def __init__(self):
from lale.lib.rasl.concat_features import ConcatFeatures
self._pipeline_suffix = (
ConcatFeatures >> Map(
columns={
"y": it.y_true, # observed values
"f": it.y_pred, # predicted values
"y2": it.y_true * it.y_true, # squares
"e2": (it.y_true - it.y_pred) *
(it.y_true - it.y_pred), # type: ignore
}) >> Aggregate(
columns={
"n": count(it.y),
"sum": sum(it.y),
"sum_sq": sum(it.y2),
"res_sum_sq": sum(it.e2), # residual sum of squares
}))
def __init__(self):
from lale.lib.rasl.concat_features import ConcatFeatures
self._pipeline_suffix = (
ConcatFeatures >> Map(
columns={"match": astype("int", it.y_true == it.y_pred)
}) # type: ignore
>> Aggregate(columns={
"match": sum(it.match),
"total": count(it.match)
}))
def _lift(X, hyperparams):
feature_names_in_ = get_columns(X)
strategy = hyperparams["strategy"]
if strategy == "constant":
fill_value = _SimpleImputerImpl._get_fill_value(X, hyperparams)
agg_data = [[fill_value for col in get_columns(X)]]
lifted_statistics = pd.DataFrame(agg_data, columns=get_columns(X))
elif strategy == "mean":
agg_op_sum = Aggregate(
columns={c: sum(it[c])
for c in get_columns(X)},
exclude_value=hyperparams["missing_values"],
)
agg_op_count = Aggregate(
columns={c: count(it[c])
for c in get_columns(X)},
exclude_value=hyperparams["missing_values"],
)
lifted_statistics = {}
agg_sum = agg_op_sum.transform(X)
if agg_sum is not None and _is_spark_df(agg_sum):
agg_sum = agg_sum.toPandas()
agg_count = agg_op_count.transform(X)
if agg_count is not None and _is_spark_df(agg_count):
agg_count = agg_count.toPandas()
lifted_statistics["sum"] = agg_sum
lifted_statistics["count"] = agg_count
else:
raise ValueError(
"_lift is only supported for imputation strategy `mean` and `constant`."
)
return (
feature_names_in_,
lifted_statistics,
strategy,
) # strategy is added so that _combine can use it
def test_with_hyperopt2(self):
from lale.expressions import (
count,
it,
max,
mean,
min,
string_indexer,
sum,
variance,
)
wrap_imported_operators()
scan = Scan(table=it["main"])
scan_0 = Scan(table=it["customers"])
join = Join(pred=[(it["main"]["group_customer_id"] == it["customers"]
["group_customer_id"])])
map = Map(
columns={
"[main](group_customer_id)[customers]|number_children|identity":
it["number_children"],
"[main](group_customer_id)[customers]|name|identity":
it["name"],
"[main](group_customer_id)[customers]|income|identity":
it["income"],
"[main](group_customer_id)[customers]|address|identity":
it["address"],
"[main](group_customer_id)[customers]|age|identity":
it["age"],
},
remainder="drop",
)
pipeline_4 = join >> map
scan_1 = Scan(table=it["purchase"])
join_0 = Join(
pred=[(it["main"]["group_id"] == it["purchase"]["group_id"])],
join_limit=50.0,
)
aggregate = Aggregate(
columns={
"[main](group_id)[purchase]|price|variance":
variance(it["price"]),
"[main](group_id)[purchase]|time|sum": sum(it["time"]),
"[main](group_id)[purchase]|time|mean": mean(it["time"]),
"[main](group_id)[purchase]|time|min": min(it["time"]),
"[main](group_id)[purchase]|price|sum": sum(it["price"]),
"[main](group_id)[purchase]|price|count": count(it["price"]),
"[main](group_id)[purchase]|price|mean": mean(it["price"]),
"[main](group_id)[purchase]|price|min": min(it["price"]),
"[main](group_id)[purchase]|price|max": max(it["price"]),
"[main](group_id)[purchase]|time|max": max(it["time"]),
"[main](group_id)[purchase]|time|variance":
variance(it["time"]),
},
group_by=it["row_id"],
)
pipeline_5 = join_0 >> aggregate
map_0 = Map(
columns={
"[main]|group_customer_id|identity": it["group_customer_id"],
"[main]|transaction_id|identity": it["transaction_id"],
"[main]|group_id|identity": it["group_id"],
"[main]|comments|identity": it["comments"],
"[main]|id|identity": it["id"],
"prefix_0_id": it["prefix_0_id"],
"next_purchase": it["next_purchase"],
"[main]|time|identity": it["time"],
},
remainder="drop",
)
scan_2 = Scan(table=it["transactions"])
scan_3 = Scan(table=it["products"])
join_1 = Join(pred=[
(it["main"]["transaction_id"] == it["transactions"]
["transaction_id"]),
(it["transactions"]["product_id"] == it["products"]["product_id"]),
])
map_1 = Map(
columns={
"[main](transaction_id)[transactions](product_id)[products]|price|identity":
it["price"],
"[main](transaction_id)[transactions](product_id)[products]|type|identity":
it["type"],
},
remainder="drop",
)
pipeline_6 = join_1 >> map_1
join_2 = Join(pred=[(it["main"]["transaction_id"] == it["transactions"]
["transaction_id"])])
map_2 = Map(
columns={
"[main](transaction_id)[transactions]|description|identity":
it["description"],
"[main](transaction_id)[transactions]|product_id|identity":
it["product_id"],
},
remainder="drop",
)
pipeline_7 = join_2 >> map_2
map_3 = Map(columns=[
string_indexer(it["[main]|comments|identity"]),
string_indexer(
it["[main](transaction_id)[transactions]|description|identity"]
),
string_indexer(it[
"[main](transaction_id)[transactions](product_id)[products]|type|identity"]
),
string_indexer(
it["[main](group_customer_id)[customers]|name|identity"]),
string_indexer(
it["[main](group_customer_id)[customers]|address|identity"]),
])
pipeline_8 = ConcatFeatures() >> map_3
relational = Relational(operator=make_pipeline_graph(
steps=[
scan,
scan_0,
pipeline_4,
scan_1,
pipeline_5,
map_0,
scan_2,
scan_3,
pipeline_6,
pipeline_7,
pipeline_8,
],
edges=[
(scan, pipeline_4),
(scan, pipeline_5),
(scan, map_0),
(scan, pipeline_6),
(scan, pipeline_7),
(scan_0, pipeline_4),
(pipeline_4, pipeline_8),
(scan_1, pipeline_5),
(pipeline_5, pipeline_8),
(map_0, pipeline_8),
(scan_2, pipeline_6),
(scan_2, pipeline_7),
(scan_3, pipeline_6),
(pipeline_6, pipeline_8),
(pipeline_7, pipeline_8),
],
))
pipeline = relational >> (KNeighborsClassifier | LogisticRegression)
from sklearn.datasets import load_iris
X, y = load_iris(return_X_y=True)
from lale.lib.lale import Hyperopt
opt = Hyperopt(estimator=pipeline, max_evals=2)
opt.fit(X, y)