def test_get_next_chunk(entityset):
times = list([datetime(2011, 4, 9, 10, 30, i * 6) for i in range(5)] +
[datetime(2011, 4, 9, 10, 31, i * 9)
for i in range(4)] + [datetime(2011, 4, 9, 10, 40, 0)] +
[datetime(2011, 4, 10, 10, 40, i) for i in range(2)] +
[datetime(2011, 4, 10, 10, 41, i * 3) for i in range(3)] +
[datetime(2011, 4, 10, 11, 10, i * 3) for i in range(2)])
cutoff_time = pd.DataFrame({'time': times, 'instance_id': range(17)})
chunks = [chunk for chunk in get_next_chunk(cutoff_time, 'time', 4)]
assert len(chunks) == 5
# test when a cutoff time is larger than a chunk
times = list([datetime(2011, 4, 9, 10, 30, 6) for i in range(5)] +
[datetime(2011, 4, 9, 10, 31, 9)
for i in range(4)] + [datetime(2011, 4, 9, 10, 40, 0)] +
[datetime(2011, 4, 10, 10, 40, i) for i in range(2)] +
[datetime(2011, 4, 10, 10, 41, i * 3) for i in range(3)] +
[datetime(2011, 4, 10, 11, 10, i * 3) for i in range(2)])
cutoff_time = pd.DataFrame({'time': times, 'instance_id': range(17)})
chunks = [chunk for chunk in get_next_chunk(cutoff_time, 'time', 4)]
assert len(chunks) == 5
# largest cutoff time handled first
largest = pd.Series([datetime(2011, 4, 9, 10, 30, 6) for i in range(4)])
assert (chunks[0]['time'] == largest).all()
# additional part of cutoff time added to another chunk
assert (chunks[2]['time'] == times[4]).any()
# test when cutoff_time is smaller than num_per_chunk
chunks = [chunk for chunk in get_next_chunk(cutoff_time, 'time', 18)]
assert len(chunks) == 1
def test_get_next_chunk(entityset):
times = list([datetime(2011, 4, 9, 10, 30, i * 6) for i in range(5)] +
[datetime(2011, 4, 9, 10, 31, i * 9) for i in range(4)] +
[datetime(2011, 4, 9, 10, 40, 0)] +
[datetime(2011, 4, 10, 10, 40, i) for i in range(2)] +
[datetime(2011, 4, 10, 10, 41, i * 3) for i in range(3)] +
[datetime(2011, 4, 10, 11, 10, i * 3) for i in range(2)])
cutoff_time = pd.DataFrame({'time': times, 'instance_id': range(17)})
chunks = [chunk for chunk in get_next_chunk(cutoff_time, 'time', 4)]
assert len(chunks) == 5
# test when a cutoff time is larger than a chunk
times = list([datetime(2011, 4, 9, 10, 30, 6) for i in range(5)] +
[datetime(2011, 4, 9, 10, 31, 9) for i in range(4)] +
[datetime(2011, 4, 9, 10, 40, 0)] +
[datetime(2011, 4, 10, 10, 40, i) for i in range(2)] +
[datetime(2011, 4, 10, 10, 41, i * 3) for i in range(3)] +
[datetime(2011, 4, 10, 11, 10, i * 3) for i in range(2)])
cutoff_time = pd.DataFrame({'time': times, 'instance_id': range(17)})
chunks = [chunk for chunk in get_next_chunk(cutoff_time, 'time', 4)]
assert len(chunks) == 5
# largest cutoff time handled first
largest = pd.Series([datetime(2011, 4, 9, 10, 30, 6) for i in range(4)])
assert (chunks[0]['time'] == largest).all()
# additional part of cutoff time added to another chunk
assert (chunks[2]['time'] == times[4]).any()
# test when cutoff_time is smaller than num_per_chunk
chunks = [chunk for chunk in get_next_chunk(cutoff_time, 'time', 18)]
assert len(chunks) == 1
def calculate_feature_matrix(features,
entityset=None,
cutoff_time=None,
instance_ids=None,
entities=None,
relationships=None,
cutoff_time_in_index=False,
training_window=None,
approximate=None,
save_progress=None,
verbose=False,
chunk_size=None,
n_jobs=1,
dask_kwargs=None):
"""Calculates a matrix for a given set of instance ids and calculation times.
