def test_novel_deltas_macro(self):
asset_info = asset_infos[0][0]
base_dates = pd.DatetimeIndex([
pd.Timestamp('2014-01-01'),
pd.Timestamp('2014-01-04')
])
baseline = pd.DataFrame({
'value': (0, 1),
'asof_date': base_dates,
'timestamp': base_dates,
})
expr = bz.Data(baseline, name='expr', dshape=self.macro_dshape)
deltas = bz.Data(baseline, name='deltas', dshape=self.macro_dshape)
deltas = bz.transform(
deltas,
value=deltas.value + 10,
timestamp=deltas.timestamp + timedelta(days=1),
)
nassets = len(asset_info)
expected_views = keymap(pd.Timestamp, {
'2014-01-03': repeat_last_axis(
np.array([10.0, 10.0, 10.0]),
nassets,
),
'2014-01-06': repeat_last_axis(
np.array([10.0, 10.0, 11.0]),
nassets,
),
})
cal = pd.DatetimeIndex([
pd.Timestamp('2014-01-01'),
pd.Timestamp('2014-01-02'),
pd.Timestamp('2014-01-03'),
# omitting the 4th and 5th to simulate a weekend
pd.Timestamp('2014-01-06'),
])
with tmp_asset_finder(equities=asset_info) as finder:
expected_output = pd.DataFrame(
list(concatv([10] * nassets, [11] * nassets)),
index=pd.MultiIndex.from_product((
sorted(expected_views.keys()),
finder.retrieve_all(asset_info.index),
)),
columns=('value',),
)
self._run_pipeline(
expr,
deltas,
expected_views,
expected_output,
finder,
calendar=cal,
start=cal[2],
end=cal[-1],
window_length=3,
compute_fn=op.itemgetter(-1),
)
def test_novel_deltas(self, asset_info):
base_dates = pd.DatetimeIndex([pd.Timestamp("2014-01-01"), pd.Timestamp("2014-01-04")])
repeated_dates = base_dates.repeat(3)
baseline = pd.DataFrame(
{
"sid": self.sids * 2,
"value": (0, 1, 2, 1, 2, 3),
"asof_date": repeated_dates,
"timestamp": repeated_dates,
}
)
expr = bz.Data(baseline, name="expr", dshape=self.dshape)
deltas = bz.Data(baseline, name="deltas", dshape=self.dshape)
deltas = bz.transform(deltas, value=deltas.value + 10, timestamp=deltas.timestamp + timedelta(days=1))
expected_views = keymap(
pd.Timestamp,
{
"2014-01-03": np.array([[10.0, 11.0, 12.0], [10.0, 11.0, 12.0], [10.0, 11.0, 12.0]]),
"2014-01-06": np.array([[10.0, 11.0, 12.0], [10.0, 11.0, 12.0], [11.0, 12.0, 13.0]]),
},
)
if len(asset_info) == 4:
expected_views = valmap(lambda view: np.c_[view, [np.nan, np.nan, np.nan]], expected_views)
expected_output_buffer = [10, 11, 12, np.nan, 11, 12, 13, np.nan]
else:
expected_output_buffer = [10, 11, 12, 11, 12, 13]
cal = pd.DatetimeIndex(
[
pd.Timestamp("2014-01-01"),
pd.Timestamp("2014-01-02"),
pd.Timestamp("2014-01-03"),
# omitting the 4th and 5th to simulate a weekend
pd.Timestamp("2014-01-06"),
]
)
with tmp_asset_finder(equities=asset_info) as finder:
expected_output = pd.DataFrame(
expected_output_buffer,
index=pd.MultiIndex.from_product(
(sorted(expected_views.keys()), finder.retrieve_all(asset_info.index))
),
columns=("value",),
)
self._run_pipeline(
expr,
deltas,
expected_views,
expected_output,
finder,
calendar=cal,
start=cal[2],
end=cal[-1],
window_length=3,
compute_fn=op.itemgetter(-1),
)
def _load_dataset(self, dates, assets, mask, columns):
try:
(dataset,) = set(map(getdataset, columns))
except ValueError:
raise AssertionError('all columns must come from the same dataset')
expr, deltas, checkpoints, odo_kwargs = self[dataset]
have_sids = (dataset.ndim == 2)
asset_idx = pd.Series(index=assets, data=np.arange(len(assets)))
assets = list(map(int, assets)) # coerce from numpy.int64
added_query_fields = [AD_FIELD_NAME, TS_FIELD_NAME] + (
[SID_FIELD_NAME] if have_sids else []
)
colnames = added_query_fields + list(map(getname, columns))
data_query_time = self._data_query_time
data_query_tz = self._data_query_tz
lower_dt, upper_dt = normalize_data_query_bounds(
dates[0],
dates[-1],
data_query_time,
data_query_tz,
)
def collect_expr(e, lower):
"""Materialize the expression as a dataframe.
