mirror of
https://github.com/wassname/catalyst.git
synced 2026-08-06 13:00:45 +08:00
MAINT: Moving yahoo loader from factory to utils.
This commit is contained in:
Thomas Wiecki
committed by
Eddie Hebert
Eddie Hebert
parent
b65f7f42c0
commit
a66f45b598
@@ -1,3 +1,4 @@
|
||||
from . import loader
|
||||
from .loader import load_from_yahoo, load_bars_from_yahoo
|
||||
|
||||
__all__ = ['loader']
|
||||
__all__ = ['loader', 'load_from_yahoo', 'load_bars_from_yahoo']
|
||||
|
||||
@@ -22,6 +22,8 @@ from datetime import timedelta
|
||||
import logbook
|
||||
|
||||
import pandas as pd
|
||||
from pandas.io.data import DataReader
|
||||
import pytz
|
||||
|
||||
from . treasuries import get_treasury_data
|
||||
from . import benchmarks
|
||||
@@ -219,3 +221,130 @@ Fetching data from data.treasury.gov
|
||||
key=lambda t: t[0]))
|
||||
|
||||
return bm_returns, tr_curves
|
||||
|
||||
|
||||
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 not start is None and not end is None:
|
||||
assert start < end, "start date is later than end date."
|
||||
|
||||
data = OrderedDict()
|
||||
|
||||
if stocks is not None:
|
||||
for stock in stocks:
|
||||
print stock
|
||||
stkd = DataReader(stock, 'yahoo', start, end).sort_index()
|
||||
data[stock] = stkd
|
||||
|
||||
if indexes is not None:
|
||||
for name, ticker in indexes.iteritems():
|
||||
print name
|
||||
stkd = DataReader(ticker, 'yahoo', start, end).sort_index()
|
||||
data[name] = stkd
|
||||
|
||||
return data
|
||||
|
||||
|
||||
def load_from_yahoo(indexes=None,
|
||||
stocks=None,
|
||||
start=None,
|
||||
end=None,
|
||||
adjusted=True):
|
||||
"""
|
||||
Loads price data from Yahoo into a dataframe for each of the indicated
|
||||
securities. By default, 'price' is taken from Yahoo's 'Adjusted Close',
|
||||
which removes the impact of splits and dividends. If the argument
|
||||
'adjusted' is False, then the non-adjusted 'close' field is used instead.
|
||||
|
||||
:param indexes: Financial indexes to load.
|
||||
:type indexes: dict
|
||||
:param stocks: Stock closing prices to load.
|
||||
:type stocks: list
|
||||
:param start: Retrieve prices from start date on.
|
||||
:type start: datetime
|
||||
:param end: Retrieve prices until end date.
|
||||
:type end: datetime
|
||||
:param adjusted: Adjust the price for splits and dividends.
|
||||
:type adjusted: bool
|
||||
|
||||
"""
|
||||
data = _load_raw_yahoo_data(indexes, stocks, start, end)
|
||||
if adjusted:
|
||||
close_key = 'Adj Close'
|
||||
else:
|
||||
close_key = 'Close'
|
||||
df = pd.DataFrame({key: d[close_key] for key, d in data.iteritems()})
|
||||
df.index = df.index.tz_localize(pytz.utc)
|
||||
return df
|
||||
|
||||
|
||||
def load_bars_from_yahoo(indexes=None,
|
||||
stocks=None,
|
||||
start=None,
|
||||
end=None,
|
||||
adjusted=True):
|
||||
"""
|
||||
Loads data from Yahoo into a panel with the following
|
||||
column names for each indicated security:
|
||||
|
||||
- open
|
||||
- high
|
||||
- low
|
||||
- close
|
||||
- volume
|
||||
- price
|
||||
|
||||
Note that 'price' is Yahoo's 'Adjusted Close', which removes the
|
||||
impact of splits and dividends. If the argument 'adjusted' is True, then
|
||||
the open, high, low, and close values are adjusted as well.
|
||||
|
||||
:param indexes: Financial indexes to load.
|
||||
:type indexes: dict
|
||||
:param stocks: Stock closing prices to load.
|
||||
:type stocks: list
|
||||
:param start: Retrieve prices from start date on.
|
||||
:type start: datetime
|
||||
:param end: Retrieve prices until end date.
|
||||
:type end: datetime
|
||||
:param adjusted: Adjust open/high/low/close for splits and dividends.
|
||||
The 'price' field is always adjusted.
