def driptest(numlist):
'''
input: a list of numbers (nums corrsp to stocks listed in tckrlist)
output: the value of a portfolio containing stocks specified in numlist starting on 9/19/2000 and ending on 7/15/2013
divs reinvested at price on close of pay dates
'''
#TODO add semi-annual contributions, invested evenly between all stocks, every 130 days
cashperstock = 50000/len(numlist) #start with $50,000 dollars divided by number of stocks
holdingslist = []
for i in numlist: #buy initial shares
price = mf.parse_yahoo_historical(mf.fetch_historical_yahoo(tckrlist[i], (2000, 9, 19), (2000, 9, 19), dividends=False), adjusted=False)
iprice = price[0][2]
ishares = round(cashperstock/iprice, 2)
holdingslist.append(ishares)
for i in fulldatelist: #for every day in window
hcount = 0
p = i.split('/')
d = int(p[1])
yahoodate = (int(p[2]), int(p[0]), d) # a yahoo fetch compatible date
hcount = 0
for j in numlist: #look at every stock in the numlist
paycount = 0
icurrprice = 0
d = int(p[1])
yahoodate = (int(p[2]), int(p[0]), d)
for k in paydatemaster[j]: #for each stock, look at payment date master list
k = k.strip()
if k == i: #check if current day is a dividend pay day
paymentmaster[j][paycount] = float(paymentmaster[j][paycount])
divpaymt = round(paymentmaster[j][paycount]*holdingslist[hcount], 2)
try:
currprice = mf.parse_yahoo_historical(mf.fetch_historical_yahoo(tckrlist[j], yahoodate, yahoodate, dividends=False), adjusted=False)
icurrprice = currprice[0][2]
holdingslist[hcount] += round(divpaymt/icurrprice, 3) #reinvest, using yahoo data, tckrlist[j]
except: #sometimes paydates are on the weekend, in which case the next available day's close price is used
while icurrprice == 0:
d+= 1
try:
yahoodate = (int(p[2]), int(p[0]), d)
currprice = mf.parse_yahoo_historical(mf.fetch_historical_yahoo(tckrlist[j], yahoodate, yahoodate, dividends=False), adjusted=False)
icurrprice = currprice[0][2]
holdingslist[hcount] += round(divpaymt/icurrprice, 3)
except:
pass
paycount += 1
hcount += 1
finaldate = (2013, 7, 15)
count = 0
value = 0
for i in numlist:
finalprice = mf.parse_yahoo_historical(mf.fetch_historical_yahoo(tckrlist[i], finaldate, finaldate, dividends=False), adjusted=False)
ifinalprice = finalprice[0][2]
value += round(ifinalprice*holdingslist[count], 2) #calculate final value
count += 1
return value
def getData(self):
self.dataLoaded = 1
fh = finance.fetch_historical_yahoo(self.name, self.startdate, self.enddate)
self.data = mlab.csv2rec(fh); fh.close()
self.data.sort()
def stockpricemasterlist(tckrlist):
stockpricedates = []
stockpricemaster = []
for j in tckrlist:
temporlist = []
temporlist2 = []
price = mf.fetch_historical_yahoo(j, (2000, 9, 19), (2013, 7, 15), dividends=False)
for i in price:
try:
i =i.split(',')
i[0] = i[0].split('-')
if i[0][1][0] == str(0):
m = i[0][1][1]
else:
m = i[0][1]
if i[0][2][0] == str(0):
d = i[0][2][1]
else:
d = i[0][2]
y = i[0][0]
date = str(m)+'/'+str(d)+'/'+str(y)
temporlist.append(date)
temporlist2.append(i[4])
except:
pass
stockpricedates.append(temporlist)
stockpricemaster.append(temporlist2)
return stockpricedates, stockpricemaster
def main():
if len(sys.argv) != 3:
print('Usage {}: <symbol-file> <destination-dir>'.format(sys.argv[0]))
exit(1)
symbols = utils.load_symbol_list(sys.argv[1])
base_dir = sys.argv[2]
for symbol in symbols:
dest_dir = os.path.join(base_dir, symbol + '.csv')
try:
finance.fetch_historical_yahoo(symbol, (2000, 1, 1), (2014, 9, 21),
cachename=dest_dir)
except urllib2.URLError:
print('Download failed for symbol: {}'.format(symbol))
time.sleep(30)
def get_stock_history(self):
"""
Fetches data using matplotlib's yahoo API (undocumented).
A call to fetch_historical_yahoo returns a CSV file containing tuples:
[(date, open, close, high, low, volume),...]
Parameters
----------
None
Returns
-------
dates: array of historical dates
prices: array of associated prices on those dates
"""
stock_history = finance.fetch_historical_yahoo(self.symbol, self.start, self.end)
r = mlab.csv2rec(stock_history)
r.sort()
dates = r.date
prices = r.adj_close
# convert to epoch time for highcharts
dates = [(int(time.mktime(time.strptime(date.strftime("%Y-%m-%d"), "%Y-%m-%d"))) - time.timezone)*1000 for date in dates]
return dates, prices
def ticker_data(ticker):
print ticker
startdate = datetime.date(2012, 10, 28)
today = enddate = datetime.date.today()
pricesd = np.zeros(1000)
datesd = np.zeros(1000)
volumed = np.zeros(1000)
try:
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
r = mlab.csv2rec(fh)
fh.close()
r.sort()
prices = r.adj_close
dates = r.date
volume = r.volume
except:
prices = pricesd
dates = datesd
volume = volumed
print "Unexpected error:"
# raise
return prices, dates, np.mean(volume), volume
def plotTicker(ticker, startdate, enddate, fillcolor):
"""
matplotlib.finance has fetch_historical_yahoo() which fetches
stock price data the url where it gets the data from is
http://ichart.yahoo.com/table.csv stores in a numpy record
array with fields:
date, open, high, low, close, volume, adj_close
"""
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
r = mlab.csv2rec(fh)
fh.close()
r.sort()
### plot the relative strength indicator
prices = r.adj_close
### plot the price and volume data
ax.plot(r.date, prices, color=fillcolor, lw=2, label=ticker)
ax.legend(loc='top right', shadow=True, fancybox=True)
# set the labels rotation and alignment
for label in ax.get_xticklabels():
# To display date label slanting at 30 degrees
label.set_rotation(30)
label.set_horizontalalignment('right')
ax.fmt_xdata = mdates.DateFormatter('%Y-%m-%d')
def get_ticker_data_from_web_stend(ticker, startdate, enddate): """ return a numpy record array with fields: date, open, high, low, close, volume, adj_close) """ fh = finance.fetch_historical_yahoo(ticker, startdate, enddate) r = mlab.csv2rec(fh); fh.close() r.sort() return r
def get_ticker_data_from_web(ticker): """ return a numpy record array with fields: date, open, high, low, close, volume, adj_close) """ startdate = datetime.date(1990,1,1) enddate = datetime.date.today() fh = finance.fetch_historical_yahoo(ticker, startdate, enddate) r = mlab.csv2rec(fh); fh.close() r.sort() return r
def download_ticker_data(ticker):
fullpath = data_folder + '/' + ticker
today = enddate = datetime.date.today() + datetime.timedelta(days=1)
startdate = enddate - datetime.timedelta(days=180)
try:
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
shutil.copy2(fh.name, fullpath)
fh.close()
return True, None
except Exception, e:
return False,str(e)
def main(stock='aapl',
start_date=None,
end_date=None,
training=None,
time_series=None,
animate=None,
**kwargs):
training = training or 20
end_date = end_date or datetime.today()
start_date = start_date or end_date - timedelta(days=int(
(training > 1 and training) or 30))
stock_data = mlab.csv2rec(
finance.fetch_historical_yahoo(stock, start_date, end_date))
stock_prices = tuple(reversed(stock_data.adj_close))
dates = tuple(reversed(stock_data.date))
training_set = stock_prices[:int(training > 1 and training or training *
len(stock_data.adj_close))]
animate = (animate in {'foreground', 'background'} and get_animated_training(dates, animate == 'background')) \
or train
def _time_series(window_size):
neural_network = train_as_time_series(training_set, window_size,
animate, **kwargs)
network_samples = sliding_window(stock_prices, window_size)
predicted_prices = list(network_samples[0][0])
predicted_prices.extend(
chain.from_iterable(
neural_network.feed(inputs) for inputs, _ in network_samples))
plot(stock_prices,
predicted_prices,
dates[len(training_set) - 1],
x_axis=dates,
title='Trained as Time Series',
errors=neural_network.errors)
def interpolation():
neural_network = train_as_function_interpolation(
training_set, animate, **kwargs)
predicted_prices = list(
chain.from_iterable(
imap(neural_network.feed, xrange(len(stock_prices)))))
plot(stock_prices,
predicted_prices,
dates[len(training_set) - 1],
x_axis=dates,
title='Trained as Function Interpolation',
errors=neural_network.errors)
if time_series:
_time_series(time_series)
else:
interpolation()
def get_quote_daily_matplotlib(ticker):
startdate = datetime.date(2006, 1, 1)
today = enddate = datetime.date.today()
#ticker = 'SPY'
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close
r = mlab.csv2rec(fh)
fh.close()
r.sort()
return r
def get_history_data(self, ticker, start, end):
try:
fh = finance.fetch_historical_yahoo(ticker, start, end)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
raw = mlab.csv2rec(fh)
fh.close()
raw.sort()
# get today data
if end == datetime.date.today():
raw = self.get_realtime_data(ticker, raw)
except:
return 0
return raw
def main(
stock='aapl',
start_date=None,
end_date=None,
training=None,
time_series=None,
animate=None,
