def main():
symbols = ['AAPL', 'MSFT', 'BRK-A']
# Specifically chosen to include the AAPL split on June 9, 2014.
for symbol in symbols:
data = DataReader(
symbol,
'yahoo',
start='2014-03-01',
end='2014-09-01',
)
data.rename(
columns={
'Open': 'open',
'High': 'high',
'Low': 'low',
'Close': 'close',
'Volume': 'volume',
},
inplace=True,
)
del data['Adj Close']
dest = join(here, symbol + '.csv')
print("Writing %s -> %s" % (symbol, dest))
data.to_csv(dest, index_label='day')
def main():
symbols = ["AAPL", "MSFT", "BRK-A"]
# Specifically chosen to include the AAPL split on June 9, 2014.
for symbol in symbols:
data = DataReader(
symbol,
"yahoo",
start="2014-03-01",
end="2014-09-01",
)
data.rename(
columns={
"Open": "open",
"High": "high",
"Low": "low",
"Close": "close",
"Volume": "volume",
},
inplace=True,
)
del data["Adj Close"]
dest = join(here, symbol + ".csv")
print("Writing %s -> %s" % (symbol, dest))
data.to_csv(dest, index_label="day")
def p03_AAPL(tomtom):
try:
DAX = DataReader('AAPL','yahoo',start = '01/01/2000')
DAX.to_csv(tomtom.get_tmp_name('p03_AAPL.csv'))
except RemoteDataError:
print('Error while reading data, revert to stored file in example_data')
shutil.copy('example_data/p03_AAPL.csv', 'temp')
def get_stock(stock, beg, end, write=False, load=False):
""" return df from yfinance """
if load == True: return pd.read_csv(f'./{stock}.csv')
ret_df = DataReader(stock, 'yahoo', beg, end)
if write: ret_df.to_csv(f'./{stock}.csv')
return ret_df
def get_outperformance(ticker_list,
idx,
start=datetime(1993, 1, 1),
end=datetime(2019, 7, 9)):
errors = []
complete = len(ticker_list)
done = 0
for ticker in ticker_list:
try:
prices = DataReader(ticker, 'yahoo', start, end)
yr_ret = list(prices['Close'].pct_change(252).dropna())
length = len(prices)
for i in range(length - len(yr_ret)):
yr_ret.append(nan)
tmp_idx = idx.loc[prices.index]
prices['yr_ret'] = yr_ret
prices['outperformance'] = (
(prices['yr_ret'] > tmp_idx).astype(int) -
(prices['yr_ret'] < -tmp_idx).astype(int))
prices['magnitude'] = abs(prices['yr-ret']) - abs(tmp_idx)
st = str(min(prices.index))[:-9]
en = str(max(prices.index))[:-9]
file = ticker + '_' + st + '_' + en + '.csv'
prices.to_csv(file)
except:
errors.append(ticker)
done += 1
print('\r' + '|' + ((u'\u2588') * (int(
(done + 1) / complete * 100))).ljust(99) +
'| {0:.2f}%'.format(min((done + 1) / complete * 100, 100)),
end='')
return errors
def addCustomColumns(df, market_upd=False):
start = datetime.date(
int(df.index.get_level_values('date')[0]) - 10,
int(df['month'].values[0]), 1)
end_date_ls = [
int(d) for d in datetime.date.today().strftime('%Y-%m-%d').split("-")
]
end = datetime.date(end_date_ls[0], end_date_ls[1], end_date_ls[2])
try:
url = "https://www.quandl.com/api/v1/datasets/WIKI/{0}.csv?column=4&sort_order=asc&trim_start={1}&trim_end={2}".format(
df.index.get_level_values('ticker')[0], start, end)
qr = pd.read_csv(url)
qr['Date'] = qr['Date'].astype('datetime64[ns]')
# quotes = DataReader(df.index.get_level_values('ticker')[0], 'yahoo', start, end, pause=1)['Close']
# quotes = DataReader(df.index.get_level_values('ticker')[0], 'yahoo', start, end, pause=1)['Close']
except:
