diff --git a/aligned/feature_store.py b/aligned/feature_store.py index bb40359b..cefc745b 100644 --- a/aligned/feature_store.py +++ b/aligned/feature_store.py @@ -821,7 +821,7 @@ async def freshness(self) -> dict[FeatureLocation, datetime | None]: return await self.store.feature_source.freshness_for(locs) - def with_labels(self) -> SupervisedModelFeatureStore: + def with_labels(self, label_refs: set[FeatureReferance] | None = None) -> SupervisedModelFeatureStore: """Will also load the labels for the model ```python @@ -847,7 +847,12 @@ def with_labels(self) -> SupervisedModelFeatureStore: Returns: SupervisedModelFeatureStore: A new queryable feature store """ - return SupervisedModelFeatureStore(self.model, self.store, self.selected_version) + return SupervisedModelFeatureStore( + self.model, + self.store, + label_refs or self.model.predictions_view.labels_estimates_refs(), + self.selected_version, + ) def cached_at(self, location: DataFileReference) -> RetrivalJob: """Loads the model features from a pre computed location diff --git a/test_data/credit_history_mater.parquet b/test_data/credit_history_mater.parquet index 02e451b9..31dfef56 100644 Binary files a/test_data/credit_history_mater.parquet and b/test_data/credit_history_mater.parquet differ diff --git a/test_data/feature-store.json b/test_data/feature-store.json index 1f291a1a..1e1eace5 100644 --- a/test_data/feature-store.json +++ b/test_data/feature-store.json @@ -1 +1 @@ -{"metadata": {"created_at": "2024-01-06T12:18:32.619686", "name": "feature_store_location.py", "repo_url": null, "github_url": null}, "feature_views": [{"name": "titanic_parquet", "tags": {}, "source": {"mapping_keys": {}, "type_name": "parquet", "path": "test_data/titanic.parquet", "config": {"engine": "auto", "compression": "snappy", "should_write_index": false}}, "entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}], "features": [{"name": "cabin", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": null}, {"name": "name", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": null}, {"name": "survived", "dtype": {"name": "bool"}, "description": "If the passenger survived", "tags": null, "constraints": null}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "in_domain", "values": ["male", "female"]}]}, {"name": "sibsp", "dtype": {"name": "int32"}, "description": "Number of siblings on titanic", "tags": null, "constraints": [{"name": "upper_bound_inc", "value": 20.0}, {"name": "lower_bound_inc", "value": 0.0}]}, {"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "upper_bound_inc", "value": 100.0}, {"name": "lower_bound_inc", "value": 0.0}]}], "derived_features": [{"name": "is_mr", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic_parquet", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "contains", "dtype": {"name": "bool"}, "key": "name", "value": "Mr."}, "depth": 1}, {"name": "has_siblings", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic_parquet", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "not-equals", "dtype": {"name": "bool"}, "key": "sibsp", "value": {"name": "int", "value": 0}}, "depth": 1}, {"name": "is_female", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic_parquet", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "female"}}, "depth": 1}, {"name": "is_male", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic_parquet", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "male"}}, "depth": 1}], "description": "Some features from the titanic dataset", "aggregated_features": [], "event_timestamp": null, "stream_data_source": null, "application_source": null, "materialized_source": null, "event_triggers": null, "contacts": null, "indexes": []}, {"name": "titanic", "tags": {}, "source": {"mapping_keys": {"PassengerId": "passenger_id", "Age": "age", "Sex": "sex", "Survived": "survived", "SibSp": "sibsp", "UpdatedAt": "updated_at"}, "type_name": "csv", "path": "test_data/titanic_scd_data.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}], "features": [{"name": "cabin", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": null}, {"name": "name", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": null}, {"name": "survived", "dtype": {"name": "bool"}, "description": "If the passenger survived", "tags": null, "constraints": null}, {"name": "updated_at", "dtype": {"name": "datetime"}, "description": null, "tags": null, "constraints": null}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "in_domain", "values": ["male", "female"]}]}, {"name": "sibsp", "dtype": {"name": "int32"}, "description": "Number of siblings on titanic", "tags": null, "constraints": [{"name": "upper_bound_inc", "value": 20.0}, {"name": "lower_bound_inc", "value": 0.0}]}, {"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "upper_bound_inc", "value": 100.0}, {"name": "lower_bound_inc", "value": 0.0}]}], "derived_features": [{"name": "has_siblings", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "not-equals", "dtype": {"name": "bool"}, "key": "sibsp", "value": {"name": "int", "value": 0}}, "depth": 1}, {"name": "is_female", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "female"}}, "depth": 1}, {"name": "is_mr", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "contains", "dtype": {"name": "bool"}, "key": "name", "value": "Mr."