Merge pull request #101 from zipline-live/iex

Move from Google to IEX for benchmarks

Author: tibkiss

docs/source/bundles.rst

@@ -153,44 +153,6 @@ Quantopian provides a mirror of the quandl WIKI dataset with the data in the
 formats that zipline expects. This is available under the name:
 ``quantopian-quandl`` and is the default bundle for zipline.
 
-Yahoo Bundle Factories
-``````````````````````
-
-Zipline also ships with a factory function for creating a data bundle out of a
-set of tickers from yahoo: :func:`~zipline.data.bundles.yahoo_equities`.
-:func:`~zipline.data.bundles.yahoo_equities` makes it easy to pre-download and
-cache the data for a set of equities from yahoo. The yahoo bundles include daily
-pricing data along with splits, cash dividends, and inferred asset metadata. To
-create a bundle from a set of equities, add the following to your
-``~/.zipline/extensions.py`` file:
-
-.. code-block:: python
-
-   from zipline.data.bundles import register, yahoo_equities
-
-   # these are the tickers you would like data for
-   equities = {
-       'AAPL',
-       'MSFT',
-       'GOOG',
-   }
-   register(
-       'my-yahoo-equities-bundle',  # name this whatever you like
-       yahoo_equities(equities),
-   )
-
-
-This may now be used like:
-
-.. code-block:: bash
-
-   $ zipline ingest -b my-yahoo-equities-bundle
-   $ zipline run -f algo.py --bundle my-yahoo-equities-bundle
-
-
-More than one yahoo equities bundle may be registered as long as they use
-different names.
-
 Writing a New Bundle
 ~~~~~~~~~~~~~~~~~~~~
 
@@ -200,7 +162,7 @@ zipline. To add a new bundle, one must implement an ``ingest`` function.
 The ``ingest`` function is responsible for loading the data into memory and
 passing it to a set of writer objects provided by zipline to convert the data to
 zipline's internal format. The ingest function may work by downloading data from
-a remote location like the ``quandl`` bundle or yahoo bundles or it may just
+a remote location like the ``quandl`` bundle or it may just
 load files that are already on the machine. The function is provided with
 writers that will write the data to the correct location transactionally. If an
 ingestion fails part way through the bundle will not be written in an incomplete

tests/data/bundles/test_yahoo.py

@@ -9,7 +9,7 @@ import numpy as np
 import pandas as pd
 
 from zipline import examples
-from zipline.data.bundles import clean, ingest, register, yahoo_equities
+from zipline.data.bundles import clean, ingest
 from zipline.testing import test_resource_path, tmp_dir
 from zipline.utils.cache import dataframe_cache
 
@@ -27,14 +27,6 @@ INPUT_DATA_SYMBOLS = (
     'AAPL',
     'MSFT',
 )
-TEST_BUNDLE_NAME = 'test'
-input_bundle = yahoo_equities(
-    INPUT_DATA_SYMBOLS,
-    INPUT_DATA_START_DATE,
-    INPUT_DATA_END_DATE,
-)
-register(TEST_BUNDLE_NAME, input_bundle)
-
 
 banner = """
 Please verify that the new performance is more correct than the old
@@ -83,19 +75,6 @@ def changed_results(new, old):
 def eof(*args, **kwargs):
     raise EOFError()
 
-
-def rebuild_input_data(environ):
-    ingest(TEST_BUNDLE_NAME, environ=environ, show_progress=True)
-    clean(TEST_BUNDLE_NAME, keep_last=1, environ=environ)
-
-
-@click.command()
-@click.option(
-    '--rebuild-input',
-    is_flag=True,
-    default=False,
-    help="Should we rebuild the input data from Yahoo?",
-)
 @click.pass_context
 def main(ctx, rebuild_input):
     """Rebuild the perf data for test_examples
@@ -109,8 +88,6 @@ def main(ctx, rebuild_input):
         # The environ here should be the same (modulo the tempdir location)
         # as we use in test_examples.py.
         environ = {'ZIPLINE_ROOT': d.getpath('example_data/root')}
-        if rebuild_input:
-            rebuild_input_data(environ)
 
         new_perf_path = d.getpath(
             'example_data/new_perf/%s' % pd.__version__.replace('.', '-'),

tests/resources/rebuild_example_data

@@ -548,7 +548,7 @@ def _create_benchmark_source(self):
         else:
             benchmark_asset = None
             # get benchmark info from trading environment, which defaults to
-            # downloading data from Yahoo.
+            # downloading data from IEX Trading.
             benchmark_returns = self.trading_environment.benchmark_returns
         return BenchmarkSource(
             benchmark_asset=benchmark_asset,

zipline/algorithm.py

@@ -1,15 +1,11 @@
 from . import loader
 from .loader import (
-    load_from_yahoo,
-    load_bars_from_yahoo,
     load_prices_from_csv,
     load_prices_from_csv_folder,
 )
 
 
 __all__ = [
-    'load_bars_from_yahoo',
-    'load_from_yahoo',
     'load_prices_from_csv',
     'load_prices_from_csv_folder',
     'loader',

zipline/data/__init__.py

@@ -12,29 +12,32 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+import json
+import pandas as pd
+import requests
 
-from zipline.utils.calendars import get_calendar
-import pandas_datareader.data as web
 
-
-def get_benchmark_returns(symbol, start_date, end_date):
+def get_benchmark_returns(symbol):
     """
-    Get a Series of benchmark returns from Google finance.
+    Get a Series of benchmark returns from IEX associated with `symbol`.
+    Default is `SPY`.
 
-    Returns a Series with returns from (start_date, end_date].
+    Parameters
+    ----------
+    symbol : str
+        Benchmark symbol for which we're getting the returns.
 
-    start_date is **not** included because we need the close from day N - 1 to
-    compute the returns for day N.
+    The data is provided by IEX (https://iextrading.com/), and we can
+    get up to 5 years worth of data.
     """
-    df = web.DataReader(symbol, 'google', start_date, end_date)
-    df.index = df.index.tz_localize('UTC')
+    r = requests.get(
+        'https://api.iextrading.com/1.0/stock/{}/chart/5y'.format(symbol)
+    )
+    data = json.loads(r.text)
 
-    calendar = get_calendar("NYSE")
-    start_index = calendar.all_sessions.searchsorted(start_date)
-    end_index = calendar.all_sessions.searchsorted(end_date)
+    df = pd.DataFrame(data)
 
-    # fill price data for missing dates
-    df = df["Close"].reindex(calendar.all_sessions[start_index:end_index],
-                             method='ffill')
+    df.index = pd.DatetimeIndex(df['date'])
+    df = df['close']
 
-    return df.pct_change(1).iloc[1:]
+    return df.sort_index().tz_localize('UTC').pct_change(1).iloc[1:]