def ret_f(ticker, startDate, endDate):
p = finance.quotes_historical_yahoo(ticker,
startDate,
endDate,
asobject=True,
adjusted=True)
return ((p.aclose[1:] - p.aclose[0:-1]) / p.aclose[:-1])
def calc_stats(ticker):
"""calculates basic statistical quantites for the daily returns
of the stock with ticker
Arguments
=========
ticker: string containg the ticker
Returns
======
None
Saves statistical quantities to 'TICKER_daily_returns_stats.txt'
"""
# start your code here5
now = datetime.datetime.now()
sp = finance.quotes_historical_yahoo(ticker, (1900, 1, 1), (now.year, now.month, now.day), asobject=True, adjusted=False)
returns = np.array([(sp.open[i+1] - sp.open[i]) / sp.open[i] for i in range(len(sp.open) - 1)])
mean = np.mean(returns)
median = np.median(returns)
std = np.std(returns)
skewness = stats.skew(returns)
kurtosis = stats.kurtosis(returns)
resultStr = "Statistical Properties of Daily Returns For: {0}\nMean = {1} Median = {2} Standard Deviation = {3} Skewness = {4} Kurtosis = {5}".format(*(ticker, mean, median, std, skewness, kurtosis))
result = open(ticker + "_daily_returns_stats.txt", 'w')
result.write(resultStr)
return None
def candlestickExample():
# (Year, month, day) tuples suffice as args for quotes_historical_yahoo
date1 = ( 2004, 2, 1)
date2 = ( 2004, 4, 12 )
mondays = WeekdayLocator(MONDAY) # major ticks on the mondays
alldays = DayLocator() # minor ticks on the days
weekFormatter = DateFormatter('%b %d') # e.g., Jan 12
dayFormatter = DateFormatter('%d') # e.g., 12
quotes = quotes_historical_yahoo('INTC', date1, date2)
if len(quotes) == 0:
raise SystemExit
fig, ax = plt.subplots()
fig.subplots_adjust(bottom=0.2)
ax.xaxis.set_major_locator(mondays)
ax.xaxis.set_minor_locator(alldays)
ax.xaxis.set_major_formatter(weekFormatter)
#ax.xaxis.set_minor_formatter(dayFormatter)
#plot_day_summary(ax, quotes, ticksize=3)
candlestick(ax, quotes, width=0.6)
ax.xaxis_date()
ax.autoscale_view()
plt.setp( plt.gca().get_xticklabels(), rotation=45, horizontalalignment='right')
print quotes
plt.show()
def __init__(self, ticker):
gtk.VBox.__init__(self)
startdate = datetime.date(2001, 1, 1)
today = enddate = datetime.date.today()
date1 = datetime.date(2011, 1, 1)
date2 = datetime.date.today()
mondays = WeekdayLocator(MONDAY) # major ticks on the mondays
alldays = DayLocator() # minor ticks on the days
weekFormatter = DateFormatter("%b %d") # Eg, Jan 12
dayFormatter = DateFormatter("%d") # Eg, 12
quotes = quotes_historical_yahoo(ticker, date1, date2)
if len(quotes) == 0:
raise SystemExit
fig = Figure(facecolor="white", figsize=(5, 4), dpi=100)
fig.subplots_adjust(bottom=0.2)
ax = fig.add_subplot(111)
ax.xaxis.set_major_locator(mondays)
ax.xaxis.set_minor_locator(alldays)
ax.xaxis.set_major_formatter(weekFormatter)
candlestick(ax, quotes, width=0.6)
ax.xaxis_date()
ax.autoscale_view()
pylab.setp(pylab.gca().get_xticklabels(), rotation=45, horizontalalignment="right")
canvas = FigureCanvas(fig) # a gtk.DrawingArea
self.pack_start(canvas)
toolbar = NavigationToolbar(canvas, win)
self.pack_start(toolbar, False, False)
def test(self):
#1. Get close prices.
today = datetime.date.today()
start = (today.year - 1, today.month, today.day)
quotes = quotes_historical_yahoo('AAPL', start, today)
close = numpy.array([q[4] for q in quotes])
#2. Get positive log returns.
logreturns = numpy.diff(numpy.log(close))
pos = logreturns[logreturns > 0]
#3. Get frequencies of returns.
counts, values = numpy.histogram(pos,bins=5)
values = values[:-1] + (values[1] - values[0])/2
freqs = 1.0/counts
freqs = numpy.log(freqs)
#4. Fit the frequencies and returns to a line.
p = numpy.polyfit(values,freqs, 1)
#5. Plot the results.