Parameters
----------
e : Expr
The baseline or deltas expression.
lower : datetime
The lower time bound to query.
Returns
-------
result : pd.DataFrame
The resulting dataframe.
Notes
-----
This can return more data than needed. The in memory reindex will
handle this.
"""
predicate = e[TS_FIELD_NAME] <= upper_dt
if lower is not None:
predicate &= e[TS_FIELD_NAME] >= lower
return odo(e[predicate][colnames], pd.DataFrame, **odo_kwargs)
if checkpoints is not None:
ts = checkpoints[TS_FIELD_NAME]
checkpoints_ts = odo(ts[ts <= lower_dt].max(), pd.Timestamp)
if pd.isnull(checkpoints_ts):
materialized_checkpoints = pd.DataFrame(columns=colnames)
lower = None
else:
materialized_checkpoints = odo(
checkpoints[ts == checkpoints_ts][colnames],
pd.DataFrame,
**odo_kwargs
)
lower = checkpoints_ts
else:
materialized_checkpoints = pd.DataFrame(columns=colnames)
lower = None
materialized_expr = collect_expr(expr, lower)
if materialized_checkpoints is not None:
materialized_expr = pd.concat(
(
materialized_checkpoints,
materialized_expr,
),
ignore_index=True,
copy=False,
)
materialized_deltas = (
collect_expr(deltas, lower)
if deltas is not None else
pd.DataFrame(columns=colnames)
)
# It's not guaranteed that assets returned by the engine will contain
# all sids from the deltas table; filter out such mismatches here.
if not materialized_deltas.empty and have_sids:
materialized_deltas = materialized_deltas[
materialized_deltas[SID_FIELD_NAME].isin(assets)
]
if data_query_time is not None:
for m in (materialized_expr, materialized_deltas):
m.loc[:, TS_FIELD_NAME] = m.loc[
:, TS_FIELD_NAME
].astype('datetime64[ns]')
normalize_timestamp_to_query_time(
m,
data_query_time,
data_query_tz,
inplace=True,
ts_field=TS_FIELD_NAME,
)
# Inline the deltas that changed our most recently known value.
# Also, we reindex by the dates to create a dense representation of
# the data.
sparse_output, non_novel_deltas = overwrite_novel_deltas(
materialized_expr,
materialized_deltas,
dates,
)
sparse_output.drop(AD_FIELD_NAME, axis=1, inplace=True)
def last_in_date_group(df, reindex, have_sids=have_sids):
idx = dates[dates.searchsorted(
df[TS_FIELD_NAME].values.astype('datetime64[D]')
)]
if have_sids:
idx = [idx, SID_FIELD_NAME]
last_in_group = df.drop(TS_FIELD_NAME, axis=1).groupby(
idx,
sort=False,
).last()
if have_sids:
last_in_group = last_in_group.unstack()
if reindex:
if have_sids:
cols = last_in_group.columns
last_in_group = last_in_group.reindex(
index=dates,
columns=pd.MultiIndex.from_product(
(cols.levels[0], assets),
names=cols.names,
),
)
else:
last_in_group = last_in_group.reindex(dates)
return last_in_group
sparse_deltas = last_in_date_group(non_novel_deltas, reindex=False)
dense_output = last_in_date_group(sparse_output, reindex=True)
dense_output.ffill(inplace=True)
