def main():
#load data
returns = data.get_data_google('SPY', start='2008-5-1', end='2009-12-1')['Close'].pct_change()
returns.plot()
plt.ylabel('daily returns in %');
with pm.Model() as sp500_model:
nu = pm.Exponential('nu', 1./10, testval=5.0)
sigma = pm.Exponential('sigma', 1./0.02, testval=0.1)
s = pm.GaussianRandomWalk('s', sigma**-2, shape=len(returns))
r = pm.StudentT('r', nu, lam=pm.math.exp(-2*s), observed=returns)
with sp500_model:
trace = pm.sample(2000)
pm.traceplot(trace, [nu, sigma]);
plt.show()
plt.figure()
returns.plot()
plt.plot(returns.index, np.exp(trace['s',::5].T), 'r', alpha=.03)
plt.legend(['S&P500', 'stochastic volatility process'])
plt.show()
def test_dtypes(self):
#GH3995, #GH8980
data = web.get_data_google('F', start='JAN-01-10', end='JAN-27-13')
assert np.issubdtype(data.Open.dtype, np.number)
assert np.issubdtype(data.Close.dtype, np.number)
assert np.issubdtype(data.Low.dtype, np.number)
assert np.issubdtype(data.High.dtype, np.number)
assert np.issubdtype(data.Volume.dtype, np.number)
def test_get_multi1(self):
for locale in self.locales:
sl = ['AAPL', 'AMZN', 'GOOG']
with tm.set_locale(locale):
pan = web.get_data_google(sl, '2012')
ts = pan.Close.GOOG.index[pan.Close.AAPL < pan.Close.GOOG]
if (hasattr(pan, 'Close') and hasattr(pan.Close, 'GOOG') and
hasattr(pan.Close, 'AAPL')):
self.assertEqual(ts[0].dayofyear, 3)
else:
self.assertRaises(AttributeError, lambda: pan.Close)
def test_get_multi2(self):
with warnings.catch_warnings(record=True) as w:
for locale in self.locales:
with tm.set_locale(locale):
pan = web.get_data_google(['GE', 'MSFT', 'INTC'],
'JAN-01-12', 'JAN-31-12')
result = pan.Close.ix['01-18-12']
assert_n_failed_equals_n_null_columns(w, result)
# sanity checking
assert np.issubdtype(result.dtype, np.floating)
result = pan.Open.ix['Jan-15-12':'Jan-20-12']
self.assertEqual((4, 3), result.shape)
assert_n_failed_equals_n_null_columns(w, result)
def test_get_multi2(self):
with warnings.catch_warnings(record=True) as w:
for locale in self.locales:
with tm.set_locale(locale):
pan = web.get_data_google(['GE', 'MSFT', 'INTC'],
'JAN-01-12', 'JAN-31-12')
result = pan.Close.ix['01-18-12']
assert_n_failed_equals_n_null_columns(w, result)
# sanity checking
assert np.issubdtype(result.dtype, np.floating)
result = pan.Open.ix['Jan-15-12':'Jan-20-12']
self.assertEqual((4, 3), result.shape)
assert_n_failed_equals_n_null_columns(w, result)
def updateAxes(self):
# clear figure
self.figure.clf()
self.figure.canvas.draw()
# get contents of ticker_widget in a list, return if empty
z = self.ticker_widget.items_model
contents = [z.item(x).text() for x in range(z.rowCount())
if z.item(x).checkState() == 2]
if contents == []:
return
# get data with pandas_datareader
try:
data = get_data_google(contents, self.start_edit.text(), self.end_edit.text())
except:
return
# plot every selected symbol
for symbol in contents:
data_tmp = data.minor_xs(symbol)['Close']
