EventPhenotype

Bases: Phenotype

EventPhenotype extracts patients that experience any event based on event_date from a domain table based on optional filters such as date range, relative time range, and categorical filters. The CodelistPhenotype is a subclass of EventPhenotype that filters based on a codelist.

Parameters:

Name	Type	Description	Default
domain	str	The domain of the phenotype.	required
name	Optional[str]	The name of the phenotype.	None
date_range	DateFilter	A date range filter to apply.	None
relative_time_range	Union[RelativeTimeRangeFilter, List[RelativeTimeRangeFilter]]	A relative time range filter or a list of filters to apply.	None
return_date		Specifies whether to return the 'first', 'last', 'nearest', or 'all' event date(s). Default is 'first'.	'first'
return_value		Specifies which values to return. None for no return value or 'all' for all return values on the selected date(s). Default is None.	None
categorical_filter	Optional[CategoricalFilter]	Additional categorical filters to apply.	None

Attributes:

Name	Type	Description
table	PhenotypeTable	The resulting phenotype table after filtering (None until execute is called)

Source code in phenex/phenotypes/event_phenotype.py

class EventPhenotype(Phenotype):
    """
    EventPhenotype extracts patients that experience any event based on event_date from a domain table based on optional filters such as date range, relative time range, and categorical filters. The CodelistPhenotype is a subclass of EventPhenotype that filters based on a codelist.

    Parameters:
        domain: The domain of the phenotype.
        name: The name of the phenotype.
        date_range: A date range filter to apply.
        relative_time_range: A relative time range filter or a list of filters to apply.
        return_date: Specifies whether to return the 'first', 'last', 'nearest', or 'all'
            event date(s). Default is 'first'.
        return_value: Specifies which values to return. None for no return value or 'all'
            for all return values on the selected date(s). Default is None.
        categorical_filter: Additional categorical filters to apply.

    Attributes:
        table (PhenotypeTable): The resulting phenotype table after filtering (None until execute is called)
    """

    def __init__(
        self,
        domain: str,
        name: Optional[str] = None,
        date_range: DateFilter = None,
        relative_time_range: Union[
            RelativeTimeRangeFilter, List[RelativeTimeRangeFilter]
        ] = None,
        return_date="first",
        return_value=None,
        categorical_filter: Optional[CategoricalFilter] = None,
        **kwargs,
    ):
        super(EventPhenotype, self).__init__(name=name, **kwargs)

        self.domain = domain
        self.categorical_filter = categorical_filter
        self.date_range = date_range
        self.return_date = return_date
        self.return_value = return_value
        assert self.return_date in [
            "first",
            "last",
            "nearest",
            "all",
        ], f"Unknown return_date: {return_date}"
        assert self.return_value in [
            None,
            "all",
        ], f"Unknown return_value: {return_value}"

        if isinstance(relative_time_range, RelativeTimeRangeFilter):
            relative_time_range = [relative_time_range]
        self.relative_time_range = relative_time_range

        if self.relative_time_range is not None:
            for rtr in self.relative_time_range:
                if rtr.anchor_phenotype is not None:
                    self.add_children(rtr.anchor_phenotype)

    def _execute(self, tables) -> PhenotypeTable:
        code_table = tables[self.domain]
        return self._execute_from_filtered_table(code_table, tables)

    def _execute_from_filtered_table(self, code_table, tables) -> PhenotypeTable:
        code_table = self._perform_categorical_filtering(code_table, tables)
        code_table = self._perform_time_filtering(code_table)
        code_table = self._perform_date_selection(code_table)
        code_table = self._perform_value_selection(code_table)
        code_table = select_phenotype_columns(code_table)
        code_table = self._perform_final_processing(code_table)
        return code_table

    def _perform_categorical_filtering(self, code_table, tables):
        if self.categorical_filter is not None:
            assert is_phenex_code_table(code_table)
            code_table = self.categorical_filter.autojoin_filter(code_table, tables)
        return code_table

    def _perform_time_filtering(self, code_table):
        if self.date_range is not None:
            code_table = self.date_range.filter(code_table)
        if self.relative_time_range is not None:
            for rtr in self.relative_time_range:
                code_table = rtr.filter(code_table)
        return code_table

    def _perform_date_selection(self, code_table):
        if self.return_date is None or self.return_date == "all":
            return code_table

        reduce = self.return_value != "all"

        if self.return_date == "first":
            aggregator = First(reduce=reduce)
        elif self.return_date == "last":
            aggregator = Last(reduce=reduce)
        elif self.return_date == "nearest":
            raise NotImplementedError("Nearest aggregation not yet implemented")
        else:
            raise ValueError(f"Unknown return_date: {self.return_date}")

        return aggregator.aggregate(code_table)

    def _perform_value_selection(self, code_table):
        return code_table

dependencies property

Recursively collect all dependencies of a node (including dependencies of dependencies).