matplotlib.pyplot.plot(values, freqs, 'o')
matplotlib.pyplot.plot(values, p[0] * values + p[1])
def get_close(ticker):
today = date.today()
start = (today.year - 1, today.month, today.day)
quotes = quotes_historical_yahoo(ticker, start, today)
return np.array([q[4] for q in quotes])
def best_fit_gaussian(ticker):
"""determines the best fit gaussian for the distribution of daily
returns for stock with ticker and makes a plot of the distribution
and the best-fit gaussian
=========
ticker: string for the stock ticker
Returns
======
None
Saves plot to 'TICKER_gaussian_fit.pdf'
"""
# start your code here
stock_data = finance.quotes_historical_yahoo(ticker, (1950, 1, 1), (2014, 9, 30), asobject=True, adjusted=True)
returns = np.array([(stock_data.open[i+1] - stock_data.open[i]) / stock_data.open[i] for i in range(len(stock_data.open) - 1)])
counts, bin_edges = np.histogram(returns, density=True, bins=200)
bin_centers = bin_edges[:-1]+(bin_edges[1]-bin_edges[0])/2.0
popt, pcov = curve_fit(gaussian, bin_centers, counts)
counts_fit = gaussian(bin_centers, *popt)
blue_dot = plt.plot(bin_centers, counts, label="Daily Returns", color = 'blue', linewidth = 0, marker = 'o', markersize=3, markeredgewidth = 0, markeredgecolor='none')
green_line = plt.plot(bin_centers, counts_fit, label="Gaussian", color='green')
x_axis = plt.xticks()[0]
text_x_pos = x_axis[math.ceil(len(x_axis) * 0.6)]
y_axis = plt.yticks()[0]
text_y_pos = y_axis[math.ceil(len(y_axis) * 0.4)]
plt.legend(loc="upper right")
plt.text(text_x_pos, text_y_pos, 'mu={0:.03f}\nsigma={1:.03f}'.format(*(popt[0], popt[1])))
plt.xlabel('Daily Returns')
plt.ylabel('Probability Density')
plt.title(ticker)
plt.savefig(ticker + '_gaussian_fit.pdf')
return None
def initialize1( self,stockTicker, date1, date2, interval, resolution, dataFeedType):
self.stockTicker = stockTicker;
if(dataFeedType =="yahoo"):
self.quotes = quotes_historical_yahoo(self.stockTicker, date1, date2)
self.N = self.quotes.__len__();
self.vDateInt = zeros(self.N)
self.vDate = empty(self.N, dtype=object);
self.vOpen = zeros(self.N)
self.vClose = zeros(self.N)
self.vHigh = zeros(self.N)
self.vLow = zeros(self.N)
self.vVolume = zeros(self.N)
index = 0;
for line in self.quotes:
self.vDateInt[index]= line [0];
self.vDate[index] = date.fromordinal( int( line [0] ) )
self.vOpen[index] = line [1];
self.vClose[index] = line [2];
self.vHigh[index] = line [3];
self.vLow[index] = line [4];
self.vVolume[index] = line [5];
index = index +1;
elif (dataFeedType == "google"):
self.vDateInt, self.vOpen, self.vHigh, self.vLow, self.vClose, self.vVolume = quotes_historical_google.getData(symbol=self.stockTicker, startDate=date1, endDate=date2, resolution=resolution);
self.N = size(self.vDateInt);
self.vDate = empty(self.N, dtype=object);
index = 0;
for d in self.vDateInt:
self.vDate[index] = date.fromordinal( int( d) );
index = index + 1;
def get_close(ticker): today = date.today() start = (today.year - 1, today.month, today.day) quotes = quotes_historical_yahoo(ticker, start, today) return numpy.array([q[4] for q in quotes])
def test(self):
# 2011 to 2012
start = datetime.datetime(2011, 01, 01)
end = datetime.datetime(2012, 01, 01)
symbols = ["AA", "AXP", "BA", "BAC", "CAT"]
quotes = [
finance.quotes_historical_yahoo(symbol, start, end, asobject=True)
for symbol in symbols
]
close = numpy.array([q.close for q in quotes]).astype(numpy.float)
dates = numpy.array([q.date for q in quotes])
data = {}
for i in xrange(len(symbols)):
data[symbols[i]] = numpy.diff(numpy.log(close[i]))
df = pandas.DataFrame(data, index=dates[0][:-1], columns=symbols)
print df
print df.corr()
df.plot()
legend(symbols)
show()
def get_quotes():
import urllib2
from socket import error as SocketError
import errno
fi = open('china.txt')
lines = fi.readlines()
symbol_dict={}
for mar, idx in Markets.iteritems():
for k, v in gen_symbols(lines, mar,idx):
symbol_dict[k] = v
quotes=[]
symbols = []
#symbol e.g.: u'603099.ss',u'002281.sz'
for symbol in symbol_dict.keys():
try:
q = finance.quotes_historical_yahoo(symbol, d1, d2, asobject=True)
#q.readlines(), return format: Date,Open,High,Low,Close,Volume,Adj Close
except Exception, e:
print symbol, e
symbol_dict.pop(symbol)
if None != q:
quotes.append(q)
symbols.append(symbol)
def main():
win = gtk.Window()
win.connect('destroy', gtk.main_quit)
win.set_title('Cursors')
vbox = gtk.VBox()
win.add(vbox)
# Get data from Yahoo Finance
enddate = datetime.date.today()
startdate = enddate + datetime.timedelta(days=-72)
quotes = finance.quotes_historical_yahoo('GOOG', startdate, enddate)
qa = array(quotes)
f = create_figure(quotes)
a = f.gca()
vbox.pack_start(gtk.Label('No Blit'), False, False)
vbox.pack_start(f.canvas)
cursor1 = SnaptoCursor(a, qa[:,0], qa[:,2], useblit=False)
f.canvas.mpl_connect('motion_notify_event', cursor1.mouse_move)
f = create_figure(quotes)
a = f.gca()
vbox.pack_start(gtk.Label('Use Blit'), False, False)
vbox.pack_start(f.canvas)
cursor2 = SnaptoCursor(a, qa[:,0], qa[:,2], useblit=True)
f.canvas.mpl_connect('motion_notify_event', cursor2.mouse_move)
win.show_all()
gtk.main()
def sample():
###############################################################################
# Downloading the data
date1 = datetime.date(2012, 1, 1) # start date
date2 = datetime.date(2012, 12, 1) # end date
# get quotes from yahoo finance
quotes = quotes_historical_yahoo("INTC", date1, date2)
if len(quotes) == 0:
raise SystemExit
# unpack quotes
dates = np.array([q[0] for q in quotes], dtype=int)
close_v = np.array([q[2] for q in quotes])
# volume = np.array([q[5] for q in quotes])[1:]
# take diff of close value
# this makes len(diff) = len(close_t) - 1
# therefore, others quantity also need to be shifted
diff = 100 * (np.exp(np.log(close_v[1:]) - np.log(close_v[:-1])) - 1)
dates = dates[1:]
close_v = close_v[1:]
print diff
# pack diff and volume for training
# X = np.column_stack([diff, volume])
X = np.column_stack([diff])
return X, dates, close_v
def test(self):
#Get close prices.