}, "depth": 1}, {"name": "square_sibsp", "dtype": {"name": "float"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "mul", "dtype": {"name": "float"}, "front": "sibsp", "behind": "sibsp"}, "depth": 1}, {"name": "is_male", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "male"}}, "depth": 1}, {"name": "name_embedding", "dtype": {"name": "embedding"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "word_vectoriser", "dtype": {"name": "embedding"}, "key": "name", "model": {"name": "gensim", "model_name": "glove-wiki-gigaword-50", "config": {"to_lowercase": false, "deaccent": false, "encoding": "utf8", "errors": "strict"}, "loaded_model": null}}, "depth": 1}, {"name": "double_sibsp", "dtype": {"name": "float"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "mul_val", "dtype": {"name": "float"}, "key": "sibsp", "value": {"name": "int", "value": 2}}, "depth": 1}], "description": "Some features from the titanic dataset", "aggregated_features": [], "event_timestamp": {"name": "updated_at", "ttl": null, "description": null, "tags": null, "dtype": {"name": "datetime"}}, "stream_data_source": {"mapping_keys": {}, "name": "redis", "topic_name": "titanic_stream", "config": {"env_var": "REDIS_URL"}, "record_coder": {"coder_type": "json", "key": "json"}}, "application_source": null, "materialized_source": null, "event_triggers": null, "contacts": null, "indexes": [{"location": {"name": "titanic", "location": "feature_view"}, "vector": {"name": "name_embedding", "dtype": {"name": "embedding"}, "description": null, "tags": null, "constraints": null}, "vector_dim": 50, "metadata": [{"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "upper_bound_inc", "value": 100.0}, {"name": "lower_bound_inc", "value": 0.0}]}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "in_domain", "values": ["male", "female"]}]}], "storage": {"type_name": "redis", "config": {"env_var": "REDIS_URL"}, "name": "name_embedding_index", "initial_cap": 10000, "distance_metric": "COSINE", "index_alogrithm": "FLAT", "embedding_type": "FLOAT32"}, "entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}]}]}], "combined_feature_views": [], "models": [{"name": "titanic", "features": {"default_version": "default", "versions": {"default": [{"name": "age", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "float"}}, {"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}, {"name": "has_siblings", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "bool"}}, {"name": "is_male", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "bool"}}]}}, "predictions_view": {"entities": [], "features": [{"name": "probability", "dtype": {"name": "float"}, "description": "The probability of target named will_survive being 'True'.", "tags": null, "constraints": null}], "derived_features": [{"name": "will_survive", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "probability", "location": {"name": "titanic", "location": "model"}, "dtype": {"name": "float"}}], "transformation": {"name": "map_arg_max", "dtype": {"name": "bool"}, "column_mappings": {"probability": {"name": "bool", "value": true}}}, "depth": 1}], "model_version_column": null, "event_timestamp": null, "source": null, "application_source": null, "stream_source": null, "regression_targets": [], "classification_targets": [{"estimating": {"name": "survived", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "bool"}}, "feature": {"name": "will_survive", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null}, "on_ground_truth_event": null, "event_trigger": null, "class_probabilities": [{"outcome": {"name": "bool", "value": true}, "feature": {"name": "probability", "dtype": {"name": "float"}, "description": null, "tags": null, "constraints": null}}], "confidence": null}]}, "description": "A model predicting if a passenger will survive", "contacts": null, "tags": null, "dataset_store": null, "exposed_at_url": null}], "enrichers": []} +{"metadata": {"created_at": "2024-01-16T07:19:23.603848", "name": "feature_store_location.py", "repo_url": null, "github_url": null}, "feature_views": [{"name": "titanic_parquet", "tags": {}, "source": {"mapping_keys": {}, "type_name": "parquet", "path": "test_data/titanic.parquet", "config": {"engine": "auto", "compression": "snappy", "should_write_index": false}}, "entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}], "features": [{"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "lower_bound_inc", "value": 