|
||||
:type adjusted: bool
|
||||
|
||||
"""
|
||||
data = _load_raw_yahoo_data(indexes, stocks, start, end)
|
||||
panel = pd.Panel(data)
|
||||
# Rename columns
|
||||
panel.minor_axis = ['open', 'high', 'low', 'close', 'volume', 'price']
|
||||
panel.major_axis = panel.major_axis.tz_localize(pytz.utc)
|
||||
# Adjust data
|
||||
if adjusted:
|
||||
adj_cols = ['open', 'high', 'low', 'close']
|
||||
for ticker in panel.items:
|
||||
ratio = (panel[ticker]['price'] / panel[ticker]['close'])
|
||||
ratio_filtered = ratio.fillna(0).values
|
||||
for col in adj_cols:
|
||||
panel[ticker][col] *= ratio_filtered
|
||||
return panel
|
||||
|
||||
+6
-128
@@ -23,7 +23,6 @@ from collections import OrderedDict
|
||||
from delorean import Delorean
|
||||
|
||||
import pandas as pd
|
||||
from pandas.io.data import DataReader
|
||||
import numpy as np
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
@@ -38,6 +37,12 @@ from zipline.sources.test_source import (
|
||||
create_trade
|
||||
)
|
||||
|
||||
# For backwards compatibility
|
||||
from zipline.data.loader import (load_from_yahoo,
|
||||
load_bars_from_yahoo)
|
||||
|
||||
__all__ = ['load_from_yahoo', 'load_bars_from_yahoo']
|
||||
|
||||
|
||||
def create_simulation_parameters(year=2006, start=None, end=None,
|
||||
capital_base=float("1.0e5"),
|
||||
@@ -389,130 +394,3 @@ def create_test_panel_ohlc_source(sim_params=None):
|
||||
panel = pd.Panel.from_dict({0: df})
|
||||
|
||||
return DataPanelSource(panel), panel
|
||||
|
||||
|
||||
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 not start is None and not end is None:
|
||||
assert start < end, "start date is later than end date."
|
||||
|
||||
data = OrderedDict()
|
||||
|
||||
if stocks is not None:
|
||||
for stock in stocks:
|
||||
print stock
|
||||
stkd = DataReader(stock, 'yahoo', start, end).sort_index()
|
||||
data[stock] = stkd
|
||||
|
||||
if indexes is not None:
|
||||
for name, ticker in indexes.iteritems():
|
||||
print name
|
||||
stkd = DataReader(ticker, 'yahoo', start, end).sort_index()
|
||||
data[name] = stkd
|
||||
|
||||
return data
|
||||
|
||||
|
||||
def load_from_yahoo(indexes=None,
|
||||
stocks=None,
|
||||
start=None,
|
||||
end=None,
|
||||
adjusted=True):
|
||||
"""
|
||||
Loads price data from Yahoo into a dataframe for each of the indicated
|
||||
securities. By default, 'price' is taken from Yahoo's 'Adjusted Close',
|
||||
which removes the impact of splits and dividends. If the argument
|
||||
'adjusted' is False, then the non-adjusted 'close' field is used instead.
|
||||
|
||||
:param indexes: Financial indexes to load.
|
||||
:type indexes: dict
|
||||
:param stocks: Stock closing prices to load.
|
||||
:type stocks: list
|
||||
:param start: Retrieve prices from start date on.
|
||||
:type start: datetime
|
||||
:param end: Retrieve prices until end date.
|
||||
:type end: datetime
|
||||
:param adjusted: Adjust the price for splits and dividends.
|
||||
:type adjusted: bool
|
||||
|
||||
"""
|
||||
data = _load_raw_yahoo_data(indexes, stocks, start, end)
|
||||
if adjusted:
|
||||
close_key = 'Adj Close'
|
||||
else:
|
||||
close_key = 'Close'
|
||||
df = pd.DataFrame({key: d[close_key] for key, d in data.iteritems()})
|
||||
df.index = df.index.tz_localize(pytz.utc)
|
||||
return df
|
||||
|
||||
|
||||
def load_bars_from_yahoo(indexes=None,
|
||||
stocks=None,
|
||||
start=None,
|
||||
end=None,
|
||||
adjusted=True):
|
||||
"""
|
||||
Loads data from Yahoo into a panel with the following
|
||||
column names for each indicated security:
|
||||
|
||||
- open
|
||||
- high
|
||||
- low
|
||||
- close
|
||||
- volume
|
||||
- price
|
||||
|
||||
Note that 'price' is Yahoo's 'Adjusted Close', which removes the
|
||||
impact of splits and dividends. If the argument 'adjusted' is True, then
|
||||
the open, high, low, and close values are adjusted as well.
|
||||
|
||||
:param indexes: Financial indexes to load.
|
||||
:type indexes: dict
|
||||
:param stocks: Stock closing prices to load.
|
||||
:type stocks: list
|
||||
:param start: Retrieve prices from start date on.
|
||||
:type start: datetime
|
||||
:param end: Retrieve prices until end date.
|
||||
:type end: datetime
|
||||
:param adjusted: Adjust open/high/low/close for splits and dividends.
|
||||
The 'price' field is always adjusted.
|
||||
:type adjusted: bool
|
||||
|
||||
"""
|
||||
data = _load_raw_yahoo_data(indexes, stocks, start, end)
|
||||
panel = pd.Panel(data)
|
||||
# Rename columns
|
||||
panel.minor_axis = ['open', 'high', 'low', 'close', 'volume', 'price']
|
||||
panel.major_axis = panel.major_axis.tz_localize(pytz.utc)
|
||||
# Adjust data
|
||||
if adjusted:
|
||||
adj_cols = ['open', 'high', 'low', 'close']
|
||||
for ticker in panel.items:
|
||||
ratio = (panel[ticker]['price'] / panel[ticker]['close'])
|
||||
ratio_filtered = ratio.fillna(0).values
|
||||
for col in adj_cols:
|
||||
panel[ticker][col] *= ratio_filtered
|
||||
return panel
|
||||
|
||||
Reference in New Issue
Block a user