ax = self.figure.add_subplot(111)
x = data_tmp.index
# scale by the max price if scale_box is checked, set label accordingly
if self.scale_box.checkState() == 0:
label = symbol
yLabel = '$'
y = data_tmp
else:
label = symbol + ', %'
yLabel = ''
y = 100 * data_tmp / data_tmp[0]
ax.plot(x, y, self.linesty, ms=self.ms, lw=self.lw, label=label)
# clean up plot
ax.set_title('Daily Closing Price')
ax.legend(loc='upper left', bbox_to_anchor=(1, 1), numpoints=3)
ax.grid(True)
ax.set_ylabel(yLabel)
self.figure.tight_layout()
self.figure.subplots_adjust(right=0.75)
self.figure.canvas.draw()
def historical_data(ticker, components):
# Prices adjusted for splits
today, dates = current_date(), []
for each in components:
if PATTERNS['valid_date'].match(each):
dates.append(each)
if not dates:
return {"message": Response.missing_dates(ticker)}
# Validate dates
for each in dates:
if each > today:
return {"message": Response.invalid_date(each)}
try:
date = datetime.datetime.strptime(each, '%Y-%m-%d')
except ValueError:
return {"message": Response.invalid_date(each)}
# Validate ticker and fetch data
try:
quotes = data.get_data_google(ticker)
except Exception:
return {"message": Response.data_notfound(ticker)}
# Return price data for one day
if len(dates)==1:
date = dates[0]
try:
quote = quotes.loc[date]
except KeyError:
return {"message": Response.no_data_for_date(date)}
return {"message": Response.historical_price(
ticker, date, quote['Open'], quote['High'], quote['Low'], quote['Close'], int(quote['Volume']))}
# If 2 dates are entered, returned the range during the given period
elif len(dates)==2:
dates = sorted(dates)
start, end = dates[0], dates[1]
quotes = quotes.loc[start:end]
high = round(quotes['High'].max(),2)
low = round(quotes['Low'].min(),2)
return {"message": Response.historical_range(ticker, start, end, high, low)}
else:
return {"message": Response.too_many_dates(ticker)}
def create_series(ticker):
time_ago = datetime.datetime.today().date() - relativedelta(months=12)
ticker_data = web.get_data_google(ticker,
time_ago)['Close'].pct_change().dropna()
ticker_data_len = len(ticker_data)
x = [0] * 17
y = [0] * 17
x_test = [0] * 17
y_test = [0] * 17
a = 0
b = 6
for i in range(0, 17):
x[i] = ticker_data[a:b]
y[i] = ticker_data[b]
a = b
b = a + 6
for i in range(0, 17):
x_test[i] = ticker_data[a:b]
y_test[i] = ticker_data[b]
a = b
b = a + 6
return y, x, y_test, x_test
def get_symbol_returns_from_yahoo(symbol, start=None, end=None):
#从雅虎或者谷歌获取数据会报错，雅虎谷歌更改了接口
"""
Wrapper for pandas.io.data.get_data_yahoo().
Retrieves prices for symbol from yahoo and computes returns
based on adjusted closing prices.
Parameters
----------
symbol : str
Symbol name to load, e.g. 'SPY'
start : pandas.Timestamp compatible, optional
Start date of time period to retrieve
end : pandas.Timestamp compatible, optional
End date of time period to retrieve
Returns
-------
pandas.DataFrame
Returns of symbol in requested period.