**kwargs
):
training = training or 20
end_date = end_date or datetime.today()
start_date = start_date or end_date - timedelta(days=int((training > 1 and training) or 30))
stock_data = mlab.csv2rec(finance.fetch_historical_yahoo(stock, start_date, end_date))
stock_prices = tuple(reversed(stock_data.adj_close))
dates = tuple(reversed(stock_data.date))
training_set = stock_prices[:int(training > 1 and training or training * len(stock_data.adj_close))]
animate = (animate in {'foreground', 'background'} and get_animated_training(dates, animate == 'background')) \
or train
def _time_series(window_size):
neural_network = train_as_time_series(training_set, window_size, animate, **kwargs)
network_samples = sliding_window(stock_prices, window_size)
predicted_prices = list(network_samples[0][0])
predicted_prices.extend(chain.from_iterable(neural_network.feed(inputs) for inputs, _ in network_samples))
plot(
stock_prices,
predicted_prices,
dates[len(training_set) - 1],
x_axis=dates,
title='Trained as Time Series',
errors=neural_network.errors
)
def interpolation():
neural_network = train_as_function_interpolation(training_set, animate, **kwargs)
predicted_prices = list(chain.from_iterable(imap(neural_network.feed, xrange(len(stock_prices)))))
plot(
stock_prices,
predicted_prices,
dates[len(training_set) - 1],
x_axis=dates,
title='Trained as Function Interpolation',
errors=neural_network.errors
)
if time_series:
_time_series(time_series)
else:
interpolation()
def get_quote_daily_matplotlib(ticker):
startdate = datetime.date(2006, 1, 1)
today = enddate = datetime.date.today()
#ticker = 'SPY'
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close
r = mlab.csv2rec(fh)
fh.close()
r.sort()
return r
def get_stock(ticker, startdate, enddate):
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields: (date, open, high, low, close, volume, adj_close)
r = mlab.csv2rec(fh)
fh.close()
r.sort()
print 'the length of data:', len(r.close)
get_stock_data = []
for i in xrange(0, len(r.close) - 1):
if (r.volume[i] != 0):
get_stock_data.append(r.close[i].tolist())
print 'after removing the datas with zero volume, the length of data:', len(
get_stock_data)
return get_stock_data
def mr_stock_price(ticker):
now = datetime.datetime.now()
earlier = now - datetime.timedelta(days = 4)
price = mf.fetch_historical_yahoo(ticker, (earlier.year, earlier.month, earlier.day), (now.year, now.month, now.day), dividends=False)
for r in price:
r = r.split(',')
try:
float(r[-1])
mr_price= float(r[-1].strip())
break
# shareprices.append(float(r[-1].strip()))
except:
continue
return mr_price
def get_data_from_yahoo_api(ticker,
startdate=datetime.date(1900, 1, 1),
enddate=datetime.date.today()):
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
r = mlab.csv2rec(fh)
fh.close()
df = pd.DataFrame(data=r,
columns=[
'date', 'open', 'high', 'low', 'close', 'volume',
'adj_close'
]).sort('date')
df['volume'] = df['volume'].astype(float)
del df['adj_close']
print 'Available data: Ticker({ticker}) from {first_day} to {last_day}'.format(
ticker=ticker, first_day=firstday(df), last_day=lastday(df))
return df, r
def get_benchmark(tick,y1,m1,d1,y2,m2,d2):
startdate = datetime.date(y1, m1, d1)
enddate = datetime.date(y2, m2, d2)
ticker= tick
benchmark_df= read_csv(finance.fetch_historical_yahoo(ticker, startdate, enddate),index_col='Date')
benchmark_Index=benchmark_df['Close']
benchmark_Index=benchmark_Index.to_frame()
benchmark_Index.columns=['values']
benchmark_Index=benchmark_Index.reset_index()
benchmark_Index["New Date"]=benchmark_Index["Date"].map(lambda x: datetime.datetime.strptime(x, '%Y-%m-%d').strftime('%d/%m/%y'))
benchmark_Index["Date"]=benchmark_Index["New Date"].map(lambda x: datetime.datetime.strptime(x, '%d/%m/%y'))
benchmark_Index=benchmark_Index.iloc[::-1]
benchmark_Index=benchmark_Index.drop(["New Date"],1)
benchmark_Index=benchmark_Index.set_index(["Date"])
benchmark_Index=benchmark_Index.divide(benchmark_Index.ix[0])
return benchmark_Index
def recuperarDados(ticker, startdate=None, enddate=None):
if startdate is None and enddate is None:
records = np.load(dadosPathMask % (ticker) + ".npy")
else:
if startdate is None:
startdate = datetime.date(2007, 1, 1)
if enddate is None:
enddate = datetime.date.today()
with finance.fetch_historical_yahoo(ticker, startdate, enddate) as fh:
records = mlab.csv2rec(fh)
records.sort()
np.save(dadosPathMask % (ticker), records)
return records
def plotSingleTickerWithVolume(ticker, startdate, enddate):
global ax
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields:
# date, open, high, low, close, volume, adj_close
r = mlab.csv2rec(fh)
fh.close()
r.sort()
plt.rc('axes', grid=True)
plt.rc('grid', color='0.78', linestyle='-', linewidth=0.5)
axt = ax.twinx()
prices = r.adj_close
fcolor = 'darkgoldenrod'
ax.plot(r.date, prices, color=r'#1066ee', lw=2, label=ticker)
ax.fill_between(r.date, prices, 0, prices, facecolor='#BBD7E5')
ax.set_ylim(0.5 * prices.max())
ax.legend(loc='upper right', shadow=True, fancybox=True)
volume = (r.close * r.volume) / 1e6 # dollar volume in millions
vmax = volume.max()
axt.fill_between(r.date,
volume,
0,
label='Volume',
facecolor=fcolor,
edgecolor=fcolor)
axt.set_ylim(0, 5 * vmax)
axt.set_yticks([])
for axis in ax, axt:
for label in axis.get_xticklabels():
label.set_rotation(30)
label.set_horizontalalignment('right')
axis.fmt_xdata = mdates.DateFormatter('%Y-%m-%d')
def _fetch_yahoo_data(self,startdate,enddate,dividends):
ticker=self.full_ticker
try:
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate,None,dividends)
# From CSV to REACARRAY
r = mlab.csv2rec(fh); fh.close()
# Order by Desc
r.sort()
except:
print "Error: %s,%s,%s" % (sys.exc_info()[0],sys.exc_info()[1],sys.exc_info()[2])
print "Error loading yahoo data for %s %s" % (self,str(startdate))
return None
return r
def hist_data_collection():
conn = MySQLdb.connect(host = "127.0.0.1", user = "******", passwd = "sshravan91", db = "test1")
c = conn.cursor(MySQLdb.cursors.DictCursor)
c.execute("SELECT DISTINCT(Symbol) AS SYMBOL FROM HISTORY")
symbol_data = c.fetchall()
for var2 in xrange(c.rowcount):
tempvar = symbol_data[var2]['SYMBOL']
print tempvar
symbolslist.append(tempvar.lower())
c.close()
del c
conn.close()
today = enddate = date.today()
startdate = today - timedelta(1)
conn = MySQLdb.connect(host = "127.0.0.1", user = "******", passwd = "sshravan91", db = "test1")
for j in xrange(len(symbolslist)):
ticker = str(symbolslist[j])
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
r = mlab.csv2rec(fh); fh.close()
r.sort()
#print r
query = "INSERT INTO HIST_STOCK (_DATE, NAME, OPEN, HIGH, LOW, CLOSE, VOLUME, ADJ_CLOSE) VALUES (%s, %s, %s, %s, %s, %s, %s, %s)"
x = conn.cursor()
x.execute(query, (str(r.date[0]), ticker, str(r.open[0]), str(r.high[0]), str(r.low[0]), str(r.close[0]), str(r.volume[0]), str(r.adj_close[0])))
conn.commit()
row = x.fetchall()
x.close()
del x
conn.close()
def _fetch_yahoo_data(self, startdate, enddate, dividends):
ticker = self.full_ticker
try:
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate,
None, dividends)
# From CSV to REACARRAY
r = mlab.csv2rec(fh)
fh.close()
# Order by Desc
r.sort()
except:
print "Error: %s,%s,%s" % (sys.exc_info()[0], sys.exc_info()[1],
sys.exc_info()[2])
print "Error loading yahoo data for %s %s" % (self, str(startdate))
return None
return r
def update_ticker_prices():
for ticker, in db.session.query(Securities.ticker).all():
data = fetch_historical_yahoo(ticker, datetime.now() - timedelta(days=7), datetime.now())
reader = csv.DictReader(data)
for row in reader:
new_record = SecurityPrices()
for key in row:
row[key.lower().replace('adj close', 'adjusted_close')] = row.pop(key)
for column in inspect(SecurityPrices).attrs:
if column.key == 'id':
continue
elif column.key == 'ticker':
setattr(new_record, column.key, ticker)
else:
setattr(new_record, column.key, row[column.key])
try:
db.session.add(new_record)
db.session.commit()
except IntegrityError:
db.session.rollback()
def fetchStockData(cls, beg, end, ffile, yahoo=True, ticker="AAPL"):
"""Depending on the boolean parameter yahoo, it will fetch the stock data from yahoo finance,
or from the file, given that the file contains date columns and price columns where ticker name is the
header for prices for that security."""
if yahoo is True:
p = fetch_historical_yahoo(ticker, beg, end)
result = parse_yahoo_historical_ochl(p, False, True)
return result
else:
result = os.path.exists(ffile)
if result is False:
raise FileNotFoundError("Error: {} file was not found.".format(ffile))
f = pd.read_csv(ffile)
max = len(f.columns)
for i in range(1, max):
cur_name = f.columns.values[i]
if cur_name == ticker:
break
prices = f.values[:, i] # f.values and f.iloc have actual data starting from 0 index. First is row.