Returns:

Type	Description
Set[Node]	List[Node]: A list of Node objects on which this Node depends.

dependency_graph property

Build a dependency graph where each node maps to its direct dependencies (children).

Returns:

Type	Description
Dict[Node, Set[Node]]	Dict[Node, Set[Node]: A mapping of Node's to their children Node's.

execution_metadata property

Retrieve the full execution metadata row for this node from the local DuckDB database.

Returns:

Type	Description
	pandas.DataFrame: A table containing NODE_NAME, NODE_HASH, NODE_PARAMS, EXECUTION_PARAMS, EXECUTION_START_TIME, EXECUTION_END_TIME, and EXECUTION_DURATION for execution of this node, or None if the node has never been executed.

namespaced_table property

A PhenotypeTable has generic column names 'person_id', 'boolean', 'event_date', and 'value'. The namespaced_table prepends the phenotype name to all of these columns. This is useful when joining multiple phenotype tables together.

Returns:

Name	Type	Description
table	Table	The namespaced table for the current phenotype.

reverse_dependency_graph property

Build a reverse dependency graph where each node maps to nodes that depend on it (parents).

Returns:

Type	Description
Dict[Node, Set[Node]]	Dict[Node, List[Node]: A mapping of Node's to their parent Node's.

clear_cache(con=None, recursive=False)

Clear the cached state for this node, forcing re-execution on the next call to execute().

This method removes the node's hash from the node states table and optionally drops the materialized table from the database. After calling this method, the node will be treated as if it has never been executed before.

Parameters:

Name	Type	Description	Default
con	Optional[object]	Database connector. If provided, clears only runs with matching execution context and drops the materialized table. If None, clears all runs for the node.	None
recursive	bool	If True, also clear the cache for all child nodes recursively. Defaults to False.	False

Example

# Clear all cached runs for a single node
my_node.clear_cache()

# Clear runs with specific execution context and drop materialized table
my_node.clear_cache(con=my_connector)

# Clear cache for node and all its dependencies
my_node.clear_cache(recursive=True)

Source code in phenex/node.py

def clear_cache(self, con: Optional[object] = None, recursive: bool = False):
    """
    Clear the cached state for this node, forcing re-execution on the next call to execute().

    This method removes the node's hash from the node states table and optionally drops the materialized table from the database. After calling this method, the node will be treated as if it has never been executed before.

    Parameters:
        con: Database connector. If provided, clears only runs with matching execution context and drops the materialized table. If None, clears all runs for the node.
        recursive: If True, also clear the cache for all child nodes recursively. Defaults to False.

    Example:
        ```python
        # Clear all cached runs for a single node
        my_node.clear_cache()

        # Clear runs with specific execution context and drop materialized table
        my_node.clear_cache(con=my_connector)

        # Clear cache for node and all its dependencies
        my_node.clear_cache(recursive=True)
        ```
    """
    # Delegate all logic to NodeManager
    return Node._node_manager.clear_cache(self, con=con, recursive=recursive)

execute(tables=None, con=None, overwrite=False, lazy_execution=False, n_threads=1)

Executes the Node computation for the current node and its dependencies.

Lazy Execution

When lazy_execution=True, nodes are only recomputed if changes are detected. The system tracks: 1. Node definition changes: Detected by hashing the node's parameters (from to_dict()) and class name 2. Execution environment changes: Detected by tracking source/destination database configurations

A node will be rerun if either: - The node's defining parameters have changed (different hash than last execution) - The database connector's source or destination databases have changed - The node has never been executed before

If no changes are detected, the node uses its cached result from the database instead of recomputing.

Requirements for lazy execution: - A database connector (con) must be provided to store and retrieve cached results - overwrite=True must be set to allow updating existing cached tables

State tracking is maintained in a local DuckDB database (__PHENEX_META__NODE_STATES table) that stores: - Node hashes, parameters, and execution metadata - Database connector configuration used during execution - Execution timing information

Parameters:

Name	Type	Description	Default
tables	Dict[str, Table]	A dictionary mapping domains to Table objects.	None
con	Optional[object]	Connection to database for materializing outputs. If provided, outputs from the node and all children nodes will be materialized (written) to the database using the connector. Required for lazy_execution.	None
overwrite	bool	If True, will overwrite any existing tables found in the database while writing. If False, will throw an error when an existing table is found. Has no effect if con is not passed. Must be True when using lazy_execution.	False
lazy_execution	bool	If True, only re-executes nodes when changes are detected in either the node definition or execution environment. Defaults to False. Requires con to be provided.	False
n_threads	int	Max number of Node's to execute simultaneously when this node has multiple children.	1

Returns:

Name	Type	Description
Table	Table	The resulting table for this node. Also accessible through self.table after calling self.execute().