"""
try:
px = web.get_data_yahoo(symbol, start=start, end=end)
px['date'] = pd.to_datetime(px['date'])
px.set_index('date', drop=False, inplace=True)
rets = px[['adjclose']].pct_change().dropna()
except Exception as e:
warnings.warn(
'Yahoo Finance read failed: {}, falling back to Google'.format(e),
UserWarning)
px = web.get_data_google(symbol, start=start, end=end)
rets = px[['Close']].pct_change().dropna()
rets.index = rets.index.tz_localize("UTC")
rets.columns = [symbol]
return rets
def test_get_goog_volume(self):
for locale in self.locales:
with tm.set_locale(locale):
df = web.get_data_google('GOOG').sort_index()
self.assertEqual(df.Volume.ix['OCT-08-2010'], 2863473)
def test_unicode_date(self):
#GH8967
data = web.get_data_google('F', start='JAN-01-10', end='JAN-27-13')
self.assertEquals(data.index.name, 'Date')
def test_bad_retry_count(self):
with pytest.raises(ValueError):
web.get_data_google('F', retry_count=-1)
def test_get_goog_volume(self):
for locale in self.locales:
with tm.set_locale(locale):
df = web.get_data_google('GOOG').sort_index()
self.assertEqual(df.Volume.ix['JAN-02-2015'], 1446662)
def test_bad_retry_count(self):
with tm.assertRaises(ValueError):
web.get_data_google('F', retry_count = -1)
def test_get_multi_all_invalid(self):
with warnings.catch_warnings(record=True):
sl = ['INVALID', 'INVALID2', 'INVALID3']
with pytest.raises(RemoteDataError):
web.get_data_google(sl, '2012')
# -*- coding: utf-8 -*- """ Name : c4_03_get_stock_data_google.py Book : Python for Finance (2nd ed.) Publisher: Packt Publishing Ltd. Author : Yuxing Yan Date : 6/6/2017 email : [email protected] [email protected] """ import pandas_datareader.data as getData df = getData.get_data_google("IBM") print(df.head())
def test_bad_retry_count(self):
with tm.assertRaises(ValueError):
web.get_data_google('F', retry_count=-1)
from pandas_datareader import data
import pymc3 as pm
import matplotlib.pyplot as plt
import numpy as np
returns = data.get_data_google('SPY', start='2008-5-1',
end='2009-12-1')['Close'].pct_change()
print(returns)
with pm.Model() as sp500_model:
nu = pm.Exponential('nu', 1. / 10, testval=5.)
sigma = pm.Exponential('sigma', 1. / .02, testval=.1)
s = pm.GaussianRandomWalk('s', sigma**-2, shape=len(returns))
volatility_process = pm.Deterministic('volatility_process',
pm.math.exp(-2 * s))
r = pm.StudentT('r', nu, lam=volatility_process, observed=returns)
with sp500_model:
trace = pm.sample(2000)
pm.traceplot(trace, [nu, sigma])
fig, ax = plt.subplots(figsize=(15, 8))
returns.plot(ax=ax)
ax.plot(returns.index, 1 / np.exp(trace['s', ::5].T), 'r', alpha=.03)
ax.set(title='volatility_process', xlabel='time', ylabel='volatility')
ax.legend(['S&P500', 'stochastic volatility process'])
plt.show()
import pandas as pd
pd.core.common.is_list_like = pd.api.types.is_list_like
import pandas_datareader.data as dataRetrieve
import datetime
beg_date = datetime.datetime(2012, 1, 5)
end_date = datetime.datetime(2012, 12, 1)
df = dataRetrieve.get_data_google('AAPL', beg_date, end_date) # always worth trying both yahoo and google in case one fails
print(df.head())
import datetime as dt
import sys