today = datetime.date.today()
start = (today.year - 1, today.month, today.day)
quotes = quotes_historical_yahoo('AAPL', start, today)
close = numpy.array([q[4] for q in quotes])
#2. Get log returns.
logreturns = numpy.diff(numpy.log(close))
#3. Calculate breakout and pullback
freq = 1 / float(50)
breakout = scipy.stats.scoreatpercentile(logreturns, 100 * (1 - freq))
pullback = scipy.stats.scoreatpercentile(logreturns, 100 * freq)
print breakout
print pullback
print logreturns
#4. Generate buys and sells
buys = numpy.compress(logreturns < pullback, close)
sells = numpy.compress(logreturns > breakout, close)
profit = sells.sum() - buys.sum()
print 'profit: from log_returns = %s' % profit
#5. Plot a histogram of the log returns
matplotlib.pyplot.hist(logreturns)
def get_data_yahoo_orig(start_date,
end_date,
fut_code="INTC",
format="candle"):
try:
quotes = quotes_historical_yahoo(fut_code, start_date, end_date)
except:
print("Unable to get quotes for %s", fut_code)
return []
if quotes == None:
print("Unable to get quotes for %s", fut_code)
return []
if len(quotes) == 0:
print("Unable to get quotes for %s", fut_code)
return []
else:
if(quotes[0][0] < float(datetime.datetime.toordinal(start_date)) or \
quotes[len(quotes)-1][0] > float(datetime.datetime.toordinal(end_date))):
print "unnable to get yahoo quotes for ticker %s for required dates" % fut_code
return None
if (format == "candle"):
return quotes
else:
dt, op, cl, hi, lo, vol = zip(*quotes)
return zip(dt, cl)
def get_data_yahoo(start_date, end_date, fut_code="INTC", format = "candle"):
try:
quotes = quotes_historical_yahoo(fut_code, start_date, end_date)
except:
print("Unable to get quotes for %s", fut_code)
return []
if quotes == None:
print("Unable to get quotes for %s", fut_code)
return []
if len(quotes)==0:
print("Unable to get quotes for %s", fut_code)
return []
else:
if(quotes[0][0] < float(datetime.datetime.toordinal(start_date)) or \
quotes[len(quotes)-1][0] > float(datetime.datetime.toordinal(end_date))):
print "unnable to get yahoo quotes for ticker %s for required dates" %fut_code
return None
if(format=="candle"):
dt, op, cl, hi, lo, vol = zip(*quotes)
dt2 = []
for d in dt:
dt2.append(datetime.datetime.fromordinal(int(d)))
quotes = zip(dt2, op, cl, hi, lo, vol)
return quotes
else:
dt, op, cl, hi, lo, vol = zip(*quotes)
return zip(dt, cl)
def stock_monthly_returns():
"""create a plot of the monthly returns for a stock
Arguments
=========
None
Prompts the user for a stock ticker
Returns
======
None
Saves plot to 'TICKER_monthly_returns.pdf'
"""
# start your code here
stock = raw_input('Input a stock ticker: ')
now = datetime.datetime.now()
sp = finance.quotes_historical_yahoo(stock, (1900, 1, 1), (now.year, now.month, now.day), asobject=True, adjusted=False)
graphDate = sp.date[30:]
graphPrice = [0] * (len(sp.date) - 30)
for idx, val in enumerate(graphPrice):
graphPrice[idx] = (sp.close[idx + 30] - sp.close[idx]) / sp.close[idx]
plt.plot(graphDate, graphPrice)
plt.xlabel('Dates')
plt.ylabel('Returns')
plt.title('Monthy return for stock ' + stock)
plt.savefig(stock + '_monthly_returns.pdf')
return None
def test(self):
# 2011 to 2012
start = datetime.datetime(2011, 01, 01)
end = datetime.datetime(2012, 01, 01)
symbols = ["AA", "AXP", "BA", "BAC", "CAT"]
quotes = [finance.quotes_historical_yahoo(symbol, start, end, asobject=True)
for symbol in symbols]
close = numpy.array([q.close for q in quotes]).astype(numpy.float)
dates = numpy.array([q.date for q in quotes])