0.0}, {"name": "upper_bound_inc", "value": 100.0}]}, {"name": "cabin", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": null}, {"name": "name", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": null}, {"name": "sibsp", "dtype": {"name": "int32"}, "description": "Number of siblings on titanic", "tags": null, "constraints": [{"name": "lower_bound_inc", "value": 0.0}, {"name": "upper_bound_inc", "value": 20.0}]}, {"name": "survived", "dtype": {"name": "bool"}, "description": "If the passenger survived", "tags": null, "constraints": null}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "in_domain", "values": ["male", "female"]}]}], "derived_features": [{"name": "has_siblings", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic_parquet", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "not-equals", "dtype": {"name": "bool"}, "key": "sibsp", "value": {"name": "int", "value": 0}}, "depth": 1}, {"name": "is_mr", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic_parquet", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "contains", "dtype": {"name": "bool"}, "key": "name", "value": "Mr."}, "depth": 1}, {"name": "is_male", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic_parquet", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "male"}}, "depth": 1}, {"name": "is_female", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic_parquet", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "female"}}, "depth": 1}], "description": "Some features from the titanic dataset", "aggregated_features": [], "event_timestamp": null, "stream_data_source": null, "application_source": null, "materialized_source": null, "event_triggers": null, "contacts": null, "indexes": []}, {"name": "titanic", "tags": {}, "source": {"mapping_keys": {"PassengerId": "passenger_id", "Age": "age", "Sex": "sex", "Survived": "survived", "SibSp": "sibsp", "UpdatedAt": "updated_at"}, "type_name": "csv", "path": "test_data/titanic_scd_data.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}], "features": [{"name": "updated_at", "dtype": {"name": "datetime"}, "description": null, "tags": null, "constraints": null}, {"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "lower_bound_inc", "value": 0.0}, {"name": "upper_bound_inc", "value": 100.0}]}, {"name": "cabin", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": null}, {"name": "name", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": null}, {"name": "sibsp", "dtype": {"name": "int32"}, "description": "Number of siblings on titanic", "tags": null, "constraints": [{"name": "lower_bound_inc", "value": 0.0}, {"name": "upper_bound_inc", "value": 20.0}]}, {"name": "survived", "dtype": {"name": "bool"}, "description": "If the passenger survived", "tags": null, "constraints": null}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "in_domain", "values": ["male", "female"]}]}], "derived_features": [{"name": "double_sibsp", "dtype": {"name": "float"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "mul_val", "dtype": {"name": "float"}, "key": "sibsp", "value": {"name": "int", "value": 2}}, "depth": 1}, {"name": "is_mr", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "contains", "dtype": {"name": "bool"}, "key": "name", "value": "Mr."}, "depth": 1}, {"name": "is_male", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "male"}}, "depth": 1}, {"name": "is_female", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "female"}}, "depth": 1}, {"name": "name_embedding", "dtype": {"name": "embedding"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "word_vectoriser", "dtype": {"name": "embedding"}, "key": "name", "model": {"name": "gensim", "model_name": "glove-wiki-gigaword-50", "config": {"to_lowercase": false, "deaccent": false, "encoding": "utf8", "errors": "strict"}, "loaded_model": null}}, "depth": 1}, {"name": "has_siblings", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "not-equals", "dtype": {"name": "bool"}, "key": "sibsp", "value": {"name": "int", "value": 0}}, "depth": 1}, {"name": "square_sibsp", "dtype": {"name": "float"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "mul", "dtype": {"name": "float"}, "front": "sibsp", "behind": "sibsp"}, "depth": 1}], "description": "Some features from the titanic