def __init__(self, stock_id, start_date = None, end_date = None):
self.df = None
self.sid = stock_id
self.start = start_date
self.end = end_date
try:
self.df = pda.get_data_yahoo(stock_id + u'.TW', start_date, end_date)
except:
pass
if self.df is None:
try:
self.df = pda.get_data_yahoo(stock_id + u'.TWO', start_date, end_date)
except:
pass
if self.df is None:
try:
self.df = pda.get_data_yahoo(stock_id, start_date, end_date)
except:
print("KEY_ERROR: Wrong stock id.")
raise
self.df = self.df[self.df.Volume != 0]
def GetStockQuote( *args ):
'''
Read the stock quote by givn stock symbol, and the time frame.
'''
try:
if len(args) == 1: #default 60 days
symbol = args[0]
quote = web.get_data_yahoo(symbol,sixty_days.strftime("%m/%d/%Y"), time.strftime("%m/%d/%Y"))
elif len(args) == 2: #can select days to today
symbol = args[0]
startdate = datetime.date.today() - datetime.timedelta(days=args[1]) #Need enough days for MACD calculation
quote = web.get_data_yahoo(symbol,startdate.strftime("%m/%d/%Y"), time.strftime("%m/%d/%Y"))
elif len(args) == 3: # symbol, start date, end date
symbol = args[0]
startdate = datetime.date.today() - datetime.timedelta(days=args[1]) #Need enough days for MACD calculation
enddate = datetime.date.today() - datetime.timedelta(days=args[2])
quote = web.get_data_yahoo(symbol,startdate.strftime("%m/%d/%Y"), enddate.strftime("%m/%d/%Y"))
print("Last day close is " , quote.Close[-1])
return quote;
except Exception as identifier:
symbol = args[0]
print("Cannot get the quote for ", symbol, "Error Message" , identifier)
return "NoQuote"
def plot_prices(self, start_date, end_date):
"""
"""
shares = get_data_yahoo(self.share_id, start=start_date,
end=end_date)
shares.Close.plot(label=self.share_id)
plt.legend()
def get(self, ticker, start = None, end = None):
if start is None:
start = datetime.date(2010, 01, 01)
if end is None:
end = datetime.date.today()
self.ticker = ticker
return pd_data.get_data_yahoo(ticker + ".AX", start, end)
def collect_new():
today = datetime.date.today()
with open(banknum,'r') as f:
for i in f.read().splitlines():
tickers = i + '.HK'
filename = i + '.csv'
data2 = pdr.get_data_yahoo(tickers, start="2006-01-01", end=today)
data2.sort_index(ascending=False).to_csv(filename)
def load_ticker(ticker):
fname='data_yahoo/'+ticker+'.csv'
if os.path.exists(fname):
df = read_csv(fname)
else:
df= data.get_data_yahoo(ticker,'1/1/2001','12/1/2017')
df.to_csv(fname)
return df
def GetSecurityData(security, startDate, endDate):
# This function grabs data from yahoo and is delayed by 15 minutes
# security - security to read in
# startDate/endDate in format of startDate = datetime.datetime(2006, 01, 15)
securityData = data.get_data_yahoo(security, startDate, endDate)
return securityData
def retrieve_prices(equity_tickers=None,
start_date=None,
end_date=dt.datetime.today()):
data = pdata.get_data_yahoo(symbols=equity_tickers,
start=start_date,
end=end_date)
return data
def up_down_ratio(self):
bars = data.get_data_yahoo(self.symbol, datetime.datetime(2015,1,1), datetime.datetime(2016,1,1))
a = bars['Open']-bars['Close']
n4 = a.mean()
a = a.sub(n4)
n1 = a.abs().mean()
n2 = a[a>=0].mean()
n3 = a[a<0].abs().mean()
return n1, n2, n3, n4
def test_get_data_interval(self):
# daily interval data
pan = web.get_data_yahoo('XOM', '2013-01-01', '2013-12-31', interval='d')
self.assertEqual(len(pan), 252)
# weekly interval data
pan = web.get_data_yahoo('XOM', '2013-01-01', '2013-12-31', interval='w')
self.assertEqual(len(pan), 53)
# montly interval data
pan = web.get_data_yahoo('XOM', '2013-01-01', '2013-12-31', interval='m')
self.assertEqual(len(pan), 12)
# dividend data
pan = web.get_data_yahoo('XOM', '2013-01-01', '2013-12-31', interval='v')
self.assertEqual(len(pan), 4)
# test fail on invalid interval
self.assertRaises(ValueError, web.get_data_yahoo, 'XOM', interval='NOT VALID')
def test_get_date_ret_index(self):
pan = web.get_data_yahoo(['GE', 'INTC', 'IBM'], '1977', '1987',
ret_index=True)
self.assertTrue(hasattr(pan, 'Ret_Index'))
if hasattr(pan, 'Ret_Index') and hasattr(pan.Ret_Index, 'INTC'):
tstamp = pan.Ret_Index.INTC.first_valid_index()
result = pan.Ret_Index.ix[tstamp]['INTC']
self.assertEqual(result, 1.0)
# sanity checking
assert np.issubdtype(pan.values.dtype, np.floating)
def yf(ticker, field, start=None, end=None, mrefresh=False):
if field is None:
field = 'Adj Close'
tmp = pdata.get_data_yahoo(ticker, start=start, end=end)
if tmp is None:
raise ValueError('failed to retrieve data for %s:%s' % (ticker, field))
if field:
return tmp[field]
else:
return tmp
def get_price(reload_data, ticker_list, start, end):
f_loc = '/Users/Potzenhotz/python/finance/data/'
f_title = 'stocks_data' + str(start) + '.csv'
f_name = f_loc + f_title
if reload_data:
write_data = True
read_data = False
else:
write_data = False
read_data = True
#-----------------------------------------------------------------------
#Load Finance Data
#-----------------------------------------------------------------------
if reload_data:
all_data = {}
i=-1
for ticker in ticker_list:
i+=1
print(i,ticker)
try:
all_data[ticker] = web.get_data_yahoo(ticker, start, end )
except:
print ("Cant find ", ticker)
pass
price = pd.DataFrame({tic: data['Adj Close']
for tic, data in all_data.items()})
#-----------------------------------------------------------------------
#Write Finance Data
#-----------------------------------------------------------------------
if write_data:
price.to_csv(f_name)
#Reread data to get right format
#while loading Date is index after reading Date will be column
price = pd.read_csv(f_name)
#-----------------------------------------------------------------------
#Read Finance Data
#-----------------------------------------------------------------------
if read_data:
#check if end date is current date
if (end.date() != dt.datetime.today().date()):