# Fill in missing values specified by each column. This is made
# significantly more complex by the fact that we need to work around
# two pandas issues:
# 1) When we have sids, if there are no records for a given sid for any
# dates, pandas will generate a column full of NaNs for that sid.
# This means that some of the columns in `dense_output` are now
# float instead of the intended dtype, so we have to coerce back to
# our expected type and convert NaNs into the desired missing value.
# 2) DataFrame.ffill assumes that receiving None as a fill-value means
# that no value was passed. Consequently, there's no way to tell
# pandas to replace NaNs in an object column with None using fillna,
# so we have to roll our own instead using df.where.
for column in columns:
# Special logic for strings since `fillna` doesn't work if the
# missing value is `None`.
if column.dtype == categorical_dtype:
dense_output[column.name] = dense_output[
column.name
].where(pd.notnull(dense_output[column.name]),
column.missing_value)
else:
# We need to execute `fillna` before `astype` in case the
# column contains NaNs and needs to be cast to bool or int.
# This is so that the NaNs are replaced first, since pandas
# can't convert NaNs for those types.
dense_output[column.name] = dense_output[
column.name
].fillna(column.missing_value).astype(column.dtype)
if have_sids:
adjustments_from_deltas = adjustments_from_deltas_with_sids
column_view = identity
else:
# If we do not have sids, use the column view to make a single
# column vector which is unassociated with any assets.
column_view = op.itemgetter(np.s_[:, np.newaxis])
adjustments_from_deltas = adjustments_from_deltas_no_sids
mask = np.full(
shape=(len(mask), 1), fill_value=True, dtype=bool_dtype,
)
for column_idx, column in enumerate(columns):
column_name = column.name
yield column, AdjustedArray(
column_view(
dense_output[column_name].values.astype(column.dtype),
),
mask,
adjustments_from_deltas(
dates,
sparse_output[TS_FIELD_NAME].values,
column_idx,
column_name,
asset_idx,
sparse_deltas,
),
column.missing_value,
)
def test_novel_deltas(self, asset_info):
base_dates = pd.DatetimeIndex(
[pd.Timestamp('2014-01-01'),
pd.Timestamp('2014-01-04')])
repeated_dates = base_dates.repeat(3)
baseline = pd.DataFrame({
'sid': self.sids * 2,
'value': (0, 1, 2, 1, 2, 3),
'asof_date': repeated_dates,
'timestamp': repeated_dates,
})
expr = bz.Data(baseline, name='expr', dshape=self.dshape)
deltas = bz.Data(baseline, name='deltas', dshape=self.dshape)
deltas = bz.transform(
deltas,
value=deltas.value + 10,
timestamp=deltas.timestamp + timedelta(days=1),
)
expected_views = keymap(
pd.Timestamp, {
'2014-01-03':
np.array([[10.0, 11.0, 12.0], [10.0, 11.0, 12.0],
[10.0, 11.0, 12.0]]),
'2014-01-06':
np.array([[10.0, 11.0, 12.0], [10.0, 11.0, 12.0],
[11.0, 12.0, 13.0]]),
})
if len(asset_info) == 4:
expected_views = valmap(
lambda view: np.c_[view, [np.nan, np.nan, np.nan]],
expected_views,
)
expected_output_buffer = [10, 11, 12, np.nan, 11, 12, 13, np.nan]
else:
expected_output_buffer = [10, 11, 12, 11, 12, 13]