import numpy as np
import pandas as pd
import pandas_datareader.data as web
import matplotlib.pyplot as plt
from arch import arch_model
start = dt.datetime(2000, 1, 1)
end = dt.datetime(2017, 1, 1)
sp500 = web.get_data_google('SPY', start=start, end=end)
returns = 100 * sp500['Close'].pct_change().dropna()
returns.plot()
plt.show()
model = arch_model(returns, vol='Garch', p=1, o=0, q=1, dist='Normal')
results = model.fit()
print(results.summary())
forecasts = results.forecast(horizon=30, method='simulation')
sims = forecasts.simulations
lines = plt.plot(sims.values[-1, ::30].T, alpha=0.33)
lines[0].set_label('Simulated paths')
plt.plot()
print(np.percentile(sims.values[-1, 30].T, 5))
plt.hist(sims.values[-1, 30], bins=50)
plt.title('Distribution of Returns')
features_indiv[0, 6] += 1
i += 1
#计算余弦距离确定该文本所属分组
dist1 = pdist(np.vstack([features_indiv, proArray]), 'cosine')
dist2 = pdist(np.vstack([features_indiv, nproArray]), 'cosine')
if dist1 > dist2:
Polarity[t, 0] += Polarity_init * 1.3
else:
Polarity[t, 0] += Polarity_init
k += 1
Polarity[t, 0] = Polarity[t, 0] / vol
t += 1
##获取公司股票信息并绘制相关折线图
#获取沃尔玛股票信息
WMT = dt.get_data_google('wmt', start='2015-12-31', end='2018-01-01')
print WMT.head()
WMT.to_csv('walmart.csv')
#绘制折线图
style.use('ggplot')
plt.rcParams['axes.unicode_minus'] = False #用来正常显示负号
df = pd.read_csv('walmart.csv', index_col='Date', parse_dates=True)
df['H-L'] = df.High - df.Low
ma = pd.rolling_mean(df.Close, 10)
#股价相关信息折线图
ax1 = plt
ax1.plot(df.Close, label='Walmart')
ax1.plot(ma, label='10MA')
plt.legend()
ax1.xlabel('date')
ax1.ylabel('price')
def _get_nasdaq_csv(self, ticker):
return data.get_data_google(ticker, start='1996-05-06')
def downloadQuotes(tickers, date1=None, date2=None, adjust=True, Verbose=False):
"""
Given a ticker sequence, return historical Yahoo! quotes as a pandas DataFrame.
Parameters
----------
tickers : sequence
A sequence (such as a list) of string tickers. For example:
['aapl', 'msft']
date1 : {datetime.date, tuple}, optional
The first date to grab historical quotes on. For example:
datetime.date(2010, 1, 1) or (2010, 1, 1). By default the first
date is (1900, 1, 1).
date2 : {datetime.date, tuple}, optional
The last date to grab historical quotes on. For example:
datetime.date(2010, 12, 31) or (2010, 12, 31). By default the last
date is 10 days beyond today's date.
adjust : bool, optional
Adjust (default) the open, close, high, and low prices. The
adjustment takes splits and dividends into account such that the
corresponding returns are correct. Volume is already split adjusted
by Yahoo so it is not changed by the value of `adjust`.
Verbose : bool, optional
Print the ticker currently being loaded. By default the tickers are
not printed.
Returns
-------
quotes_df : DataFrame
A pandas dataframe is returned. In order, the axes contain: dates,
quotes (adjusted close). The elements along the item axis depend on the value
of `adjust`. When `adjust` is False, the items are
['open', 'close', 'high', 'low', 'volume', 'adjclose']
When adjust is true (default), the adjusted close ('adjclose') is
not included. The dates are datetime.date objects.