dataset", "aggregated_features": [], "event_timestamp": {"name": "updated_at", "ttl": null, "description": null, "tags": null, "dtype": {"name": "datetime"}}, "stream_data_source": {"mapping_keys": {}, "name": "redis", "topic_name": "titanic_stream", "config": {"env_var": "REDIS_URL"}, "record_coder": {"coder_type": "json", "key": "json"}}, "application_source": null, "materialized_source": null, "event_triggers": null, "contacts": null, "indexes": [{"location": {"name": "titanic", "location": "feature_view"}, "vector": {"name": "name_embedding", "dtype": {"name": "embedding"}, "description": null, "tags": null, "constraints": null}, "vector_dim": 50, "metadata": [{"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "lower_bound_inc", "value": 0.0}, {"name": "upper_bound_inc", "value": 100.0}]}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "in_domain", "values": ["male", "female"]}]}], "storage": {"type_name": "redis", "config": {"env_var": "REDIS_URL"}, "name": "name_embedding_index", "initial_cap": 10000, "distance_metric": "COSINE", "index_alogrithm": "FLAT", "embedding_type": "FLOAT32"}, "entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}]}]}], "combined_feature_views": [], "models": [{"name": "titanic", "features": {"default_version": "default", "versions": {"default": [{"name": "age", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "float"}}, {"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}, {"name": "has_siblings", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "bool"}}, {"name": "is_male", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "bool"}}]}}, "predictions_view": {"entities": [], "features": [{"name": "probability", "dtype": {"name": "float"}, "description": "The probability of target named will_survive being 'True'.", "tags": null, "constraints": null}], "derived_features": [{"name": "will_survive", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "probability", "location": {"name": "titanic", "location": "model"}, "dtype": {"name": "float"}}], "transformation": {"name": "map_arg_max", "dtype": {"name": "bool"}, "column_mappings": {"probability": {"name": "bool", "value": true}}}, "depth": 1}], "model_version_column": null, "event_timestamp": null, "source": null, "application_source": null, "stream_source": null, "regression_targets": [], "classification_targets": [{"estimating": {"name": "survived", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "bool"}}, "feature": {"name": "will_survive", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null}, "on_ground_truth_event": null, "event_trigger": null, "class_probabilities": [{"outcome": {"name": "bool", "value": true}, "feature": {"name": "probability", "dtype": {"name": "float"}, "description": null, "tags": null, "constraints": null}}], "confidence": null}]}, "description": "A model predicting if a passenger will survive", "contacts": null, "tags": null, "dataset_store": null, "exposed_at_url": null}], "enrichers": []} diff --git a/test_data/test_model.parquet b/test_data/test_model.parquet index 0b560788..1794e9c0 100644 Binary files a/test_data/test_model.parquet and b/test_data/test_model.parquet differ diff --git a/test_data/titanic-sets.json b/test_data/titanic-sets.json index a72c0e82..6d55b228 100644 --- a/test_data/titanic-sets.json +++ b/test_data/titanic-sets.json @@ -1 +1 @@ -{"raw_data": [], "train_test": [], "train_test_validation": [{"id": "titanic_test", "name": null, "request_result": {"entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}], "features": [{"name": "cabin", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}]}, {"name": "has_siblings", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "not-equals", "dtype": {"name": "bool"}, "key": "sibsp", "value": {"name": "int", "value": 0}}, "depth": 1}, {"name": "is_female", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "female"}}, "depth": 1}, {"name": "is_mr", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "contains", "dtype": {"name": "bool"}, "key": "name", "value": "Mr."}, "depth": 1}, {"name": "name", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}]}, {"name": "survived", "dtype": {"name": "bool"}, "description": "If the passenger survived", "tags": null, "constraints": null}, {"name": "is_male", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "male"}}, "depth": 1}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "in_domain", "values": ["male", "female"]}, {"name": "optional"}]}, {"name": "sibsp", "dtype": {"name": "int32"}, "description": "Number of siblings on titanic", "tags": null, "constraints": [{"name": "upper_bound_inc", "value": 20.0}, {"name": "lower_bound_inc", "value": 0.0}, {"name": "optional"}]}, {"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "upper_bound_inc", "value": 100.0}, {"name": "lower_bound_inc", "value": 0.0}]}], "event_timestamp": null}, "train_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-train.