def listStock_gen(self, combobox):
# gather stock symbols from major US exchanges
df1 = pd.DataFrame( si.tickers_sp500() )
df2 = pd.DataFrame( si.tickers_nasdaq() )
df3 = pd.DataFrame( si.tickers_dow() )
df4 = pd.DataFrame( si.tickers_other() )
# convert DataFrame to list, then to sets
sym1 = set( symbol for symbol in df1[0].values.tolist() )
sym2 = set( symbol for symbol in df2[0].values.tolist() )
sym3 = set( symbol for symbol in df3[0].values.tolist() )
sym4 = set( symbol for symbol in df4[0].values.tolist() )
# join the 4 sets into one. Because it's a set, there will be no duplicate symbols
symbols = set.union( sym1, sym2, sym3, sym4 )
# Some stocks are 5 characters. Those stocks with the suffixes listed below are not of interest.
my_list = ['W', 'R', 'P', 'Q']
del_set = set()
sav_set = set()
for symbol in symbols:
if len( symbol ) > 4 and symbol[-1] in my_list:
del_set.add( symbol )
else:
sav_set.add( symbol )
for ticker in sav_set:
combobox.addItem(str(ticker))
def get_tickers():
'''
Get ticker symbols for stocks listed on major stock exchanges.
At time of writing, this function retrieves 9899 stock symbols
'''
print("Retrieving Stock Symbols...")
dow_tickers = stock_info.tickers_dow()
nasdaq_ticker = stock_info.tickers_nasdaq()
sp500_ticker = stock_info.tickers_sp500()
other_tickers = stock_info.tickers_other()
all_tickers = list(
set(dow_tickers + nasdaq_ticker + sp500_ticker + other_tickers))
print(f"\nTotal number of stock symbols retrieved: {len(all_tickers)}")
tickers_dict = {
'DOW': dow_tickers,
'NASDAQ': nasdaq_ticker,
'SP500': sp500_ticker,
'others': other_tickers
}
for exchange_name, ticker_list in tickers_dict.items():
print(f"\t{exchange_name}: {len(ticker_list)}")
return all_tickers
def load_tickers(self, cur, conn):
self.df_ticker = pd.DataFrame()
self.nasdaq = si.tickers_nasdaq()
self.sp500 = si.tickers_sp500()
self.dow = si.tickers_dow()
self.other = si.tickers_other()
self.tickers = list(set([*nasdaq, *sp500, *dow, *other]))
self.df_ticker['ticker'] = self.tickers
self.df_ticker.replace("", float("NaN"), inplace=True)
self.df_ticker.dropna(subset=["ticker"], inplace=True)
self.df_ticker['isdow'] = self.df_ticker['ticker'].isin(self.dow)
self.df_ticker['issp500'] = self.df_ticker['ticker'].isin(self.sp500)
self.df_ticker['isnasdaq'] = self.df_ticker['ticker'].isin(self.nasdaq)
self.insert = [
list(row) for row in self.df_ticker.itertuples(index=False)
]
self.SQL_Ticker_insert = """ INSERT INTO public.tickers(ticker,isdow, isnasdaq, issp500) VALUES (%s,%s,%s,%s) ON CONFLICT DO NOTHING"""
self.cur.executemany(self.SQL_Ticker_insert, self.insert)
self.conn.commit()
self.rowcount = self.cur.rowcount
return None
def main():
# get key stats, financial statements, and prices data of SP500 stocks
tickers_nasdaq = set(si.tickers_nasdaq())
tickers_other = set(si.tickers_other())
tickers_sp500 = set(si.tickers_sp500())
tickers_nasdaq_ = list(tickers_nasdaq - tickers_sp500)
tickers_other_ = list(tickers_other - tickers_sp500)
tickers_sp500 = list(tickers_sp500)
yr = YahooReader()
yr.save_data(tickers_nasdaq_, folder_path='data_nasdaq')
print("All Done!")
def tickers(request):
dow = si.tickers_dow()
nasdaq = si.tickers_nasdaq()
sp500 = si.tickers_sp500()
other = si.tickers_other()
all = json.dumps({
'dow': dow,
'nasdaq': nasdaq,
'sp500': sp500,
'other': other
})
return HttpResponse(all)
def get_US_price(start_date, end_date):
"""
Download US stocks prices.
Parameters
----------
start_date : string
example : '2000-01-01'.
end_date : string
example : '2019-12-31'.
Returns
-------
total_df : pd.DataFrame
Stocks prices from start_date to end_date.
