empty and not iex_financials.empty:
mask = iex_financials['reportDate'] > mdb_financial['reportDate'].iloc[0]
iex_financials = iex_financials.loc[mask]
#Insert if financials exist
if not iex_financials.empty:
#Update progress bar
printProgressBar(index+1, len(mdb_symbols.index), prefix = 'Progress:', suffix = "Inserting financials for " + mdb_symbol + " ", length = 50)
self.db.iex_financials.insert_many( iex_financials.to_dict('records') )
else:
#Update progress bar
printProgressBar(index+1, len(mdb_symbols.index), prefix = 'Progress:', suffix = "No new data for " + mdb_symbol + " ", length = 50)
def insert_stats(self):
print( "Insert new stats" )
mdb_query = Query()
iex = Iex()
#Get all symbols in MongoDB
mdb_symbols_full = mdb_query.get_active_companies()
#mdb_symbols_full = mdb_symbols_full[mdb_symbols_full == 'A']
#Get current date
currDate = datetime.datetime.now().strftime("%Y-%m-%d")
#Initial call to print 0% progress
printProgressBar(0, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = '', length = 50)
idx_min = 0
query_num = 100
#flag = True
while idx_min < len(mdb_symbols_full.index):
#if idx_min > 1:
# break
idx_max = idx_min + query_num
if idx_max > len(mdb_symbols_full.index):
idx_max = len(mdb_symbols_full.index)
mdb_symbols = mdb_symbols_full.iloc[ idx_min:idx_max ]
mdb_symbols.reset_index(drop=True, inplace=True)
#Get latest price in MongoDB for each symbol up to 50 days ago
mdb_stats = mdb_query.get_stats( mdb_symbols.tolist(), currDate, "latest" )
#Loop through symbols
for index, mdb_symbol in mdb_symbols.iteritems():
#Get stat from IEX
#print( mdb_symbol )
#print( mdb_symbol["symbol"] )
#if mdb_symbol == "BAH":
# flag = False
#if flag:
# continue
iex_stat = iex.get_stats( mdb_symbol )
#Get matching stat in MongoDB
if not mdb_stats.empty:
mdb_stat = mdb_stats[ mdb_stats['symbol'] == mdb_symbol ]
else:
mdb_stat = mdb_stats
#Select stats more recent than MongoDB
if not iex_stat.empty and not mdb_stat.empty:
mask = iex_stat['date'] > mdb_stat['date'].iloc[0]
iex_stat = iex_stat.loc[mask]
#Insert if stats exist
#print( iex_stat )
if not iex_stat.empty:
#Update progress bar
printProgressBar(idx_min+index+1, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = "Inserting stat for " + mdb_symbol + " ", length = 50)
self.db.iex_stats.insert_many( iex_stat.to_dict('records') )
else:
#Update progress bar
printProgressBar(idx_min+index+1, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = "No new data for " + mdb_symbol + " ", length = 50)
idx_min = idx_min + query_num
def insert_quotes(self):
print( "Insert new quotes" )
mdb_query = Query()
iex = Iex()
#Get all symbols in MongoDB
mdb_symbols_full = mdb_query.get_active_companies()
#Get current date
currDate = datetime.datetime.now().strftime("%Y-%m-%d")
#Initial call to print 0% progress
printProgressBar(0, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = '', length = 50)
idx_min = 0
query_num = 100
while idx_min < len(mdb_symbols_full.index):
idx_max = idx_min + query_num
if idx_max > len(mdb_symbols_full.index):
idx_max = len(mdb_symbols_full.index)
mdb_symbols = mdb_symbols_full.iloc[ idx_min:idx_max ]
mdb_symbols.reset_index(drop=True, inplace=True)
#Get latest price in MongoDB for each symbol up to 50 days ago
mdb_quotes = mdb_query.get_quotes( mdb_symbols.tolist(), currDate, "latest" )
#Loop through symbols
iex_quotes = pandas.DataFrame()
for index, mdb_symbol in mdb_symbols.iteritems():
#Get matching quote in MongoDB
if not mdb_quotes.empty:
mdb_quote = mdb_quotes[ mdb_quotes['symbol'] == mdb_symbol ]
else:
mdb_quote = mdb_quotes
#continue if already up to date
if not mdb_quote.empty and (mdb_quote['date'].iloc[0] == currDate):
#Update progress bar