Raises:

Type	Description
ValueError	If lazy_execution=True but overwrite=False or con=None.

Source code in phenex/node.py

def execute(
    self,
    tables: Dict[str, Table] = None,
    con: Optional[object] = None,
    overwrite: bool = False,
    lazy_execution: bool = False,
    n_threads: int = 1,
) -> Table:
    """
    Executes the Node computation for the current node and its dependencies.

    Lazy Execution:
        When lazy_execution=True, nodes are only recomputed if changes are detected. The system tracks:
        1. Node definition changes: Detected by hashing the node's parameters (from to_dict()) and class name
        2. Execution environment changes: Detected by tracking source/destination database configurations

        A node will be rerun if either:
        - The node's defining parameters have changed (different hash than last execution)
        - The database connector's source or destination databases have changed
        - The node has never been executed before

        If no changes are detected, the node uses its cached result from the database instead of recomputing.

        Requirements for lazy execution:
        - A database connector (con) must be provided to store and retrieve cached results
        - overwrite=True must be set to allow updating existing cached tables

        State tracking is maintained in a local DuckDB database (__PHENEX_META__NODE_STATES table) that stores:
        - Node hashes, parameters, and execution metadata
        - Database connector configuration used during execution
        - Execution timing information

    Parameters:
        tables: A dictionary mapping domains to Table objects.
        con: Connection to database for materializing outputs. If provided, outputs from the node and all children nodes will be materialized (written) to the database using the connector. Required for lazy_execution.
        overwrite: If True, will overwrite any existing tables found in the database while writing. If False, will throw an error when an existing table is found. Has no effect if con is not passed. Must be True when using lazy_execution.
        lazy_execution: If True, only re-executes nodes when changes are detected in either the node definition or execution environment. Defaults to False. Requires con to be provided.
        n_threads: Max number of Node's to execute simultaneously when this node has multiple children.

    Returns:
        Table: The resulting table for this node. Also accessible through self.table after calling self.execute().

    Raises:
        ValueError: If lazy_execution=True but overwrite=False or con=None.
    """
    # Handle None tables
    if tables is None:
        tables = {}

    # Build dependency graph for all dependencies
    all_deps = self.dependencies
    nodes = {node.name: node for node in all_deps}
    nodes[self.name] = self  # Add self to the nodes

    # Build dependency and reverse graphs
    dependency_graph = self._build_dependency_graph(nodes)
    reverse_graph = self._build_reverse_graph(dependency_graph)

    # Track completion status and results
    completed = set()
    completion_lock = threading.Lock()
    worker_exceptions = []  # Track exceptions from worker threads
    stop_all_workers = (
        threading.Event()
    )  # Signal to stop all workers on first error

    # Track in-degree for scheduling
    in_degree = {}
    for node_name, dependencies in dependency_graph.items():
        in_degree[node_name] = len(dependencies)
    for node_name in nodes:
        if node_name not in in_degree:
            in_degree[node_name] = 0

    # Queue for nodes ready to execute
    ready_queue = queue.Queue()

    # Add nodes with no dependencies to ready queue
    for node_name, degree in in_degree.items():
        if degree == 0:
            ready_queue.put(node_name)

    def _run_and_materialise(node, node_name):
        """Execute *node*, materialise the result, record timing, and update the run hash."""
        node.lastexecution_start_time = datetime.now()
        table = node._execute(tables)
        if table is not None:
            con.create_table(table, node_name, overwrite=overwrite)
            table = con.get_dest_table(node_name)
        node.lastexecution_end_time = datetime.now()
        node.lastexecution_duration = (
            node.lastexecution_end_time - node.lastexecution_start_time
        ).total_seconds()
        Node._node_manager.update_run_params(node, con)
        return table

    def worker():
        """Worker function for thread pool"""
        while not stop_all_workers.is_set():
            try:
                node_name = ready_queue.get(timeout=1)
                # timeout forces to wait 1 second to avoid busy waiting
                if node_name is None:  # Sentinel value to stop worker
                    break
            except queue.Empty:
                continue

            try:
                logger.info(
                    f"Thread {threading.current_thread().name}: executing node '{node_name}'"
                )
                node = nodes[node_name]