Args:
features (list[:class:`.FeatureBase`]): Feature definitions to be calculated.
entityset (EntitySet): An already initialized entityset. Required if `entities` and `relationships`
not provided
cutoff_time (pd.DataFrame or Datetime): Specifies at which time to calculate
the features for each instance. The resulting feature matrix will use data
up to and including the cutoff_time. Can either be a DataFrame with
'instance_id' and 'time' columns, DataFrame with the name of the
index variable in the target entity and a time column, or a single
value to calculate for all instances. If the dataframe has more than two columns, any additional
columns will be added to the resulting feature matrix.
instance_ids (list): List of instances to calculate features on. Only
used if cutoff_time is a single datetime.
entities (dict[str -> tuple(pd.DataFrame, str, str)]): dictionary of
entities. Entries take the format
{entity id: (dataframe, id column, (time_column))}.
relationships (list[(str, str, str, str)]): list of relationships
between entities. List items are a tuple with the format
(parent entity id, parent variable, child entity id, child variable).
cutoff_time_in_index (bool): If True, return a DataFrame with a MultiIndex
where the second index is the cutoff time (first is instance id).
DataFrame will be sorted by (time, instance_id).
training_window (Timedelta or str, optional):
Window defining how much time before the cutoff time data
can be used when calculating features. If ``None``, all data before cutoff time is used.
Defaults to ``None``.
approximate (Timedelta or str): Frequency to group instances with similar
cutoff times by for features with costly calculations. For example,
if bucket is 24 hours, all instances with cutoff times on the same
day will use the same calculation for expensive features.
verbose (bool, optional): Print progress info. The time granularity is
per chunk.
chunk_size (int or float or None or "cutoff time"): Number of rows of
output feature matrix to calculate at time. If passed an integer
greater than 0, will try to use that many rows per chunk. If passed
a float value between 0 and 1 sets the chunk size to that
percentage of all instances. If passed the string "cutoff time",
rows are split per cutoff time.
n_jobs (int, optional): number of parallel processes to use when
calculating feature matrix
dask_kwargs (dict, optional): Dictionary of keyword arguments to be
passed when creating the dask client and scheduler. Even if n_jobs
is not set, using `dask_kwargs` will enable multiprocessing.
Main parameters:
cluster (str or dask.distributed.LocalCluster):
cluster or address of cluster to send tasks to. If unspecified,
a cluster will be created.
diagnostics port (int):
port number to use for web dashboard. If left unspecified, web
interface will not be enabled.
Valid keyword arguments for LocalCluster will also be accepted.
save_progress (str, optional): path to save intermediate computational results.
"""
assert (isinstance(features, list) and features != [] and
all([isinstance(feature, FeatureBase) for feature in features])), \
"features must be a non-empty list of features"
# handle loading entityset
from featuretools.entityset.entityset import EntitySet
if not isinstance(entityset, EntitySet):
if entities is not None and relationships is not None:
entityset = EntitySet("entityset", entities, relationships)
target_entity = entityset[features[0].entity.id]
pass_columns = []
if not isinstance(cutoff_time, pd.DataFrame):
if isinstance(cutoff_time, list):
raise TypeError("cutoff_time must be a single value or DataFrame")
if cutoff_time is None:
if entityset.time_type == NumericTimeIndex:
cutoff_time = np.inf
else:
cutoff_time = datetime.now()
if instance_ids is None:
index_var = target_entity.index
df = target_entity._handle_time(target_entity.df,
time_last=cutoff_time,
training_window=training_window)
instance_ids = df[index_var].tolist()
cutoff_time = [cutoff_time] * len(instance_ids)
map_args = [(id, time) for id, time in zip(instance_ids, cutoff_time)]
cutoff_time = pd.DataFrame(map_args, columns=['instance_id', 'time'])
cutoff_time = cutoff_time.reset_index(drop=True)
# handle how columns are names in cutoff_time
# maybe add _check_time_dtype helper function
if "instance_id" not in cutoff_time.columns:
if target_entity.index not in cutoff_time.columns:
raise AttributeError(
'Name of the index variable in the target entity'
' or "instance_id" must be present in cutoff_time')
# rename to instance_id
cutoff_time.rename(columns={target_entity.index: "instance_id"},
inplace=True)
if "time" not in cutoff_time.columns:
# take the first column that isn't instance_id and assume it is time
not_instance_id = [
c for c in cutoff_time.columns if c != "instance_id"
]
cutoff_time.rename(columns={not_instance_id[0]: "time"}, inplace=True)
# Check that cutoff_time time type matches entityset time type
if entityset.time_type == NumericTimeIndex:
if cutoff_time['time'].dtype.name not in PandasTypes._pandas_numerics:
raise TypeError("cutoff_time times must be numeric: try casting "
"via pd.to_numeric(cutoff_time['time'])")
elif entityset.time_type == DatetimeTimeIndex:
if cutoff_time['time'].dtype.name not in PandasTypes._pandas_datetimes:
raise TypeError(
"cutoff_time times must be datetime type: try casting via pd.to_datetime(cutoff_time['time'])"
)
assert (cutoff_time[['instance_id', 'time']].duplicated().sum() == 0), \
"Duplicated rows in cutoff time dataframe."
