def copy_market_data(src_market_data_dir, dest_root_dir):
symbol = 'SPY'
filenames = (get_benchmark_filename(symbol), INDEX_MAPPING[symbol][1])
ensure_directory(os.path.join(dest_root_dir, 'data'))
for filename in filenames:
shutil.copyfile(
os.path.join(src_market_data_dir, filename),
os.path.join(dest_root_dir, 'data', filename)
)
def ingest(name, environ=os.environ, timestamp=None, show_progress=False):
"""Ingest data for a given bundle.
Parameters
----------
name : str
The name of the bundle.
environ : mapping, optional
The environment variables. By default this is os.environ.
timestamp : datetime, optional
The timestamp to use for the load.
By default this is the current time.
show_progress : bool, optional
Tell the ingest function to display the progress where possible.
"""
try:
bundle = bundles[name]
except KeyError:
raise UnknownBundle(name)
if timestamp is None:
timestamp = pd.Timestamp.utcnow()
timestamp = timestamp.tz_convert('utc').tz_localize(None)
timestr = to_bundle_ingest_dirname(timestamp)
cachepath = cache_path(name, environ=environ)
pth.ensure_directory(pth.data_path([name, timestr], environ=environ))
pth.ensure_directory(cachepath)
with dataframe_cache(cachepath, clean_on_failure=False) as cache, \
ExitStack() as stack:
# we use `cleanup_on_failure=False` so that we don't purge the
# cache directory if the load fails in the middle
if bundle.create_writers:
wd = stack.enter_context(
working_dir(pth.data_path([], environ=environ)))
daily_bars_path = wd.ensure_dir(*daily_equity_relative(
name,
timestr,
environ=environ,
))
daily_bar_writer = BcolzDailyBarWriter(
daily_bars_path,
bundle.calendar,
bundle.start_session,
bundle.end_session,
)
# Do an empty write to ensure that the daily ctables exist
# when we create the SQLiteAdjustmentWriter below. The
# SQLiteAdjustmentWriter needs to open the daily ctables so
# that it can compute the adjustment ratios for the dividends.
daily_bar_writer.write(())
minute_bar_writer = BcolzMinuteBarWriter(
wd.ensure_dir(*minute_equity_relative(
name, timestr, environ=environ)),
bundle.calendar,
bundle.start_session,
bundle.end_session,
minutes_per_day=bundle.minutes_per_day,
)
asset_db_writer = AssetDBWriter(
wd.getpath(*asset_db_relative(
name,
timestr,
environ=environ,
)))
adjustment_db_writer = stack.enter_context(
SQLiteAdjustmentWriter(
wd.getpath(*adjustment_db_relative(
name, timestr, environ=environ)),
BcolzDailyBarReader(daily_bars_path),
bundle.calendar.all_sessions,
overwrite=True,
))
else:
daily_bar_writer = None
minute_bar_writer = None
asset_db_writer = None
adjustment_db_writer = None
bundle.ingest(
environ,
asset_db_writer,
minute_bar_writer,
daily_bar_writer,
adjustment_db_writer,
bundle.calendar,
bundle.start_session,
bundle.end_session,
cache,
show_progress,
pth.data_path([name, timestr], environ=environ),
)
def ingest(name,
environ=os.environ,
timestamp=None,
show_progress=False):
"""Ingest data for a given bundle.
Parameters
----------
name : str
The name of the bundle.
environ : mapping, optional
The environment variables. By default this is os.environ.
timestamp : datetime, optional
The timestamp to use for the load.
By default this is the current time.
show_progress : bool, optional
Tell the ingest function to display the progress where possible.
"""
try:
bundle = bundles[name]
except KeyError:
raise UnknownBundle(name)
if timestamp is None:
timestamp = pd.Timestamp.utcnow()
timestamp = timestamp.tz_convert('utc').tz_localize(None)
timestr = to_bundle_ingest_dirname(timestamp)
cachepath = cache_path(name, environ=environ)
pth.ensure_directory(pth.data_path([name, timestr], environ=environ))
pth.ensure_directory(cachepath)
with dataframe_cache(cachepath, clean_on_failure=False) as cache, \
ExitStack() as stack:
# we use `cleanup_on_failure=False` so that we don't purge the
# cache directory if the load fails in the middle
if bundle.create_writers:
wd = stack.enter_context(working_dir(
pth.data_path([], environ=environ))
)
daily_bars_path = wd.ensure_dir(
*daily_equity_relative(
name, timestr, environ=environ,
)
)
daily_bar_writer = BcolzDailyBarWriter(
daily_bars_path,
nyse_cal,
bundle.calendar[0],
bundle.calendar[-1]
)