max_rows = len(f.values[:, 0])
"""date, year, month, day, d, open, close, high, low, volume, adjusted_close"""
results = []
for j in range(0, max_rows):
dt = datetime.date(*[int(val) for val in f.values[j, 0].split('-')])
results.append((dt, 0, 0, 0,
0, 0, float(prices[j]), 0, 0, 0, float(prices[j])))
my_type = np.dtype(
[(str('date'), object),
(str('year'), np.int16),
(str('month'), np.int8),
(str('day'), np.int8),
(str('d'), np.float),
(str('open'), np.float),
(str('close'), np.float),
(str('high'), np.float),
(str('low'), np.float),
(str('volume'), np.float),
(str('aclose'), np.float)])
d = np.array(results, dtype=my_type)
return d.view(np.recarray)
return result
def get_benchmark(tick, y1, m1, d1, y2, m2, d2):
startdate = datetime.date(y1, m1, d1)
enddate = datetime.date(y2, m2, d2)
ticker = tick
benchmark_df = read_csv(finance.fetch_historical_yahoo(
ticker, startdate, enddate),
index_col='Date')
benchmark_Index = benchmark_df['Close']
benchmark_Index = benchmark_Index.to_frame()
benchmark_Index.columns = ['values']
benchmark_Index = benchmark_Index.reset_index()
benchmark_Index["New Date"] = benchmark_Index["Date"].map(
lambda x: datetime.datetime.strptime(x, '%Y-%m-%d').strftime('%d/%m/%y'
))
benchmark_Index["Date"] = benchmark_Index["New Date"].map(
lambda x: datetime.datetime.strptime(x, '%d/%m/%y'))
benchmark_Index = benchmark_Index.iloc[::-1]
benchmark_Index = benchmark_Index.drop(["New Date"], 1)
benchmark_Index = benchmark_Index.set_index(["Date"])
benchmark_Index = benchmark_Index.divide(benchmark_Index.ix[0])
return benchmark_Index
def div(stock_symbol):
today = date.today()
start = (today.year - year_to_cal, today.month, today.day)
a = fetch_historical_yahoo(stock_symbol, start, today, cachename=None,dividends=True)
dd = pd.DataFrame(list(a))
re1='.*?' # Non-greedy match on filler
re2='([+-]?\\d*\\.\\d+)(?![-+0-9\\.])' # Float 1
rg = re.compile(re1+re2,re.IGNORECASE|re.DOTALL)
sum = 0
#print dd[0][2]
for i in xrange(dd.shape[0]):
m = rg.search(dd[0][i])
if m:
if m.group(1) == 'None':
pass
else:
sum += float(m.group(1))
#print "("+float1+")"+"\n"
return sum/year_to_cal
def download_ticker_US(ticker, sd=startdate, ed=enddate, market=''):
fh = finance.fetch_historical_yahoo(ticker, sd, ed)
# archive to disk
# append to the existing files without the header
# otherwise create it with the header
f = 'data/' + market + '/' + ticker + '.txt'
if not os.path.exists(f):
fhWrite = open(f, 'w')
header = fh.readline()
fhWrite.write(header)
else:
fhWrite = open(f, 'a')
# get the content, ignore the header
fh.readline()
r = fh.read()
if r:
# sort the records based on the dates
r = '\r\n'.join(sorted(r.split()))
fhWrite.write(r)
# fhWrite.write('\r\n')
fhWrite.close()
def download_ticker(ticker, sd=startdate, ed=enddate):
"""Download stocks open/close/high/close/volume from ASX and push to the central csv"""
fh = finance.fetch_historical_yahoo(ticker, sd, ed)
# archive to disk
# append to the existing files without the header
# otherwise create it with the header
f = 'data/' + ticker + '.txt'
if not os.path.exists(f):
fhWrite = open(f, 'w')
header = fh.readline()
fhWrite.write(header)
else:
fhWrite = open(f, 'a')
# get the content, ignore the header
fh.readline()
r = fh.read()
r = '\r\n'.join(sorted(r.split()))
fhWrite.write(r)
fhWrite.write('\r\n')
fhWrite.close()
def update_ticker_prices():
for ticker, in db.session.query(Securities.ticker).all():
start_date = datetime.now() - timedelta(days=7)
end_date = datetime.now()
data = fetch_historical_yahoo(ticker, start_date, end_date)
reader = csv.DictReader(data)
for row in reader:
new_record = SecurityPrices()
for key in list(row.keys()):
key_name = key.lower().replace('adj close', 'adjusted_close')
row[key_name] = row.pop(key)
for column in inspect(SecurityPrices).attrs:
if column.key == 'id':
continue
elif column.key == 'ticker':
setattr(new_record, column.key, ticker)
else:
setattr(new_record, column.key, row[column.key])
try:
db.session.add(new_record)
db.session.commit()
except IntegrityError:
db.session.rollback()
def hist_data_collection(ticker_up):
ticker=ticker_up.lower()
today = enddate = date.today()
startdate = datetime.date(2000,1,1)
conn = MySQLdb.connect(host = "127.0.0.1", user = "******", passwd = "sshravan91", db = "test1")
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
r = mlab.csv2rec(fh); fh.close()
r.sort()
for j in xrange(len(r)):
query = "INSERT INTO HIST_STOCK (_DATE, NAME, OPEN, HIGH, LOW, CLOSE, VOLUME, ADJ_CLOSE) VALUES (%s, %s, %s, %s, %s, %s, %s, %s)"
x = conn.cursor()
x.execute(query, (str(r.date[j]), ticker.upper(), str(r.open[j]), str(r.high[j]), str(r.low[j]), str(r.close[j]), str(r.volume[j]), str(r.adj_close[j])))
conn.commit()
row = x.fetchall()
x.close()
del x
conn.close()
def getDataFromYahoo(self, symbol, startDate):
hist = fi.fetch_historical_yahoo(symbol,
startDate,
datetime.today())
newEntries = [] # new container
for i in hist: # split each line
newEntries.append(i[:-1].replace("-","/").split(','))
try:
col = newEntries.pop(0)
for i in newEntries: # convert i[0] in datetime
i[0] = datetime.strptime(i[0], '%Y/%m/%d')
data = pd.DataFrame(newEntries, columns = col)
except ValueError as e:
logging.error('error in data set')
return data
def ticker_data(ticker):
print ticker
startdate = datetime.date(2012,10,28)
today = enddate = datetime.date.today()
pricesd = np.zeros(1000)
datesd = np.zeros(1000)
volumed = np.zeros(1000)
try:
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
r = mlab.csv2rec(fh); fh.close()
r.sort()
prices = r.adj_close
dates = r.date
volume = r.volume
except:
prices = pricesd
dates = datesd
volume = volumed
print "Unexpected error:"
# raise
return prices, dates, np.mean(volume), volume
def weekendDiff():
'''
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 see weekend effect on the prices.
:return:
'''
tickerName = 'CSCO'
begdate = datetime.date(2014, 1, 1)
enddate = datetime.date.today()
price = finance.fetch_historical_yahoo(tickerName, begdate, enddate)
r = mlab.csv2rec(price)
price.close()
r.sort()
r = r[-30:] # get the last 30 days
fig, ax = plt.subplots()
ax.plot(r.date, r.adj_close, 'o-', color='steelblue')
ax.set_title('Normal Representation:' + tickerName +
' Plot with Weekend gaps')
fig.autofmt_xdate()
N = len(r)
ind = np.arange(N) # the evenly spaced plot indices
def formatDate(x, pos=None):
thisind = np.clip(int(x + 0.5), 0, N - 1)
return r.date[thisind].strftime('%Y-%m-%d')
fig, ax = plt.subplots()
ax.plot(ind, r.adj_close, 'd-', color='lightsalmon', lw=2)
ax.set_title('New Representation:' + tickerName +
' Evenlyspaced out points')
ax.xaxis.set_major_formatter(ticker.FuncFormatter(formatDate))
fig.autofmt_xdate()
plt.show()
import matplotlib.finance as finance
import matplotlib.dates as mdates
import matplotlib.ticker as mticker
import matplotlib.mlab as mlab
import matplotlib.pyplot as plt
import matplotlib.font_manager as font_manager
stockArray = [[datetime.date(2006,1,1), datetime.date.today(), 'IBM'],[datetime.date(2006,1,1), datetime.date.today(), 'SPY']]
startdate = datetime.date(2006,1,1)
today = enddate = datetime.date.today()
ticker = 'IBM'
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
r = mlab.csv2rec(fh); fh.close()
r.sort()
print r
fh2 = finance.fetch_historical_yahoo('AAPL', startdate, enddate)
r2 = mlab.csv2rec(fh2); fh2.close()
r2.sort()
def moving_average(x, n, type='simple'):
"""
compute an n period moving average.
type is 'simple' | 'exponential'
def FinancialCharts():
import datetime
import numpy as np
import matplotlib.colors as colors
import matplotlib.finance as finance
import matplotlib.dates as mdates
import matplotlib.ticker as mticker
import matplotlib.mlab as mlab
import matplotlib.pyplot as plt
import matplotlib.font_manager as font_manager
startdate = datetime.date(2006,1,1)
today = enddate = datetime.date.today()
ticker = 'SPY'
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
r = mlab.csv2rec(fh); fh.close()
r.sort()
def moving_average(x, n, type='simple'):
"""
compute an n period moving average.
type is 'simple' | 'exponential'
"""
x = np.asarray(x)
if type=='simple':
weights = np.ones(n)
else:
weights = np.exp(np.linspace(-1., 0., n))
weights /= weights.sum()
a = np.convolve(x, weights, mode='full')[:len(x)]
a[:n] = a[n]
return a
def relative_strength(prices, n=14):
"""
compute the n period relative strength indicator
http://stockcharts.com/school/doku.php?id=chart_school:glossary_r#relativestrengthindex
http://www.investopedia.com/terms/r/rsi.asp
"""
deltas = np.diff(prices)
seed = deltas[:n+1]
up = seed[seed>=0].sum()/n
down = -seed[seed<0].sum()/n
rs = up/down
rsi = np.zeros_like(prices)
rsi[:n] = 100. - 100./(1.+rs)
for i in range(n, len(prices)):
delta = deltas[i-1] # cause the diff is 1 shorter
if delta>0:
upval = delta
downval = 0.
else:
upval = 0.