data = {}
for i in xrange(len(symbols)):
data[symbols[i]] = numpy.diff(numpy.log(close[i]))
df = pandas.DataFrame(data, index=dates[0][:-1], columns=symbols)
print df
print df.corr()
df.plot()
legend(symbols)
show()
def get_data(id, start, end):
try:
res = quotes_historical_yahoo(id, start, end)
except urllib2.HTTPError:
return None
else:
return res
def test(self):
# Download AAPL data for 2011 to 2012
start = datetime.datetime(2011, 01, 01)
end = datetime.datetime(2012, 01, 01)
symbol = "AAPL"
quotes = finance.quotes_historical_yahoo(symbol,
start,
end,
asobject=True)
# Create date time index
dt_idx = pandas.DatetimeIndex(quotes.date)
#Create data frame
df = pandas.DataFrame(quotes.close, index=dt_idx, columns=[symbol])
# Resample with monthly frequency
resampled = df.resample('M', how=numpy.mean)
print resampled
# Plot
df.plot()
resampled.plot()
show()
def main():
win = gtk.Window()
win.connect('destroy', gtk.main_quit)
win.set_title('Cursors')
vbox = gtk.VBox()
win.add(vbox)
# Get data from Yahoo Finance
enddate = datetime.date.today()
startdate = enddate + datetime.timedelta(days=-72)
quotes = finance.quotes_historical_yahoo('GOOG', startdate, enddate)
qa = array(quotes)
f = create_figure(quotes)
a = f.gca()
vbox.pack_start(gtk.Label('No Blit'), False, False)
vbox.pack_start(f.canvas)
cursor1 = SnaptoCursor(a, qa[:, 0], qa[:, 2], useblit=False)
f.canvas.mpl_connect('motion_notify_event', cursor1.mouse_move)
f = create_figure(quotes)
a = f.gca()
vbox.pack_start(gtk.Label('Use Blit'), False, False)
vbox.pack_start(f.canvas)
cursor2 = SnaptoCursor(a, qa[:, 0], qa[:, 2], useblit=True)
f.canvas.mpl_connect('motion_notify_event', cursor2.mouse_move)
win.show_all()
gtk.main()
def plot_opening_closing_prices(self):
if len(self.ticker_symbol_input_line.text()) == 0 or len(self.start_date_input_line.text()) == 0 or len(self.end_date_input_line.text()) == 0:
return
start_date = date(*[int(x) for x in self.start_date_input_line.text().split('-')])
end_date = date(*[int(x) for x in self.end_date_input_line.text().split('-')])
quotes = quotes_historical_yahoo(str(self.ticker_symbol_input_line.text()), start_date, end_date)
if len(quotes) == 0:
return
dates, opening_prices, closing_prices = zip(*[[q[0], q[1], q[2]] for q in quotes])
self.axes.cla()
self.axes.grid(b=True, which='both')
self.axes.set_title('Historical Opening/Closing Prices')
self.axes.set_xlabel('Date')
self.axes.set_ylabel('Price')
opening_plot, = self.axes.plot_date(dates, opening_prices, 'b-')
closing_plot, = self.axes.plot_date(dates, closing_prices, 'r-')
self.axes.legend([opening_plot, closing_plot], ['Opening Price', 'Closing Price'], title='Ticker Symbol: ' + str(self.ticker_symbol_input_line.text()).upper(), loc=2)
years = YearLocator()
years_format = DateFormatter('%Y')
months = MonthLocator()
self.axes.xaxis.set_major_locator(years)
self.axes.xaxis.set_major_formatter(years_format)
self.axes.xaxis.set_minor_locator(months)
self.axes.autoscale_view()
self.figure.autofmt_xdate()
self.axes.fmt_xdata = DateFormatter('%Y-%m-%d')
self.axes.fmt_ydata = lambda x: '$%1.2f' % x
self.canvas.draw()
def ret_f(ticker, begdate, enddate):
p = quotes_historical_yahoo(ticker,
begdate,
enddate,
asobject=True,
adjusted=True)
return ((p.open[1:] - p.open[:-1]) / p.open[1:])
def annualBeta():
'''
exercise.
This function was in the handouts and looked very interesting.
So I implemented it to see the inner workings.
Purpose of this function is to calculate beta of a stock.