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "test_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-test.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "validation_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-validate.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "train_size_fraction": 0.6, "test_size_fraction": 0.20000000000000007, "validate_size_fraction": 0.19999999999999996, "target": ["survived"], "description": null, "tags": null}], "active_learning": []} +{"raw_data": [], "train_test": [], "train_test_validation": [{"id": "titanic_test", "name": null, "request_result": {"entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}], "features": [{"name": "survived", "dtype": {"name": "bool"}, "description": "If the passenger survived", "tags": null, "constraints": null}, {"name": "is_mr", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "contains", "dtype": {"name": "bool"}, "key": "name", "value": "Mr."}, "depth": 1}, {"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "lower_bound_inc", "value": 0.0}, {"name": "upper_bound_inc", "value": 100.0}]}, {"name": "cabin", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}]}, {"name": "name", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}]}, {"name": "sibsp", "dtype": {"name": "int32"}, "description": "Number of siblings on titanic", "tags": null, "constraints": [{"name": "lower_bound_inc", "value": 0.0}, {"name": "optional"}, {"name": "upper_bound_inc", "value": 20.0}]}, {"name": "is_male", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "male"}}, "depth": 1}, {"name": "is_female", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "female"}}, "depth": 1}, {"name": "has_siblings", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "not-equals", "dtype": {"name": "bool"}, "key": "sibsp", "value": {"name": "int", "value": 0}}, "depth": 1}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "in_domain", "values": ["male", "female"]}, {"name": "optional"}]}], "event_timestamp": null}, "train_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-train.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "test_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-test.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "validation_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-validate.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "train_size_fraction": 0.6, "test_size_fraction": 0.20000000000000007, "validate_size_fraction": 0.19999999999999996, "target": ["survived"], "description": null, "tags": null}], "active_learning": []} diff --git a/test_data/titanic-test.csv b/test_data/titanic-test.csv index a0f9bb6d..8aa49a61 100644 --- a/test_data/titanic-test.csv +++ b/test_data/titanic-test.csv @@ -1,21 +1,21 @@ -cabin,has_siblings,is_female,is_mr,name,survived,age,is_male,sex,sibsp,passenger_id -,False,False,True,"Sirayanian, Mr. Orsen",False,22.0,True,male,0,61 -B28,False,True,False,"Icard, Miss. Amelie",True,38.0,False,female,0,62 -C83,True,False,True,"Harris, Mr. Henry Birkhardt",False,45.0,True,male,1,63 -,True,False,False,"Skoog, Master. Harald",False,4.0,True,male,3,64 -,False,False,True,"Stewart, Mr. Albert A",False,,True,male,0,65 -,True,False,False,"Moubarek, Master. Gerios",True,,True,male,1,66 -F33,False,True,True,"Nye, Mrs. (Elizabeth Ramell)",True,29.0,False,female,0,67 -,False,False,True,"Crease, Mr. Ernest James",False,19.0,True,male,0,68 -,True,True,False,"Andersson, Miss. Erna Alexandra",True,17.0,False,female,4,69 -,True,False,True,"Kink, Mr. Vincenz",False,26.0,True,male,2,70 -,False,False,True,"Jenkin, Mr. Stephen Curnow",False,32.0,True,male,0,71 -,True,True,False,"Goodwin, Miss. Lillian Amy",False,16.0,False,female,5,72 -,False,False,True,"Hood, Mr. Ambrose Jr",False,21.0,True,male,0,73 -,True,False,True,"Chronopoulos, Mr. Apostolos",False,26.0,True,male,1,74 -,False,False,True,"Bing, Mr. Lee",True,32.0,True,male,0,75 -F G73,False,False,True,"Moen, Mr. Sigurd Hansen",False,25.0,True,male,0,76 -,False,False,True,"Staneff, Mr. Ivan",False,,True,male,0,77 -,False,False,True,"Moutal, Mr. Rahamin Haim",False,,True,male,0,78 -,False,False,False,"Caldwell, Master. Alden Gates",True,0.83,True,male,0,79 -,False,True,False,"Dowdell, Miss. Elizabeth",True,30.0,False,female,0,80 +passenger_id,has_siblings,is_mr,age,cabin,name,sibsp,is_male,is_female,survived,sex +61,False,True,22.0,,"Sirayanian, Mr. Orsen",0,True,False,False,male +62,False,False,38.0,B28,"Icard, Miss. Amelie",0,False,True,True,female +63,True,True,45.0,C83,"Harris, Mr. Henry Birkhardt",1,True,False,False,male +64,True,False,4.0,,"Skoog, Master. Harald",3,True,False,False,male +65,False,True,,,"Stewart, Mr. Albert