print('#####')
print('Caution data is out of date: %s' % (end))
print('#####')
price = pd.read_csv(f_name)
return price
def get_stock_values(self):
'''
extracts the stock data from yahoo and calculates the mean for:
-last week
-6 months ago
-12 month ago
'''
try:
if self.country == 'ger':
self.stock_yahoo = self.stock + '.DE'
elif self.country == 'us':
self.stock_yahoo = self.stock
elif self.country == 'uk':
self.stock_yahoo = self.stock + '.L'
end = dt.date.today()
yesterday = dt.date.today()
last_week = dt.date.today() - dt.timedelta(14)
six_months = dt.date.today() + relativedelta(months=-6)
six_months_start = six_months-dt.timedelta(7)
twelve_months = dt.date.today() + relativedelta(months=-12)
twelve_months_start = twelve_months-dt.timedelta(7)
self.stock_week = web.get_data_yahoo(self.stock_yahoo, last_week, end )
self.stock_6_months_ago = web.get_data_yahoo(self.stock_yahoo,six_months_start, six_months )
self.stock_12_months_ago = web.get_data_yahoo(self.stock_yahoo, twelve_months_start, twelve_months)
self.stock_avg_week = self.stock_week['Adj Close'].mean()
self.stock_avg_6_months = self.stock_6_months_ago['Adj Close'].mean()
self.stock_avg_12_months = self.stock_12_months_ago['Adj Close'].mean()
except:
if self.__print_debug: print('Problem with yahoo stock extract')
e_1 = sys.exc_info()[0]
e_2 = sys.exc_info()[1]
if self.__print_debug: print( "Error: %s with %s" % (e_1, e_2) )
def test_get_data_multiple_symbols_two_dates(self):
pan = web.get_data_yahoo(['GE', 'MSFT', 'INTC'], 'JAN-01-12',
'JAN-31-12')
result = pan.Close.ix['01-18-12']
self.assertEqual(len(result), 3)
# sanity checking
assert np.issubdtype(result.dtype, np.floating)
expected = np.array([[18.99, 28.4, 25.18],
[18.58, 28.31, 25.13],
[19.03, 28.16, 25.52],
[18.81, 28.82, 25.87]])
result = pan.Open.ix['Jan-15-12':'Jan-20-12']
self.assertEqual(expected.shape, result.shape)
def query_stock(stock, start='2011.01.01', end='today'):
stock+=".TW"
st = datetime.date(datetime.strptime(start, '%Y.%m.%d'))
if end == 'today':
en = datetime.date(datetime.today())
else:
en = datetime.date(datetime.strptime(end, '%Y.%m.%d'))
df = data.get_data_yahoo(stock, st, en)
fig = FF.create_candlestick(df.Open, df.High, df.Low, df.Close, dates=df.index)
SMA20=moving_average(df.Close.values, 20)
add_line = Scatter(
x=df.index[-len(SMA20):],
y=SMA20,
name= '20SMA',
line=Line(color='rgb(200, 200, 250)')
)
fig['data'].extend([add_line])
plotly.offline.plot(fig, validate=False)
def calculate_investment(self):
share_details = get_data_yahoo(self.share_id, start=self.start_date)
share_details['Shares Owned'] = Series(np.zeros(len(share_details)),
index=share_details.index)
share_details['Investment'] = Series(np.zeros(len(share_details)),
index=share_details.index)
for idx, investment in enumerate(self.monthly_investments):
start_date, end_date = self.monthly_investment_dates[idx]
add_monthly(share_details, start_date, end_date, investment)
for idx, investment in enumerate(self.investments):
add_shares(share_details, self.investment_dates[idx], investment)
share_details['Value'] = Series(share_details['Shares Owned'] *
share_details.Close / 100,
index=share_details.index)
self.share_details = share_details
def load_data(self):
'''Download the data using panda'''
self.data_exist = False
self.check_data_exist()
self.all_data = {}
if self.data_exist == False:
i=-1
for ticker in self.stock_list:
i+=1
if self.__print_info: print ('Info: ',i, ticker)
try:
self.all_data[ticker] = web.get_data_yahoo(ticker, self.start_date, self.end_date )
except:
if self.__print_info: print('Cant find: ', ticker)
pass
self.raw_df = pd.DataFrame({tic: data['Adj Close'] for tic, data in self.all_data.items()})
self.write_raw_df()
else:
self.read_raw_df()
def update_index(sid, n_year):
end_date = datetime.datetime.now().strftime('%Y-%m-%d')
# n 年的資料
start_date = (datetime.datetime.now()- datetime.timedelta(days=n_year*365)).strftime('%Y-%m-%d')
SID = sid
out_file = "測試資料/台股/{0}d.csv".format(SID)
def true_val(current_date, current_val, dividend_dataframe):
return current_val # 不還原權值, adj close 就是還原值了
# ret = current_val
# for idx, dividend_date in enumerate(dividend_dataframe.index.values):
# if dividend_date <= current_date:
# ret = ret + dividend_dataframe.iloc[idx][0]
# return ret
# 分紅資料
# dividend_dataframe = pdr.get_data_yahoo(SID, start=start_date, end=end_date,actions='only')
dividend_dataframe = ""
# print(dividend_dataframe)
time.sleep(1)
# 日K 資料
data = pdr.get_data_yahoo(SID, start=start_date, end=end_date)
for idx, current_date in enumerate(data.index.values):
o = true_val(current_date, data.iloc[idx][0], dividend_dataframe)
h = true_val(current_date, data.iloc[idx][1], dividend_dataframe)
l = true_val(current_date, data.iloc[idx][2], dividend_dataframe)
c = true_val(current_date, data.iloc[idx][3], dividend_dataframe)
data.at[current_date,"Open"]=o
data.at[current_date,"High"]=h
data.at[current_date,"Low"]=l
data.at[current_date,"Close"]=c
print(len(data.index.values))
data.to_csv(out_file, sep=',', encoding='utf-8')
# download Panel
#= pdr.get_data_yahoo(["SPY", "IWM"], start="2017-01-01", end="2017-04-30")
#print(data3)
time.sleep(3)
def graph_date(stock):
stock_price_url = 'https://hk.finance.yahoo.com/chart/TSLA#eyJtdWx0aUNvbG9yTGluZSI6ZmFsc2UsImJvbGxpbmdlclVwcGVyQ29sb3IiOiIjZTIwMDgxIiwiYm9sbGluZ2VyTG93ZXJDb2xvciI6IiM5NTUyZmYiLCJtZmlMaW5lQ29sb3IiOiIjNDVlM2ZmIiwibWFjZERpdmVyZ2VuY2VDb2xvciI6IiNmZjdiMTIiLCJtYWNkTWFjZENvbG9yIjoiIzc4N2Q4MiIsIm1hY2RTaWduYWxDb2xvciI6IiMwMDAwMDAiLCJyc2lMaW5lQ29sb3IiOiIjZmZiNzAwIiwic3RvY2hLTGluZUNvbG9yIjoiI2ZmYjcwMCIsInN0b2NoRExpbmVDb2xvciI6IiM0NWUzZmYiLCJyYW5nZSI6IjF5In0%3D'
souce_code = urllib.request.urlopen(stock_price_url).read().decode()
# stock_price_url = 'http://chartapi.finance.yahoo.com/instrument/1.0/'+stock+'/chartdata;type=quote;range=10y/csv'
#print(souce_code)
stock_data = []