:return:
'''
def ret_f(ticker, startDate, endDate):
p = finance.quotes_historical_yahoo(ticker,
startDate,
endDate,
asobject=True,
adjusted=True)
return ((p.aclose[1:] - p.aclose[0:-1]) / p.aclose[:-1])
startDate = (1990, 1, 1)
endDate = (2014, 12, 31)
# Pandas Series for Oracle's Data
y0 = pd.Series(ret_f('ORCL', startDate, endDate))
# Pandas Series for S&P500 Data
x0 = pd.Series(ret_f('^GSPC', startDate, endDate))
# Historical Date values of S&P500
dateVal = finance.quotes_historical_yahoo('^GSPC',
startDate,
endDate,
asobject=True,
adjusted=True).date[0:-1]
lag_year = dateVal[0].strftime("%Y")
y1, x1, beta, index0 = [], [], [], []
# Calculate Beta for each year
for i in range(1, len(dateVal)):
year = dateVal[i].strftime("%Y")
if (year == lag_year):
x1.append(x0[i])
y1.append(y0[i])
else:
model = pd.ols(y=pd.Series(y1), x=pd.Series(x1))
print(lag_year, round(model.beta[0], 4))
beta.append(model.beta[0])
index0.append(lag_year)
x1 = []
y1 = []
lag_year = year
# Plot the main graph
plt.plot(beta, c='firebrick', label='ORCL Beta w.r.t S&P500')
plt.hlines(y=1,
xmin=0,
xmax=25,
label='Perfect Correlation',
lw=2,
color='steelblue')
plt.legend()
plt.show()
def vol_annual(ticker):
x = quotes_historical_yahoo(ticker,
begdate,
enddate,
asobject=True,
adjusted=True)
ret = (x.aclose[1:] - x.aclose[:-1]) / x.aclose[:-1]
return (std(ret))
def download_data(symbol, days_delta=60):
finish_date = datetime.today()
start_date = finish_date - timedelta(days=days_delta)
stocks_raw = quotes_historical_yahoo(symbol, start_date, finish_date)
stocks_df = pd.DataFrame(stocks_raw, columns=["n_date", "open", "close",
"high", "low", "volume"])
return stocks_df
def download_data(symbol, days_delta=60):
finish_date = datetime.today()
start_date = finish_date - timedelta(days=days_delta)
stocks_raw = quotes_historical_yahoo(symbol, start_date, finish_date)
stocks_df = pd.DataFrame(stocks_raw, columns=["n_date", "open", "close",
"high", "low", "volume"])
return stocks_df
def download_data(symbol, finish_date, start_date):
stocks_raw = quotes_historical_yahoo(symbol, start_date, finish_date)
stocks_df = pd.DataFrame(
stocks_raw,
columns=["TimeStamp", "Open", "Close", "High", "Low", "Volume"])
stocks_df["TimeStamp"] = stocks_df["TimeStamp"].astype(np.int32)
stocks_df["TimeStamp"] = stocks_df["TimeStamp"].apply(datetime.fromordinal)
return stocks_df
def download_data(symbol, finish_date, start_date):
stocks_raw = quotes_historical_yahoo(symbol, start_date, finish_date)
stocks_df = pd.DataFrame(stocks_raw, columns=["TimeStamp", "Open", "Close",
"High", "Low", "Volume"])
stocks_df["TimeStamp"] = stocks_df["TimeStamp"].astype(np.int32)
stocks_df["TimeStamp"] = stocks_df["TimeStamp"].apply(datetime.fromordinal)
return stocks_df
def get_close(symbol): today = date.today() start = (today.year - 1, today.month, today.day) quotes = quotes_historical_yahoo(symbol, start, today) quotes = numpy.array(quotes) return quotes.T[4]
def getQuotes(symbol, start, end):
quotes = fin.quotes_historical_yahoo(symbol, start, end)
dates, open, close, high, low, volume = zip(*quotes)
data = {"open": open, "close": close, "high": high, "low": low, "volume": volume}
dates = Index([datetime.fromordinal(int(d)) for d in dates])
return DataFrame(data, index=dates)
def ret_annual(ticker):
x = quotes_historical_yahoo(ticker,
begdate,
enddate,
asobject=True,
adjusted=True)
logret = log(x.aclose[1:] / x.aclose[:-1])
return (exp(sum(logret)) - 1)
def get_close(symbol):
today = date.today()
start = (today.year - 1, today.month, today.day)
quotes = quotes_historical_yahoo(symbol, start, today)
quotes = np.array(quotes)
return quotes.T[4]
def getQuotes(symbol, start, end):
'''getQuotes documentation'''
quotes = fin.quotes_historical_yahoo(symbol, start, end)
dates, opn, close, high, low, volume = zip(*quotes)
data = {'open': opn, 'close': close, 'high' : high,
'low' : low, 'volume': volume}
dates = Index([datetime.fromordinal(int(d)) for d in dates])
return DataFrame(data, index=dates)
def ret_annual(ticker,begdate,enddte):
x=quotes_historical_yahoo(ticker,begdate,enddate,asobject=True,adjusted=True)
logret = log(x.aclose[1:]/x.aclose[:-1])
date=[]
d0=x.date
for i in range(0,size(logret)):