Examples
--------
items = ['Adj Close']
date1 = '2012-01-01'
date2 = datetime.date.today()
ticker = 'GOOGL'
data = get_data_yahoo(ticker, start = date1, end = date2)[items]
dates = data.index
data.columns = [ticker]
ticker = 'AMZN'
data2 = get_data_yahoo(ticker, start = date1, end = date2)[items]
dates2 = data2.index
data2.columns = [ticker]
data = data.join(data2, how='outer')
data.sort_index( axis=0, inplace=True )
data.tail()
GOOGL AMZN
Date
2014-04-07 540.63 317.76
2014-04-08 557.51 327.07
2014-04-09 567.04 331.81
2014-04-10 546.69 317.11
2014-04-11 537.76 311.73
"""
from time import sleep
from matplotlib.finance import *
#from la.external.matplotlib import quotes_historical_yahoo
import pandas as pd
from pandas_datareader.data import DataReader, get_data_yahoo, get_data_google
##from pandas.io.data import DataReader
##from pandas.io.data import get_data_yahoo, get_data_google
#import la
if date1 is None:
date1 = datetime.date(1900, 1, 1)
if date2 is None:
date2 = datetime.date.today() + datetime.timedelta(+10)
#quotes_df = None
#lar = None
items = ['Adj Close','volume']
items_to_drop = ['Open', 'High', 'Low', 'Close']
google_items = ['Close']
if Verbose:
print "Load data"
i=0
number_tries = 0
re_tries = 0
for itick, ticker in enumerate(tickers):
if Verbose:
print "\t" + ticker + " ",
data = []
dates = []
#number_tries = 0
##try:
# read in dataframe containing adjusted close quotes for a ticker in the list
#print "number_tries = ", number_tries
if number_tries < 11:
#print "number_tries = ", number_tries, " trying with yahoo"
'''
try:
data = get_data_yahoo(ticker, start = date1, end = date2)[items,:]
number_tries = 0
except:
pass
'''
print "items = ", items
data = get_data_yahoo(ticker, start = date1, end = date2)
print "data = ", data
print "type(data) = ", type(data)
data = data['Adj Close']
#data = data.drop(items_to_drop)
else:
#print "number_tries = ", number_tries, " trying with google"
print " ...retrieving quotes using google"
try:
data = get_data_google(ticker, start = date1, end = date2)[google_items]
number_tries = 0
except:
pass
#print ' data = ', data
dates = data.index
#print ' dates = ', dates
dates = [d.to_datetime() for d in dates]
data.columns = [ticker]
#print ' ticker = ', [ticker]
#print ' data.columns = ', data.columns
if Verbose:
print i," of ",len(tickers)," ticker ",ticker," has ",data.shape[0]," quotes"
if itick-re_tries == 0:
#print " creating dataframe..."
quotes_df = data
else:
#print " joining to dataframe..."
quotes_df = quotes_df.join( data, how='outer' )
#print " joined to dataframe..."
i += 1
'''
except:
print "could not get quotes for ", ticker, " will try again and again.", number_tries
sleep(3)
number_tries += 1
re_tries += 1
if number_tries < 20:
tickers[itick+1:itick+1] = [ticker]
'''
print "number of tickers successfully processed = ", i
if i > 0 :
quotes_df.sort_index( axis=0, inplace=True )
return quotes_df
else :
# return empty DataFrame
quotes_df = pd.DataFrame( [0,0], ['Dates',date2])
quotes_df.columns = ['None']
return quotes_df
import pandas as pd
from datetime import datetime
from pandas_datareader import data
start = datetime(2017, 1, 1)
end = datetime(2017, 4, 30)
df = data.get_data_google("KRX:KOSPI", start, end)
df.head()
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pandas_datareader import data as dr
import datetime
import seaborn
end_date=datetime.datetime.now()
start_date=end_date-datetime.timedelta(days=365)
data=dr.get_data_google('AMD',start=start_date,end=end_date)
print(data.head())
from pandas_datareader import data
import pandas as pd
import numpy as np
import talib as ta
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import matplotlib.gridspec as gridspec
from matplotlib.dates import date2num
from matplotlib.finance import candlestick_ohlc as candlestick