A",0,True,False,False,male +66,True,False,,,"Moubarek, Master. Gerios",1,True,False,True,male +67,False,True,29.0,F33,"Nye, Mrs. (Elizabeth Ramell)",0,False,True,True,female +68,False,True,19.0,,"Crease, Mr. Ernest James",0,True,False,False,male +69,True,False,17.0,,"Andersson, Miss. Erna Alexandra",4,False,True,True,female +70,True,True,26.0,,"Kink, Mr. Vincenz",2,True,False,False,male +71,False,True,32.0,,"Jenkin, Mr. Stephen Curnow",0,True,False,False,male +72,True,False,16.0,,"Goodwin, Miss. Lillian Amy",5,False,True,False,female +73,False,True,21.0,,"Hood, Mr. Ambrose Jr",0,True,False,False,male +74,True,True,26.0,,"Chronopoulos, Mr. Apostolos",1,True,False,False,male +75,False,True,32.0,,"Bing, Mr. Lee",0,True,False,True,male +76,False,True,25.0,F G73,"Moen, Mr. Sigurd Hansen",0,True,False,False,male +77,False,True,,,"Staneff, Mr. Ivan",0,True,False,False,male +78,False,True,,,"Moutal, Mr. Rahamin Haim",0,True,False,False,male +79,False,False,0.83,,"Caldwell, Master. Alden Gates",0,True,False,True,male +80,False,False,30.0,,"Dowdell, Miss. Elizabeth",0,False,True,True,female diff --git a/test_data/titanic-train.csv b/test_data/titanic-train.csv index 6a49850f..309f6d98 100644 --- a/test_data/titanic-train.csv +++ b/test_data/titanic-train.csv @@ -1,61 +1,61 @@ -cabin,has_siblings,is_female,is_mr,name,survived,age,is_male,sex,sibsp,passenger_id -,True,False,True,"Braund, Mr. Owen Harris",False,22.0,True,male,1,1 -C85,True,True,True,"Cumings, Mrs. John Bradley (Florence Briggs Thayer)",True,38.0,False,female,1,2 -,False,True,False,"Heikkinen, Miss. Laina",True,26.0,False,female,0,3 -C123,True,True,True,"Futrelle, Mrs. Jacques Heath (Lily May Peel)",True,35.0,False,female,1,4 -,False,False,True,"Allen, Mr. William Henry",False,35.0,True,male,0,5 -,False,False,True,"Moran, Mr. James",False,,True,male,0,6 -E46,False,False,True,"McCarthy, Mr. Timothy J",False,54.0,False,other,0,7 -,True,False,False,"Palsson, Master. Gosta Leonard",False,2.0,True,male,3,8 -,False,True,True,"Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",True,27.0,False,female,0,9 -,True,True,True,"Nasser, Mrs. Nicholas (Adele Achem)",True,14.0,False,female,1,10 -G6,True,True,False,"Sandstrom, Miss. Marguerite Rut",True,4.0,False,female,1,11 -C103,False,True,False,"Bonnell, Miss. Elizabeth",True,58.0,False,female,0,12 -,False,False,True,"Saundercock, Mr. William Henry",False,20.0,True,male,0,13 -,True,False,True,"Andersson, Mr. Anders Johan",False,39.0,True,male,1,14 -,False,True,False,"Vestrom, Miss. Hulda Amanda Adolfina",False,14.0,False,female,0,15 -,False,True,True,"Hewlett, Mrs. (Mary D Kingcome) ",True,55.0,False,female,0,16 -,True,False,False,"Rice, Master. Eugene",False,2.0,True,male,4,17 -,False,False,True,"Williams, Mr. Charles Eugene",True,,True,male,0,18 -,True,True,True,"Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)",False,31.0,False,female,1,19 -,False,True,True,"Masselmani, Mrs. Fatima",True,,False,female,0,20 -,False,False,True,"Fynney, Mr. Joseph J",False,35.0,True,male,0,21 -D56,False,False,True,"Beesley, Mr. Lawrence",True,34.0,True,male,0,22 -,False,True,False,"McGowan, Miss. Anna ""Annie""",True,15.0,False,female,0,23 -A6,False,False,True,"Sloper, Mr. William Thompson",True,28.0,True,male,0,24 -,True,True,False,"Palsson, Miss. Torborg Danira",False,8.0,False,female,3,25 -,True,True,True,"Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson)",True,38.0,False,female,1,26 -,False,False,True,"Emir, Mr. Farred Chehab",False,,True,male,0,27 -C23 C25 C27,True,False,True,"Fortune, Mr. Charles Alexander",False,19.0,True,male,3,28 -,False,True,False,"O'Dwyer, Miss. Ellen ""Nellie""",True,,False,female,0,29 -,False,False,True,"Todoroff, Mr. Lalio",False,,True,male,0,30 -,False,False,False,"Uruchurtu, Don. Manuel E",False,40.0,True,male,0,31 -B78,True,True,True,"Spencer, Mrs. William Augustus (Marie Eugenie)",True,,False,female,1,32 -,False,True,False,"Glynn, Miss. Mary Agatha",True,,False,female,0,33 -,False,False,True,"Wheadon, Mr. Edward H",False,66.0,True,male,0,34 -,True,False,True,"Meyer, Mr. Edgar Joseph",False,28.0,True,male,1,35 -,True,False,True,"Holverson, Mr. Alexander Oskar",False,42.0,True,male,1,36 -,False,False,True,"Mamee, Mr. Hanna",True,,True,male,0,37 -,False,False,True,"Cann, Mr. Ernest Charles",False,21.0,True,male,0,38 -,True,True,False,"Vander Planke, Miss. Augusta Maria",False,18.0,False,female,2,39 -,True,True,False,"Nicola-Yarred, Miss. Jamila",True,14.0,False,female,1,40 -,True,True,True,"Ahlin, Mrs. Johan (Johanna Persdotter Larsson)",False,40.0,False,female,1,41 -,True,True,True,"Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott)",False,27.0,False,female,1,42 -,False,False,True,"Kraeff, Mr. Theodor",False,,True,male,0,43 -,True,True,False,"Laroche, Miss. Simonne Marie Anne Andree",True,3.0,False,female,1,44 -,False,True,False,"Devaney, Miss. Margaret Delia",True,19.0,False,female,0,45 -,False,False,True,"Rogers, Mr. William John",False,,True,male,0,46 -,True,False,True,"Lennon, Mr. Denis",False,,True,male,1,47 -,False,True,False,"O'Driscoll, Miss. Bridget",True,,False,female,0,48 -,True,False,True,"Samaan, Mr. Youssef",False,,True,male,2,49 -,True,True,True,"Arnold-Franchi, Mrs. Josef (Josefine Franchi)",False,18.0,False,female,1,50 -,True,False,False,"Panula, Master. Juha Niilo",False,7.0,True,male,4,51 -,False,False,True,"Nosworthy, Mr. Richard Cater",False,21.0,True,male,0,52 -D33,True,True,True,"Harper, Mrs. Henry Sleeper (Myna Haxtun)",True,49.0,False,female,1,53 -,True,True,True,"Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)",True,29.0,False,female,1,54 -B30,False,False,True,"Ostby, Mr. Engelhart Cornelius",False,65.0,True,male,0,55 -C52,False,False,True,"Woolner, Mr. Hugh",True,,True,male,0,56 -,False,True,False,"Rugg, Miss. Emily",True,21.0,False,female,0,57 -,False,False,True,"Novel, Mr. Mansouer",False,28.5,True,male,0,58 -,True,True,False,"West, Miss. Constance Mirium",True,5.0,False,female,1,59 -,True,False,False,"Goodwin, Master. William Frederick",False,11.0,True,male,5,60 +passenger_id,has_siblings,is_mr,age,cabin,name,sibsp,is_male,is_female,survived,sex +1,True,True,22.0,,"Braund, Mr. Owen Harris",1,True,False,False,male +2,True,True,38.0,C85,"Cumings, Mrs. John Bradley (Florence Briggs Thayer)",1,False,True,True,female +3,False,False,26.0,,"Heikkinen, Miss. Laina",0,False,True,True,female +4,True,True,35.0,C123,"Futrelle, Mrs. Jacques Heath (Lily May Peel)",1,False,True,True,female +5,False,True,35.0,,"Allen, Mr. William Henry",0,True,False,False,male +6,False,True,,,"Moran, Mr. James",0,True,False,False,male +7,False,True,54.0,E46,"McCarthy, Mr. Timothy J",0,False,False,False,other +8,True,False,2.0,,"Palsson, Master. Gosta Leonard",3,True,False,False,male +9,False,True,27.0,,"Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",0,False,True,True,female +10,True,True,14.0,,"Nasser, Mrs. Nicholas (Adele Achem)",1,False,True,True,female +11,True,False,4.0,G6,"Sandstrom, Miss. Marguerite Rut",1,False,True,True,female +12,False,False,58.0,C103,"Bonnell, Miss. Elizabeth",0,False,True,True,female +13,False,True,20.0,,"Saundercock, Mr. William Henry",0,True,False,False,male +14,True,True,39.0,,"Andersson, Mr. Anders Johan",1,True,False,False,male +15,False,False,14.0,,"Vestrom, Miss. Hulda Amanda Adolfina",0,False,True,False,female +16,False,True,55.0,,"Hewlett, Mrs. (Mary D Kingcome) ",0,False,True,True,female +17,True,False,2.0,,"Rice, Master. Eugene",4,True,False,False,male +18,False,True,,,"Williams, Mr. Charles Eugene",0,True,False,True,male +19,True,True,31.0,,"Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)",1,False,True,False,female +20,False,True,,,"Masselmani, Mrs. Fatima",0,False,True,True,female +21,False,True,35.0,,"Fynney, Mr. Joseph J",0,True,False,False,male +22,False,True,34.0,D56,"Beesley, Mr. Lawrence",0,True,False,True,male +23,False,False,15.0,,"McGowan, Miss. Anna ""Annie""",0,False,True,True,female +24,False,True,28.0,A6,"Sloper, Mr. William Thompson",0,True,False,True,male +25,True,False,8.0,,"Palsson, Miss. Torborg Danira",3,False,True,False,female +26,True,True,38.0,,"Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson)",1,False,True,True,female +27,False,True,,,"Emir, Mr. Farred Chehab",0,True,False,False,male +28,True,True,19.0,C23 C25 C27,"Fortune, Mr. Charles Alexander",3,True,False,False,male +29,False,False,,,"O'Dwyer, Miss. Ellen ""Nellie""",0,False,True,True,female +30,False,True,,,"Todoroff, Mr. Lalio",0,True,False,False,male +31,False,False,40.0,,"Uruchurtu, Don. Manuel E",0,True,False,False,male +32,True,True,,B78,"Spencer, Mrs. William Augustus (Marie Eugenie)",1,False,True,True,female +33,False,False,,,"Glynn, Miss. Mary Agatha",0,False,True,True,female +34,False,True,66.0,,"Wheadon, Mr. Edward H",0,True,False,False,male +35,True,True,28.0,,"Meyer, Mr. Edgar Joseph",1,True,False,False,male +36,True,True,42.0,,"Holverson, Mr. Alexander Oskar",1,True,False,False,male +37,False,True,,,"Mamee, Mr. Hanna",0,True,False,True,male +38,False,True,21.0,,"Cann, Mr. Ernest Charles",0,True,False,False,male +39,True,False,18.0,,"Vander Planke, Miss. Augusta Maria",2,False,True,False,female +40,True,False,14.0,,"Nicola-Yarred, Miss. Jamila",1,False,True,True,female +41,True,True,40.0,,"Ahlin, Mrs. Johan (Johanna Persdotter Larsson)",1,False,True,False,female +42,True,True,27.0,,"Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott)",1,False,True,False,female +43,False,True,,,"Kraeff, Mr. Theodor",0,True,False,False,male +44,True,False,3.0,,"Laroche, Miss. Simonne Marie Anne Andree",1,False,True,True,female +45,False,False,19.0,,"Devaney, Miss. Margaret Delia",0,False,True,True,female +46,False,True,,,"Rogers, Mr. William John",0,True,False,False,male +47,True,True,,,"Lennon, Mr. Denis",1,True,False,False,male +48,False,False,,,"O'Driscoll, Miss. Bridget",0,False,True,True,female +49,True,True,,,"Samaan, Mr. Youssef",2,True,False,False,male +50,True,True,18.0,,"Arnold-Franchi, Mrs. Josef (Josefine Franchi)",1,False,True,False,female +51,True,False,7.0,,"Panula, Master. Juha Niilo",4,True,False,False,male +52,False,True,21.0,,"Nosworthy, Mr. Richard Cater",0,True,False,False,male +53,True,True,49.0,D33,"Harper, Mrs. Henry Sleeper (Myna Haxtun)",1,False,True,True,female +54,True,True,29.0,,"Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)",1,False,True,True,female +55,False,True,65.0,B30,"Ostby, Mr. Engelhart Cornelius",0,True,False,False,male +56,False,True,,C52,"Woolner, Mr. Hugh",0,True,False,True,male +57,False,False,21.0,,"Rugg, Miss. Emily",0,False,True,True,female +58,False,True,28.5,,"Novel, Mr. Mansouer",0,True,False,False,male +59,True,False,5.0,,"West, Miss. Constance Mirium",1,False,True,True,female +60,True,False,11.0,,"Goodwin, Master. William Frederick",5,True,False,False,male diff --git a/test_data/titanic-validate.csv b/test_data/titanic-validate.csv index 2e611483..804f9f31 100644 --- a/test_data/titanic-validate.csv +++ b/test_data/titanic-validate.csv @@ -1,21 +1,21 @@ -cabin,has_siblings,is_female,is_mr,name,survived,age,is_male,sex,sibsp,passenger_id -,False,False,True,"Waelens, Mr. Achille",False,22.0,True,male,0,81 -,False,False,True,"Sheerlinck, Mr. Jan Baptist",True,29.0,True,male,0,82 -,False,True,False,"McDermott, Miss. Brigdet Delia",True,,False,female,0,83 -,False,False,True,"Carrau, Mr. Francisco M",False,28.0,True,male,0,84 -,False,True,False,"Ilett, Miss. Bertha",True,17.0,False,female,0,85 -,True,True,True,"Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson)",True,33.0,False,female,3,86 -,True,False,True,"Ford, Mr. William Neal",False,16.0,True,male,1,87 -,False,False,True,"Slocovski, Mr. Selman Francis",False,,True,male,0,88 -C23 C25 C27,True,True,False,"Fortune, Miss. Mabel Helen",True,23.0,False,female,3,89 -,False,False,True,"Celotti, Mr. Francesco",False,24.0,True,male,0,90 -,False,False,True,"Christmann, Mr. Emil",False,29.0,True,male,0,91 -,False,False,True,"Andreasson, Mr. Paul Edvin",False,20.0,True,male,0,92 -E31,True,False,True,"Chaffee, Mr. Herbert Fuller",False,46.0,True,male,1,93 -,True,False,True,"Dean, Mr. Bertram Frank",False,26.0,True,male,1,94 -,False,False,True,"Coxon, Mr. Daniel",False,59.0,True,male,0,95 -,False,False,True,"Shorney, Mr. Charles Joseph",False,,True,male,0,96 -A5,False,False,True,"Goldschmidt, Mr. George B",False,71.0,True,male,0,97 -D10 D12,False,False,True,"Greenfield, Mr. William Bertram",True,23.0,True,male,0,98 -,False,True,True,"Doling, Mrs. John T (Ada Julia Bone)",True,34.0,False,female,0,99 -,True,False,True,"Kantor, Mr. Sinai",False,34.0,True,male,1,100 +passenger_id,has_siblings,is_mr,age,cabin,name,sibsp,is_male,is_female,survived,sex +81,False,True,22.0,,"Waelens, Mr. Achille",0,True,False,False,male +82,False,True,29.0,,"Sheerlinck, Mr. Jan Baptist",0,True,False,True,male +83,False,False,,,"McDermott, Miss. Brigdet Delia",0,False,True,True,female +84,False,True,28.0,,"Carrau, Mr. Francisco M",0,True,False,False,male +85,False,False,17.0,,"Ilett, Miss. Bertha",0,False,True,True,female +86,True,True,33.0,,"Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson)",3,False,True,True,female +87,True,True,16.0,,"Ford, Mr. William Neal",1,True,False,False,male +88,False,True,,,"Slocovski, Mr. Selman Francis",0,True,False,False,male +89,True,False,23.0,C23 C25 C27,"Fortune, Miss. Mabel Helen",3,False,True,True,female +90,False,True,24.0,,"Celotti, Mr. Francesco",0,True,False,False,male +91,False,True,29.0,,"Christmann, Mr. Emil",0,True,False,False,male +92,False,True,20.0,,"Andreasson, Mr. Paul Edvin",0,True,False,False,male +93,True,True,46.0,E31,"Chaffee, Mr. Herbert Fuller",1,True,False,False,male +94,True,True,26.0,,"Dean, Mr. Bertram Frank",1,True,False,False,male +95,False,True,59.0,,"Coxon, Mr. Daniel",0,True,False,False,male +96,False,True,,,"Shorney, Mr. Charles Joseph",0,True,False,False,male +97,False,True,71.0,A5,"Goldschmidt, Mr. George B",0,True,False,False,male +98,False,True,23.0,D10 D12,"Greenfield, Mr. William Bertram",0,True,False,True,male +99,False,True,34.0,,"Doling, Mrs. John T (Ada Julia Bone)",0,False,True,True,female +100,True,True,34.0,,"Kantor, Mr. Sinai",1,True,False,False,male