cal = pd.DatetimeIndex([
pd.Timestamp('2014-01-01'),
pd.Timestamp('2014-01-02'),
pd.Timestamp('2014-01-03'),
# omitting the 4th and 5th to simulate a weekend
pd.Timestamp('2014-01-06'),
])
with tmp_asset_finder(equities=asset_info) as finder:
expected_output = pd.DataFrame(
expected_output_buffer,
index=pd.MultiIndex.from_product((
sorted(expected_views.keys()),
finder.retrieve_all(asset_info.index),
)),
columns=('value', ),
)
self._run_pipeline(
expr,
deltas,
expected_views,
expected_output,
finder,
calendar=cal,
start=cal[2],
end=cal[-1],
window_length=3,
compute_fn=op.itemgetter(-1),
)
def test_novel_deltas_macro(self):
asset_info = asset_infos[0][0]
base_dates = pd.DatetimeIndex(
[pd.Timestamp('2014-01-01'),
pd.Timestamp('2014-01-04')])
baseline = pd.DataFrame({
'value': (0, 1),
'asof_date': base_dates,
'timestamp': base_dates,
})
expr = bz.Data(baseline, name='expr', dshape=self.macro_dshape)
deltas = bz.Data(baseline, name='deltas', dshape=self.macro_dshape)
deltas = bz.transform(
deltas,
value=deltas.value + 10,
timestamp=deltas.timestamp + timedelta(days=1),
)
nassets = len(asset_info)
expected_views = keymap(
pd.Timestamp, {
'2014-01-03':
repeat_last_axis(
np.array([10.0, 10.0, 10.0]),
nassets,
),
'2014-01-06':
repeat_last_axis(
np.array([10.0, 10.0, 11.0]),
nassets,
),
})
cal = pd.DatetimeIndex([
pd.Timestamp('2014-01-01'),
pd.Timestamp('2014-01-02'),
pd.Timestamp('2014-01-03'),
# omitting the 4th and 5th to simulate a weekend
pd.Timestamp('2014-01-06'),
])
with tmp_asset_finder(equities=asset_info) as finder:
expected_output = pd.DataFrame(
list(concatv([10] * nassets, [11] * nassets)),
index=pd.MultiIndex.from_product((
sorted(expected_views.keys()),
finder.retrieve_all(asset_info.index),
)),
columns=('value', ),
)
self._run_pipeline(
expr,
deltas,
expected_views,
expected_output,
finder,
calendar=cal,
start=cal[2],
end=cal[-1],
window_length=3,
compute_fn=op.itemgetter(-1),
)
def _load_dataset(self, dates, assets, mask, columns):
try:
(dataset, ) = set(map(getdataset, columns))
except ValueError:
raise AssertionError('all columns must come from the same dataset')
expr, deltas, checkpoints, odo_kwargs, apply_deltas_adjustments = self[
dataset]
have_sids = (dataset.ndim == 2)
asset_idx = pd.Series(index=assets, data=np.arange(len(assets)))
assets = list(map(int, assets)) # coerce from numpy.int64
added_query_fields = {AD_FIELD_NAME, TS_FIELD_NAME
} | ({SID_FIELD_NAME} if have_sids else set())
requested_columns = set(map(getname, columns))
colnames = sorted(added_query_fields | requested_columns)
data_query_time = self._data_query_time
data_query_tz = self._data_query_tz
lower_dt, upper_dt = normalize_data_query_bounds(
dates[0],
dates[-1],
data_query_time,
data_query_tz,
)
def collect_expr(e, lower):
"""Materialize the expression as a dataframe.
Parameters
----------
e : Expr
The baseline or deltas expression.
lower : datetime
The lower time bound to query.
Returns
-------
result : pd.DataFrame
The resulting dataframe.
Notes
-----
This can return more data than needed. The in memory reindex will
handle this.