import datetime
ticker = 'OPK'
# Download sample data
sec_id = data.get_data_google(ticker, '2014-06-01')
# Data for matplotlib finance plot
sec_id_ochl = np.array(
pd.DataFrame({
'0': date2num(sec_id.index.to_pydatetime()),
'1': sec_id.Open,
'2': sec_id.Close,
'3': sec_id.High,
'4': sec_id.Low
}))
# Technical Analysis
SMA_FAST = 50
SMA_SLOW = 200
RSI_PERIOD = 14
RSI_AVG_PERIOD = 15
def test_get_multi_invalid(self):
with warnings.catch_warnings(record=True):
sl = ['AAPL', 'AMZN', 'INVALID']
pan = web.get_data_google(sl, '2012')
assert 'INVALID' in pan.minor_axis
df.sum()
df.sum(axis=1)
df.mean(axis=1,skipna=False)
df.mean(axis=1)
df.idxmax()
df.cumsum()
df.cumsum(axis=1)
df.describe()
obj = Series(['a','a','b','c'] * 4)
obj.describe()
obj
%run Dataframe.py
from pandas_datareader import data
all_data = {}
for ticker in ['AAPL','IBM','MSFT','GOOG']:
all_data[ticker] = data.get_data_google(ticker,'1/1/2000','1/1/2010')
price = DataFrame({tic: data['Adj Close'] for tic, data in all_data.iteriterms()})
price = DataFrame({tic: data['Adj Close'] for tic, data in all_data.iteritems()})
all_data.iteritems()
a,b in for a, b in all_data.iteritems()
a,b for a, b in all_data.iteritems()
[(a,b) for a, b in all_data.iteritems()]
price = DataFrame({tic: data['Close'] for tic, data in all_data.iteriterms()})
price = DataFrame({tic: data['Close'] for tic, data in all_data.iteritems()})
volume = DataFrame({tic: data['Volumn'] for tic, data in all_data.iteritems()})
volume = DataFrame({tic: data['Volume'] for tic, data in all_data.iteritems()})
returns = price.pct_change()
returns.tail()
returns.MSFT.corr(returns.IBM)
returns.MSFT.cov(returns.IBM)
returns.corr()
def test_unicode_date(self):
# see gh-8967
data = web.get_data_google('F', start='JAN-01-10', end='JAN-27-13')
assert data.index.name == 'Date'
def test_get_goog_volume(self):
for locale in self.locales:
with tm.set_locale(locale):
df = web.get_data_google('GOOG').sort_index()
self.assertEqual(df.Volume.ix['OCT-08-2010'], 2863473)
def test_unicode_date(self):
#GH8967
data = web.get_data_google('F', start='JAN-01-10', end='JAN-27-13')
self.assertEquals(data.index.name, 'Date')
Created on Mon Jun 12 16:07:55 2017
@author: Varun Divakar
"""
from pandas_datareader import data as web
import numpy as np
import pandas as pd
from sklearn import mixture as mix
import seaborn as sns
import matplotlib.pyplot as plt
import talib as ta
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
df = web.get_data_google('SPY', start='2015-01-01', end='2016-08-01')
df = df[['Open', 'High', 'Low', 'Close']]
n = 10
t = 0.8
split = int(t * len(df))
df['high'] = df['High'].shift(1)
df['low'] = df['Low'].shift(1)
df['close'] = df['Close'].shift(1)
df['RSI'] = ta.RSI(np.array(df['close']), timeperiod=n)
df['SMA'] = df['close'].rolling(window=n).mean()
df['Corr'] = df['SMA'].rolling(window=n).corr(df['close'])
df['SAR']=ta.SAR(np.array(df['high']),np.array(df['low']),\
0.2,0.2)
df['ADX']=ta.ADX(np.array(df['high']),np.array(df['low']),\
def test_get_multi_invalid(self):
sl = ['AAPL', 'AMZN', 'INVALID']
pan = web.get_data_google(sl, '2012')
self.assertIn('INVALID', pan.minor_axis)
def _get(cls, symbol, date_from, date_to):
# FIXME: temporary fix
from pandas_datareader.google.daily import GoogleDailyReader
GoogleDailyReader.url = 'http://finance.google.com/finance/historical'
return get_data_google(symbol, date_from, date_to)
def _mine_from_url(self, url):
html = BeautifulSoup(requests.get(url, headers=self.HEADERS).text, "html5lib")
self.logger.info('searching for table with class - {}'.format(self.PRICING_TABLE_CLASS))
table = html.find('div', {'class': 'genTable'})
if not table or not table.text or not table.tbody or not table.tbody.text or not table.tbody.find_all('tr'):