"""
dow_list = si.tickers_dow()
sp500_list = si.tickers_sp500()
nasdaq_list = si.tickers_nasdaq()
other_list = si.tickers_other()
ticker = dow_list + sp500_list + nasdaq_list + other_list
ticker = [ticker[i] for i in range(len(ticker)) if not ticker[i] in ticker[:i]]
ticker = pd.DataFrame(ticker, columns=['Ticker'])
for num, code in enumerate(ticker['Ticker']):
try:
print(num, code)
time.sleep(1)
try:
df = fdr.DataReader(code, start_date, end_date)
df = df['Close']
df = pd.DataFrame(df)
df.columns = [code]
except Exception as e:
print(e, 'Error in Ticker', code)
continue
if num == 0:
total_df = df
else:
total_df = pd.merge(total_df, df, how='outer', right_index=True, left_index=True)
except ValueError:
continue
except KeyError:
continue
total_df.to_csv(r'C:\Users\Samsung\Downloads\quant\Python\data\US_price.csv')
return total_df
def __init__(self):
#self.tickers_dow = si.tickers_dow()
self.tickers_ftse100 = si.tickers_ftse100()
self.tickers_ftse250 = si.tickers_ftse250()
self.tickers_nasdaq = si.tickers_nasdaq()
self.tickers_other = si.tickers_other()
self.tickers_sp500 = si.tickers_sp500()
self.tickers_all = self.get_all_tickers()
self.tickers_high_vol = []
self.my_stocks = {}
# Train data for all my_stocks
self.X = None
self.y = None
self.label = None
def gather_all_stock_symbols():
"""
Retrieves all available stock symbols from
yahoo-fin.stock_info(si) and then removes duplicates.
Total number of symbols = 9181.
"""
# ......... MongoDb initialization................................
db = client['trading']
coll = db['all_stock_symbols']
##................................................................
# Some stocks are 5 characters. Those stocks with the suffixes listed below are not of interest.
my_list = ['W', 'R', 'P', ]
del_set = set()
sav_set = set()
# gather stock symbols from major US exchanges
df1 = pd.DataFrame( si.tickers_sp500() )
df2 = pd.DataFrame( si.tickers_nasdaq() )
# df3 = pd.DataFrame(si.tickers_dow())
df4 = pd.DataFrame( si.tickers_other() )
# convert DataFrame to list, then to sets
sym1 = set( symbol for symbol in df1[0].values.tolist() )
sym2 = set( symbol for symbol in df2[0].values.tolist() )
# sym3 = set( symbol for symbol in df3[0].values.tolist() )
sym4 = set( symbol for symbol in df4[0].values.tolist() )
# join the 4 sets into one. Because it's a set, there will be no duplicate symbols
symbols = set.union( sym1, sym2, sym4 ) # sym3,
for symbol in symbols:
if len( symbol ) > 4 and symbol[-1] in my_list: # we identify the above suffixed symbols here,
del_set.add( symbol ) # and separate them here
else:
sav_set.add( symbol ) # updated data without suffixed symbols
# insert data to MongoDb..........................................
for symbol in sav_set:
coll.insert_one( {"symbol": symbol} )
##................................................................
print( f'Removed {len( del_set )} unqualified stock symbols...' )
print( f'There are {len( sav_set )} qualified stock symbols...' )
def update_tickers(path, name):
'''
Gets a list of tickers from the yahoo finance database and saves the list to a .csv file under a given directory and name
:param path: string, must be denoted as path\\to\\main\\folder\\
:param name: string, will be the name of the .csv file saved, must not have any file denotion in it
:return: saves a list of tickers to path\\name.csv
'''
sources, tickers = [
stock_info.tickers_dow(),
stock_info.tickers_nasdaq(),
stock_info.tickers_other(),
stock_info.tickers_sp500()
], []
for source in sources:
for ticker in source:
if ticker not in tickers:
tickers.append(ticker)
pd.DataFrame(tickers).to_csv(path + name + '.csv')
from tkinter import ttk
from yahoo_fin import stock_info as si
from yahoo_fin import options
from tkinter import *
from tkinter.ttk import *
import matplotlib.pyplot as plt
from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
from pandas import DataFrame
dow_tickers = si.tickers_dow()
sp500_tickers = si.tickers_sp500()
nasdaq_tickers = si.tickers_nasdaq()
other_tickers = si.tickers_other()
class Application(tk.Frame):
def __init__(self, master=None):
tk.Frame.__init__(self, master)
self.createWidgets()
def createWidgets(self):
#Button images~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
photo = PhotoImage(
file=
r"C:\Users\User\Desktop\Python coding\finance\StockScreening\StockScreener\images\button_update.png"
)
days = 0
constDate = str("0001") + "-" + str("01") + "-" + str("01")
if args.days:
days = int(args.days)
if args.processes:
noOfProcesses = int(args.processes)
else:
noOfProcesses = 10
if args.filename:
fileName = args.filename + ".xlsx"
else:
fileName = "insider_trading.xlsx"
if args.stocklist:
l1 = args.stocklist.split(',')
else:
l1 = si.tickers_sp500() + si.tickers_nasdaq() + si.tickers_other() + si.tickers_dow()
l1 = list(set(l1))
l1.sort()
l1.pop(0)
tickerList = []
for i,ticker in enumerate(l1):
if not re.search(r"\$", ticker):
tickerList.append(ticker)
l1 = tickerList
if args.insidersales:
value = int(args.insidersales)
if value > 1:
print("ERROR insider sales value can only be 0 or 1 and you have passed %d" %(value))
sys.exit(1)
else:
insiderSales = value
def others(self):
self.symb = si.tickers_other()