# Do an empty write to ensure that the daily ctables exist
# when we create the SQLiteAdjustmentWriter below. The
# SQLiteAdjustmentWriter needs to open the daily ctables so
# that it can compute the adjustment ratios for the dividends.
daily_bar_writer.write(())
minute_bar_writer = BcolzMinuteBarWriter(
bundle.calendar[0],
wd.ensure_dir(*minute_equity_relative(
name, timestr, environ=environ)
),
bundle.opens,
bundle.closes,
minutes_per_day=bundle.minutes_per_day,
)
asset_db_writer = AssetDBWriter(
wd.getpath(*asset_db_relative(
name, timestr, environ=environ,
))
)
adjustment_db_writer = stack.enter_context(
SQLiteAdjustmentWriter(
wd.getpath(*adjustment_db_relative(
name, timestr, environ=environ)),
BcolzDailyBarReader(daily_bars_path),
bundle.calendar,
overwrite=True,
)
)
else:
daily_bar_writer = None
minute_bar_writer = None
asset_db_writer = None
adjustment_db_writer = None
bundle.ingest(
environ,
asset_db_writer,
minute_bar_writer,
daily_bar_writer,
adjustment_db_writer,
bundle.calendar,
cache,
show_progress,
pth.data_path([name, timestr], environ=environ),
)
def backtest_result_path():
from zipline.utils import paths as pth
ret = pth.zipline_path(['backtest'])
pth.ensure_directory(ret)
return ret
def ingest(name,
environ=os.environ,
timestamp=None,
assets_versions=(),
show_progress=False):
"""Ingest data for a given bundle.
Parameters
----------
name : str
The name of the bundle.
environ : mapping, optional
The environment variables. By default this is os.environ.
timestamp : datetime, optional
The timestamp to use for the load.
By default this is the current time.
assets_versions : Iterable[int], optional
Versions of the assets db to which to downgrade.
show_progress : bool, optional
Tell the ingest function to display the progress where possible.
"""
try:
bundle = bundles[name]
except KeyError:
raise UnknownBundle(name)
calendar = get_calendar(bundle.calendar_name)
start_session = bundle.start_session
end_session = bundle.end_session
if start_session is None or start_session < calendar.first_session:
start_session = calendar.first_session
if end_session is None or end_session > calendar.last_session:
end_session = calendar.last_session
if timestamp is None:
timestamp = pd.Timestamp.utcnow()
timestamp = timestamp.tz_convert('utc').tz_localize(None)
timestr = to_bundle_ingest_dirname(timestamp)
cachepath = cache_path(name, environ=environ)
pth.ensure_directory(pth.data_path([name, timestr], environ=environ))
pth.ensure_directory(cachepath)
with dataframe_cache(cachepath, clean_on_failure=False) as cache, \
ExitStack() as stack:
# we use `cleanup_on_failure=False` so that we don't purge the
# cache directory if the load fails in the middle
if bundle.create_writers:
wd = stack.enter_context(
working_dir(pth.data_path([], environ=environ)))
daily_bars_path = wd.ensure_dir(
*daily_equity_relative(name, timestr))
daily_bar_writer = BcolzDailyBarWriter(
daily_bars_path,
calendar,
start_session,
end_session,
)
# Do an empty write to ensure that the daily ctables exist
# when we create the SQLiteAdjustmentWriter below. The
# SQLiteAdjustmentWriter needs to open the daily ctables so
# that it can compute the adjustment ratios for the dividends.
daily_bar_writer.write(())
minute_bar_writer = BcolzMinuteBarWriter(
wd.ensure_dir(*minute_equity_relative(name, timestr)),
calendar,
start_session,
end_session,
minutes_per_day=bundle.minutes_per_day,
)
assets_db_path = wd.getpath(*asset_db_relative(name, timestr))
asset_db_writer = AssetDBWriter(assets_db_path)
adjustment_db_writer = stack.enter_context(
SQLiteAdjustmentWriter(
wd.getpath(*adjustment_db_relative(name, timestr)),
BcolzDailyBarReader(daily_bars_path),
overwrite=True,
))
else:
daily_bar_writer = None
minute_bar_writer = None
asset_db_writer = None
adjustment_db_writer = None
if assets_versions:
raise ValueError('Need to ingest a bundle that creates '
'writers in order to downgrade the assets'
' db.')