print("Could not read time series data for %s" %
df.index.get_level_values('ticker')[0])
exc_type, exc_obj, exc_tb = sys.exc_info()
app.logger.info(
"Could not read time series data for {3}: {0}, {1}, {2}".format(
exc_type, exc_tb.tb_lineno, exc_obj,
df.index.get_level_values('ticker')[0]))
raise
df = addBasicCustomCols(df, qr)
df = addGrowthCustomCols(df, qr)
df = addTimelineCustomCols(df, qr)
pdb.set_trace()
if market_upd:
# market = DataReader(".INX", 'google', start, end, pause=1)['Close']
market = DataReader('^GSPC', 'yahoo', start, end, pause=1)['Close']
market.to_csv(
'/home/ubuntu/workspace/finance/app/static/docs/market.csv')
quotes = pd.DataFrame(quotes)
market.columns = ['Date', 'market']
market.set_index('Date')
quotes['market'] = market
else:
market = pd.read_csv(
'/home/ubuntu/workspace/finance/app/static/docs/market.csv')
market.columns = ['Date', 'market']
market['Date'] = market['Date'].apply(pd.to_datetime)
market = market.set_index('Date')
qr = pd.merge(qr.set_index('Date'),
market,
left_index=True,
right_index=True)
df = calcBetas(df, qr)
'''
Still need to do:
'enterpriseToEbitda'
'ebitdaMargins'
'ebitda',
'shortRatio'
'''
return df
def load_data(*func_codes):
datas = []
for code in func_codes:
if os.path.exists(f"{code}.csv"):
data = pd.read_csv(f"{code}.csv")
else:
data = DataReader(f"{code}.SZ", "yahoo", start, end)
data.to_csv(f'{code}.csv')
datas.append(data)
return datas
def load_data():
if os.path.exists('000001.csv'):
data_ss = pd.read_csv('000001.csv')
data_kdxf = pd.read_csv('002230.csv')
else:
# 上证综指
data_ss = DataReader("000001.SS", "yahoo", start, end)
# 002230 科大讯飞 深证
data_kdxf = DataReader("002230.SZ", "yahoo", start, end)
data_ss.to_csv('000001.csv')
data_kdxf.to_csv('002230.csv')
return data_ss, data_kdxf
def getcsv(self):
'''
pandas DataReaderを利用してYahooFinanceから過去一年ぶんの株価データを抽出、
csvファイル化する関数
'''
if os.path.exists(self.basedir):
end = datetime.now()
start = datetime(end.year - 1, end.month, end.day)
for index in INDEX_LIST:
filename = self.basedir + index + ".csv"
price = DataReader(index, 'yahoo', start, end)
price.to_csv(filename)
def load_data():
if os.path.exists('000001.csv'):
data_ss = pd.read_csv('000001.csv')
data_tlz = pd.read_csv('300005.csv')
else:
# 上证综指
data_ss = DataReader("000001.SS", "yahoo", start, end)
# 300005 探路者股票 深证
data_tlz = DataReader("300005.SZ", "yahoo", start, end)
data_ss.to_csv('000001.csv')
data_tlz.to_csv('300005.csv')
return data_ss, data_tlz
def _load_raw_yahoo_data(indexes=None, stocks=None, start=None, end=None):
"""Load closing prices from yahoo finance.
:Optional:
indexes : dict (Default: {'SPX': '^GSPC'})
Financial indexes to load.
stocks : list (Default: ['AAPL', 'GE', 'IBM', 'MSFT',
'XOM', 'AA', 'JNJ', 'PEP', 'KO'])
Stock closing prices to load.
start : datetime (Default: datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc))
Retrieve prices from start date on.
end : datetime (Default: datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc))
Retrieve prices until end date.