downval = -delta
up = (up*(n-1) + upval)/n
down = (down*(n-1) + downval)/n
rs = up/down
rsi[i] = 100. - 100./(1.+rs)
return rsi
def moving_average_convergence(x, nslow=26, nfast=12):
"""
compute the MACD (Moving Average Convergence/Divergence) using a fast and slow exponential moving avg'
return value is emaslow, emafast, macd which are len(x) arrays
"""
emaslow = moving_average(x, nslow, type='exponential')
emafast = moving_average(x, nfast, type='exponential')
return emaslow, emafast, emafast - emaslow
plt.rc('axes', grid=True)
plt.rc('grid', color='0.75', linestyle='-', linewidth=0.5)
textsize = 9
left, width = 0.1, 0.8
rect1 = [left, 0.7, width, 0.2]
rect2 = [left, 0.3, width, 0.4]
rect3 = [left, 0.1, width, 0.2]
fig = plt.figure(facecolor='white')
axescolor = '#f6f6f6' # the axes background color
ax1 = fig.add_axes(rect1, axisbg=axescolor) #left, bottom, width, height
ax2 = fig.add_axes(rect2, axisbg=axescolor, sharex=ax1)
ax2t = ax2.twinx()
ax3 = fig.add_axes(rect3, axisbg=axescolor, sharex=ax1)
### plot the relative strength indicator
prices = r.adj_close
rsi = relative_strength(prices)
fillcolor = 'darkgoldenrod'
ax1.plot(r.date, rsi, color=fillcolor)
ax1.axhline(70, color=fillcolor)
ax1.axhline(30, color=fillcolor)
ax1.fill_between(r.date, rsi, 70, where=(rsi>=70), facecolor=fillcolor, edgecolor=fillcolor)
ax1.fill_between(r.date, rsi, 30, where=(rsi<=30), facecolor=fillcolor, edgecolor=fillcolor)
ax1.text(0.6, 0.9, '>70 = overbought', va='top', transform=ax1.transAxes, fontsize=textsize)
ax1.text(0.6, 0.1, '<30 = oversold', transform=ax1.transAxes, fontsize=textsize)
ax1.set_ylim(0, 100)
ax1.set_yticks([30,70])
ax1.text(0.025, 0.95, 'RSI (14)', va='top', transform=ax1.transAxes, fontsize=textsize)
ax1.set_title('%s daily'%ticker)
### plot the price and volume data
dx = r.adj_close - r.close
low = r.low + dx
high = r.high + dx
deltas = np.zeros_like(prices)
deltas[1:] = np.diff(prices)
up = deltas>0
ax2.vlines(r.date[up], low[up], high[up], color='black', label='_nolegend_')
ax2.vlines(r.date[~up], low[~up], high[~up], color='black', label='_nolegend_')
ma20 = moving_average(prices, 20, type='simple')
ma200 = moving_average(prices, 200, type='simple')
linema20, = ax2.plot(r.date, ma20, color='blue', lw=2, label='MA (20)')
linema200, = ax2.plot(r.date, ma200, color='red', lw=2, label='MA (200)')
last = r[-1]
s = '%s O:%1.2f H:%1.2f L:%1.2f C:%1.2f, V:%1.1fM Chg:%+1.2f' % (
today.strftime('%d-%b-%Y'),
last.open, last.high,
last.low, last.close,
last.volume*1e-6,
last.close-last.open )
t4 = ax2.text(0.3, 0.9, s, transform=ax2.transAxes, fontsize=textsize)
props = font_manager.FontProperties(size=10)
leg = ax2.legend(loc='center left', shadow=True, fancybox=True, prop=props)
leg.get_frame().set_alpha(0.5)
volume = (r.close*r.volume)/1e6 # dollar volume in millions
vmax = volume.max()
poly = ax2t.fill_between(r.date, volume, 0, label='Volume', facecolor=fillcolor, edgecolor=fillcolor)
ax2t.set_ylim(0, 5*vmax)
ax2t.set_yticks([])
### compute the MACD indicator
fillcolor = 'darkslategrey'
nslow = 26
nfast = 12
nema = 9
emaslow, emafast, macd = moving_average_convergence(prices, nslow=nslow, nfast=nfast)
ema9 = moving_average(macd, nema, type='exponential')
ax3.plot(r.date, macd, color='black', lw=2)
ax3.plot(r.date, ema9, color='blue', lw=1)
ax3.fill_between(r.date, macd-ema9, 0, alpha=0.5, facecolor=fillcolor, edgecolor=fillcolor)
ax3.text(0.025, 0.95, 'MACD (%d, %d, %d)'%(nfast, nslow, nema), va='top',
transform=ax3.transAxes, fontsize=textsize)
#ax3.set_yticks([])
# turn off upper axis tick labels, rotate the lower ones, etc
for ax in ax1, ax2, ax2t, ax3:
if ax!=ax3:
for label in ax.get_xticklabels():
label.set_visible(False)
else:
for label in ax.get_xticklabels():
label.set_rotation(30)
label.set_horizontalalignment('right')
ax.fmt_xdata = mdates.DateFormatter('%Y-%m-%d')
class MyLocator(mticker.MaxNLocator):
def __init__(self, *args, **kwargs):
mticker.MaxNLocator.__init__(self, *args, **kwargs)
def __call__(self, *args, **kwargs):
return mticker.MaxNLocator.__call__(self, *args, **kwargs)
# at most 5 ticks, pruning the upper and lower so they don't overlap
# with other ticks
#ax2.yaxis.set_major_locator(mticker.MaxNLocator(5, prune='both'))
#ax3.yaxis.set_major_locator(mticker.MaxNLocator(5, prune='both'))
ax2.yaxis.set_major_locator(MyLocator(5, prune='both'))
ax3.yaxis.set_major_locator(MyLocator(5, prune='both'))
plt.show()
""" Name : 4375OS_07_15_Yahoo_price.py Book : Python for Finance Publisher: Packt Publishing Ltd. Author : Yuxing Yan Date : 12/26/2013 email : [email protected] [email protected] """ import datetime import matplotlib.finance as finance import matplotlib.mlab as mlab ticker = 'IBM' begdate = datetime.date(2013,1,1) enddate = datetime.date.today() price = finance.fetch_historical_yahoo(ticker, begdate, enddate) r = mlab.csv2rec(price); price.close() r.sort()
def gen_data_vector(ticker, threeavg, divmonths):
try:
if os.path.isdir('/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker):# if it's already there, skip it
return None
os.mkdir('/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker)
fredobjs = joblib.load('/home/ubuntu/dgrpred/dump/fred_obj_temp_dump')
divmonth = divmonths[ticker]
print '*********************'
print ticker, divmonth
if divmonth < 10:
divmonth = '0'+str(divmonth)
else:
divmonth = str(divmonth)
oldcsvs = os.listdir('/home/ubuntu/dgrpred/old_csv/')
olddata = {}
for i in oldcsvs:
# print i
olddata[i.split('.')[0]] = readcsv(i, False)
url = 'http://financials.morningstar.com/ajax/exportKR2CSV.html?&callback=?&t='+ticker.upper()+'®ion=usa&culture=en-US&cur=USD&order=asc'
opener = urllib2.build_opener()
f = opener.open(url)
data = f.read()
with open('/home/ubuntu/dgrpred/new_csv/'+ticker.replace('/', '').upper()+'.csv', 'wb') as code:
code.write(data)
content = readcsv('/home/ubuntu/dgrpred/new_csv/'+ticker.upper()+'.csv', True)
##################fill in downloaded data with old data if new data is missing
for i in content:
for j in content[i]:
if content[i][j] == '' or content[i][j] == '--':
try:
content[i][j] = olddata[ticker.upper()][i][j]
except:
pass
# for i in olddata[ticker.upper()]:
# print i, olddata[ticker.upper()][i]
# print
# exit()
years = []
fye = []
for i in content['Profitability']:
years.append(int(i.split('-')[0]))
fye.append(int(i.split('-')[1]))
years.sort()
fye = list(set(fye))[0]
if fye < 10:
fye = '0'+str(fye)
else:
fye = str(fye)
count = 0
content_cleaned = copy.deepcopy(content)
for measure in content:
# print measure
for year in content[measure]:
if content[measure][year] == '':
del content_cleaned[measure]
break
else:
try:
content[measure][year] = float(content[measure][year])
except:
del content_cleaned[measure]
break
print '---'
# for measure in content_cleaned:
# print measure
# for year in content_cleaned[measure]:
# print content_cleaned[measure][year]
content = content_cleaned
# exit()
content['shareprices'] = {}
count = 0
for x in range(int(years[0]), int(years[-1])+1):
dd = 8
while calendar.weekday(x, 8, dd) >= 5:
dd +=1
price = mf.fetch_historical_yahoo(ticker, (x, 8, dd), (x, 8, dd), dividends=False)
for r in price:
r = r.split(',')
try:
float(r[-1])
content['shareprices'][str(years[count])+'-'+str(fye)] = float(r[-1].strip())
# shareprices.append(float(r[-1].strip()))
except:
continue
count += 1
content['divyoy'] = {}
divs = []
for i in years:
divs.append(content['Dividends USD'][str(i)+'-'+str(fye)])
divdelta= calc_delta(divs)
count = 1
for i in divdelta:
content['divyoy'][str(years[count])+'-'+str(fye)] = i
count += 1
for i in content:
for j in content[i]:
if content[i][j] == '':
print i, j
cogs = [] #
cogs_prior = []
count = 1
for i in years[1:]:
print i
eps_prior = float(content['Earnings Per Share USD'][str(years[count-1])+'-'+fye])
# print content['rev-Year over Year'][str(years[count-1])+'-'+fye]
rev_prior = float(content['rev-Year over Year'][str(years[count-1])+'-'+fye])
roe_prior = float(content['Return on Equity %'][str(years[count-1])+'-'+fye])
cog = round((rev_prior/roe_prior)*eps_prior, 5)
cogs_prior.append(cog)
eps = float(content['Earnings Per Share USD'][str(years[count])+'-'+fye])
rev = float(content['rev-Year over Year'][str(years[count])+'-'+fye])
roe = float(content['Return on Equity %'][str(years[count])+'-'+fye])
cog = round((rev/roe)*eps, 5)
cogs.append(cog)
#
count += 1
count = 1
fgs = [] #
fgs_prior = []
for i in cogs_prior:
fg = round((float(content['Earnings Per Share USD'][str(years[count-1])+'-'+fye]) - float(content['Dividends USD'][str(years[count-1])+'-'+fye]) - i), 5)