log.info("Ingesting {}.", name)
bundle.ingest(
environ,
asset_db_writer,
minute_bar_writer,
daily_bar_writer,
adjustment_db_writer,
calendar,
start_session,
end_session,
cache,
show_progress,
pth.data_path([name, timestr], environ=environ),
)
for version in sorted(set(assets_versions), reverse=True):
version_path = wd.getpath(*asset_db_relative(
name,
timestr,
db_version=version,
))
with working_file(version_path) as wf:
shutil.copy2(assets_db_path, wf.path)
downgrade(wf.path, version)
def ingest(name,
environ=os.environ,
timestamp=None,
assets_versions=(),
show_progress=False):
"""Ingest data for a given bundle.
Parameters
----------
name : str
The name of the bundle.
environ : mapping, optional
The environment variables. By default this is os.environ.
timestamp : datetime, optional
The timestamp to use for the load.
By default this is the current time.
assets_versions : Iterable[int], optional
Versions of the assets db to which to downgrade.
show_progress : bool, optional
Tell the ingest function to display the progress where possible.
"""
try:
bundle = bundles[name]
except KeyError:
raise UnknownBundle(name)
calendar = get_calendar(bundle.calendar_name)
start_session = bundle.start_session
end_session = bundle.end_session
if start_session is None or start_session < calendar.first_session:
start_session = calendar.first_session
if end_session is None or end_session > calendar.last_session:
end_session = calendar.last_session
if timestamp is None:
timestamp = pd.Timestamp.utcnow()
timestamp = timestamp.tz_convert('utc').tz_localize(None)
timestr = to_bundle_ingest_dirname(timestamp)
cachepath = cache_path(name, environ=environ)
pth.ensure_directory(pth.data_path([name, timestr], environ=environ))
pth.ensure_directory(cachepath)
with dataframe_cache(cachepath, clean_on_failure=False) as cache, \
ExitStack() as stack:
# we use `cleanup_on_failure=False` so that we don't purge the
# cache directory if the load fails in the middle
if bundle.create_writers:
wd = stack.enter_context(working_dir(
pth.data_path([], environ=environ))
)
daily_bars_path = wd.ensure_dir(
*daily_equity_relative(
name, timestr, environ=environ,
)
)
daily_bar_writer = BcolzDailyBarWriter(
daily_bars_path,
calendar,
start_session,
end_session,
)
# Do an empty write to ensure that the daily ctables exist
# when we create the SQLiteAdjustmentWriter below. The
# SQLiteAdjustmentWriter needs to open the daily ctables so
# that it can compute the adjustment ratios for the dividends.
daily_bar_writer.write(())
minute_bar_writer = BcolzMinuteBarWriter(
wd.ensure_dir(*minute_equity_relative(
name, timestr, environ=environ)
),
calendar,
start_session,
end_session,
minutes_per_day=bundle.minutes_per_day,
)
assets_db_path = wd.getpath(*asset_db_relative(
name, timestr, environ=environ,
))
asset_db_writer = AssetDBWriter(assets_db_path)
adjustment_db_writer = stack.enter_context(
SQLiteAdjustmentWriter(
wd.getpath(*adjustment_db_relative(
name, timestr, environ=environ)),
BcolzDailyBarReader(daily_bars_path),
calendar.all_sessions,
overwrite=True,
)
)
else:
daily_bar_writer = None
minute_bar_writer = None
asset_db_writer = None
adjustment_db_writer = None
if assets_versions:
raise ValueError('Need to ingest a bundle that creates '
'writers in order to downgrade the assets'
' db.')