:Note:
This is based on code presented in a talk by Wes McKinney:
http://wesmckinney.com/files/20111017/notebook_output.pdf
"""
assert indexes is not None or stocks is not None, """
must specify stocks or indexes"""
if start is None:
start = pd.datetime(1990, 1, 1, 0, 0, 0, 0, pytz.utc)
if start is not None and end is not None:
assert start < end, "start date is later than end date."
data = OrderedDict()
if stocks is not None:
for stock in stocks:
print(stock)
stock_pathsafe = stock.replace(os.path.sep, '--')
cache_filename = "{stock}-{start}-{end}.csv".format(
stock=stock_pathsafe,
start=start,
end=end).replace(':', '-')
cache_filepath = get_cache_filepath(cache_filename)
if os.path.exists(cache_filepath):
stkd = pd.DataFrame.from_csv(cache_filepath)
else:
stkd = DataReader(stock, 'yahoo', start, end).sort_index()
stkd.to_csv(cache_filepath)
data[stock] = stkd
if indexes is not None:
for name, ticker in iteritems(indexes):
print(name)
stkd = DataReader(ticker, 'yahoo', start, end).sort_index()
data[name] = stkd
return data
def stocks_yahoo():
if not os.path.exists('stocks_dfs'):
os.makedirs('stocks_dfs')
start = datetime(2017,12,1)
end = datetime(2020,12,1)
for ticker in tickers:
print(ticker)
if not os.path.exists('stocks_dfs/{}.csv'.format(ticker)) and ticker not in problems:
df = DataReader(ticker,'yahoo',start,end)
df.to_csv('stocks_dfs/{}.csv'.format(ticker))
def _load_raw_yahoo_data(indexes=None, stocks=None, start=None, end=None):
"""Load closing prices from yahoo finance.
:Optional:
indexes : dict (Default: {'SPX': 'SPY'})
Financial indexes to load.
stocks : list (Default: ['AAPL', 'GE', 'IBM', 'MSFT',
'XOM', 'AA', 'JNJ', 'PEP', 'KO'])
Stock closing prices to load.
start : datetime (Default: datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc))
Retrieve prices from start date on.
end : datetime (Default: datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc))
Retrieve prices until end date.
:Note:
This is based on code presented in a talk by Wes McKinney:
http://wesmckinney.com/files/20111017/notebook_output.pdf
"""
assert indexes is not None or stocks is not None, """
must specify stocks or indexes"""
if start is None:
start = pd.datetime(1990, 1, 1, 0, 0, 0, 0, pytz.utc)
if start is not None and end is not None:
assert start < end, "start date is later than end date."
data = OrderedDict()
if stocks is not None:
for stock in stocks:
logger.info('Loading stock: {}'.format(stock))
stock_pathsafe = stock.replace(os.path.sep, '--')
cache_filename = "{stock}-{start}-{end}.csv".format(
stock=stock_pathsafe,
start=start,
end=end).replace(':', '-')
cache_filepath = get_cache_filepath(cache_filename)
if os.path.exists(cache_filepath):
stkd = pd.DataFrame.from_csv(cache_filepath)
else:
stkd = DataReader(stock, 'yahoo', start, end).sort_index()
stkd.to_csv(cache_filepath)
data[stock] = stkd
if indexes is not None:
for name, ticker in iteritems(indexes):
logger.info('Loading index: {} ({})'.format(name, ticker))
stkd = DataReader(ticker, 'yahoo', start, end).sort_index()
data[name] = stkd
return data
def HistoricalData(symbol: str,
start: str,
end=datetime.today().strftime("%Y-%m-%d")):
with open("./apikey", "r") as f:
key = f.readline()
data = DataReader(symbol, "av-daily-adjusted", start, end, api_key=key)
# adjusted close price and dates
data.to_csv("./data/{}.csv".format(symbol))
price = list(data["adjusted close"]) # adjusted close price
with open("./data/{}.csv".format(symbol), "r") as f:
dates = [
line[:10] for line in f.readlines()[1:]
] # get date of each price (ignore first line; column description)
return {"price": price, "dates": dates}
def load_data():
if os.path.exists('000001.csv'):
data_ss = pd.read_csv('000001.csv')
else:
# 上证综指
data_ss = DataReader("000001.SS", "yahoo", start, end)
data_ss.to_csv('000001.csv')