self.logger.warn('did not find anything for url - {}; skipping'.format(url))
return []
entries = []
rows = table.tbody.find_all('tr')
for i, row in enumerate(rows):
columns = row.find_all('td')
if not columns:
self.logger.warn('skipping entry #{} - no columns found'.format(i))
continue
company = columns[0].a.text
company_url = columns[0].a.attrs['href']
symbol = columns[1].a.text
market = columns[2].text
price = columns[3].text
shares = columns[4].text
amount = columns[5].text
date = columns[6].text
price_num = float(re.sub('[^\d\.]+', '', price))
self.logger.info('Mining entry #{} for company - {}'.format(i, company))
try:
ipo_data = self._mine_company_url(company_url)
except Exception as e:
self.logger.exception('failed fetching company data for - #{} - {}'.format(i, company))
ipo_data = {}
try:
end_date = dateutil.parser.parse(date) + timedelta(days=1)
trade_data = web.get_data_google(symbol, date, end_date.strftime('%m/%d/%Y'))
first_day_open = trade_data.ix[0].Open
first_day_close = trade_data.ix[0].Close
first_day_change = float((first_day_close - first_day_open) / first_day_open * 100) if trade_data is not None else None
first_day_ipo_change = float((first_day_close - price_num) / price_num * 100) if trade_data is not None else None
first_day_positive = first_day_change > 0 if first_day_change is not None else None
trade_data = json.loads(trade_data.to_json())
except Exception as e:
self.logger.exception('failed fetching finance data for - #{} - {}'.format(i, company))
trade_data = {}
first_day_change = None
first_day_positive = None
first_day_open = None
first_day_close = None
first_day_ipo_change = None
entries.append({
'company': company,
'company_url': company_url,
'symbol': symbol,
'market': market,
'price': price,
'shares': shares,
'amount': amount,
'date': date,
'ipo_data': ipo_data,
'trade_data': trade_data,
'first_day_market_change': first_day_change,
'first_day_market_positive': first_day_positive,
'first_day_open': first_day_open,
'first_day_close': first_day_close,
'price_num': price_num,
'first_day_ipo_change': first_day_ipo_change
})
return entries
def test_get_multi_invalid(self):
sl = ['AAPL', 'AMZN', 'INVALID']
data = web.get_data_google(sl, '2012')
assert 'INVALID' in data.columns.levels[1]
def test_get_goog_volume(self):
for locale in self.locales:
with tm.set_locale(locale):
df = web.get_data_google('GOOG').sort_index()
self.assertEqual(df.Volume.ix['JAN-02-2015'], 1446662)
def test_get_multi_all_invalid(self):
sl = ['INVALID', 'INVALID2', 'INVALID3']
with pytest.raises(RemoteDataError):
web.get_data_google(sl, '2012')
def test_get_multi_invalid(self):
sl = ['AAPL', 'AMZN', 'INVALID']
pan = web.get_data_google(sl, '2012')
self.assertIn('INVALID', pan.minor_axis)
def downloadQuotes(tickers,
date1=None,
date2=None,
adjust=True,
Verbose=False):
"""
Given a ticker sequence, return historical Yahoo! quotes as a pandas DataFrame.
Parameters
----------
tickers : sequence
A sequence (such as a list) of string tickers. For example:
['aapl', 'msft']
date1 : {datetime.date, tuple}, optional
The first date to grab historical quotes on. For example:
datetime.date(2010, 1, 1) or (2010, 1, 1). By default the first
date is (1900, 1, 1).
date2 : {datetime.date, tuple}, optional
The last date to grab historical quotes on. For example:
datetime.date(2010, 12, 31) or (2010, 12, 31). By default the last
date is 10 days beyond today's date.
adjust : bool, optional
Adjust (default) the open, close, high, and low prices. The
adjustment takes splits and dividends into account such that the
corresponding returns are correct. Volume is already split adjusted
by Yahoo so it is not changed by the value of `adjust`.
Verbose : bool, optional
Print the ticker currently being loaded. By default the tickers are
not printed.