"""
predicate = e[TS_FIELD_NAME] <= upper_dt
if lower is not None:
predicate &= e[TS_FIELD_NAME] >= lower
return odo(e[predicate][colnames], pd.DataFrame, **odo_kwargs)
lower, materialized_checkpoints = get_materialized_checkpoints(
checkpoints, colnames, lower_dt, odo_kwargs)
materialized_expr = self.pool.apply_async(collect_expr, (expr, lower))
materialized_deltas = (self.pool.apply(collect_expr,
(deltas, lower)) if deltas
is not None else pd.DataFrame(columns=colnames))
if materialized_checkpoints is not None:
materialized_expr = pd.concat(
(
materialized_checkpoints,
materialized_expr.get(),
),
ignore_index=True,
copy=False,
)
# It's not guaranteed that assets returned by the engine will contain
# all sids from the deltas table; filter out such mismatches here.
if not materialized_deltas.empty and have_sids:
materialized_deltas = materialized_deltas[
materialized_deltas[SID_FIELD_NAME].isin(assets)]
if data_query_time is not None:
for m in (materialized_expr, materialized_deltas):
m.loc[:, TS_FIELD_NAME] = m.loc[:, TS_FIELD_NAME].astype(
'datetime64[ns]')
normalize_timestamp_to_query_time(
m,
data_query_time,
data_query_tz,
inplace=True,
ts_field=TS_FIELD_NAME,
)
# Inline the deltas that changed our most recently known value.
# Also, we reindex by the dates to create a dense representation of
# the data.
sparse_output, non_novel_deltas = overwrite_novel_deltas(
materialized_expr,
materialized_deltas,
dates,
)
if AD_FIELD_NAME not in requested_columns:
sparse_output.drop(AD_FIELD_NAME, axis=1, inplace=True)
sparse_deltas = last_in_date_group(non_novel_deltas,
dates,
assets,
reindex=False,
have_sids=have_sids)
dense_output = last_in_date_group(sparse_output,
dates,
assets,
reindex=True,
have_sids=have_sids)
ffill_across_cols(dense_output, columns,
{c.name: c.name
for c in columns})
# By default, no non-novel deltas are applied.
def no_adjustments_from_deltas(*args):
return {}
adjustments_from_deltas = no_adjustments_from_deltas
if have_sids:
if apply_deltas_adjustments:
adjustments_from_deltas = adjustments_from_deltas_with_sids
column_view = identity
else:
# If we do not have sids, use the column view to make a single
# column vector which is unassociated with any assets.
column_view = op.itemgetter(np.s_[:, np.newaxis])
if apply_deltas_adjustments:
adjustments_from_deltas = adjustments_from_deltas_no_sids
mask = np.full(
shape=(len(mask), 1),
fill_value=True,
dtype=bool_dtype,
)
return {
column: AdjustedArray(
column_view(
dense_output[column.name].values.astype(column.dtype), ),
mask,
adjustments_from_deltas(
dates,
sparse_output[TS_FIELD_NAME].values,
column_idx,
column.name,
asset_idx,
sparse_deltas,
),
column.missing_value,
)
for column_idx, column in enumerate(columns)
}
def _load_dataset(self, dates, assets, mask, columns):
try:
(dataset,) = set(map(getdataset, columns))
except ValueError:
raise AssertionError('all columns must come from the same dataset')
expr, deltas, checkpoints, odo_kwargs = self[dataset]
have_sids = (dataset.ndim == 2)
asset_idx = pd.Series(index=assets, data=np.arange(len(assets)))
assets = list(map(int, assets)) # coerce from numpy.int64
added_query_fields = [AD_FIELD_NAME, TS_FIELD_NAME] + (
[SID_FIELD_NAME] if have_sids else []
)
colnames = added_query_fields + list(map(getname, columns))
data_query_time = self._data_query_time
data_query_tz = self._data_query_tz
lower_dt, upper_dt = normalize_data_query_bounds(
dates[0],
dates[-1],
data_query_time,
data_query_tz,
)
def collect_expr(e, lower):
"""Materialize the expression as a dataframe.