split_source = souce_code.split('\n')
#print(souce_code.encode("GBK", 'ignore'))
for line in split_source:
split_line = line.split(',')
if len(split_line) == 6:
if 'values' not in line:
stock_data.append(line)
#print(line.encode("GBK", 'ignore'))
print(web.get_data_yahoo('AAPL','1/1/2014','20/8/2015'))
#date, closep, highp, lowp, openp, volume = np.loadtxt(stock_data, delimiter=',', unpack=True, converters={0: bytespdate2num('%Y%m%d', 'utf-8')})
# %Y = full year. 2015
# %y = partial year 15
# %m = number month
# %d = number day
# %H = hours
# %M = minutes
# %S = seconds
# 12-06-2014
# %m-%d-%Y
#plt.plot_data(date, closep, '-', label='Price')
plt.xlabel('date')
plt.ylabel('price')
plt.title('data from web')
plt.legend()
plt.show()
def _getDatas(self):
combIndex = None
for s in self.symbolList:
self.symbolData[s] = web.get_data_yahoo(s,
start=self.startDate.strftime("%Y%m%d"),
end=self.endDate.strftime("%Y%m%d"),
adjust_price=True).sort_index()
del self.symbolData[s]['Adj_Ratio']
self.symbolData[s].columns = ['open', 'high', 'low', 'close', 'volume']
if combIndex is None:
combIndex = self.symbolData[s].index
else:
combIndex = combIndex.union(self.symbolData[s].index)
self.latestSymbolData[s] = []
self.symbolData[s] = transfromDFtoDict(self.symbolData[s])
self.dateIndex = combIndex
self.start = 0
for i, s in enumerate(self.symbolList):
if s not in self.symbolData:
del self.symbolList[i]
def test_returns_verifiable(ticker):
# Test that the quotes line up with data off of Yahoo
now = datetime.now()
prior_day = now - TradingDay(1)
quotes = Tradeking1mTimesales.retrieve_data(prior_day, ticker)
yahoo_ohlc = list(map(tuple, get_data_yahoo(ticker, prior_day, prior_day)[
['Open', 'High', 'Low', 'Close']
].values))[0]
open = high = close = 0
low = 999999
for index, quote in enumerate(quotes['quotes']):
if index == 0:
open = quote['opn']
if index == len(quotes['quotes']) - 1:
close = quote['last']
high = max(high, quote['hi'])
low = min(low, quote['lo'])
tradeking_ohlc = (open, high, low, close)
assert_allclose(tradeking_ohlc, yahoo_ohlc, rtol=1e-3)
def get_symbol_from_yahoo(symbol, start=None, end=None):
"""Wrapper for pandas.io.data.get_data_yahoo().
Retrieves prices for symbol from yahoo and computes returns
based on adjusted closing prices.
Parameters
----------
symbol : str
Symbol name to load, e.g. 'SPY'
start : pandas.Timestamp compatible, optional
Start date of time period to retrieve
end : pandas.Timestamp compatible, optional
End date of time period to retrieve
Returns
-------
pandas.DataFrame
Returns of symbol in requested period.
"""
px = web.get_data_yahoo(symbol, start=start, end=end)
rets = px[['Adj Close']].pct_change().dropna()
rets.index = rets.index.tz_localize("UTC")
rets.columns = [symbol]
return rets
import pandas_datareader.data as web
from pandas.io.data import _yahoo_codes
a=web.get_quote_yahoo("MSFT")
b=_yahoo_codes.update({'MarketCap' : 'j1'})
print(a)
print(b)
a=web.get_quote_yahoo("GEN.CO")
b=_yahoo_codes.update({'52WeekLow' : 'j'})
print(a)
print(b)
print("stop")
aapl = web.get_data_yahoo("GEN.CO",'1/1/2016', '5/20/2016')
#appl = web.get_data_google("GEN",'1/1/2016', '5/20/2016')
#print(aapl.Close) # get all close price
#closeprice = ta.SMA(numpy.array(aapl.Close)) # Avoid Argument 'real' has incorrect type (expected numpy.ndarray, got Series) error.
sma = ta.SMA(numpy.array(aapl.Close))
rsi = ta.RSI(numpy.array(aapl.Close))
macddiv, macdsignal, macdhist = ta.MACD(numpy.array(aapl.Close), fastperiod=12, slowperiod=26, signalperiod=9)
cross = macdsignal - macddiv
bollinger =
def test_get_data_single_symbol(self):
#single symbol
#http://finance.yahoo.com/q/hp?s=GOOG&a=09&b=08&c=2010&d=09&e=10&f=2010&g=d
# just test that we succeed
web.get_data_yahoo('GOOG')
factors = DataFrame({'f1': fac1, 'f2': fac2, 'f3': fac3}, index=ticker_subset)
print(factors.corrwith(port))
print(pd.ols(y=port, x=factors).beta)
def beta_exposure(chunk, factors=None):
return pd.ols(y=chunk, x=factors).beta
by_ind = port.groupby(industries)
exposures = by_ind.apply(beta_exposure, factors=factors)
print(exposures.unstack())
data = web.get_data_yahoo('SPY', '2006-01-01','2012-07-27')
px = data['Adj Close']
returns = px.pct_change()
def to_index(rets):
index = (1 + rets).cumprod()
first_loc = max(index.notnull().index.get_loc(index.notnull().argmax()) - 1, 0)
index.values[first_loc] = 1
return index
def trend_signal(rets, lookback, lag):
signal = Series.rolling(rets, lookback, min_periods=lookback - 5).std()
def my_form_post():
text = request.form.get('stock')
if("none" in text):
my_form_post()
y = Share(text)
t = str(datetime.now())
date = t[:10]
price = float(y.get_price())
change = float(y.get_change())
book = float(y.get_book_value())
p_b = 1
if(book != 0):
p_b = price/book
short = float(y.get_short_ratio())
vol = float(y.get_avg_daily_volume())
capital = (y.get_market_cap())
result = 0
show = ""
if(change == 0 and short == 0):
result = 0
elif(short < 2):
result = 1
elif(short > 3 and vol >1):
result = -1
elif(change < 0 and vol > 1):
result = -1
elif(change > 0 and vol < 1):
if(p_b > 1):
result = 1
elif(p_b < 1):
result = -1
up = 1
if(change < 0):
up = -1
show = "\nCurrent price of the stock is : " + str(price)
if(up >= 0):
show = show + "\nStocks are up by " + str(change)
else:
show = show + "\nStocks are down by : " + str(change)
if(capital is not None):
show = show + "\nMarket Capitalisation of the current stock is " + capital
if(result == -1):
show = show + "\n\nAccording to our analysis, the stocks are vulnerable to fall.\nSo it's not advised to invest in them."
elif(result == 0):
show = show + "\n\nAccording to our analysis, the stocks seem to be neutral.\nSo, nothing can be said regarding investing in them."
else:
show = show + "\n\nAccording to our analysis, the stocks seem to be going up.\nSo, it's the right time to invest in them."