fgs_prior.append(fg)
fg = round((float(content['Earnings Per Share USD'][str(years[count])+'-'+fye]) - float(content['Dividends USD'][str(years[count-1])+'-'+fye]) - cogs[count-1]), 5)
fgs.append(fg)
count += 1
sc = [] #
sc_prior = []
count = 0
print content['shareprices']
for i in fgs:
sharep = float(content['shareprices'][str(years[count])+'-'+str(fye)])
t = round((i/sharep)*100, 5)
sc.append(t)
t = round((fgs_prior[count]/sharep)*100, 5)
sc_prior.append(t)
count += 1
pred = [] #
pred_prior = []
count = 1
for i in sc:
rev = float(content['rev-Year over Year'][str(years[count])+'-'+fye])
t = i + rev
pred.append(t)
rev_prior = float(content['rev-Year over Year'][str(years[count-1])+'-'+fye])
t = sc_prior[count-1] + rev_prior
print sc_prior[count-1], rev_prior
pred_prior.append(t)
count += 1
x = []
y = []
count = 1
# feature_labels = ['eps_prior', 'eps_future', 'payoutratio_prior', 'divs_prior', 'cogs_prior', 'cogs_future', 'sharechange_prior', 'sharechange_future', 'funding_gap_prior', 'funding_gap_future', 'prediction_prior', 'prediction_future', 'revYOY_prior', 'revYOY_future', 'roe_prior', 'roe_future', 'shareprice_prior', 'three_yr_trailing_dgr', 'NAPMIImean', 'NAPMIIslope', 'CUUR0000SA0L2mean', 'CUUR0000SA0L2slope', 'IPFINALmean', 'IPFINALslope', 'CUUR0000SADmean', 'CUUR0000SADslope', 'HOUSTNEmean', 'HOUSTNEslope', 'MHHNGSPmean', 'MHHNGSPslope', 'WJFUELUSGULFmean', 'WJFUELUSGULFslope', 'CES1021000001mean', 'CES1021000001slope', 'PRRESCONSmean', 'PRRESCONSslope', 'PNRESCONSmean', 'PNRESCONSslope', 'DDURRG3M086SBEAmean', 'DDURRG3M086SBEAslope', 'DSERRG3M086SBEAmean', 'DSERRG3M086SBEAslope', 'IPNCONGDmean', 'IPNCONGDslope', 'IPCONGDmean', 'IPCONGDslope', 'HOUSTMWmean', 'HOUSTMWslope', 'USGOODmean', 'USGOODslope', 'ACOGNOmean', 'ACOGNOslope', 'PPICMMmean', 'PPICMMslope', 'NONREVSLmean', 'NONREVSLslope', 'IPFUELSmean', 'IPFUELSslope', 'IPMATmean', 'IPMATslope', 'BAAFFMmean', 'BAAFFMslope', 'M2REALmean', 'M2REALslope', 'IPDCONGDmean', 'IPDCONGDslope', 'IPBUSEQmean', 'IPBUSEQslope', 'USTRADEmean', 'USTRADEslope', 'PPIITMmean', 'PPIITMslope', 'CES3000000008mean', 'CES3000000008slope', 'BUSINVmean', 'BUSINVslope', 'CPIAUCSLmean', 'CPIAUCSLslope', 'NAPMNOImean', 'NAPMNOIslope', 'MCOILWTICOmean', 'MCOILWTICOslope', 'INDPROmean', 'INDPROslope', 'HOUSTmean', 'HOUSTslope', 'UNRATEmean', 'UNRATEslope', 'DGORDERmean', 'DGORDERslope', 'PPIFGSmean', 'PPIFGSslope', 'CPIMEDSLmean', 'CPIMEDSLslope', 'RSAFSmean', 'RSAFSslope', 'CPIAPPSLmean', 'CPIAPPSLslope', 'CPITRNSLmean', 'CPITRNSLslope', 'IPMANSICSmean', 'IPMANSICSslope', 'USCONSmean', 'USCONSslope', 'NAPMEImean', 'NAPMEIslope', 'NAPMPRImean', 'NAPMPRIslope', 'NAPMPImean', 'NAPMPIslope', 'NAPMSDImean', 'NAPMSDIslope', 'PPICRMmean', 'PPICRMslope']
fred_labels = ['NAPMIImean', 'NAPMIIslope', 'CUUR0000SA0L2mean', 'CUUR0000SA0L2slope', 'IPFINALmean', 'IPFINALslope', 'CUUR0000SADmean', 'CUUR0000SADslope', 'HOUSTNEmean', 'HOUSTNEslope', 'MHHNGSPmean', 'MHHNGSPslope', 'WJFUELUSGULFmean', 'WJFUELUSGULFslope', 'CES1021000001mean', 'CES1021000001slope', 'PRRESCONSmean', 'PRRESCONSslope', 'PNRESCONSmean', 'PNRESCONSslope', 'DDURRG3M086SBEAmean', 'DDURRG3M086SBEAslope', 'DSERRG3M086SBEAmean', 'DSERRG3M086SBEAslope', 'IPNCONGDmean', 'IPNCONGDslope', 'IPCONGDmean', 'IPCONGDslope', 'HOUSTMWmean', 'HOUSTMWslope', 'USGOODmean', 'USGOODslope', 'ACOGNOmean', 'ACOGNOslope', 'PPICMMmean', 'PPICMMslope', 'NONREVSLmean', 'NONREVSLslope', 'IPFUELSmean', 'IPFUELSslope', 'IPMATmean', 'IPMATslope', 'BAAFFMmean', 'BAAFFMslope', 'M2REALmean', 'M2REALslope', 'IPDCONGDmean', 'IPDCONGDslope', 'IPBUSEQmean', 'IPBUSEQslope', 'USTRADEmean', 'USTRADEslope', 'PPIITMmean', 'PPIITMslope', 'CES3000000008mean', 'CES3000000008slope', 'BUSINVmean', 'BUSINVslope', 'CPIAUCSLmean', 'CPIAUCSLslope', 'NAPMNOImean', 'NAPMNOIslope', 'MCOILWTICOmean', 'MCOILWTICOslope', 'INDPROmean', 'INDPROslope', 'HOUSTmean', 'HOUSTslope', 'UNRATEmean', 'UNRATEslope', 'DGORDERmean', 'DGORDERslope', 'PPIFGSmean', 'PPIFGSslope', 'CPIMEDSLmean', 'CPIMEDSLslope', 'RSAFSmean', 'RSAFSslope', 'CPIAPPSLmean', 'CPIAPPSLslope', 'CPITRNSLmean', 'CPITRNSLslope', 'IPMANSICSmean', 'IPMANSICSslope', 'USCONSmean', 'USCONSslope', 'NAPMEImean', 'NAPMEIslope', 'NAPMPRImean', 'NAPMPRIslope', 'NAPMPImean', 'NAPMPIslope', 'NAPMSDImean', 'NAPMSDIslope', 'PPICRMmean', 'PPICRMslope']
# feature_labels = ['cog', 'cog_prior', 'sc', 'sc_prior', 'funding gap', 'funding gap_prior', 'pred', 'pred_prior', 'rev', 'rev_prior', 'CPIAUCSL-mean','CPIAUCSL-slope','UNRATE-mean','UNRATE-slope','MCOILWTICO-mean','MCOILWTICO-slope','INDPRO-mean','INDPRO-slope', 'HOUST-mean','HOUST-slope', 'NAPMNOI-mean','NAPMNOI-slope', 'DGORDER-mean','DGORDER-slope', 'PPIFGS-mean','PPIFGS-slope', 'CPIMEDSL-mean','CPIMEDSL-slope', 'RSAFS-mean','RSAFS-slope', 'CPIAPPSL-mean','CPIAPPSL-slope', 'CPITRNSL-mean','CPITRNSL-slope', 'IPMANSICS-mean','IPMANSICS-slope', 'USCONS-mean','USCONS-slope', 'NAPMEI-mean','NAPMEI-slope', 'NAPMPRI-mean','NAPMPRI-slope', 'NAPMPI-mean','NAPMPI-slope', 'NAPMSDI-mean','NAPMSDI-slope', 'PPICRM-mean', 'PPICRM-slope']
# fseries = ['NAPM', 'CPIAUCSL','UNRATE','MCOILWTICO','INDPRO','HOUST','NAPMNOI','DGORDER','PPIFGS','CPIMEDSL','RSAFS','CPIAPPSL','CPITRNSL','IPMANSICS','USCONS','NAPMEI','NAPMPRI','NAPMPI','NAPMSDI','PPICRM']
labelsSaved= False
for i in years[1:]:
feature_labels =[]
temp = []
############################################# future (aka future prior data)
temp.append(float(cogs[count-1]))
feature_labels.append('cogs_future')
temp.append(float(float(sc[count-1])))
feature_labels.append('sc_future')
temp.append(float(fgs[count-1]))
feature_labels.append('fg_future')
temp.append(float(pred[count-1]))
feature_labels.append('pred_future')
temp.append(float(content['Return on Equity %'][str(years[count])+'-'+fye]))
feature_labels.append('roe_future')
rev = float(content['rev-Year over Year'][str(years[count])+'-'+fye])
temp.append(rev)
feature_labels.append('revyoy_future')
netmarg = float(content['Net Margin %'][str(years[count])+'-'+fye])
temp.append(netmarg)
feature_labels.append('netmarg_future')
temp.append(float(content['Earnings Per Share USD'][str(years[count])+'-'+fye]))
feature_labels.append('eps_future')
temp.append(float(content['Debt/Equity'][str(years[count])+'-'+str(fye)])) #d-to-e
feature_labels.append('dtoe_future')
if i == years[-1]:
future_prior_data = copy.deepcopy(temp)
print len(future_prior_data), '********'
payout_future = float(content['Payout Ratio %'][str(years[count])+'-'+fye])
future_prior_data.append(payout_future)
threeyravg = calc_delta(divs)
mr_threeyravg = sum(threeyravg[-3:])/3
future_prior_data.append(mr_threeyravg)
mr_price = mr_stock_price(ticker)
future_prior_data.append(mr_price)
print future_prior_data
future_prior_data = np.array(future_prior_data, dtype=np.float32)
print len(future_prior_data), '********'
#############################################prior
temp.append(float(cogs_prior[count-1]))
feature_labels.append('cogs_prior')
temp.append(float(float(sc_prior[count-1])))
feature_labels.append('sc_prior')
temp.append(float(fgs_prior[count-1]))
feature_labels.append('fg_prior')
temp.append(float(pred_prior[count-1]))
feature_labels.append('pred_prior')
temp.append(float(content['Return on Equity %'][str(years[count-1])+'-'+fye]))
feature_labels.append('roe_prior')
rev_prior = float(content['rev-Year over Year'][str(years[count-1])+'-'+fye])
temp.append(rev_prior)
feature_labels.append('revyoy_prior')
netmarg_prior = float(content['Net Margin %'][str(years[count-1])+'-'+fye])
temp.append(netmarg_prior)
feature_labels.append('netmarg_prior')
temp.append(float(content['Earnings Per Share USD'][str(years[count-1])+'-'+fye]))
feature_labels.append('eps_prior')
temp.append(float(content['Debt/Equity'][str(years[count-1])+'-'+str(fye)])) #d-to-e prior year
feature_labels.append('dtoe_prior')
try:
temp.append(float(content['Payout Ratio %'][str(years[count-1])+'-'+fye]))
feature_labels.append('payout_prior')
except:
try:
payoutr = float(content['Dividends USD'][str(years[count-1])+'-'+str(fye)]) / float(content['Earnings Per Share USD'][str(years[count-1])+'-'+fye])
temp.append(payoutr)
feature_labels.append('payout_prior')
except:
raise TypeError
temp.append(float(threeavg[ticker][str(i)]))
feature_labels.append('thryravgdgr')
temp.append(float(content['shareprices'][str(years[count-1])+'-'+str(fye)]))
feature_labels.append('sp_prior')
print len(temp), 'before first!'