                # Execute the node (without recursive child execution since we handle dependencies here)
                if lazy_execution:
                    if not overwrite:
                        raise ValueError(
                            "lazy_execution only works with overwrite=True."
                        )
                    if con is None:
                        raise ValueError(
                            "A DatabaseConnector is required for lazy execution."
                        )

                    if Node._node_manager.should_rerun(node, con):
                        table = _run_and_materialise(node, node_name)
                    else:
                        try:
                            table = con.get_dest_table(node_name)
                        except Exception:
                            # Cached table was dropped or is inaccessible; recompute.
                            logger.warning(
                                f"Cached table for '{node_name}' not found; recomputing."
                            )
                            table = _run_and_materialise(node, node_name)
                else:
                    # Time the execution
                    node.lastexecution_start_time = datetime.now()
                    table = node._execute(tables)

                    if (
                        con and table is not None
                    ):  # Only create table if _execute returns something
                        logger.info(
                            f"Thread {threading.current_thread().name}: materializing '{node_name}' to database ..."
                        )
                        _t_mat = datetime.now()
                        con.create_table(table, node_name, overwrite=overwrite)
                        logger.info(
                            f"Thread {threading.current_thread().name}: materialized '{node_name}' "
                            f"in {(datetime.now() - _t_mat).total_seconds():.3f}s"
                        )
                        table = con.get_dest_table(node_name)

                    node.lastexecution_end_time = datetime.now()
                    node.lastexecution_duration = (
                        node.lastexecution_end_time - node.lastexecution_start_time
                    ).total_seconds()

                node.table = table

                with completion_lock:
                    completed.add(node_name)

                    # Update in-degree for dependent nodes and add ready ones to queue
                    for dependent in reverse_graph.get(node_name, set()):
                        in_degree[dependent] -= 1
                        if in_degree[dependent] == 0:
                            # Check if all dependencies are completed
                            deps_completed = all(
                                dep in completed
                                for dep in dependency_graph.get(dependent, set())
                            )
                            if deps_completed:
                                ready_queue.put(dependent)

                # Log completion with timing info
                if node.lastexecution_duration is not None:
                    logger.info(
                        f"Thread {threading.current_thread().name}: completed node '{node_name}' "
                        f"in {node.lastexecution_duration:.3f} seconds"
                    )
                else:
                    logger.info(
                        f"Thread {threading.current_thread().name}: completed node '{node_name}' (cached)"
                    )

            except Exception as e:
                logger.error(f"Error executing node '{node_name}': {str(e)}")
                with completion_lock:
                    # Store exception for main thread
                    worker_exceptions.append(e)
                    # Signal all workers to stop immediately and exit worker loop
                    stop_all_workers.set()
                    break
            finally:
                ready_queue.task_done()

    # Start worker threads
    threads = []
    for i in range(min(n_threads, len(nodes))):
        thread = threading.Thread(target=worker, name=f"PhenexWorker-{i}")
        thread.daemon = True
        thread.start()
        threads.append(thread)

    # Wait for all nodes to complete or for an error to occur
    _last_heartbeat = datetime.now()
    while (
        len(completed) < len(nodes)
        and not worker_exceptions
        and not stop_all_workers.is_set()
    ):
        threading.Event().wait(0.1)  # Small delay to prevent busy waiting
        _now = datetime.now()
        if (_now - _last_heartbeat).total_seconds() >= 30:
            _pending = sorted(set(nodes.keys()) - completed)
            logger.info(
                f"Node '{self.name}': still waiting for {len(_pending)} nodes: {_pending}"
            )
            _last_heartbeat = _now

    if not stop_all_workers.is_set():
        # Time to stop workers and cleanup
        stop_all_workers.set()

    # Check if any worker thread had an exception
    if worker_exceptions:
        # Signal workers to stop
        for _ in threads:
            ready_queue.put(None)
        # Wait for threads to finish
        for thread in threads:
            thread.join(timeout=1)
        # Re-raise the first exception
        raise worker_exceptions[0]

    # Signal workers to stop and wait for them
    for _ in threads:
        ready_queue.put(None)  # Sentinel value to stop workers

    for thread in threads:
        thread.join(timeout=1)

    logger.info(
        f"Node '{self.name}': completed multithreaded execution of {len(nodes)} nodes"
    )
    return self.table

visualize_dependencies()

Create a text visualization of the dependency graph for this node and its dependencies.

Returns:

Name	Type	Description
str	str	A text representation of the dependency graph

Source code in phenex/node.py

def visualize_dependencies(self) -> str:
    """
    Create a text visualization of the dependency graph for this node and its dependencies.

    Returns:
        str: A text representation of the dependency graph
    """
    lines = [f"Dependencies for Node '{self.name}':"]

    # Get all dependencies
    all_deps = self.dependencies
    nodes = {node.name: node for node in all_deps}
    nodes[self.name] = self  # Add self to the nodes

    # Build dependency graph
    dependency_graph = self._build_dependency_graph(nodes)

    for node_name in sorted(nodes.keys()):
        dependencies = dependency_graph.get(node_name, set())
        if dependencies:
            deps_str = ", ".join(sorted(dependencies))
            lines.append(f"  {node_name} depends on: {deps_str}")
        else:
            lines.append(f"  {node_name} (no dependencies)")

    return "\n".join(lines)