data1 = web.get_data_yahoo(str(text), start = '2015-01-01', end = date)[['Close']]
data1.plot(subplots = True, figsize = (30, 12))
plt.title(text,fontsize=30)
plt.figtext(0.50, -0.001, show,verticalalignment='bottom', horizontalalignment='center',color='green', fontsize=15)
plt.legend(loc = 'best')
plt.savefig("C:/Python34/financial hackathon/static/p1.png")
return send_from_directory("static","p1.png")
st.table(df.iloc[0:10])
stocknames = df['NAME']
stocknames = ['Select Stock : '] + list(stocknames)
selection = st.selectbox("Select Intended Stock : ", stocknames)
if selection != 'Select Stock : ':
# st.write('You selected:', format_text(option, 0, len(option)))
st.write('Selected File Name:', selection)
res = df[df['NAME'] == selection]
st.dataframe(res)
with st.spinner("Fetching Data..."):
data = pdr.get_data_yahoo(str(res['YCODE'].iloc[0]),
start="2017-01-01",
end="2021-04-17")
st.dataframe(data.tail(10))
st.line_chart(data['Open'])
# st.line_chart(data['High'])
# with st.spinner(text='In progress'):
# time.sleep(5)
# st.success('Done')
# st.balloons()
arr = np.random.normal(1, 1, size=100)
def _get_data_yahoo(names, start, end):
return pdr.get_data_yahoo(names, start=start, end=end)
import matplotlib.pyplot as plt
from pandas_datareader import data as pdr
import yfinance as yf
from utilities import (get_betas, get_capm, portfolio_expected_returns,
multi_portfolio_sigma, portfolio_sigma,
generate_random_weights, calc_holding_returns, mvo)
from portfolio import portfolio, benchmarks
yf.pdr_override()
holdings = pd.DataFrame(portfolio).fillna(0.0)
holdings['min_weight'] = 0.0
holdings['max_weight'] = 1.0
print('---- Downloading Ticker Data ----')
holdings_th = pdr.get_data_yahoo(
holdings['symbol'].tolist())['Adj Close'][holdings['symbol'].tolist()]
holdings_dr = holdings_th.pct_change()[-756:]
holdings_cov = holdings_dr.cov()
benchmarks = pd.DataFrame(benchmarks).set_index('symbol')
benchmarks_th = pdr.get_data_yahoo(
benchmarks.index.tolist())['Adj Close'][benchmarks.index.tolist()]
benchmarks_dr = benchmarks_th.pct_change()[-756:]
#%%
print('---- Calculating Expected Returns ----')
holdings = calc_holding_returns(holdings, benchmarks, holdings_dr,
benchmarks_dr)
print('---- Generating 10000 random portfolios ----')
w = generate_random_weights(10000, len(holdings))
return priceChange
def calc(companyname):
# 获取公司2017年股票数据
start_date = '2017-01-01'
end_date = '2018-01-01'
companyDf = data.get_data_yahoo(gafataDict[companyname],start_date,end_date)
# 累计涨幅
closeCol = companyDf['Close']
companyChange = change(closeCol)
return companyChange
#获取阿里巴巴2017年的股票数据
start_date = '2017-01-01'
end_date = '2018-01-01'
babaDf=data.get_data_yahoo(gafataDict['阿里'],start_date, end_date)
#累计涨幅
closeCol=babaDf['Close']
babaChange=change(closeCol)
#谷歌
googDf=data.get_data_yahoo(gafataDict['谷歌'],start_date, end_date)
closeCol=googDf['Close']
googChange=change(closeCol)
#亚马逊
amazDf=data.get_data_yahoo(gafataDict['亚马逊'],start_date, end_date)
closeCol=amazDf['Close']
amazChange=change(closeCol)
import datetime
import fix_yahoo_finance as yf
from pandas_datareader import data as pdr
if __name__ == '__main__':
# Date Ranges for SP 500 and for all tickers
# Modify these date ranges each week.
# The below will pull back stock prices from the start date until end date specified.
start_sp = datetime.datetime(1992, 1, 1)
end_sp = datetime.datetime(2018, 3, 9)
# This variable is used for YTD performance.
yf.pdr_override() # <== that's all it takes :-)
sp500 = pdr.get_data_yahoo('^GSPC', start_sp, end_sp)
sp500.to_csv('sp500.csv')
print(sp500.head())
from pandas_datareader import data as pdr
yf.pdr_override()
stock = input("enter a stock ticker symbol: ")
print(stock)
startyear = 2010
startmonth = 1
startday = 1
startdate = dt.datetime(startyear, startmonth, startday)
now = dt.datetime.now()
while stock != "quit":
df = pdr.get_data_yahoo(stock, startdate, now)
df.drop(df[df["Volume"] < 1000].index, inplace=True)
dfmonth = df.groupby(pd.Grouper(freq="M"))["High"].max()
glDate = 0
lastGLV = 0
currentDate = ""
currentGLV = 0
for index, value in dfmonth.items():
if (value > currentGLV):
currentGLV = value
currentDate = index
counter = 0
if (value < currentGLV):
counter = counter + 1
if (counter == 3 and ((index.month != now.month) or
(index.year != now.year))):
import pandas_datareader.data as pdr
import yfinance as yf
import datetime as dt
import pandas as pd
import yahoo_fin.stock_info as si
yf.pdr_override()
tickers = si.tickers_sp500()
tickers = [item.replace('.', '-') for item in tickers]
num_of_years = 10
start = dt.date.today() - dt.timedelta(days=int(365.25 * num_of_years))
for ticker in tickers:
try:
df = pdr.get_data_yahoo(ticker, start)
df.to_csv(
f'/Users/shashank/Documents/Code/Python/Outputs/S&P500/{ticker}.csv'
)
print(f'{ticker} is done')
except:
continue
def plotTsS2(start_date, end_date):
plt.close()
yf.pdr_override()
data = pdr.get_data_yahoo("BTC-USD", start_date, end_date)
btc = pd.DataFrame(data)
btc = btc[['Adj Close']]
btc.columns = ['Close']
btc.reset_index(level=0, inplace=True)
b = pd.DataFrame()
for x in btc:
b['price'] = btc['Close']
b['sma'] = btc['Close'].rolling(window=20).mean()
b['std'] = btc['Close'].rolling(window=20).std()
b['bolU'] = b['sma'] + (2 * b['std']) #Calculating Upper Bound
b['bolD'] = b['sma'] - (2 * b['std']) #Calculating Lower Bound
#Convert Bollinger Bands to %b - bollinger column
b['bollinger'] = (b['price'] - b['bolD']) / (b['bolU'] - b['bolD'])
bb1 = b[['price', 'bolU', 'bolD', 'bollinger']]
bb1.columns = ['Price', 'Upper Band', 'Lower Band', 'Bollinger']
bb1.fillna(0, inplace=True)
# In[ ]:
# In[9]:
RSI = pd.DataFrame(index=btc.index)
RSI['price'] = btc['Close']
RSI['val'] = None
RSI['up'] = 0 #When there is no up value 0