if os.path.exists('000002.csv'):
data_tlz = pd.read_csv('000002.csv')
else:
# A股指数
data_tlz = DataReader("000002.SS", "yahoo", start, end)
data_tlz.to_csv('000002.csv')
return data_ss, data_tlz
def download_stock(stock_id="", start_date="", period=1, log=True):
""" stock_id --> ex: AAPL (str)
start_date --> ex: 2020-01-19 (str) """
if (stock_id == "") & (start_date == ""):
stock_id = input("Enter stock ID (ex: AAPL) = ")
start_date = input("Enter start date (ex: 2020-01-19) = ")
else:
pass
stock = DataReader(stock_id, "yahoo", start_date)
csv = "../Database/" + stock_id + ".csv"
stock.to_csv(csv)
uploaded = []
data = []
file = open(csv, "r")
info = file.readlines()
for x in info:
data.append(x)
data[len(data) - 1] = data[len(data) - 1].replace("-", ",")
del data[
0] # delete the line: "Date,Open,High,Low,Close,Adj Close,Volume" on the .csv file
raw = []
count = 0
print("\nReading stock data from [", csv, "]")
if log == True:
loop = tqdm.tqdm(total=int(len(data) / period),
position=0,
leave=False)
for i in range(0, len(data), period):
line = data[i].split(",")
raw.append(float(line[CLOSE]))
count += 1
if log == True:
loop.set_description('Reading stock data...'.format(len(data)))
loop.update(1)
time.sleep(0.001)
else:
pass
print("\n\nUploaded stock data successfully!")
return raw, stock_id
def load_data():
"""
加载数据集
:return:
"""
data_info_dict = {}
for stock_code in spec_stock_code_list:
if not os.path.exists(f'{stock_code.split(".")[0]}.csv'):
# 获取列表中的股票信息
data = DataReader(stock_code,
'yahoo',
start=start_date,
end=end_date)
# 保存为本地的csv文件
data.to_csv(f'{stock_code.split(".")[0]}.csv')
data_df = pd.read_csv(f'{stock_code.split(".")[0]}.csv')
data_info_dict[stock_code.split('.')[0]] = data_df
return data_info_dict
end = date(2017, 11, 06)
# DataReader is a function to import, there are different sources available to import data
# such as ggogle fin, yahoo fin,fred, Oanda(for exchange rates)
# for eg Importing FB data from goolge
stockFb = DataReader('fb', 'google', start, end)
type(stockFb)
# DataReader returns a pandas data frame object
stockFb.head()
stockFb.info()
# from yahoo
stockApl = DataReader('AAPL', 'yahoo', start, end)
stockApl.head()
stockApl.info()
#plotting
stockApl['Close'].plot(title='APPLE')
plt.show()
#sp500 from fred up to now
sp500 = DataReader('SP500', 'fred', start)
#note sys date is deafult for end argument
sp500.tail()
sp500.plot(title='SP500')
#saving locally
sp500.to_csv('SP500')
def p03_AAPL(location):
dax = DataReader('AAPL', 'yahoo', start='01/01/2000')
dax.to_csv(work_directory_path(location, 'p03_AAPL.csv'))
return dax
def p03_DAX(location):
dax = DataReader('^GDAXI', 'yahoo', start='01/01/2000')
dax.to_csv(work_directory_path(location, 'p03_DAX.csv'))
return dax
def p03_AAPL(location):
dax = DataReader('AAPL', 'yahoo', start='01/01/2000')
dax.to_csv(work_directory_path(location, 'p03_AAPL.csv'))
return dax
# -*- coding: utf-8 -*- """ @author: [email protected] @site: e-smartdata.org """ import pandas as pd from pandas_datareader.data import DataReader import matplotlib.pyplot as plt import seaborn as sns sns.set() # %% amazon = DataReader('AMZN', 'stooq') amazon.to_csv('data.csv') # %% amazon['Close'].plot() amazon['Close'].plot(alpha=0.5) # %% amazon['Close'].plot(alpha=0.7) amazon.resample('BQ').mean()['Close'].\ plot(color='green', style='--', alpha=0.7) plt.legend(['price', 'quarter average']) # %% shifting fig, ax = plt.subplots(3, sharex=True) amazon['Close'].plot(ax=ax[0])
def p03_DAX(tomtom):
DAX = DataReader('^GDAXI','yahoo',start = '01/01/2000')
DAX.to_csv(tomtom.get_tmp_name('p03_DAX.csv'))
def p03_DAX(tomtom):
DAX = DataReader('^GDAXI', 'yahoo', start='01/01/2000')
DAX.to_csv(tomtom.get_tmp_name('p03_DAX.csv'))
class Prices(object):
"""
Prices gets local or remote data, clean it and gets some statistic from the data.