printProgressBar(idx_min+index+1, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = "No new data for " + mdb_symbol + " ", length = 50)
continue
#Get quote from IEX
iex_quote = iex.get_quote( mdb_symbol )
#Select quotes more recent than MongoDB
if not iex_quote.empty and not mdb_quote.empty:
mask = iex_quote['date'] > mdb_quote['date'].iloc[0]
iex_quote = iex_quote.loc[mask]
#Insert if quotes exist
if not iex_quote.empty:
#Update progress bar
printProgressBar(idx_min+index+1, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = "Inserting quote for " + mdb_symbol + " ", length = 50)
#Append quote
iex_quotes = iex_quotes.append(iex_quote, ignore_index=True, sort=False)
else:
#Update progress bar
printProgressBar(idx_min+index+1, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = "No new data for " + mdb_symbol + " ", length = 50)
#Bulk insert quotes
if not iex_quotes.empty:
self.db.iex_quotes.insert_many( iex_quotes.to_dict('records') )
idx_min = idx_min + query_num
def insert_balancesheets(self):
print( "Insert new balance sheets" )
mdb_query = Query()
iex = Iex()
#Get all symbols in MongoDB
mdb_symbols = mdb_query.get_active_companies()
#Get current date
currDate = datetime.datetime.now().strftime("%Y-%m-%d")
threeMonthsAgo = (pandas.Timestamp(currDate) + pandas.DateOffset(days=-120)).strftime('%Y-%m-%d')
#Get latest balancesheets in MongoDB for each symbol
mdb_balancesheets = mdb_query.get_balancesheets( mdb_symbols.tolist(), currDate, "latest" )
#Initial call to print 0% progress
printProgressBar(0, len(mdb_symbols.index), prefix = 'Progress:', suffix = '', length = 50)
#flag = False
#Loop through symbols
for index, mdb_symbol in mdb_symbols.iteritems():
#if mdb_symbol == 'YETI':
# flag = True
#if not flag:
# continue
#Get matching balancesheet in MongoDB
if not mdb_balancesheets.empty:
mdb_balancesheet = mdb_balancesheets[ mdb_balancesheets['symbol'] == mdb_symbol ]
else:
mdb_balancesheet = mdb_balancesheets
#Skip is less than 3 months since most recent
if not mdb_balancesheet.empty:
mask = mdb_balancesheet['reportDate'] > threeMonthsAgo
mdb_recent_balancesheet = mdb_balancesheet.loc[mask]
if not mdb_recent_balancesheet.empty:
#Update progress bar
printProgressBar(index+1, len(mdb_symbols.index), prefix = 'Progress:', suffix = "Data too recent for " + mdb_symbol + " ", length = 50)
continue
#Get balancesheets from IEX
iex_balancesheets = iex.get_balancesheets( mdb_symbol )
#Select balancesheets more recent than MongoDB
if not mdb_balancesheet.empty and not iex_balancesheets.empty:
mdb_balancesheet = mdb_balancesheet.sort_values(by='reportDate', ascending=False, axis='index')
mask = iex_balancesheets['reportDate'] > mdb_balancesheet['reportDate'].iloc[0]
iex_balancesheets = iex_balancesheets.loc[mask]
#Insert if balancesheets exist
if not iex_balancesheets.empty:
#Update progress bar
printProgressBar(index+1, len(mdb_symbols.index), prefix = 'Progress:', suffix = "Inserting balancesheets for " + mdb_symbol + " ", length = 50)
self.db.iex_balancesheets.insert_many( iex_balancesheets.to_dict('records') )
else:
#Update progress bar
printProgressBar(index+1, len(mdb_symbols.index), prefix = 'Progress:', suffix = "No new data for " + mdb_symbol + " ", length = 50)
def calculate_top_stocks_old(self, ref_date):
"""
Calculate ranked list of stocks
@params:
ref_date - Required : date YYYY-MM-DD (Str)
"""
mdb_query = Query()
#Get ranked stock list for given date
symbols = mdb_query.get_active_companies().tolist()
print("Query earnings")
earnings = mdb_query.get_earnings(symbols, ref_date, "latest",
"EPSReportDate")
earnings = earnings[[
"EPSReportDate", "actualEPS", "fiscalEndDate", "fiscalPeriod",
"symbol"
]]
#print( earnings )
#Get financials within 6 months
print("Query financials")