RSI['down'] = 0 #When there is no down value 0
size = RSI.shape[0]
dp = 14
for x in range(size):
if x == 0:
continue #first day will continue
#calculating the ups , when closing price is higher in day x than x -1
if RSI['price'].iloc[x] > RSI['price'].iloc[x - 1]: #
RSI['up'].iloc[x] = RSI['price'].iloc[x] - RSI['price'].iloc[x - 1]
else:
#calculating the downs days , when closing price is lower in day x than x -1
RSI['down'].iloc[x] = RSI['price'].iloc[x -
1] - RSI['price'].iloc[x]
if x >= dp:
avgUp = RSI['up'][x - dp:x].sum(
) / dp #calculates avg up of last dp days
avgDown = RSI['down'][x - dp:x].sum(
) / dp #calculates avg down of last dp days
rs = avgUp / avgDown #calculation of RS
RSI['val'].iloc[x] = 100 - 100 / (1 + rs)
signals = pd.DataFrame(index=btc.index) #copy index for BTC
signals['price'] = btc['Close']
signals['id'] = 0.0
signals['RSI'] = RSI['val']
signals['RSI'].fillna(0, inplace=True)
signals['bollinger'] = bb1['Bollinger']
signals['id'] = [np.nan for i in signals.index]
# only verifications for days after DPth (period of RSI) day
signals['id'][dp:].loc[((signals['RSI'] < 30) &
(signals['bollinger'] < 0))] = 1
signals['id'][dp:].loc[((signals['RSI'] > 70) &
(signals['bollinger'] > 1))] = 0
signals['id'].ffill(inplace=True) #fill empty values with 0
signals['id'].fillna(0, inplace=True)
signals['buySell'] = signals['id'].diff()
signals['buySell'].fillna(0, inplace=True)
fig, (ax) = plt.subplots(1, 1)
ax.plot(signals['price'])
ax.set_xlabel('Date')
ax.set_ylabel('Value in $')
day = signals.loc[signals.buySell == 1.0].index
day2 = signals.loc[signals.buySell == -1.0].index
#x cordinates, index of day --> y cordinate,price of day index
ax.scatter(
x=day,
y=signals.loc[day, 'price'],
marker='^',
color='green',
)
ax.scatter(x=day2, y=signals.loc[day2, 'price'], marker='v', color='red')
plt.show()
# Variables
tickers = si.tickers_sp500()
tickers = [item.replace(".", "-")
for item in tickers] # Yahoo Finance uses dashes instead of dots
index_name = '^GSPC' # S&P 500
start_date = datetime.datetime.now() - datetime.timedelta(days=365)
end_date = datetime.date.today()
exportList = pd.DataFrame(columns=[
'Stock', "RS_Rating", "50 Day MA", "150 Day Ma", "200 Day MA",
"52 Week Low", "52 week High"
])
returns_multiples = []
# Index Returns
index_df = pdr.get_data_yahoo(index_name, start_date, end_date)
index_df['Percent Change'] = index_df['Adj Close'].pct_change()
index_return = (index_df['Percent Change'] + 1).cumprod()[-1]
# Find top 30% performing stocks (relative to the S&P 500)
for ticker in tickers:
# Download historical data as CSV for each stock (makes the process faster)
df = pdr.get_data_yahoo(ticker, start_date, end_date)
df.to_csv(f'{ticker}.csv')
# Calculating returns relative to the market (returns multiple)
df['Percent Change'] = df['Adj Close'].pct_change()
stock_return = (df['Percent Change'] + 1).cumprod()[-1]
returns_multiple = round((stock_return / index_return), 2)
returns_multiples.extend([returns_multiple])
def test_get_data_multiple_symbols(self):
# just test that we succeed
sl = ['AAPL', 'AMZN', 'GOOG']
web.get_data_yahoo(sl, '2012')
def getStockData(self, tickers, st, ed):
""" Get data from yahoo Finance"""
data = pdr.get_data_yahoo(tickers, start = st, end = ed)[['High','Low',\
'Open','Adj Close','Volume']]
data.columns = ['high', 'low', 'open', 'close', 'volume']
return data
import numpy as np
# For Visualization
import matplotlib.pyplot as plt
import seaborn as sns
# For data retrival
from pandas_datareader import data, wb
from datetime import datetime
sns.set_style('whitegrid')
# Let us consider the stocks for various tech gaints
tech_list = ['AAPL', 'GOOG', 'MSFT', 'AMZN', 'C']
end = datetime(2020, 6, 1)
start = datetime(end.year - 1, end.month, end.day)
for stock in tech_list:
globals()[stock] = data.get_data_yahoo(stock, start, end)
# AAPL['Adj Close'].plot(legend = True,figsize=(10,4))
AAPL['Volume'].plot(legend=True, figsize=(10, 4))
# Finding moving averages for fav AAPL stock
ma_day = [10, 20, 50]
for ma in ma_day:
column_name = "MA for days" + str(ma)
AAPL[column_name] = AAPL['Adj Close'].rolling(ma).mean()
# To understand the flowing line and trading averages
AAPL[['Adj Close', 'MA for days10', 'MA for days20',
'MA for days50']].plot(subplots=False, figsize=(10, 4))
# To check for daily returns
4. When de MACD line cuts the signal line from below = bullish period, cuts the signal from above = bearish period
Cons: Many false positives (especially during sideways markets). It's a lagging indicator.
- People use it in conjunction with another indicator.
'''
# Import necesary libraries
import pandas_datareader.data as pdr
import datetime
import matplotlib.pyplot as plt
# Download historical data for required stocks
ticker = "MSFT"
ohlcv = pdr.get_data_yahoo(ticker,
datetime.date.today() - datetime.timedelta(1825),
datetime.date.today())
def MACD(DF, a, b, c):
"""function to calculate MACD
typical values a = 12; b =26, c =9"""
df = DF.copy(
) #Copy because i don't wanna make any change in the original DF
df["MA_Fast"] = df["Adj Close"].ewm(span=a, min_periods=a).mean()
df["MA_Slow"] = df["Adj Close"].ewm(span=b, min_periods=b).mean()
df["MACD"] = df["MA_Fast"] - df["MA_Slow"]
df["Signal"] = df["MACD"].ewm(span=c, min_periods=c).mean()
df.dropna(inplace=True) #Delete the NaN rows
return df
import pandas as pd
from pandas_datareader import data as pdr
import yfinance as yf
yf.pdr_override()
dow = pdr.get_data_yahoo('^DJI', '2000-01-04')
kospi = pdr.get_data_yahoo('^KS11', '2000-01-04')
df = pd.DataFrame({'DOW' dow['Close'], 'KOSPI' kospi['Close']})
df = df.fillna(method='bfill')
df = df.fillna(method='ffill')
import matplotlib.pyplot as plt
plt.figure(figsize=(7, 7))
plt.scatter(df['DOW'], df['KOSPI'], marker='.')