"""
def __init__(self):
self.__loaded = False
self.data = None
self._volatility = None
self.source = "Yahoo"
#self.roll_volatility = None
def download(self,
code,
start,
end,
downloadPath=None,
source='morningstar'):
self.source = source
Protocol.sendStatus("Data source", source)
if source == "Yahoo":
result = self.downloadYahoo(code, start, end, downloadPath)
if not result:
return self.download(code, start, end, downloadPath)
else:
return result
else:
start = dt.datetime.fromtimestamp(
int(start)) if type(start) == str else start
if start != None:
self.data = DataReader(code,
data_source=source,
start=start,
end=dt.datetime.today())
else:
self.data = DataReader(code,
data_source=source,
end=dt.datetime.today())
self.__loaded = True
if downloadPath != None:
filepath = os.path.join(downloadPath,
code + str(int(end)) + '.csv')
self.data.to_csv(filepath)
return filepath
return None
def downloadYahoo(self, code, start, end, downloadPath):
"""
download take arguments and download from Yahoo! the data, save
them in the given path and returns the csv route.
"""
cookier = urllib.request.HTTPCookieProcessor()
opener = urllib.request.build_opener(cookier)
urllib.request.install_opener(opener)
# cookie and corresponding crumb
_cookie = None
_crumb = None
# headers to fake a user agent
_headers = {
'User-Agent':
'Mozilla/5.0 (X11; U; Linux i686) Gecko/20071127 Firefox/2.0.0.11'
}
# perform a Yahoo financial lookup on SP500
req = urllib.request.Request('https://finance.yahoo.com/quote/^GSPC',
headers=_headers)
f = urllib.request.urlopen(req)
alines = f.read().decode('utf-8')
# extract the crumb from the response
cs = alines.find('CrumbStore')
cr = alines.find('crumb', cs + 10)
cl = alines.find(':', cr + 5)
q1 = alines.find('"', cl + 1)
q2 = alines.find('"', q1 + 1)
_crumb = alines[q1 + 1:q2]
# extract the cookie from cookiejar
for c in cookier.cookiejar:
if c.domain != '.yahoo.com':
continue
if c.name != 'B':
continue
_cookie = c.value
# print the cookie and crumb
#print('Cookie:', _cookie)
#print('Crumb:', _crumb)
# prepare the parameters and the URL
param = dict()
param['period1'] = int(start)
param['period2'] = int(end)
param['interval'] = '1d'
param['events'] = 'history'
param['crumb'] = _crumb
params = urllib.parse.urlencode(param)
url = 'https://query1.finance.yahoo.com/v7/finance/download/{}?{}'.format(
code, params)
req = urllib.request.Request(url, headers=_headers)
# perform the query
# there is no need to enter the cookie here, as it is automatically handled by opener
try:
f = urllib.request.urlopen(req)
except urllib.error.URLError as e:
if hasattr(e, 'code'):
Protocol.sendError("Downloading from Yahoo failded", e.code)
if hasattr(e, 'reason'):
Protocol.sendError("Downloading from Yahoo failded", e.reason)
return False
except urllib.error.HTTPError as e:
if hasattr(e, 'code'):
Protocol.sendError("Downloading from Yahoo failded", e.code)
if hasattr(e, 'reason'):
Protocol.sendError("Downloading from Yahoo failded", e.reason)
return False
#urlopen(req)
alines = f.read().decode('utf-8')
#print(alines)
holder = alines.split('\n')
# generates csv filename
filename = downloadPath + code + str(int(end)) + '.csv'
# creates csv
with open(filename, 'w') as csvfile:
filewriter = csv.writer(csvfile,
delimiter=',',
quotechar='|',
quoting=csv.QUOTE_MINIMAL)
for line in holder:
b = line.split(',')
filewriter.writerow(b)
return filename
def load(self, csv_filepath):
"""
load reads a csv file
"""
try:
self.data = pd.read_csv(csv_filepath)
self.source = "Yahoo"
self.__loaded = True
except Exception:
if csv_filepath == "":
Protocol.sendError("csv path empty")
else:
Protocol.sendError("csv not found", csv_filepath)
def isValidData(self):
"""
isValidData verifies data integrity in csv, if valid use them for calculations.