pass_columns = [column_name for column_name in cutoff_time.columns[2:]]
if _check_time_type(cutoff_time['time'].iloc[0]) is None:
raise ValueError("cutoff_time time values must be datetime or numeric")
# make sure dtype of instance_id in cutoff time
# is same as column it references
target_entity = features[0].entity
dtype = entityset[target_entity.id].df[target_entity.index].dtype
cutoff_time["instance_id"] = cutoff_time["instance_id"].astype(dtype)
feature_set = FeatureSet(features)
# Get features to approximate
if approximate is not None:
approximate_feature_trie = gather_approximate_features(feature_set)
# Make a new FeatureSet that ignores approximated features
feature_set = FeatureSet(
features, approximate_feature_trie=approximate_feature_trie)
# Check if there are any non-approximated aggregation features
no_unapproximated_aggs = True
for feature in features:
if isinstance(feature, AggregationFeature):
# do not need to check if feature is in to_approximate since
# only base features of direct features can be in to_approximate
no_unapproximated_aggs = False
break
if approximate is not None:
all_approx_features = {
f
for _, feats in feature_set.approximate_feature_trie
for f in feats
}
else:
all_approx_features = set()
deps = feature.get_dependencies(deep=True, ignored=all_approx_features)
for dependency in deps:
if isinstance(dependency, AggregationFeature):
no_unapproximated_aggs = False
break
cutoff_df_time_var = 'time'
target_time = '_original_time'
num_per_chunk = calc_num_per_chunk(chunk_size, cutoff_time.shape)
if approximate is not None:
# If there are approximated aggs, bin times
binned_cutoff_time = bin_cutoff_times(cutoff_time.copy(), approximate)
# Think about collisions: what if original time is a feature
binned_cutoff_time[target_time] = cutoff_time[cutoff_df_time_var]
cutoff_time_to_pass = binned_cutoff_time
else:
cutoff_time_to_pass = cutoff_time
if num_per_chunk == "cutoff time":
iterator = cutoff_time_to_pass.groupby(cutoff_df_time_var)
else:
iterator = get_next_chunk(cutoff_time=cutoff_time_to_pass,
time_variable=cutoff_df_time_var,
num_per_chunk=num_per_chunk)
chunks = []
if num_per_chunk == "cutoff time":
for _, group in iterator:
chunks.append(group)
else:
for chunk in iterator:
chunks.append(chunk)
if n_jobs != 1 or dask_kwargs is not None:
feature_matrix = parallel_calculate_chunks(
chunks=chunks,
feature_set=feature_set,
approximate=approximate,
training_window=training_window,
verbose=verbose,
save_progress=save_progress,
entityset=entityset,
n_jobs=n_jobs,
no_unapproximated_aggs=no_unapproximated_aggs,
cutoff_df_time_var=cutoff_df_time_var,
target_time=target_time,
pass_columns=pass_columns,
dask_kwargs=dask_kwargs or {})
else:
feature_matrix = linear_calculate_chunks(
chunks=chunks,
feature_set=feature_set,
approximate=approximate,
training_window=training_window,
verbose=verbose,
save_progress=save_progress,
entityset=entityset,
no_unapproximated_aggs=no_unapproximated_aggs,
cutoff_df_time_var=cutoff_df_time_var,
target_time=target_time,
pass_columns=pass_columns)
feature_matrix = pd.concat(feature_matrix)
feature_matrix.sort_index(level='time', kind='mergesort', inplace=True)
if not cutoff_time_in_index:
feature_matrix.reset_index(level='time', drop=True, inplace=True)
if save_progress and os.path.exists(os.path.join(save_progress, 'temp')):
shutil.rmtree(os.path.join(save_progress, 'temp'))
return feature_matrix