date.append(d0[i].strftime("%Y"))
y=pd.DataFrame(logret,date,columns=[ticker])
return exp(y.groupby(y.index).sum())-1
def getQuotes(symbol, start, end):
'''getQuotes documentation'''
quotes = fin.quotes_historical_yahoo(symbol, start, end)
dates, opn, close, high, low, volume = zip(*quotes)
data = {'open': opn, 'close': close, 'high' : high,
'low' : low, 'volume': volume}
dates = Index([datetime.fromordinal(int(d)) for d in dates])
return DataFrame(data, index=dates)
def ret_monthly(ticker):
x = quotes_historical_yahoo(ticker,(begYear,1,1),(endYear,12,31),asobject=True,adjusted=True)
logret=log(x.aclose[1:]/x.aclose[:-1])
date=[]
d0=x.date
for i in range(0,size(logret)):
date.append(''.join([d0[i].strftime("%Y"),d0[i].strftime("%m")]))
y=pd.DataFrame(logret,date,columns=[ticker])
return y.groupby(y.index).sum()
def gpcs_trade(series, trade):
"""Function to plot a candle graph from a given series"""
"""takes as input the security code, default TY"""
from matplotlib.dates import DateFormatter, WeekdayLocator, HourLocator, \
DayLocator, MONDAY
from matplotlib.finance import quotes_historical_yahoo, candlestick,\
plot_day_summary, candlestick2
mondays = WeekdayLocator(MONDAY) # major ticks on the mondays
alldays = DayLocator() # minor ticks on the days
monthFormatter = DateFormatter('%b %d') # Eg, Jan 12
dayFormatter = DateFormatter('%d') # Eg, 12
#quotes contains a list of tuples:
#(date, open, close, high, low, volume)
quotes = series
if len(quotes) == 0:
today = datetime.datetime.now()
date2 = (today.year, today.month, today.day)
date1 = ( today.year -1, today.month, 1)
quotes = quotes_historical_yahoo('fut_code', date1, date2)
if len(quotes) == 0:
raise SystemExit
fig = figure()
fig.subplots_adjust(bottom=0.2)
ax = fig.add_subplot(111)
#ax.xaxis.set_major_locator(mondays)
#ax.xaxis.set_minor_locator(mondays)
#ax.xaxis.set_major_formatter(monthFormatter)
#ax.xaxis.set_minor_formatter(dayFormatter)
#plot_day_summary(ax, quotes, ticksize=3)
dt, o, c, h, l, v = zip(*quotes)
dt2 = []
for d in dt:
dt2.append(datetime.datetime.fromordinal(int(d)))
ser = DataFrame(data = {0:o, 1:c, 2:h, 3:l, 4:v}, index = dt2)
tmdelta = len(ser[trade.trend.a:])
ax.plot([trade.trend.a, max(ser.index)], [trade.trend.c_reg, (tmdelta*trade.trend.m_reg + trade.trend.c_reg)], color='r', linestyle='-', linewidth=2)
ax.plot([trade.trend.a, max(ser.index)], [trade.trend.c_reg+trade.trend.stdev_p_reg, (trade.trend.stdev_p_reg +tmdelta*trade.trend.m_reg + trade.trend.c_reg)], color='g', linestyle='-', linewidth=2)
ax.plot([trade.trend.a, max(ser.index)], [trade.trend.c_reg-trade.trend.stdev_p_reg, (-trade.trend.stdev_p_reg +tmdelta*trade.trend.m_reg + trade.trend.c_reg)], color='g', linestyle='-', linewidth=2)
tmdelta = len(ser[trade.trend.a:trade.trend.e])
ax.plot([trade.trend.a, trade.trend.e], [trade.trend.c_reg, (tmdelta*trade.trend.m_reg + trade.trend.c_reg)], color='b', linestyle='-', linewidth=2)
candlestick(ax, quotes, width=0.6)
#ax.xaxis_date()
ax.autoscale_view()
setp( gca().get_xticklabels(), rotation=45, horizontalalignment='right')
show()
def ret_monthly(ticker):
x = quotes_historical_yahoo(ticker,(begYear,1,1),(endYear,12,31),asobject=True,adjusted=True)
logret=log(x.aclose[1:]/x.aclose[:-1])
date=[]
d0=x.date
for i in range(0,size(logret)):
date.append(''.join([d0[i].strftime("%Y"),d0[i].strftime("%m")]))
y=pd.DataFrame(logret,date,columns=[ticker])
return y.groupby(y.index).sum()
def ret_f(ticker, begdate, enddate):
p = quotes_historical_yahoo(ticker,
begdate,
enddate,
asobject=True,
adjusted=True)
ret = (p.aclose[1:] - p.aclose[:-1]) / p.aclose[1:]
date_ = p.date
return pd.DataFrame(data=ret, index=date_[:-1], columns=['ret'])
def getYahooData(ticker, date1, date2):
data = quotes_historical_yahoo(ticker, date1, date2, asobject=True, adjusted=True)
data.date = [datetime.date.fromordinal(int(dt)) for dt in data.date]
data = zip(data.date, data.open, data.close, data.high, data.low, data.volume)
data = np.array(data, dtype = [('Date', datetime.date),
('Open', float), ('Close', float), ('High', float),
('Low', float), ('Volume', float)])
idx = np.where(data['Volume'] > 0)
data = data[idx]
return data