"""
if self.__loaded:
#TODO check data
return True
else:
return False
def isLoaded(self):
"""
isLoaded verifies if there are loaded data
"""
return self.__loaded
def cleanData(self):
"""
cleanData removes incongruencies in data
"""
#TODO
pass
def getLastPrice(self):
"""
getLastPrice return the last closing price of the loaded data, otherwise return None
"""
if self.isLoaded and self.isValidData():
return self.data["Close"].iloc[-1]
return None
def getPlot(self):
"""
getPlot plots loaded data, saves image in predefines path
"""
if not self.isLoaded:
return
data = self.data
plt.figure(figsize=(20, 10))
# close
plt.plot(data["Date"], data["Close"], "g", linewidth=5)
# high and low
plt.plot(data["Date"],
data["High"],
"r--",
data["Low"],
"b--",
linewidth=2)
# format axes #TODO
#ax.yaxis.set_major_formatter(mticker.FormatStrFormatter('$%1.2f'))
#ax.xaxis.set_major_formatter(mdates.DateFormatter('%d'))
plt.gcf().autofmt_xdate()
plt.grid()
plt.ylabel('Valor $', fontsize=24)
plt.legend(["Close", "High", "Low"], prop={'size': 24})
plt.tick_params(axis='both', which='major', labelsize=25)
filename = TEMP_DATA_PATH + "plot_" + datetime.datetime.now().strftime(
"%y%m%d_%H%M%S") + ".png"
plt.savefig(filename)
return filename
def getPlotDash(self):
if self.source.lower() == "yahoo":
return {'data': [{'x': self.data.Date, 'y': self.data.Close}]}
elif self.source == "morningstar":
return {
'data': [{
'x': self.data.index.get_level_values(1),
'y': self.data.Close
}]
}
def getVolatility(self):
"""
getVolatility evaluate data and retrives its volatility
This method was taken from 'A Review of Volatility and Option Pricing' by Sovan Mitra, Section 3.2
We can calculate the historical volatility (or sigma) of prices X using this
sigma = sqrt(Vx)/sqrt(dt)
where
Vx is the sample variance
Vx = 1/(n-1) * SUM((Xi - MEAN(X))**2)
Xi is calculated in all steps
Xi = ln(X(t_{i})/ X(t_{i-1}))
dt is the interval between to samples, we use one day
dt = 1 day
X(t_{i}) is a sample price.