bundle.ingest(
environ,
asset_db_writer,
minute_bar_writer,
daily_bar_writer,
adjustment_db_writer,
calendar,
start_session,
end_session,
cache,
show_progress,
pth.data_path([name, timestr], environ=environ),
)
for version in sorted(set(assets_versions), reverse=True):
version_path = wd.getpath(*asset_db_relative(
name, timestr, environ=environ, db_version=version,
))
with working_file(version_path) as wf:
shutil.copy2(assets_db_path, wf.path)
downgrade(wf.path, version)
def show_draw_result(title, results_df, bundle):
import matplotlib
from matplotlib import gridspec
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
from zipline.utils import paths
from datetime import datetime
plt.style.use('ggplot')
red = "#aa4643"
blue = "#4572a7"
black = "#000000"
figsize = (18, 6)
f = plt.figure(title, figsize=figsize)
gs = gridspec.GridSpec(10, 8)
# TODO draw logo
# ax = plt.subplot(gs[:3, -1:])
# ax.axis("off")
# filename = os.path.join(paths.zipline_root(), 'zipline.png')
# img = mpimg.imread(filename)
# imgplot = ax.imshow(img, interpolation="nearest")
# ax.autoscale_view()
# draw risk and portfolio
series = results_df.iloc[-1]
font_size = 12
value_font_size = 11
label_height, value_height = 0.8, 0.6
label_height2, value_height2 = 0.35, 0.15
fig_data = [
(0.00, label_height, value_height, "Total Returns",
"{0:.3%}".format(series.algorithm_period_return), red, black),
(0.15, label_height, value_height, "Annual Returns",
"{0:.3%}".format(series.annualized_algorithm_return), red, black),
(0.00, label_height2, value_height2, "Benchmark Total",
"{0:.3%}".format(series.benchmark_period_return), blue, black),
(0.15, label_height2, value_height2, "Benchmark Annual",
"{0:.3%}".format(series.annualized_benchmark_return), blue, black),
(0.30, label_height, value_height, "Alpha",
"{0:.4}".format(series.alpha), black, black),
(0.40, label_height, value_height, "Beta",
"{0:.4}".format(series.beta), black, black),
(0.55, label_height, value_height, "Sharpe",
"{0:.4}".format(series.sharpe), black, black),
(0.70, label_height, value_height, "Sortino",
"{0:.4}".format(series.sortino), black, black),
(0.85, label_height, value_height, "Information Ratio",
"{0:.4}".format(series.information), black, black),
(0.30, label_height2, value_height2, "Volatility",
"{0:.4}".format(series.algo_volatility), black, black),
(0.40, label_height2, value_height2, "MaxDrawdown",
"{0:.3%}".format(series.max_drawdown), black, black),
# (0.55, label_height2, value_height2, "Tracking Error", "{0:.4}".format(series.tracking_error), black, black),
# (0.70, label_height2, value_height2, "Downside Risk", "{0:.4}".format(series.downside_risk), black, black),
]
ax = plt.subplot(gs[:3, :-1])
ax.axis("off")
for x, y1, y2, label, value, label_color, value_color in fig_data:
ax.text(x, y1, label, color=label_color, fontsize=font_size)
ax.text(x, y2, value, color=value_color, fontsize=value_font_size)
# strategy vs benchmark
ax = plt.subplot(gs[4:, :])
ax.get_xaxis().set_minor_locator(matplotlib.ticker.AutoMinorLocator())
ax.get_yaxis().set_minor_locator(matplotlib.ticker.AutoMinorLocator())
ax.grid(b=True, which='minor', linewidth=.2)
ax.grid(b=True, which='major', linewidth=1)
ax.plot(results_df["benchmark_period_return"],
label="benchmark",
alpha=1,
linewidth=2,
color=blue)
ax.plot(results_df["algorithm_period_return"],
label="algorithm",
alpha=1,
linewidth=2,
color=red)
# manipulate
vals = ax.get_yticks()
ax.set_yticklabels(['{:3.2f}%'.format(x * 100) for x in vals])
leg = plt.legend(loc="upper left")
leg.get_frame().set_alpha(0.5)
plt.show()
now = datetime.now()
paths.ensure_directory(paths.zipline_path(['perf']))
plt.savefig(filename=os.path.join(
paths.zipline_path(['perf']),
os.path.basename(title).split('.')[0] + '_' + bundle + '_' +
now.strftime('%Y%m%dT%H%M%s') + '.png'))
def backtest_result_path():
from zipline.utils import paths as pth
ret = pth.zipline_path(['backtest'])
pth.ensure_directory(ret)
return ret