plt.xlabel('Dow Jones Industrial Average')
plt.ylabel('KOSPI')
plt.show()
def stockHistory(symbol, startDate, endDate, code):
stock = pdr.get_data_yahoo(symbol, start=startDate, end=endDate)
# Assign `Adj Close` to `daily_close`
daily_close = stock[['Adj Close']]
# Daily returns
daily_pct_change = daily_close.pct_change()
# Replace NA values with 0
daily_pct_change.fillna(0, inplace=True)
stock['pctChange'] = stock[['Adj Close']].pct_change()
# stock['logDelta'] = np.log(daily_close.pct_change()+1)
stock.fillna(0, inplace=True)
stock['delta'] = "Test"
stock['EMA12'] = 0.0
stock['EMA26'] = 0.0
stock['MACD'] = 0.0
stock['MACD Signal'] = 0.0
stock['MACD Trend'] = 0.0
stock['RSI'] = 0.0
stock['RSI Trend'] = 0.0
stock['Stochastic'] = 0.0
stock['Stochastic SMA'] = 0.0
probabilities = [0, 0, 0]
transitions = [[0, 0, 0], [0, 0, 0], [0, 0, 0]]
transitionsDict = {}
for key in [('Up', 'Up'), ('Up', 'Neutral'), ('Up', 'Down')]:
transitionsDict[key] = 0
for key in [('Neutral', 'Up'), ('Neutral', 'Neutral'),
('Neutral', 'Down')]:
transitionsDict[key] = 0
for key in [('Down', 'Up'), ('Down', 'Neutral'), ('Down', 'Down')]:
transitionsDict[key] = 0
sums = 0
classes = []
for i in range(0, len(stock.index)):
# test.append(stock.iloc[i]['pctChange'])
result = convert(stock.iloc[i]['pctChange'], probabilities)
stock['delta'][i] = result[0]
classes.append(result[2])
if i > 0:
transitionsDict[(result[0], stock['delta'][i - 1])] += 1
if stock['delta'][i - 1] is "Up":
transitions[result[2]][0] += 1
sums += 1
elif stock['delta'][i - 1] is "Neutral":
transitions[result[2]][1] += 1
sums += 1
elif stock['delta'][i - 1] is "Down":
transitions[result[2]][2] += 1
sums += 1
probabilities = result[1]
probabilitiesPct = []
summed = probabilities[0] + probabilities[1] + probabilities[2]
probabilitiesPct = [
probabilities[0] / summed, probabilities[1] / summed,
probabilities[2] / summed
]
print(transitions)
stock = ema(stock, 12, 'EMA')
stock = ema(stock, 26, 'EMA')
stock = macd(stock)
stock = ema(stock, 9, 'MACD')
stock = rsi(stock, 14)
stock = stochastic(stock, 14)
# print(stock)
stock.to_csv(symbol + code + ".csv")
return (stock, classes, transitions)
def plotPorts2(start_date, end_date):
plt.close()
yf.pdr_override()
data = pdr.get_data_yahoo("BTC-USD", start_date, end_date)
btc = pd.DataFrame(data)
btc = btc[['Adj Close']]
btc.columns = ['Close']
btc.reset_index(level=0, inplace=True)
# In[8]:
b = pd.DataFrame()
for x in btc:
b['price'] = btc['Close']
b['sma'] = btc['Close'].rolling(window=20).mean()
b['std'] = btc['Close'].rolling(window=20).std()
b['bolU'] = b['sma'] + (2 * b['std']) #Calculating Upper Bound
b['bolD'] = b['sma'] - (2 * b['std']) #Calculating Lower Bound
#Convert Bollinger Bands to %b - bollinger column
b['bollinger'] = (b['price'] - b['bolD']) / (b['bolU'] - b['bolD'])
bb1 = b[['price', 'bolU', 'bolD', 'bollinger']]
bb1.columns = ['Price', 'Upper Band', 'Lower Band', 'Bollinger']
bb1.fillna(0, inplace=True)
# In[ ]:
# In[9]:
RSI = pd.DataFrame(index=btc.index)
RSI['price'] = btc['Close']
RSI['val'] = None
RSI['up'] = 0 #When there is no up value 0
RSI['down'] = 0 #When there is no down value 0
size = RSI.shape[0]
dp = 14
for x in range(size):
if x == 0:
continue #first day will continue
#calculating the ups , when closing price is higher in day x than x -1
if RSI['price'].iloc[x] > RSI['price'].iloc[x - 1]: #
RSI['up'].iloc[x] = RSI['price'].iloc[x] - RSI['price'].iloc[x - 1]
else:
#calculating the downs days , when closing price is lower in day x than x -1
RSI['down'].iloc[x] = RSI['price'].iloc[x -
1] - RSI['price'].iloc[x]
if x >= dp:
avgUp = RSI['up'][x - dp:x].sum(
) / dp #calculates avg up of last dp days
avgDown = RSI['down'][x - dp:x].sum(
) / dp #calculates avg down of last dp days
rs = avgUp / avgDown #calculation of RS
RSI['val'].iloc[x] = 100 - 100 / (1 + rs)
signals = pd.DataFrame(index=btc.index) #copy index for BTC
signals['price'] = btc['Close']
signals['id'] = 0.0
signals['RSI'] = RSI['val']
signals['RSI'].fillna(0, inplace=True)
signals['bollinger'] = bb1['Bollinger']
signals['id'] = [np.nan for i in signals.index]
# only verifications for days after DPth (period of RSI) day
signals['id'][dp:].loc[((signals['RSI'] < 30) &
(signals['bollinger'] < 0))] = 1
signals['id'][dp:].loc[((signals['RSI'] > 70) &
(signals['bollinger'] > 1))] = 0
signals['id'].ffill(inplace=True) #fill empty values with 0
signals['id'].fillna(0, inplace=True)
signals['buySell'] = signals['id'].diff()
signals['buySell'].fillna(0, inplace=True)
###################################################################################
# Code taken from Willems, K., 2019. (Tutorial) Python For Finance: Algorithmic Trading
initInvestment = 100000
stocksOwned = pd.DataFrame(index=signals.index).fillna(0.0)
noCur = 10 #No of currency to be purchased
stocksOwned['BTC'] = noCur * signals['id']
portfolio = pd.DataFrame(index=signals.index)
portfolio['Holdings'] = stocksOwned['BTC'].multiply(btc['Close'], axis=0)
buySell = stocksOwned['BTC'].diff()
portfolio['cash'] = initInvestment - (buySell.multiply(btc['Close'],
axis=0)).cumsum()
portfolio['total'] = portfolio['cash'] + portfolio['Holdings']
portfolio['cash'][0] = initInvestment
portfolio['total'][0] = initInvestment
###################################################################################
# In[50]:
fig, (ax) = plt.subplots(1, 1, sharex=True)
ax.plot(portfolio.index, portfolio['total'], label='Price')
ax.set_xlabel('Date')
ax.set_ylabel('Value of portfolio in USD')
day = signals.loc[signals.buySell == 1.0].index
day2 = signals.loc[signals.buySell == -1.0].index
ax.scatter(x=day, y=portfolio.loc[day, 'total'], color='green')
ax.scatter(x=day2, y=portfolio.loc[day2, 'total'], color='red')
plt.show()
"PG", "TRV", "UTX", "UNH", "VZ", "V", "WMT", "DIS"
] # Constituents of dow jones as of 2014-02-01 (except dow chemicals because Yahoo didn't have all the data)
ohlc_mon = {} # directory with ohlc value for each stock
attempt = 0 # initializing passthrough variable
drop = [
] # initializing list to store tickers whose close price was successfully extracted
while len(tickers) != 0 and attempt <= 5:
tickers = [
j for j in tickers if j not in drop
] # removing stocks whose data has been extracted from the ticker list
for i in range(len(tickers)):
try:
ohlc_mon[tickers[i]] = pdr.get_data_yahoo(tickers[i],
datetime.date.today() -
datetime.timedelta(2419),
datetime.date.today(),
interval='m')
ohlc_mon[tickers[i]].dropna(inplace=True)
drop.append(tickers[i])
except:
print(tickers[i], " :failed to fetch data...retrying")
continue
attempt += 1
tickers = ohlc_mon.keys(
) # redefine tickers variable after removing any tickers with corrupted data
################################Backtesting####################################
# calculating monthly return for each stock and consolidating return info by stock in a separate dataframe
def test_yfinance():
for symbol in ['MSFT', 'IWO', 'VFINX','BTC-USD']:
print(">>", symbol, end=' ... ')
data = pdr.get_data_yahoo(symbol,start='2020-09-25', end='2020-10-02')
print(data)
def download_historical(ticker: str, period: str, interval: str):
data = pdr.get_data_yahoo(ticker, period=period, interval=interval)
return data
def data(ticker):
return (pdr.get_data_yahoo(ticker, start=startdate, end=enddate))
def get_history(symbols, start, end, data_path, visible=False):
from pandas_datareader import data as y_data
""" to get Yahoo data from saved csv files. If the file does not exist for the symbol,
data is read from Yahoo finance and the csv saved.