Parameters
----------
e : Expr
The baseline or deltas expression.
lower : datetime
The lower time bound to query.
Returns
-------
result : pd.DataFrame
The resulting dataframe.
Notes
-----
This can return more data than needed. The in memory reindex will
handle this.
"""
predicate = e[TS_FIELD_NAME] <= upper_dt
if lower is not None:
predicate &= e[TS_FIELD_NAME] >= lower
return odo(e[predicate][colnames], pd.DataFrame, **odo_kwargs)
lower, materialized_checkpoints = get_materialized_checkpoints(
checkpoints, colnames, lower_dt, odo_kwargs
)
materialized_expr = self.pool.apply_async(collect_expr, (expr, lower))
materialized_deltas = (
self.pool.apply(collect_expr, (deltas, lower))
if deltas is not None else
pd.DataFrame(columns=colnames)
)
if materialized_checkpoints is not None:
materialized_expr = pd.concat(
(
materialized_checkpoints,
materialized_expr.get(),
),
ignore_index=True,
copy=False,
)
# It's not guaranteed that assets returned by the engine will contain
# all sids from the deltas table; filter out such mismatches here.
if not materialized_deltas.empty and have_sids:
materialized_deltas = materialized_deltas[
materialized_deltas[SID_FIELD_NAME].isin(assets)
]
if data_query_time is not None:
for m in (materialized_expr, materialized_deltas):
m.loc[:, TS_FIELD_NAME] = m.loc[
:, TS_FIELD_NAME
].astype('datetime64[ns]')
normalize_timestamp_to_query_time(
m,
data_query_time,
data_query_tz,
inplace=True,
ts_field=TS_FIELD_NAME,
)
# Inline the deltas that changed our most recently known value.
# Also, we reindex by the dates to create a dense representation of
# the data.
sparse_output, non_novel_deltas = overwrite_novel_deltas(
materialized_expr,
materialized_deltas,
dates,
)
sparse_output.drop(AD_FIELD_NAME, axis=1, inplace=True)
sparse_deltas = last_in_date_group(non_novel_deltas,
dates,
assets,
reindex=False,
have_sids=have_sids)
dense_output = last_in_date_group(sparse_output,
dates,
assets,
reindex=True,
have_sids=have_sids)
ffill_across_cols(dense_output, columns, {c.name: c.name
for c in columns})
if have_sids:
adjustments_from_deltas = adjustments_from_deltas_with_sids
column_view = identity
else:
# If we do not have sids, use the column view to make a single
# column vector which is unassociated with any assets.
column_view = op.itemgetter(np.s_[:, np.newaxis])
adjustments_from_deltas = adjustments_from_deltas_no_sids
mask = np.full(
shape=(len(mask), 1), fill_value=True, dtype=bool_dtype,
)
return {
column: AdjustedArray(
column_view(
dense_output[column.name].values.astype(column.dtype),
),
mask,
adjustments_from_deltas(
dates,
sparse_output[TS_FIELD_NAME].values,
column_idx,
column.name,
asset_idx,
sparse_deltas,
),
column.missing_value,
)
for column_idx, column in enumerate(columns)
}
def _load_dataset(self, dates, assets, mask, columns):
try:
(dataset, ) = set(map(getdataset, columns))
except ValueError:
raise AssertionError('all columns must come from the same dataset')
expr, deltas, checkpoints, odo_kwargs = self[dataset]
have_sids = (dataset.ndim == 2)
asset_idx = pd.Series(index=assets, data=np.arange(len(assets)))
assets = list(map(int, assets)) # coerce from numpy.int64
added_query_fields = [AD_FIELD_NAME, TS_FIELD_NAME
] + ([SID_FIELD_NAME] if have_sids else [])
colnames = added_query_fields + list(map(getname, columns))
data_query_time = self._data_query_time
data_query_tz = self._data_query_tz
lower_dt, upper_dt = normalize_data_query_bounds(
dates[0],
dates[-1],
data_query_time,
data_query_tz,
)
def collect_expr(e, lower):
"""Materialize the expression as a dataframe.