############################################# combine:
nd, glabels = gendata(temp, feature_labels)
for q in glabels:
feature_labels.append(q)
for q in nd:
temp.append(float(q))
print len(temp), 'before fred'
for fo in fredobjs:
# print fo.metric
start = str(years[count-1])+'-'+divmonth+'-01'
end = str(years[count])+'-'+divmonth+'-01'
# print start, end
mean, slope = calc_vals(start, end, fo.dates, fo.vals)
temp.append(float(mean))
temp.append(float(slope))
# print mean, slope
# print
for label in fred_labels:
feature_labels.append(label)
nd, glabels = gendata(temp, feature_labels)
for q in glabels:
feature_labels.append(q)
for q in nd:
temp.append(float(q))
if labelsSaved == False:
joblib.dump(feature_labels, '/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker+'/'+ticker+'_featlabels')
labelsSaved = True
temp = np.array(temp, np.float32)
x.append(temp)
y.append(float(content['divyoy'][str(years[count])+'-'+fye]))
count += 1
x = np.array(x, dtype = np.float32)
y = np.array(y, dtype = np.float32)
print years[-1]
np.savetxt('/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker+'/'+ticker+'_mr_year', np.array([years[-1]]), delimiter = ',')
np.savetxt('/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker+'/'+ticker+'_x', x, delimiter = ',')
np.savetxt('/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker+'/'+ticker+'_y', y, delimiter = ',')
np.savetxt('/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker+'/'+ticker+'_mr_price', np.array([mr_price], dtype= np.float32), delimiter=',')
np.savetxt('/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker+'/'+ticker+'_future_prior', future_prior_data, delimiter=',')
np.savetxt('/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker+'/'+ticker+'_mr_div', np.array([divs[-1]], dtype=np.float32), delimiter = ',')
except:
shutil.rmtree('/home/ubuntu/dgrpred/dump/temp_persistence/'+ticker)
pass
import pandas as pd
startdate = datetime.date(2014, 1, 1)
today=enddate = datetime.date.today()
ticker = "Nifty"
##str5 = "Nifty"
##print str5
##int4 =raw_input("Enter the index Name(For Niftty :1,Bank Nifty2 ) :")
##if int4 == 1:
## str5 ="^NSEI"
##elif int4 == 2:
## str5 ="^NSEBANK"
#fh=web.DataReader("^NSEI","yahoo", start , end)
fh = finance.fetch_historical_yahoo("^NSEI" , startdate, enddate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
# new=pd.DataFrame({'Open':fh[:,0],'High':fh[:,1],'Low':fh[:,2],'Close':fh[:,3],'volume':fh[:,4]})
#new=pd.DataFrame(r)
r = mlab.csv2rec(fh)
fh.close()
r.sort()
def moving_average(x, n, type='simple'):
def __init__(self, ticker):
gtk.VBox.__init__(self)
startdate = datetime.date(2006, 1, 1)
today = enddate = datetime.date.today()
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
r = mlab.csv2rec(fh)
fh.close()
r.sort()
plt.rc("axes", grid=True)
plt.rc("grid", color="0.75", linestyle="-", linewidth=0.5)
textsize = 9
left, width = 0.1, 0.8
rect1 = [left, 0.7, width, 0.2]
rect2 = [left, 0.3, width, 0.4]
rect3 = [left, 0.1, width, 0.2]
fig = Figure(facecolor="white", figsize=(5, 4), dpi=100)
axescolor = "#f6f6f6" # the axies background color
ax1 = fig.add_axes(rect1, axisbg=axescolor) # left, bottom, width, height
ax2 = fig.add_axes(rect2, axisbg=axescolor, sharex=ax1)
ax2t = ax2.twinx()
ax3 = fig.add_axes(rect3, axisbg=axescolor, sharex=ax1)
# plot the relative strength indicator
prices = r.adj_close
rsi = relative_strength(prices)
fillcolor = "darkgoldenrod"
ax1.plot(r.date, rsi, color=fillcolor)
ax1.axhline(70, color=fillcolor)
ax1.axhline(30, color=fillcolor)
ax1.fill_between(r.date, rsi, 70, where=(rsi >= 70), facecolor=fillcolor, edgecolor=fillcolor)
ax1.fill_between(r.date, rsi, 30, where=(rsi <= 30), facecolor=fillcolor, edgecolor=fillcolor)
ax1.text(0.6, 0.9, ">70 = overbought", va="top", transform=ax1.transAxes, fontsize=textsize)
ax1.text(0.6, 0.1, "<30 = oversold", transform=ax1.transAxes, fontsize=textsize)
ax1.set_ylim(0, 100)
ax1.set_yticks([30, 70])
ax1.text(0.025, 0.95, "RSI (14)", va="top", transform=ax1.transAxes, fontsize=textsize)
ax1.set_title("%s daily" % ticker)
# plot the price and volume data
dx = r.adj_close - r.close
low = r.low + dx
high = r.high + dx
deltas = np.zeros_like(prices)
deltas[1:] = np.diff(prices)
up = deltas > 0
ax2.vlines(r.date[up], low[up], high[up], color="black", label="_nolegend_")
ax2.vlines(r.date[~up], low[~up], high[~up], color="black", label="_nolegend_")
ma50 = moving_average(prices, 50, type="simple")
ma100 = moving_average(prices, 100, type="simple")
ma200 = moving_average(prices, 200, type="simple")
linema50, = ax2.plot(r.date, ma50, color="blue", lw=2, label="MA (50)")
linema100, = ax2.plot(r.date, ma100, color="green", lw=2, label="MA (100)")
linema200, = ax2.plot(r.date, ma200, color="red", lw=2, label="MA (200)")
last = r[-1]
s = "%s O:%1.2f H:%1.2f L:%1.2f C:%1.2f, V:%1.1fM Chg:%+1.2f" % (
today.strftime("%d-%b-%Y"),
last.open,
last.high,
last.low,
last.close,
last.volume * 1e-6,
last.close - last.open,
)
t4 = ax2.text(0.3, 0.9, s, transform=ax2.transAxes, fontsize=textsize)
props = font_manager.FontProperties(size=10)
leg = ax2.legend(loc="center left", shadow=True, fancybox=True, prop=props)
leg.get_frame().set_alpha(0.5)
volume = (r.close * r.volume) / 1e6 # dollar volume in millions
vmax = volume.max()
poly = ax2t.fill_between(r.date, volume, 0, label="Volume", facecolor=fillcolor, edgecolor=fillcolor)
ax2t.set_ylim(0, 5 * vmax)
ax2t.set_yticks([])
# compute the MACD indicator
fillcolor = "darkslategrey"
nslow = 26
nfast = 12
nema = 9
emaslow, emafast, macd = moving_average_convergence(prices, nslow=nslow, nfast=nfast)
ema9 = moving_average(macd, nema, type="exponential")
ax3.plot(r.date, macd, color="black", lw=2)
ax3.plot(r.date, ema9, color="blue", lw=1)
ax3.fill_between(r.date, macd - ema9, 0, alpha=0.5, facecolor=fillcolor, edgecolor=fillcolor)
ax3.text(
0.025,
0.95,
"MACD (%d, %d, %d)" % (nfast, nslow, nema),
va="top",
transform=ax3.transAxes,
fontsize=textsize,
)
# turn off upper axis tick labels, rotate the lower ones, etc
for ax in ax1, ax2, ax2t, ax3:
if ax != ax3:
for label in ax.get_xticklabels():
label.set_visible(False)
else:
for label in ax.get_xticklabels():
label.set_rotation(30)
label.set_horizontalalignment("right")
ax.fmt_xdata = mdates.DateFormatter("%Y-%m-%d")
canvas = FigureCanvas(fig) # a gtk.DrawingArea
self.pack_start(canvas)
toolbar = NavigationToolbar(canvas, win)
self.pack_start(toolbar, False, False)
""" Name : 4375OS_07_27_volume_and_price_2_plots.py Book : Python for Finance Publisher: Packt Publishing Ltd. Author : Yuxing Yan Date : 12/26/2013 email : [email protected] [email protected] """ from pylab import plotfile, show import matplotlib.finance as finance ticker = 'IBM' begdate = datetime.date(2013, 1, 1) enddate = datetime.date.today() x = finance.fetch_historical_yahoo(ticker, begdate, enddate) plotfile(x, (0, 5, 6)) show()
def manualtest(numlist):
'''
input: a list of numbers (nums corrsp to stocks listed in tckrlist)
output: the value of a portfolio containing stocks specified in numlist starting on 9/19/2000 and ending on 7/15/2013
using a manual reinvestment strategy
'''
daycount = 0
cash = 0
transactions = 0
cashperstock = 50000/len(numlist) #start with $50,000 dollars divided by number of stocks
holdingslist = []
for i in numlist: #buy initial shares
price = mf.parse_yahoo_historical(mf.fetch_historical_yahoo(tckrlist[i], (2000, 9, 19), (2000, 9, 19), dividends=False), adjusted=False)
iprice = price[0][2]
ishares = round(cashperstock/iprice, 2)
holdingslist.append(ishares)
for i in fulldatelist: #for every day in window
fiftydaylist = []
buyconditiontf =[]
tendaylist= []
mrdaystckprice = []
hcount = 0
for j in numlist: #look at every stock in the randomly chosen numlist
paycount = 0
for k in paydatemaster[j]: #for each stock, look at payment date master list
k = k.strip()
if k == i: #check if current day is a div pay day
paymentmaster[j][paycount] = float(paymentmaster[j][paycount])