"""
if self._volatility == None:
X = self.data["Close"]
self._volatility = np.diff(np.log(X)).std()
return self._volatility
def p03_DAX(location):
dax = DataReader('^GDAXI', 'yahoo', start='01/01/2000')
dax.to_csv(work_directory_path(location, 'p03_DAX.csv'))
return dax
def p03_AAPL(tomtom):
DAX = DataReader('AAPL','yahoo',start = '01/01/2000')
DAX.to_csv(tomtom.get_tmp_name('p03_AAPL.csv'))
#%% Importing modules
from pandas_datareader.data import DataReader
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()
#%% Import data to dataframe
raw_uber = DataReader('UBER', 'stooq')
#%% Export imported data to csv
raw_uber.to_csv('./source_data/Uber.csv')
#%% Plot close Uber values
raw_uber['Close'].plot()
#%% Create new sample with monthly periods and calculated mean
resampled_uber = raw_uber.resample('BM').mean()
#%% Plot resampled and raw close data on one plot
raw_uber['Close'].plot()
resampled_uber['Close'].plot(style='--', color='green')
#%% Plot raw close values with shift on one plot
fig, ax = plt.subplots(3, sharex=True)
raw_uber['Close'].plot(ax=ax[0])
raw_uber['Close'].shift(100).plot(ax=ax[1])
raw_uber['Close'].shift(-100).plot(ax=ax[2])
ax[0].legend(['Input'])
ax[1].legend(['Shift by 100 days'])
ax[2].legend(['Shift by -100 days'])
def p03_AAPL(tomtom):
DAX = DataReader('AAPL', 'yahoo', start='01/01/2000')
DAX.to_csv(tomtom.get_tmp_name('p03_AAPL.csv'))
def downloadData(string):
"""
INPUT
@string: Source of data - Quandl or Yahoo
OUTPUT
The master security sheet is opened and data for the mentioned securties
are downloaded from the mentioned source.
The columns in the master sheet are:
Country, Ticker, Staging and Dest
For Quandl the dataFolder is D:\Personal\Projects\SecData\Quandl
For Yahoo Finance: D:\Personal\Projects\SecData\Yahoo_Finance
"""
### The input must be string
if not isinstance(string, str):
print("The input type is not expected.")
### Read in the master sheet
masterFolder = "D:\\Trading\\Rawdata\\"
### My_Watch is the name of the sheet I want to read
master = pd.read_excel(masterFolder + 'Master_Sheet.xlsx', 'My_Watch')
### This is where the securities are stored
dataFolder = "D:\\Trading\\Rawdata\\Securities\\"
### The input must be Quandl or Yahoo
if string == 'Quandl':
with open("D:\\Trading\\myQuandlAuthToken.txt", 'r') as authToken:
auth = authToken.readline()
### i is the row count of the DataFrame master
### ticker is the name of the ticker
### Country is which country the ticker is registered
for i, name, country, filename in zip(range(master.shape[0]), \
master['Ticker'], master['Country'], master['Staging']):
if country == 'USA':
ticker = 'EOD/' + name
else:
ticker = 'XNSE/' + name
### Declare the path where it is to be stored
### Example: D:\Personal\Projects\SecData\Quandl\India
path = dataFolder + country + "\\" + string + "\\"
### Set the date since when the data is to be downloaded
lastDate = checkDate(path + filename)
### If the file does not exist then we want to download data
### for the last 5 years
if lastDate == 'Null':
end = datetime.date.today()
lastDate = end.replace(year=end.year - 5)
### Download the data
temp = quandl.get(ticker, authtoken=auth, start_date=lastDate)
### Save it to the Staging file
temp.to_csv(path + filename + ".csv")
elif string == 'Yahoo':
for i, name, country, filename in zip(range(master.shape[0]), \
master['Ticker'], master['Country'], master['Staging']):
### The Indian stocks in Yahoo are listed with the suffix .NS
if country == 'India':
ticker = name + ".NS"
else:
ticker = name
### Declare the path where it is to be stored
### Example: D:\Personal\Projects\SecData\Quandl\India
path = dataFolder + country + "\\" + string + "\\"
### Set the date since when the data is to be downloaded
lastDate = checkDate(path + filename)
### If the file does not exist then we want to download data
### for the last 5 years
if lastDate == 'Null':
end = datetime.date.today()
lastDate = end.replace(year=end.year - 5)
### Download the data
temp = DataReader(ticker, 'yahoo', start=lastDate)
### Save the data to the staging file
temp.to_csv(path + filename + ".csv")
else:
print("We can download data from the following only:")
print("1. Quandl")
print("2. Yahoo")