def GetStockDataWithThreading(symbol, index, d1, d2, quotes, symbols, names, fullSymbols, fullNames, badIndx):
try:
quote = finance.quotes_historical_yahoo(symbol, d1, d2, asobject=True)
#print("Succesfully Loaded %s, %s\n"%(fullSymbols[index], fullNames[index]))
quotes[index] = [quote]
symbols[index] = fullSymbols[index]
names[index] = fullNames[index]
badIndx[index] = -1 #Filter these out before we apply the mask
except:
#print("Failed to Load %s, %s\n"%(fullSymbols[index],fullNames[index]))
badIndx[index] = index
def GetStockDataWithThreading(symbol, index, d1, d2, quotes, symbols, names, fullSymbols, fullNames, badIndx):
try:
quote = finance.quotes_historical_yahoo(symbol, d1, d2, asobject=True)
#print("Succesfully Loaded %s, %s\n"%(fullSymbols[index], fullNames[index]))
quotes[index] = [quote]
symbols[index] = fullSymbols[index]
names[index] = fullNames[index]
badIndx[index] = -1 #Filter these out before we apply the mask
except:
#print("Failed to Load %s, %s\n"%(fullSymbols[index],fullNames[index]))
badIndx[index] = index
def download_history(self, ticker):
date1 = datetime.date(2015,1,1)
date2 = datetime.date.today()
try:
quotes = quotes_historical_yahoo(ticker, date1, date2)
datafile = os.path.join(us_dir, ticker)
output = open(datafile, "wb")
pickle.dump(quotes, output)
output.close()
except Exception, e:
print e
def test(self):
#1. Download price data
# 2011 to 2012
start = datetime.datetime(2011, 01, 01)
end = datetime.datetime(2012, 01, 01)
quotes = finance.quotes_historical_yahoo('AAPL', start, end, asobject=True)
close = numpy.array(quotes.close).astype(numpy.float)
self.assertAlmostEqual(normal_ad(numpy.diff(numpy.log(close)))[0], 0.57, 2)
self.assertAlmostEqual(normal_ad(numpy.diff(numpy.log(close)))[1], 0.13, 2)
def _redraw():
_redraw.f.clf()
quotes = quotes_historical_yahoo( getInputs(), date1, date2)
if len(quotes) == 0:
raise SystemExit
dates = [q[0] for q in quotes]
opens = [q[1] for q in quotes]
fig =Figure(figsize=(5,4), dpi=100)
ax = _redraw.f.add_subplot(111)
ax.plot_date(dates, opens, '-')
_redraw.canvas.show()
_redraw.canvas.get_tk_widget().pack(side=Tk.TOP, fill=Tk.BOTH, expand=1)
def dataAccess(self):
# access data from yahoo
# return: date, open, close, high, low, volume
quotes = quotes_historical_yahoo(self.stockName, self.startDate, self.endDate)
# if error
if len(quotes) == 0:
print self.stockName
raise SystemExit
#quotes = np.array(map(list, quotes))
quotes = np.array(quotes)
return quotes
def ret_annual(ticker, begdate, enddte):
x = quotes_historical_yahoo(ticker,
begdate,
enddate,
asobject=True,
adjusted=True)
logret = log(x.aclose[1:] / x.aclose[:-1])
date = []
d0 = x.date
for i in range(0, size(logret)):
date.append(d0[i].strftime("%Y"))
y = pd.DataFrame(logret, date, columns=[ticker])
return exp(y.groupby(y.index).sum()) - 1
def plot_funds(tickerlist, initial, start, end):
'''Plot a fund by its ticker symbol,
normalized to a given initial value.
'''
numdays = (end - start).days
daysinyear = 365.0
print '%9s %9s %9s %9s' % ('Ticker', 'daily', 'CC', 'abs')
# For testing, use something like
# FUSVX = quotes_historical_yahoo('FUSVX', datetime.datetime(2012, 10, 1),
# datetime.datetime(2013, 4, 1),
# asobject=True)
for i, ticker in enumerate(tickerlist):
# This gives a runtime warning for SCAL, and all the aclose vals
# come out zero. Catching a RuntimeWarning isn't as simple as try;
# http://stackoverflow.com/questions/10519237/python-how-to-avoid-runtimewarning-in-function-definition
# http://stackoverflow.com/questions/9349434/how-do-i-check-for-numeric-overflow-without-getting-a-warning-in-python
fund_data = quotes_historical_yahoo(ticker, start, end, asobject=True)
# Guard against failures of quotes_historical_yahoo;
# without this check you'll see more uncatchable RuntimeWarnings.
if fund_data['aclose'][0] == 0:
print ticker, ": First adjusted close is 0!"
continue
# Calculate effective daily-compounded interest rate
fixed_pct = fund_data['aclose'][-1] / fund_data['aclose'][0] - 1.
Rcc = daysinyear / numdays * \
numpy.log(fund_data['aclose'][-1] / fund_data['aclose'][0])
# Convert CC return to daily-compounded return:
Rdaily = daysinyear * (math.exp(Rcc / daysinyear) - 1.)
