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 get(self, symbol, asset_type=None, **kwargs):
"""
Get the latest data for the specified symbol
"""
if not asset_type:
logger.error("No asset_type argument set")
raise Exception("asset_type must be set")
if asset_type == "F":
symbol = symbol.replace("/", "") + "=X"
try:
df = DataReader(symbol, "yahoo", start="1950-01-01", **kwargs)
except (RemoteDataError, KeyError):
logger.error(f"Symbol {symbol} not found")
raise SymbolNotFound(symbol)
df = (df.rename(
columns={
"Open": "open",
"High": "high",
"Low": "low",
"Close": "close",
"Volume": "volume",
"Adj Close": "adj_close"
}).sort_index())
df = (df[["adj_close"]].rename({"adj_close": "close"}, axis=1))
return df
def yahoo_prices(symbols, start_date, verbose = True):
ticker_df_list = []
start_dates = {};
for index, row in symbols.iterrows():
try:
data = DataReader(row.Ticker, 'yahoo', start_date)
data['Ref'] = row.Ticker
data = data.loc[:, ['Ref', 'Adj Close']]
data.rename(columns={'Adj Close': 'Price'}, inplace=True)
if verbose:
print("{}: Historical Perf: {}".format(row.Ticker, data.tail(1).iloc[0]['Price']/data.head(1).iloc[0]['Price']-1))
ticker_df_list.append(data)
start_dates[row.Ticker] = data.head(1).index[0]
except Exception as e:
if verbose:
print("No data for ticker %s\n%s" % (row.Ticker, str(e)))
df = pd.concat(ticker_df_list)
cell= df[['Ref','Price']]
return cell.pivot(columns='Ref'), start_dates
def get_adtv(symbols, startdate, enddate):
"""Returns pricing/volume table field timeseries
fields used 'Close', 'Volume'
"""
if type(symbols) == str:
symbols = [symbols]
data = []
for symbol in symbols:
try:
df = DataReader(symbol, 'yahoo', startdate,
enddate)[['Close', 'Volume']]
df['adtv'] = df['Close'] * df['Volume']
df.rename(columns={'adtv': symbol}, inplace=True)
df = df[symbol]
except:
df = pd.DataFrame(np.nan,
index=pd.bdate_range(startdate, enddate),
columns=[symbol])
data.append(df)
df = pd.concat(data, axis=1)
df = pd.DataFrame(df.apply(np.mean, axis=0), columns=['adtv'])
df['Ticker'] = df.index
return df.reset_index(drop=True)
def download_stock(symbol, start_date=dt.datetime(1990, 1, 1)):
# Download assets.
stock = DataReader(symbol, "yahoo", start_date)
stock.rename(columns={"Adj Close": "Adj. Close"}, inplace=True)
# Compute the adjusted prices.
ratio = stock["Adj. Close"] / stock["Close"]
stock["Adj. Open"] = stock["Open"] * ratio
stock["Adj. High"] = stock["High"] * ratio
stock["Adj. Low"] = stock["Low"] * ratio
stock["Adj. Volume"] = stock["Volume"] * ratio
stock["Split Ratio"] = 1.0
stock["Ex-Dividend"] = 0.0
# Fetch the dividends and splits for this stock. Notice that we restrict the
# dates to lie in the appropriate range.
ds = download_splits_dividends(symbol)
# Store dividend data.
if "DIVIDEND" in ds.index:
divs = ds.ix[["DIVIDEND"]].set_index("datetime")
idx = divs.index.intersection(stock.index)
stock.ix[idx, "Ex-Dividend"] = [
float(x) for x in divs.ix[idx, "adjustment"]
]
# Store stock split data.
if "SPLIT" in ds.index:
splits = ds.ix[["SPLIT"]].set_index("datetime")
splits["adjustment"] = [
float(x.split(":")[0]) / float(x.split(":")[1])
for x in splits["adjustment"]
]
idx = splits.index.intersection(stock.index)
stock.ix[idx, "Split Ratio"] = splits.ix[idx, "adjustment"]
return stock
import pandas as pd
import matplotlib.pyplot as plt
from pandas_datareader.data import DataReader
from datetime import date
start = date(1900,1,1) # default Jan 1, 2010
series_code = 'DGS10' # 10-year Treasury Rate
data_source = 'fred' # FED Economic Data Service
data = DataReader(series_code, data_source, start)
data.info()
pd.concat([data.head(3), data.tail(3)])
series_name = '10-year Treasury'
data = data.rename(columns={series_code: series_name})
data.plot(title=series_name)
plt.show()
#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))