divpaymt = round(paymentmaster[j][paycount]*holdingslist[hcount], 2)
cash += divpaymt # if it's a pay day, add the div payment to cash
paycount += 1
hcount += 1
if daycount > 50: # if more than 50 days have passed
for u in numlist:
tempolist = []
dcount = 0
for p in stockdatemaster[u]:
if p == i:
tempolist = stockpricemaster[u][dcount:dcount+50] #stock prices for last 50 days
dcount += 1
if len(tempolist) != 0:
fstdv, favg = meanstdv(tempolist) #calculate fifty day moving average
tstdv, tavg = meanstdv(tempolist[:10]) #calculate 10 day moving average
fiftydaylist.append(favg)
tendaylist.append(tavg)
mrdaystckprice.append(tempolist[0])
fcount = 0
truelist = []
for s in mrdaystckprice:
if float(s) < fiftydaylist[fcount] and float(s) < tendaylist[fcount] and tendaylist[fcount] < fiftydaylist[fcount]: #buy criteria defined
buyconditiontf.append(True)
truelist.append(fcount)
# print i
else:
buyconditiontf.append(False)
fcount += 1
fcount = 0
if cash != 0 and len(truelist) != 0: #if there is cash available and one or more buy criteria have been met
if cash/len(truelist) > 500: #if there's more than $500 cash
for e in buyconditiontf:
if e == True:
holdingslist[fcount] += (cash/len(truelist))/float(mrdaystckprice[fcount]) #for all stocks meeting buy criteria, add to holdings using available cash
transactions += 1 #add one transaction to the list
fcount += 1
cash = 0 #reset cash to zero; all cash was spent adding to stocks meeting buy criteria
daycount += 1
finaldate = (2013, 7, 15)
count = 0
value = 0
for i in numlist:
finalprice = mf.parse_yahoo_historical(mf.fetch_historical_yahoo(tckrlist[i], finaldate, finaldate, dividends=False), adjusted=False)
ifinalprice = finalprice[0][2]
value += round((ifinalprice*holdingslist[count])+cash, 2) #calculate final value for each stock
count += 1
return value, transactions
def run():
startdate = datetime.date(2000,1,1)
today = enddate = datetime.date.today()
ticker = 'SPY'
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
r = mlab.csv2rec(fh); fh.close()
r.sort()
plt.rc('axes', grid=True)
plt.rc('grid', color='0.75', linestyle='-', linewidth=0.5)
textsize = 9
left, width = 0.1, 0.8
rect1 = [left, 0.7, width, 0.2]
rect2 = [left, 0.3, width, 0.4]
rect3 = [left, 0.1, width, 0.2]
fig = plt.figure(facecolor='white')
axescolor = '#f6f6f6' # the axes background color
ax1 = fig.add_axes(rect1, axisbg=axescolor) #left, bottom, width, height
ax2 = fig.add_axes(rect2, axisbg=axescolor, sharex=ax1)
ax2t = ax2.twinx()
ax3 = fig.add_axes(rect3, axisbg=axescolor, sharex=ax1)
### plot the relative strength indicator
prices = r.adj_close
rsi = relative_strength(prices)
fillcolor = 'darkgoldenrod'
ax1.plot(r.date, rsi, color=fillcolor)
ax1.axhline(70, color=fillcolor)
ax1.axhline(30, color=fillcolor)
ax1.fill_between(r.date, rsi, 70, where=(rsi>=70), facecolor=fillcolor, edgecolor=fillcolor)
ax1.fill_between(r.date, rsi, 30, where=(rsi<=30), facecolor=fillcolor, edgecolor=fillcolor)
ax1.text(0.6, 0.9, '>70 = overbought', va='top', transform=ax1.transAxes, fontsize=textsize)
ax1.text(0.6, 0.1, '<30 = oversold', transform=ax1.transAxes, fontsize=textsize)
ax1.set_ylim(0, 100)
ax1.set_yticks([30,70])
ax1.text(0.025, 0.95, 'RSI (14)', va='top', transform=ax1.transAxes, fontsize=textsize)
ax1.set_title('%s daily'%ticker)
### plot the price and volume data
dx = r.adj_close - r.close
low = r.low + dx
high = r.high + dx
deltas = np.zeros_like(prices)
deltas[1:] = np.diff(prices)
up = deltas>0
ax2.vlines(r.date[up], low[up], high[up], color='black', label='_nolegend_')
ax2.vlines(r.date[~up], low[~up], high[~up], color='black', label='_nolegend_')
ma20 = moving_average(prices, 20, type='simple')
ma200 = moving_average(prices, 200, type='simple')
linema20, = ax2.plot(r.date, ma20, color='blue', lw=2, label='MA (20)')
linema200, = ax2.plot(r.date, ma200, color='red', lw=2, label='MA (200)')
last = r[-1]
s = '%s O:%1.2f H:%1.2f L:%1.2f C:%1.2f, V:%1.1fM Chg:%+1.2f' % (
today.strftime('%d-%b-%Y'),
last.open, last.high,
last.low, last.close,
last.volume*1e-6,
last.close-last.open )
t4 = ax2.text(0.3, 0.9, s, transform=ax2.transAxes, fontsize=textsize)
props = font_manager.FontProperties(size=10)
leg = ax2.legend(loc='center left', shadow=True, fancybox=True, prop=props)
leg.get_frame().set_alpha(0.5)
volume = (r.close*r.volume)/1e6 # dollar volume in millions
vmax = volume.max()
poly = ax2t.fill_between(r.date, volume, 0, label='Volume', facecolor=fillcolor, edgecolor=fillcolor)
ax2t.set_ylim(0, 5*vmax)
ax2t.set_yticks([])
### compute the MACD indicator
fillcolor = 'darkslategrey'
nslow = 26
nfast = 12
nema = 9
emaslow, emafast, macd = moving_average_convergence(prices, nslow=nslow, nfast=nfast)
ema9 = moving_average(macd, nema, type='exponential')
ax3.plot(r.date, macd, color='black', lw=2)
ax3.plot(r.date, ema9, color='blue', lw=1)
ax3.fill_between(r.date, macd-ema9, 0, alpha=0.5, facecolor=fillcolor, edgecolor=fillcolor)
ax3.text(0.025, 0.95, 'MACD (%d, %d, %d)'%(nfast, nslow, nema), va='top',
transform=ax3.transAxes, fontsize=textsize)
#ax3.set_yticks([])
# turn off upper axis tick labels, rotate the lower ones, etc
for ax in ax1, ax2, ax2t, ax3:
if ax!=ax3:
for label in ax.get_xticklabels():
label.set_visible(False)
else:
for label in ax.get_xticklabels():
label.set_rotation(30)
label.set_horizontalalignment('right')
ax.fmt_xdata = mdates.DateFormatter('%Y-%m-%d')
class MyLocator(mticker.MaxNLocator):
def __init__(self, *args, **kwargs):
mticker.MaxNLocator.__init__(self, *args, **kwargs)
def __call__(self, *args, **kwargs):
return mticker.MaxNLocator.__call__(self, *args, **kwargs)
# at most 5 ticks, pruning the upper and lower so they don't overlap
# with other ticks
#ax2.yaxis.set_major_locator(mticker.MaxNLocator(5, prune='both'))
#ax3.yaxis.set_major_locator(mticker.MaxNLocator(5, prune='both'))
ax2.yaxis.set_major_locator(MyLocator(5, prune='both'))
ax3.yaxis.set_major_locator(MyLocator(5, prune='both'))
plt.show()
import datetime
from matplotlib import verbose, get_cachedir
from matplotlib.dates import date2num
from matplotlib.cbook import iterable, mkdirs
from matplotlib.collections import LineCollection, PolyCollection
from matplotlib.colors import colorConverter
from matplotlib.lines import Line2D, TICKLEFT, TICKRIGHT
from matplotlib.patches import Rectangle
from matplotlib.transforms import Affine2D
if __name__ == '__main__':
starttime = dt.date(2015,1,1)
endtime = dt.date.today()
ticker = 'SPY'
fh = mpf.fetch_historical_yahoo(ticker, starttime, endtime)
r = mlab.csv2rec(fh);
fh.close()
r.sort()
df = pd.DataFrame.from_records(r)
quotes = mpf.quotes_historical_yahoo_ohlc(ticker, starttime, endtime)
fig, (ax1, ax2) = plt.subplots(2, sharex=True)
tdf = df.set_index('date')
cdf = tdf['close']
cdf.plot(label = "close price", ax=ax1)
pd.rolling_mean(cdf, window=30, min_periods=1).plot(label = "30-day moving averages", ax=ax1)
pd.rolling_mean(cdf, window=10, min_periods=1).plot(label = "10-day moving averages", ax=ax1)
ax1.set_xlabel(r'Date')
ax1.set_ylabel(r'Price')
ax1.grid(True)
props = font_manager.FontProperties(size=10)
from scipy.optimize import fsolve
# (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
startdate = datetime.date(2013,4,1)
today = enddate = datetime.date(2013,12,13)#datetime.date.today()
matplotlib.dates.date2num(today)
ticker = 'QQQ'
#quotes = quotes_historical_yahoo(ticker, startdate, enddate)#fetch_historical_yahoo quotes_historical_yahoo
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
fh = fetch_historical_yahoo(ticker, startdate, enddate)
r = mlab.csv2rec(fh); fh.close()
r.sort()
#quotes = quotes_historical_yahoo('INTC', date1, date2)
quotes = [(matplotlib.dates.date2num(x[0]), x[1], x[2], x[3], x[4], x[5]) for x in r]
v = 0.1207 # 0.2258 # 0.2472
k = 206
rate = 0.025/100
t0 = 72 #217-60 360/365 146
t1 = datetime.datetime(2014,2,24) # 2012,11,16
t2 = datetime.datetime(2015,2,2) # 2013,6,21
price = 1.12 # 77.78