Parameters
----------
e : Expr
The baseline or deltas expression.
lower : datetime
The lower time bound to query.
Returns
-------
result : pd.DataFrame
The resulting dataframe.
Notes
-----
This can return more data than needed. The in memory reindex will
handle this.
"""
predicate = e[TS_FIELD_NAME] <= upper_dt
if lower is not None:
predicate &= e[TS_FIELD_NAME] >= lower
return odo(e[predicate][colnames], pd.DataFrame, **odo_kwargs)
if checkpoints is not None:
ts = checkpoints[TS_FIELD_NAME]
checkpoints_ts = odo(ts[ts <= lower_dt].max(), pd.Timestamp)
if pd.isnull(checkpoints_ts):
materialized_checkpoints = pd.DataFrame(columns=colnames)
lower = None
else:
materialized_checkpoints = odo(
checkpoints[ts == checkpoints_ts][colnames], pd.DataFrame,
**odo_kwargs)
lower = checkpoints_ts
else:
materialized_checkpoints = pd.DataFrame(columns=colnames)
lower = None
materialized_expr = self.pool.apply_async(collect_expr, (expr, lower))
materialized_deltas = (self.pool.apply(collect_expr,
(deltas, lower)) if deltas
is not None else pd.DataFrame(columns=colnames))
if materialized_checkpoints is not None:
materialized_expr = pd.concat(
(
materialized_checkpoints,
materialized_expr.get(),
),
ignore_index=True,
copy=False,
)
# It's not guaranteed that assets returned by the engine will contain
# all sids from the deltas table; filter out such mismatches here.
if not materialized_deltas.empty and have_sids:
materialized_deltas = materialized_deltas[
materialized_deltas[SID_FIELD_NAME].isin(assets)]
if data_query_time is not None:
for m in (materialized_expr, materialized_deltas):
m.loc[:, TS_FIELD_NAME] = m.loc[:, TS_FIELD_NAME].astype(
'datetime64[ns]')
normalize_timestamp_to_query_time(
m,
data_query_time,
data_query_tz,
inplace=True,
ts_field=TS_FIELD_NAME,
)
# Inline the deltas that changed our most recently known value.
# Also, we reindex by the dates to create a dense representation of
# the data.
sparse_output, non_novel_deltas = overwrite_novel_deltas(
materialized_expr,
materialized_deltas,
dates,
)
sparse_output.drop(AD_FIELD_NAME, axis=1, inplace=True)
def last_in_date_group(df, reindex, have_sids=have_sids):
idx = dates[dates.searchsorted(
df[TS_FIELD_NAME].values.astype('datetime64[D]'))]
if have_sids:
idx = [idx, SID_FIELD_NAME]
last_in_group = df.drop(TS_FIELD_NAME, axis=1).groupby(
idx,
sort=False,
).last()
if have_sids:
last_in_group = last_in_group.unstack()
if reindex:
if have_sids:
cols = last_in_group.columns
last_in_group = last_in_group.reindex(
index=dates,
columns=pd.MultiIndex.from_product(
(cols.levels[0], assets),
names=cols.names,
),
)
else:
last_in_group = last_in_group.reindex(dates)
return last_in_group
sparse_deltas = last_in_date_group(non_novel_deltas, reindex=False)
dense_output = last_in_date_group(sparse_output, reindex=True)
dense_output.ffill(inplace=True)