Returns
-------
quotes_df : DataFrame
A pandas dataframe is returned. In order, the axes contain: dates,
quotes (adjusted close). The elements along the item axis depend on the value
of `adjust`. When `adjust` is False, the items are
['open', 'close', 'high', 'low', 'volume', 'adjclose']
When adjust is true (default), the adjusted close ('adjclose') is
not included. The dates are datetime.date objects.
Examples
--------
items = ['Adj Close']
date1 = '2012-01-01'
date2 = datetime.date.today()
ticker = 'GOOGL'
data = get_data_yahoo(ticker, start = date1, end = date2)[items]
dates = data.index
data.columns = [ticker]
ticker = 'AMZN'
data2 = get_data_yahoo(ticker, start = date1, end = date2)[items]
dates2 = data2.index
data2.columns = [ticker]
data = data.join(data2, how='outer')
data.sort_index( axis=0, inplace=True )
data.tail()
GOOGL AMZN
Date
2014-04-07 540.63 317.76
2014-04-08 557.51 327.07
2014-04-09 567.04 331.81
2014-04-10 546.69 317.11
2014-04-11 537.76 311.73
"""
from time import sleep
from matplotlib.finance import *
#from la.external.matplotlib import quotes_historical_yahoo
import pandas as pd
from pandas_datareader.data import DataReader, get_data_yahoo, get_data_google
##from pandas.io.data import DataReader
##from pandas.io.data import get_data_yahoo, get_data_google
#import la
if date1 is None:
date1 = datetime.date(1900, 1, 1)
if date2 is None:
date2 = datetime.date.today() + datetime.timedelta(+10)
#quotes_df = None
#lar = None
items = ['Adj Close', 'volume']
items_to_drop = ['Open', 'High', 'Low', 'Close']
google_items = ['Close']
if Verbose:
print "Load data"
i = 0
number_tries = 0
re_tries = 0
for itick, ticker in enumerate(tickers):
if Verbose:
print "\t" + ticker + " ",
data = []
dates = []
#number_tries = 0
##try:
# read in dataframe containing adjusted close quotes for a ticker in the list
#print "number_tries = ", number_tries
if number_tries < 11:
#print "number_tries = ", number_tries, " trying with yahoo"
'''
try:
data = get_data_yahoo(ticker, start = date1, end = date2)[items,:]
number_tries = 0
except:
pass
'''
print "items = ", items
data = get_data_yahoo(ticker, start=date1, end=date2)
print "data = ", data
print "type(data) = ", type(data)
data = data['Adj Close']
#data = data.drop(items_to_drop)
else:
#print "number_tries = ", number_tries, " trying with google"
print " ...retrieving quotes using google"
try:
data = get_data_google(ticker, start=date1,
end=date2)[google_items]
number_tries = 0
except:
pass
#print ' data = ', data
dates = data.index
#print ' dates = ', dates
dates = [d.to_datetime() for d in dates]
data.columns = [ticker]
#print ' ticker = ', [ticker]
#print ' data.columns = ', data.columns
if Verbose:
print i, " of ", len(
tickers), " ticker ", ticker, " has ", data.shape[0], " quotes"
if itick - re_tries == 0:
#print " creating dataframe..."
quotes_df = data
else:
#print " joining to dataframe..."
quotes_df = quotes_df.join(data, how='outer')
#print " joined to dataframe..."
i += 1
'''
except:
print "could not get quotes for ", ticker, " will try again and again.", number_tries
sleep(3)
number_tries += 1
re_tries += 1
if number_tries < 20:
tickers[itick+1:itick+1] = [ticker]
'''
print "number of tickers successfully processed = ", i
if i > 0:
quotes_df.sort_index(axis=0, inplace=True)
return quotes_df
else:
# return empty DataFrame
quotes_df = pd.DataFrame([0, 0], ['Dates', date2])
quotes_df.columns = ['None']
return quotes_df