sixMonthsBeforeDate = (
pandas.Timestamp(ref_date) +
pandas.DateOffset(months=-6)).strftime('%Y-%m-%d')
financials = mdb_query.get_financials(symbols, sixMonthsBeforeDate,
"after")
financials = financials[
financials['reportDate'] <= earnings['fiscalEndDate'].max()]
financials = financials[[
"symbol", "reportDate", "netIncome", "shareholderEquity"
]]
#print( financials )
#Get prices for inception date
print("Query prices")
idx_min = 0
query_num = 100
prices = pandas.DataFrame()
while idx_min < len(symbols):
idx_max = idx_min + query_num
if idx_max > len(symbols):
idx_max = len(symbols)
symbols_split = symbols[idx_min:idx_max]
prices_split = mdb_query.get_chart(symbols_split, ref_date,
"latest")
prices = prices.append(prices_split, ignore_index=True, sort=False)
idx_min = idx_min + query_num
prices.reset_index(drop=True, inplace=True)
#print( prices )
#Get company data
company = mdb_query.get_company(symbols)
company = company[['symbol', 'companyName', 'industry', 'sector']]
#Merge dataframes together
print("Merge dataframes")
merged = pandas.merge(earnings,
financials,
how='inner',
left_on=["symbol", "fiscalEndDate"],
right_on=["symbol", "reportDate"],
sort=False)
merged = pandas.merge(merged,
prices,
how='inner',
on="symbol",
sort=False)
merged = pandas.merge(merged,
company,
how='inner',
on='symbol',
sort=False)
#Remove any rows with missing values
merged = merged.dropna(
axis=0,
subset=["netIncome", "actualEPS", "close", "shareholderEquity"])
#Calculate marketCap value
# price * netIncome / EPS = price * sharesOutstanding = mcap
# Actually not 100% accurate, should be netIncome - preferred dividend
# Doesn't perfectly match IEX value or google - probably good enough
merged["sharesOutstanding"] = merged.netIncome / merged.actualEPS
merged["marketCap"] = merged.sharesOutstanding * merged.close
#Calculate PE, ROE, and ratio
merged["peRatio"] = merged.close / merged.actualEPS
merged["returnOnEquity"] = merged.netIncome / merged.shareholderEquity
merged["peROERatio"] = merged.peRatio / merged.returnOnEquity
#Count number of stocks above mcap value
# A useful indicator of how universe compares to S&P500
print("Universe before cuts...")
print("mcap > 50M: " +
str(merged[merged["marketCap"] > 50000000].count()["marketCap"]))
print(
"mcap > 100M: " +
str(merged[merged["marketCap"] > 100000000].count()["marketCap"]))
print(
"mcap > 500M: " +
str(merged[merged["marketCap"] > 500000000].count()["marketCap"]))
print(
"mcap > 1B: " +
str(merged[merged["marketCap"] > 1000000000].count()["marketCap"]))
print(
"mcap > 5B: " +
str(merged[merged["marketCap"] > 5000000000].count()["marketCap"]))
print("mcap > 10B: " + str(merged[
merged["marketCap"] > 10000000000].count()["marketCap"]))
print("mcap > 50B: " + str(merged[
merged["marketCap"] > 50000000000].count()["marketCap"]))
print("mcap > 100B: " + str(merged[
merged["marketCap"] > 100000000000].count()["marketCap"]))
#Rank stocks
#Cut negative PE and ROE
merged = merged[(merged.peRatio > 0) & (merged.returnOnEquity > 0)]
#Remove invalid stock symbols, and different voting options
# Do the different voting options affect marketCap?
#forbidden = [ "#", ".", "-" ]
#merged = merged[ merged.apply( lambda x: not any( s in x['symbol'] for s in forbidden ), axis=1 ) ]
#Remove American Depositary Shares
#ads_str = 'American Depositary Shares'
#merged = merged[ merged.apply( lambda x: ads_str not in x['companyName'], axis=1 ) ]
#Remove industries that do not compare well
# e.g. Companies that have investments as assets
#forbidden_industry = ['Brokers & Exchanges','REITs','Asset Management','Banks']
#merged = merged[ ~merged.industry.isin( forbidden_industry ) ]
#Count number of stocks after cuts
print("Universe after cuts...")