def future_levels(begin_data, days_step):
import csv
import codecs
from datetime import date
import sqlite3
import numpy as np
import matplotlib.finance as finance
import matplotlib.mlab as mlab
import sys
server = 'HKI.db'
startdate = date(2016,6,1)
enddate = date(2016,6,30)
fh = finance.fetch_historical_yahoo('^HSCE', startdate, enddate)#, cachename=ticker + '.csv'
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
r = mlab.csv2rec(fh); fh.close()
r.sort()
r=r[r.volume>0]
conn = sqlite3.connect('HKI.db')
cursor = conn.cursor()
cursor.execute("""
CREATE TABLE IF NOT EXISTS HKITRI (
secid text NOT NULL,
tradedate text,
closeprice real,
up = (up*(n-1) + upval)/n
down = (down*(n-1) + downval)/n
rs = up/down
rsi[i] = 100. - 100./(1.+rs)
return rsi
# preparing data
startdate = datetime.date(2006,1,1)
today = enddate = datetime.date.today()
ticker = 'GS'
fh = finance.fetch_historical_yahoo(ticker,startdate,today) # a numpy record array with fields: date, open, high, low, close, volume, adj_close
r = mlab.csv2rec(fh); fh.close()
r.sort()
dates = r.date[9:]
px = r.adj_close
prices = px[9:]
rsi = relative_strength(px, 10)[9:]
dtcount = 0
pxdict = {}
for date in dates:
pxdict[date] = prices[dtcount]
dtcount = dtcount + 1
from pylab import figure, show
from matplotlib.finance import fetch_historical_yahoo
from matplotlib.dates import YearLocator, MonthLocator, DateFormatter
import datetime
date1 = datetime.date(2012, 1, 1)
date2 = datetime.date(2012, 11, 11)
daysFmt = DateFormatter('%m-%d-%Y')
quotes = fetch_historical_yahoo('MSFT', date1, date2)
if len(quotes) == 0:
raise SystemExit
dates = [q[0] for q in quotes]
opens = [q[1] for q in quotes]
fig = figure()
ax = fig.add_subplot(111)
ax.plot_date(dates, opens, '-')
# format the ticks
ax.xaxis.set_major_formatter(daysFmt)
ax.autoscale_view()
# format the coords message box
def price(x):
return '$%1.2f' % x
ax.fmt_xdata = DateFormatter('%Y-%m-%d')
def run():
startdate = datetime.date(2000, 1, 1)
today = enddate = datetime.date.today()
ticker = 'SPY'
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
r = mlab.csv2rec(fh)
fh.close()
r.sort()
plt.rc('axes', grid=True)
plt.rc('grid', color='0.75', linestyle='-', linewidth=0.5)
textsize = 9
left, width = 0.1, 0.8
rect1 = [left, 0.7, width, 0.2]
rect2 = [left, 0.3, width, 0.4]
rect3 = [left, 0.1, width, 0.2]
fig = plt.figure(facecolor='white')
axescolor = '#f6f6f6' # the axes background color
ax1 = fig.add_axes(rect1, axisbg=axescolor) #left, bottom, width, height
ax2 = fig.add_axes(rect2, axisbg=axescolor, sharex=ax1)
ax2t = ax2.twinx()
ax3 = fig.add_axes(rect3, axisbg=axescolor, sharex=ax1)
### plot the relative strength indicator
prices = r.adj_close
rsi = relative_strength(prices)
fillcolor = 'darkgoldenrod'
ax1.plot(r.date, rsi, color=fillcolor)
ax1.axhline(70, color=fillcolor)
ax1.axhline(30, color=fillcolor)
ax1.fill_between(r.date,
rsi,
70,
where=(rsi >= 70),
facecolor=fillcolor,
edgecolor=fillcolor)
ax1.fill_between(r.date,
rsi,
30,
where=(rsi <= 30),
facecolor=fillcolor,
edgecolor=fillcolor)
ax1.text(0.6,
0.9,
'>70 = overbought',
va='top',
transform=ax1.transAxes,
fontsize=textsize)
ax1.text(0.6,
0.1,
'<30 = oversold',
transform=ax1.transAxes,
fontsize=textsize)
ax1.set_ylim(0, 100)
ax1.set_yticks([30, 70])
ax1.text(0.025,
0.95,
'RSI (14)',
va='top',
transform=ax1.transAxes,
fontsize=textsize)
ax1.set_title('%s daily' % ticker)
### plot the price and volume data
dx = r.adj_close - r.close
low = r.low + dx
high = r.high + dx
deltas = np.zeros_like(prices)
deltas[1:] = np.diff(prices)
up = deltas > 0
ax2.vlines(r.date[up],
low[up],
high[up],
color='black',
label='_nolegend_')
ax2.vlines(r.date[~up],
low[~up],
high[~up],
color='black',
label='_nolegend_')
ma20 = moving_average(prices, 20, type='simple')
ma200 = moving_average(prices, 200, type='simple')
linema20, = ax2.plot(r.date, ma20, color='blue', lw=2, label='MA (20)')
linema200, = ax2.plot(r.date, ma200, color='red', lw=2, label='MA (200)')
last = r[-1]
s = '%s O:%1.2f H:%1.2f L:%1.2f C:%1.2f, V:%1.1fM Chg:%+1.2f' % (
today.strftime('%d-%b-%Y'), last.open, last.high, last.low, last.close,
last.volume * 1e-6, last.close - last.open)
t4 = ax2.text(0.3, 0.9, s, transform=ax2.transAxes, fontsize=textsize)
props = font_manager.FontProperties(size=10)
leg = ax2.legend(loc='center left', shadow=True, fancybox=True, prop=props)
leg.get_frame().set_alpha(0.5)
volume = (r.close * r.volume) / 1e6 # dollar volume in millions
vmax = volume.max()
poly = ax2t.fill_between(r.date,
volume,
0,
label='Volume',
facecolor=fillcolor,
edgecolor=fillcolor)
ax2t.set_ylim(0, 5 * vmax)
ax2t.set_yticks([])
### compute the MACD indicator
fillcolor = 'darkslategrey'
nslow = 26
nfast = 12
nema = 9
emaslow, emafast, macd = moving_average_convergence(prices,
nslow=nslow,
nfast=nfast)
ema9 = moving_average(macd, nema, type='exponential')
ax3.plot(r.date, macd, color='black', lw=2)
ax3.plot(r.date, ema9, color='blue', lw=1)
ax3.fill_between(r.date,
macd - ema9,
0,
alpha=0.5,
facecolor=fillcolor,
edgecolor=fillcolor)
ax3.text(0.025,
0.95,
'MACD (%d, %d, %d)' % (nfast, nslow, nema),
va='top',
transform=ax3.transAxes,
fontsize=textsize)
#ax3.set_yticks([])
# turn off upper axis tick labels, rotate the lower ones, etc
for ax in ax1, ax2, ax2t, ax3:
if ax != ax3:
for label in ax.get_xticklabels():
label.set_visible(False)
else:
for label in ax.get_xticklabels():
label.set_rotation(30)
label.set_horizontalalignment('right')
ax.fmt_xdata = mdates.DateFormatter('%Y-%m-%d')
class MyLocator(mticker.MaxNLocator):
def __init__(self, *args, **kwargs):
mticker.MaxNLocator.__init__(self, *args, **kwargs)
def __call__(self, *args, **kwargs):
return mticker.MaxNLocator.__call__(self, *args, **kwargs)
# at most 5 ticks, pruning the upper and lower so they don't overlap
# with other ticks
#ax2.yaxis.set_major_locator(mticker.MaxNLocator(5, prune='both'))
#ax3.yaxis.set_major_locator(mticker.MaxNLocator(5, prune='both'))
ax2.yaxis.set_major_locator(MyLocator(5, prune='both'))
ax3.yaxis.set_major_locator(MyLocator(5, prune='both'))
plt.show()
import matplotlib.colors as colors
import matplotlib.finance as finance
import matplotlib.dates as mdates
import matplotlib.ticker as mticker
import matplotlib.mlab as mlab
import matplotlib.pyplot as plt
import matplotlib.font_manager as font_manager
import time, sys
from sklearn import cross_validation
startdate = datetime.date(2012, 1, 1)
today = enddate = datetime.date.today()
ticker = '^DJI'
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
fh = finance.fetch_historical_yahoo(ticker, startdate, enddate)
r = mlab.csv2rec(fh)
fh.close()
r.sort()
view_length = 3000
# Plot data
plt.style.use('ggplot')
plt.figure(1)
plt.subplot(211)
plt.title(ticker)
plt.xlabel('Date')
plt.ylabel('Closing Price')
plt.plot(r.date[-view_length:], r.close[-view_length:])
# Transform time series to difference returns
# these are the constants required by the various tools.
macdFast = 8 #Rule#1:8 def:12
macdSlow = 17 #Rule#1:17 def:26
macdSmoothing = 9 #Rule#1:9 def:9
stoLength = 14
#stoKPeriods=1#%K period
stoDPeriods = 5 # %D periods Rule#1 recommends 5, default is 3
movAvePeriods = 10 # number of periods for a moving average
fs = 6
if macdFast > macdSlow:
exit('ERROR: MACDFast>MACDSlow')
for ticIdx in range(np.size(tickers)):
fh = finance.fetch_historical_yahoo(tickers[ticIdx], startDate, endDate)
# a numpy record array with fields: date, open, high, low, close, volume, adj_close)
finData = mlab.csv2rec(fh)
fh.close()
finData.sort()
timeDelt = finData.date[-1] - finData.date[1]
if timeDelt.days <= (macdSlow + macdSmoothing +
1): # not enough data to calculate the MACD
exit(
sprintf(
'ERROR: not enough days to calculate the MACD timeDelta=:%i days',
int(timeDelt.days)))
#MACD, EMAfast, EMAslow, MACDsign, MACDdiff=ff2.MACD(finData, n_slow, n_fast,macdSmoothing):
rule1Orders, ordersTechnik1, ordersTechnik2, priceTechnik2, macdDiff, fastStok, stoD, ma, ma20, ma50, ma200 = ff2.buyOrSell(
