def get_data_for_multiple_stocks(tickers, start_date, end_date):
'''
tickers: list of tickers to get data for
start_date, end_date: dt.datetime objects
method returns a dictionary b{ticker: pd.DataFrame}
'''
start_date_str = start_date.strftime('%Y-%m-%d')
end_date_str = end_date.strftime('%Y-%m-%d')
stocks = dict()
# loop through all the tickers
for i, ticker in enumerate(tickers):
if i % 5 == 0:
print(f'{i}/{len(tickers)}')
try:
# get the data for the specific ticker
s = DataReader(ticker, 'yahoo', start_date_str, end_date_str)
s.insert(0, "Ticker", ticker)
s['Prev Close'] = s['Adj Close'].shift(1)
s['daily_return'] = (s['Adj Close'] / s['Prev Close']) - 1
s['log_return'] = np.log(s['Adj Close'] / s['Prev Close'])
# s['perc_return'] = (s['Adj Close']/s['Prev Close'])
# add it to the dictionary
stocks[ticker] = s
except:
print(f'something went wrong with {ticker}')
continue
# return the dictionary
return stocks
def get_data_for_multiple_stocks(tickers, start_date, end_date):
'''
Obtain stocks information (Date, OHLC, Volume and Adjusted Close).
Uses Pandas DataReader to make an API Call to Yahoo Finance and download the data directly.
Computes other values - Log Return and Arithmetic Return.
Args:
tickers: List of Stock Tickers
start_date: Start Date of the stock data
end_date: End Date of the stock data
Returns:
A dictionary of dataframes for each stock
'''
stocks = dict()
for ticker in tickers:
s = DataReader(ticker, 'yahoo', start_date, end_date)
s.insert(
0, "Ticker",
ticker) #insert ticker column so you can reference better later
s['Date'] = pd.to_datetime(s.index) #useful for transformation later
s['Prev Adj Close'] = s['Adj Close'].shift(1)
s['Log Return'] = np.log(s['Adj Close'] / s['Prev Adj Close'])
s['Return'] = (s['Adj Close'] / s['Prev Adj Close'] - 1)
s = s.reset_index(drop=True)
cols = list(s.columns.values) # re-arrange columns
cols.remove("Date")
s = s[["Date"] + cols]
s["Date"] = pd.to_datetime(s["Date"])
s = s.set_index("Date")
stocks[ticker] = s
return stocks
#companies = pdconn.read_table('companies')
#cursor = pdconn.execute('select ticker from company c left join industry i on c.industry = i.industry where sector = "Healthcare"')
cursor = pdconn.execute('select ticker from company')
companies = cursor.fetchall()
start_date = '1985-01-01'
#start_date = '2016-01-01'
end_date = '2016-05-10'
#companies is a list of tuples
for co in companies:
co = co[0]
if co in done: continue
done.append(co)
print("Fetching data for " + co)
#fetch data from yahoo as pandas dataframe
try:
ts = DataReader(co, 'yahoo', start=start_date, end=end_date)
except:
print('Could not read data for ' + co)
continue
ts.rename(columns={'Adj Close': 'AdjClose'}, inplace=True)
# AdjClose values sometimes get extremely large, causing out of bounds errors. Limit those values here.
if max(ts['AdjClose']) > 9.99e5:
ts.loc[ts.AdjClose > 9.99e5, 'AdjClose'] = 9.99e5
ts.insert(0, 'ticker', co) #add ticker to dataframe
ts = ts.round(decimals=2)
pdconn.to_sql(ts, 'histPrice', if_exists='append')
time.sleep(random.randint(1, 5))