print("mcap > 50M: " +
str(merged[merged["marketCap"] > 50000000].count()["marketCap"]))
print(
"mcap > 100M: " +
str(merged[merged["marketCap"] > 100000000].count()["marketCap"]))
print(
"mcap > 500M: " +
str(merged[merged["marketCap"] > 500000000].count()["marketCap"]))
print(
"mcap > 1B: " +
str(merged[merged["marketCap"] > 1000000000].count()["marketCap"]))
print(
"mcap > 5B: " +
str(merged[merged["marketCap"] > 5000000000].count()["marketCap"]))
print("mcap > 10B: " + str(merged[
merged["marketCap"] > 10000000000].count()["marketCap"]))
print("mcap > 50B: " + str(merged[
merged["marketCap"] > 50000000000].count()["marketCap"]))
print("mcap > 100B: " + str(merged[
merged["marketCap"] > 100000000000].count()["marketCap"]))
#Order by peROERatio
merged = merged.sort_values(by="peROERatio",
ascending=True,
axis="index")
return merged
def insert_prices(self):
print( "Insert new charts" )
mdb_query = Query()
iex = Iex()
#Get all symbols in MongoDB
mdb_symbols_full = mdb_query.get_active_companies()
mdb_symbols_full = mdb_symbols_full[mdb_symbols_full == 'SPY']
#Get current date
currDate = datetime.datetime.now().strftime("%Y-%m-%d")
#Initial call to print 0% progress
printProgressBar(0, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = '', length = 50)
idx_min = 0
query_num = 100
#flag = False
while idx_min < len(mdb_symbols_full.index):
#if idx_min > 1:
# break
idx_max = idx_min + query_num
if idx_max > len(mdb_symbols_full.index):
idx_max = len(mdb_symbols_full.index)
mdb_symbols = mdb_symbols_full.iloc[ idx_min:idx_max ]
mdb_symbols.reset_index(drop=True, inplace=True)
#Get latest price in MongoDB for each symbol up to 50 days ago
mdb_charts = mdb_query.get_chart( mdb_symbols.tolist(), currDate, "latest" )
#print( mdb_charts )
#break
#Loop through symbols
for index, mdb_symbol in mdb_symbols.iteritems():
#Get matching chart in MongoDB
mdb_chart = mdb_charts[ mdb_charts['symbol'] == mdb_symbol ]
#Get first date to insert
date = mdb_chart.date.iloc[0]
date = (pandas.Timestamp(date) + pandas.DateOffset(days=1)).strftime('%Y-%m-%d')
iex_chart = pandas.DataFrame()
while date <= currDate:
#Get date in correct format for IEX query
iex_date = (pandas.Timestamp(date)).strftime('%Y%m%d')
#Get IEX chart
iex_chart_day = iex.get_chart( mdb_symbol, ref_range=iex_date )
iex_chart = iex_chart.append(iex_chart_day, ignore_index=True, sort=False)
#Increment date
date = (pandas.Timestamp(date) + pandas.DateOffset(days=1)).strftime('%Y-%m-%d')
#Get 1y of charts from IEX
#print( mdb_symbol )
#print( mdb_symbol["symbol"] )
#if mdb_symbol["symbol"] == "ZZZZZZZZZ":
# flag = True
#if not flag:
# continue
#iex_chart = iex.get_chart( mdb_symbol, ref_range='5d' )
#Get matching chart in MongoDB
#mdb_chart = mdb_charts[ mdb_charts['symbol'] == mdb_symbol ]
#Select charts more recent than MongoDB
#if not iex_chart.empty and not mdb_chart.empty:
# mask = iex_chart['date'] > mdb_chart['date'].iloc[0]
# iex_chart = iex_chart.loc[mask]
#Insert if charts exist
#print( iex_chart )
if not iex_chart.empty:
#Update progress bar
printProgressBar(idx_min+index+1, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = "Inserting chart for " + mdb_symbol + " ", length = 50)
#Print write error if couldn't insert charts
try:
print( iex_chart )
self.db.iex_charts.insert_many( iex_chart.to_dict('records') )
except BulkWriteError as bwe:
print( bwe.details )
raise
else:
#Update progress bar
printProgressBar(idx_min+index+1, len(mdb_symbols_full.index), prefix = 'Progress:', suffix = "No new data for " + mdb_symbol + " ", length = 50)
idx_min = idx_min + query_num