# Fill in missing values specified by each column. This is made
# significantly more complex by the fact that we need to work around
# two pandas issues:
# 1) When we have sids, if there are no records for a given sid for any
# dates, pandas will generate a column full of NaNs for that sid.
# This means that some of the columns in `dense_output` are now
# float instead of the intended dtype, so we have to coerce back to
# our expected type and convert NaNs into the desired missing value.
# 2) DataFrame.ffill assumes that receiving None as a fill-value means
# that no value was passed. Consequently, there's no way to tell
# pandas to replace NaNs in an object column with None using fillna,
# so we have to roll our own instead using df.where.
for column in columns:
# Special logic for strings since `fillna` doesn't work if the
# missing value is `None`.
if column.dtype == categorical_dtype:
dense_output[column.name] = dense_output[column.name].where(
pd.notnull(dense_output[column.name]),
column.missing_value)
else:
# We need to execute `fillna` before `astype` in case the
# column contains NaNs and needs to be cast to bool or int.
# This is so that the NaNs are replaced first, since pandas
# can't convert NaNs for those types.
dense_output[column.name] = dense_output[column.name].fillna(
column.missing_value).astype(column.dtype)
if have_sids:
adjustments_from_deltas = adjustments_from_deltas_with_sids
column_view = identity
else:
# If we do not have sids, use the column view to make a single
# column vector which is unassociated with any assets.
column_view = op.itemgetter(np.s_[:, np.newaxis])
adjustments_from_deltas = adjustments_from_deltas_no_sids
mask = np.full(
shape=(len(mask), 1),
fill_value=True,
dtype=bool_dtype,
)
return {
column: AdjustedArray(
column_view(
dense_output[column.name].values.astype(column.dtype), ),
mask,
adjustments_from_deltas(
dates,
sparse_output[TS_FIELD_NAME].values,
column_idx,
column.name,
asset_idx,
sparse_deltas,
),
column.missing_value,
)
for column_idx, column in enumerate(columns)
}
def test_novel_deltas(self, asset_info):
base_dates = pd.DatetimeIndex([
pd.Timestamp('2014-01-01'),
pd.Timestamp('2014-01-04')
])
repeated_dates = base_dates.repeat(3)
baseline = pd.DataFrame({
'sid': self.sids * 2,
'value': (0., 1., 2., 1., 2., 3.),
'int_value': (0, 1, 2, 1, 2, 3),
'asof_date': repeated_dates,
'timestamp': repeated_dates,
})
expr = bz.data(baseline, name='expr', dshape=self.dshape)
deltas = bz.data(
odo(
bz.transform(
expr,
value=expr.value + 10,
timestamp=expr.timestamp + timedelta(days=1),
),
pd.DataFrame,
),
name='delta',
dshape=self.dshape,
)
expected_views = keymap(pd.Timestamp, {
'2014-01-03': np.array([[10.0, 11.0, 12.0],
[10.0, 11.0, 12.0],
[10.0, 11.0, 12.0]]),
'2014-01-06': np.array([[10.0, 11.0, 12.0],
[10.0, 11.0, 12.0],
[11.0, 12.0, 13.0]]),
})
if len(asset_info) == 4:
expected_views = valmap(
lambda view: np.c_[view, [np.nan, np.nan, np.nan]],
expected_views,
)
expected_output_buffer = [10, 11, 12, np.nan, 11, 12, 13, np.nan]
else:
expected_output_buffer = [10, 11, 12, 11, 12, 13]
cal = pd.DatetimeIndex([
pd.Timestamp('2014-01-01'),
pd.Timestamp('2014-01-02'),
pd.Timestamp('2014-01-03'),
# omitting the 4th and 5th to simulate a weekend
pd.Timestamp('2014-01-06'),
])
with tmp_asset_finder(equities=asset_info) as finder:
expected_output = pd.DataFrame(
expected_output_buffer,
index=pd.MultiIndex.from_product((
sorted(expected_views.keys()),
finder.retrieve_all(asset_info.index),
)),
columns=('value',),
)
self._run_pipeline(
expr,
deltas,
expected_views,
expected_output,
finder,
calendar=cal,
start=cal[2],
end=cal[-1],
window_length=3,
compute_fn=op.itemgetter(-1),
)