# Another attempt to compute the daily rate, but it's wrong.
# Reff = daysinyear * (math.exp(math.log(fund_data['aclose'][-1]
# - fund_data['aclose'][0])
# /numdays) - 1)
print "%9s %9.2f %9.2f %9.2f" % (ticker, Rdaily * 100, Rcc * 100,
fixed_pct * 100)
# Normalize to the initial investment:
fund_data['aclose'] *= initial / fund_data['aclose'][0]
# and plot
ax1.plot_date(x=fund_data['date'],
y=fund_data['aclose'],
fmt=pick_color(i),
label=ticker)
def ret_vol_f(stocks, begtime, endtime):
ret = []
vol = []
for i in stocks:
price = finance.quotes_historical_yahoo(i,
begtime,
endtime,
asobject=True,
adjusted=True)
close = price.aclose
log_ret = np.log(close[1:] / close[:-1])
ret.append(np.exp(log_ret.sum()) - 1)
vol.append(np.std(log_ret))
return (ret, vol)
def get_stock_data(id, startdate, enddate):
import matplotlib.finance as finance
try:
# fh = finance.fetch_historical_yahoo(id, startdate, enddate)
# (date, open, high, low, close, volume, adj_close)
# rows = mlab.csv2rec(fh)
# fh.close()
rows = finance.quotes_historical_yahoo(id, startdate, enddate,
adjusted=True)
# (d, open, close, high, low, volume)
except urllib2.HTTPError as ex:
logger.debug('Cant get data for %s %s' % (id, str(ex)))
return []
return rows
def getquotes(symbol, start, end):
quotes = fin.quotes_historical_yahoo(symbol, start, end)
dates, open, close, high, low, volume = lzip(*quotes)
data = {
'open': open,
'close': close,
'high': high,
'low': low,
'volume': volume
}
dates = pa.Index([dt.datetime.fromordinal(int(d)) for d in dates])
return pa.DataFrame(data, index=dates)
def getquotes(symbol, start, end):
quotes = fin.quotes_historical_yahoo(symbol, start, end)
dates, open, close, high, low, volume = lzip(*quotes)
data = {
'open' : open,
'close' : close,
'high' : high,
'low' : low,
'volume' : volume
}
dates = pa.Index([dt.datetime.fromordinal(int(d)) for d in dates])
return pa.DataFrame(data, index=dates)
def getquotes(symbol, start, end):
# Taken from the no-longer-existent pandas.examples.finance
quotes = fin.quotes_historical_yahoo(symbol, start, end)
dates, open, close, high, low, volume = lzip(*quotes)
data = {
'open' : open,
'close' : close,
'high' : high,
'low' : low,
'volume' : volume
}
dates = pd.Index([dt.datetime.fromordinal(int(d)) for d in dates])
return pd.DataFrame(data, index=dates)
def get_basic_records(tickers, d1, d2, option):
"""
This function is to get daily basic records.
Args:
tickers (list) : a list containing company tickers
d1 (datetime) : start date
d2 (datetime) : end date
option (string) : a string of feature name.
Available: "open","close","volume","return","return rate".
Return:
results (array) : an numpy array containing requested features.
Array with shape m,d.
m: number of instances; d: number of features.
"""
quotes = [
finance.quotes_historical_yahoo(ticker, d1, d2, asobject=True)
for ticker in tickers
]
if option == "open":
results = np.array([q.open for q in quotes]).astype(np.float)
elif option == "close":
results = np.array([q.close for q in quotes]).astype(np.float)
elif option == "volume":
results = np.array([q.volume for q in quotes]).astype(np.float)
elif option == "return":
opens = np.array([q.open for q in quotes]).astype(np.float)
closes = np.array([q.close for q in quotes]).astype(np.float)
results = closes - opens
elif option == "return rate":
opens = np.array([q.open for q in quotes]).astype(np.float)
closes = np.array([q.close for q in quotes]).astype(np.float)
results = (closes - opens) / opens
else:
print "Option Not Found!"
results = None
return results
def getYahooData(ticker, date1, date2):
data = quotes_historical_yahoo(ticker,
date1,
date2,
asobject=True,
adjusted=True)
data.date = [datetime.date.fromordinal(int(dt)) for dt in data.date]
data = zip(data.date, data.open, data.close, data.high, data.low,
data.volume)
data = np.array(data,
dtype=[('Date', datetime.date), ('Open', float),
('Close', float), ('High', float), ('Low', float),
('Volume', float)])
idx = np.where(data['Volume'] > 0)
data = data[idx]
return data
def test(self):
#1. Download price data
# 2011 to 2012
start = datetime.datetime(2011, 01, 01)
end = datetime.datetime(2012, 01, 01)
quotes = finance.quotes_historical_yahoo('AAPL',
start,
end,
asobject=True)
close = numpy.array(quotes.close).astype(numpy.float)
self.assertAlmostEqual(
normal_ad(numpy.diff(numpy.log(close)))[0], 0.57, 2)
self.assertAlmostEqual(
normal_ad(numpy.diff(numpy.log(close)))[1], 0.13, 2)
def get(symbol, daysBack, fileWrite):
if __debug__ and resolution != 1:
print "get_yahoo_hist_data:get - Does not support resolution other then 1"
date1 = date.today() - timedelta(days=daysBack)
# end
date2 = date.today()
quotes = quotes_historical_yahoo(symbol, date1, date2)
if (fileWrite == 1):
f = open(symbol + ".csv", 'w')
for line in quotes:
for val in line:
f.write(str(val))
f.write(',')
f.write('\n')
f.close()