symbols: symbol list
start, end : datetime start/end dates
data_path : datapath for csv files - use double \\ and terminate path with \\
"""
symbols_ls = list(symbols)
for ticker in symbols:
print(ticker, )
try:
#see if csv data available
data = pd.read_csv(data_path + ticker + '.csv',
index_col='Date',
parse_dates=True)
except:
#if no csv data, create an empty dataframe
data = pd.DataFrame(data=None, index=[start])
#check if there is data for the start-end data range
if start.toordinal() < data.index[0].toordinal() \
or end.toordinal() > data.index[-1].toordinal():
if visible:
print('Refresh data.. ', )
try:
new_data = y_data.get_data_yahoo(ticker, start, end)
if new_data.empty == False:
if data.empty == False:
try:
ticker_data = data.append(new_data).groupby(
level=0, by=['rownum']).last()
except:
print('Merge failed.. ')
else:
ticker_data = new_data
try:
ticker_data.to_csv(data_path + ticker + '.csv')
if visible:
print(' UPDATED.. ')
except:
print('Save failed.. ')
else:
if visible:
print('No new data.. ')
except:
print('Download failed.. ')
# remove symbol from list
symbols_ls.remove(ticker)
else:
if visible:
print('OK.. ')
pass
pdata = pd.Panel(dict((symbols_ls[i], pd.read_csv(data_path + symbols_ls[i] + '.csv',\
index_col='Date', parse_dates=True).sort_index(ascending=True)) for i in range(len(symbols_ls))) )
return pdata.iloc[:, start:end, :]
def test_get_data_adjust_price(self):
goog = web.get_data_yahoo('GOOG')
goog_adj = web.get_data_yahoo('GOOG', adjust_price=True)
self.assertTrue('Adj Close' not in goog_adj.columns)
self.assertTrue((goog['Open']*goog_adj['Adj_Ratio']).equals(goog_adj['Open']))
print('The RMS error is {}'.format(rms))
return {'loss': rms, 'status': STATUS_OK, 'model': model}
#'main' program
if __name__ == '__main__':
#data_df = pd.read_csv('GOOG_2015-04-01_2020-03-31.csv', index_col='Date', parse_dates=True)
#using pandas_datareader library to get the data from Yahoo-Finance
start_date = datetime(2015, 4, 1)
end_date = datetime(2020, 3, 31)
ticker = 'GOOG'
data_df = pdr.get_data_yahoo(tickers=ticker,
start=start_date,
end=end_date)
#In our model, we will try to predict the future close price of a stock using only the past
#close prices of that particular stock. So let's a create a new dataframe with only the
#'Date' and 'Close' price columns
new_data = pd.DataFrame(index=range(0, len(data_df)),
columns=['Date', 'Close'])
for i in range(0, len(data_df)):
new_data['Date'][i] = data_df.index[i]
new_data['Close'][i] = data_df['Close'][i]
#setting 'Date' column as index and dropping the original column
new_data.index = new_data.Date
new_data.drop('Date', axis=1, inplace=True)
def GetStockQuote(symbol) :
quote = web.get_data_yahoo(symbol,thirty_days.strftime("%m/%d/%Y"), time.strftime("%m/%d/%Y"))
#quote = web.get_data_yahoo(symbol,thirty_days.strftime("%m/%d/%Y"), twenty_days.strftime("%m/%d/%Y"))
return quote
import pandas as pd
# to correct is_list_like method which as change from pandas.core.common to pandas.api.types
pd.core.common.is_list_like = pd.api.types.is_list_like
from pandas_datareader import data as pdr
import fix_yahoo_finance as yf
yf.pdr_override()
# download dataframe
start_date = '2007-01-01'
end_date = '2018-07-26'
firstreits = 'AW9U.SI'
silverlake = '5CP.SI'
perennial = 'P22.SI'
oue = 'LJ3.SI'
mystocklist = [firstreits, silverlake, perennial, oue]
for stock in mystocklist:
try:
print('Reading stock code {0}'.format(stock))
sdata = pdr.get_data_yahoo(stock, start_date, end_date)
sdata.to_csv(stock + '.csv')
except Exception as e:
sdata.to_csv(stock + '.csv')
print("{0} encounter problem {1}".format(stock, e.args))
os.chdir('/home/vesis/Documents/Python/Portfolio_analysis')
init_notebook_mode(connected=True)
# Define the date variables
# Make a function considering different opening dates and the time difference(!!!)
start_omxh = datetime.datetime(2011, 12, 29)
end_omxh = datetime.datetime(2020, 12, 29)
end_of_last_year = datetime.datetime(2019, 12, 30)
start_stocks = datetime.datetime(2011, 12, 29)
end_stocks = datetime.datetime(2020, 12, 29)
# DATA PULL
# Pull OMXH25 data from Yahoo! Finance
# Form a subset containing only daily closing values
# Define last year's closing value for YTD calculation
omxh25 = pdr.get_data_yahoo('^OMXH25', start_omxh, end_omxh)
omxh25_adj_close = omxh25[['Adj Close']].reset_index()
omxh25_adj_close_start = omxh25_adj_close[omxh25_adj_close['Date'] ==
end_of_last_year]
# PORTFOLIO DATA PULL #
# Read in the analyzed portfolio and pull corresponding data from Yahoo! Finance
portfolio_df = pd.read_excel('Stocks_v3.xls')
tickers = portfolio_df['Ticker'].unique()
# Function for pulling the ticker data
def get(tickers, startdate, enddate):
def data(ticker):
return (pdr.get_data_yahoo(ticker, start=startdate, end=enddate))
cf.go_offline()
# Defining today's Date
from datetime import date
today = date.today()
from pandas_datareader import data as pdr
import yfinance as yf
yf.pdr_override() # <== that's all it takes :-)
import PortfolioLab as pl
# %%
# download dataframe using pandas_datareader
data = pdr.get_data_yahoo("^GSPC", start="1970-12-21",
end="2021-04-30")[['Close']]
# %%
data.columns = ['S&P 500']
# %%
data['DD'] = pl.compute_drawdowns(data)
# %%
data['<10'] = data['DD'].apply(lambda x: 1 if x < -10 else 0)
# %%
data['Shade'] = True
# %%
data
# %%
for i in range(len(data) - 1):
# print title of web app
st.title("Stock Market Analysis and Prediction")
st.markdown(
"> Stock Market Analysis and Prediction is the project on technical analysis, visualization and prediction using data provided by Yahoo Finance."
)
st.markdown(
"> It is web app which predicts the future value of company stock or other financial instrument traded on an exchange."
)
# Create a text element and let the reader know the data is loading.
data_load_state = st.text('Loading data...')
# Load data from yahoo finance.
start = dt.date(2010, 1, 1)
end = dt.date.today()
data = pdr.get_data_yahoo("GOOG", start, end)
#fill nan vale with next value within columns
data.fillna(method="ffill", inplace=True)
# Notify the reader that the data was successfully loaded.
data_load_state.text('Loading data...done!')
# create checkbox
if st.checkbox('Show raw data'):
st.subheader('Raw data')
st.write(data)
# show the description of data
st.subheader('Detail description about Datasets:-')
descrb = data.describe()
mean_prediction_error_array = []
for s in epoch:
epoch = s
from numpy.random import seed
seed(0)
# from tensorflow import set_random_seed
# set_random_seed(1)
# Split Method 1 is 70% train / 20% test / 10% predict
################################################################################################################
################################################# Get Stock Data ###############################################
yf.pdr_override() # <== that's all it takes :-)
df = pdr.get_data_yahoo(ticker, period='5d', interval='1m')
# if Load_Saved_Ticker_data == False:
# df = web.DataReader(ticker, 'yahoo', start, end)
# df.to_csv("C:/Projects/Stock Tools/Stock Data/{ticker}.csv".format(ticker=ticker))
# if Load_Saved_Ticker_data == True:
# df = pd.read_csv("C:/Projects/Stock Tools/Stock Data/{ticker}.csv".format(ticker=ticker))
df = df['Adj Close'].values
df = df.reshape(-1, 1)
print('Stock data Loaded')
################################################################################################################
################################################# Training / Test ##############################################
if split_method == 1:
dataset_train = np.array(df[:int(df.shape[0] * 0.8)])
#e6-3-3: 上網路抓取股價資料畫高低圖
import pandas as pd
from pandas_datareader import data as web
import fix_yahoo_finance
#下載資料起始日與股票代號
start = "2017-01-01"
end = "2017-04-30"
df = web.get_data_yahoo('2317.tw', start, end)
#日股價資料寫入excel檔
writer = pd.ExcelWriter('2317.xlsx')
df.to_excel(writer, '2317')
workbook = writer.book
worksheet = writer.sheets['2317']
#畫高低圖
chart = workbook.add_chart({'type': 'stock'})
chart.add_series({
'name': '=2317!$B$1',
'categories': '=2317!$A$2:$A$14',
'values': '=2317!$B$2:$B$14'
})
chart.add_series({
'name': '=2317!$C$1',
'categories': '=2317!$A$2:$A$14',
'values': '=2317!$C$2:$C$14'
})
chart.add_series({
'name': '=2317!$D$1',
'categories': '=2317!$A$2:$A$14',
'values': '=2317!$D$2:$D$14'
})
chart.set_title({'name': 'High-Low-Close'})
import pandas as pd pd.core.common.is_list_like = pd.api.types.is_list_like #is_list_like is moved to pandas.api.types import pandas_datareader.data as pdr #.data allows you to extract information from Yahoo import datetime as dt ticker = 'AMZN' start_date = dt.date.today() - dt.timedelta(365) end_date = dt.date.today() #extract daily data (smallest granuality) data = pdr.get_data_yahoo(ticker, start_date, end_date) print(data) #extracts daily data - open, high, adj colse and volume #get monthly data data_monthly = pdr.get_data_yahoo(ticker, start_date, end_date, interval = 'm') print(data_monthly) #returns monthly data
## 최대손실 낙폭
# MDD(Maximum Drawdown, 최대손실 낙폭)은 특정 기간에 발생한 최고점에서 최저점까지의 가장 큰
# 손실을 의미한다. 퀀트 투자에서 수익률을 높이는 것보다 MDD를 낮추는 것이 더 중요하다.
# 특정 기간 동안 최대한 얼마의 손실이 일어날 수 있는지를 나타낸다.
# MDD = (최저점 - 최고점) / 최저점
from pandas_datareader import data as pdr
import yfinance as yf
yf.pdr_override()
import matplotlib.pyplot as plt
# KOSPI 지수의 심볼은 ^KS11 이다.
kospi = pdr.get_data_yahoo('^KS11', '2004-01-04')
# 산정 기간에 해당하는 window 값은 1년 동안 개장일을 252일로 설정한다.
window = 252
# KOSPI 종가 컬럼에서 1년(거래일 기준) 기간 단위로 최고치 peak를 구한다.
peak = kospi['Adj Close'].rolling(window, min_periods=1).max()
# drawdown 은 최고치(peak) 대비 현재 KOSPI 종가가 얼마나 하락 했는지 구한다.
drawdown = kospi['Adj Close'] / peak - 1.0
# drawdown 에서 1년 기간 단위로 최저치 min_dd 를 구한다.
# 마이너스값이기 때문에 최저치가 바로 최대 손실 낙폭이 된다.
### rolling -> 앞에 있는 숫자 만큼씩 묶어서 계산(7일선, 30일선 등과 같은 걸 계산할 때)
max_dd = drawdown.rolling(window, min_periods=1).min()
end_date = "2020-02-14"
date_now = datetime.strftime(now, "%Y%m%d")
# for multiple stock tickers from csv
if ticker1 == "":
read_csv = pd.read_csv('./db/0.etf_db_metadata.csv')
tickers = read_csv['Symbol']
tickers = pd.Series(tickers)
tickers.drop_duplicates(inplace=True)
tickers.reset_index(drop=True, inplace=True)
tickers.sort_values(ascending=True, inplace=True)
print(tickers)
for i in tqdm(range(len(tickers))):
ticker2 = tickers[i].replace('.', '-')
data = pdr.get_data_yahoo(ticker2, start=start_date, end=end_date)
data = data[['Open', 'High', 'Low', 'Close', 'Volume']]
data = pd.DataFrame(data)
data = round(data, 2)
savename = './db/' + ticker2 + '.csv'
data.to_csv(savename)
# get one simply
else:
data = pdr.get_data_yahoo(ticker1, start=start_date, end=end_date)
data = data[['Open', 'High', 'Low', 'Close', 'Volume']]
data = pd.DataFrame(data)
data = round(data, 2)
savename = './db/' + ticker1 + '.csv'
data.to_csv(savename)
