TimeShiftPhenotype

TimeShiftPhenotype

Bases: Phenotype

TimeShiftPhenotype shifts a base date by the defined number of days.

The base date is determined as follows: - If phenotype is provided, the base date is phenotype.EVENT_DATE. - If phenotype is None, the base date is the INDEX_DATE column of the domain table identified by domain. A ValueError is raised at execution time if the table has no INDEX_DATE column.

If a date_range is provided, the shifted date is additionally clipped to stay within that range. The VALUE column is the number of days between the base date and the final (possibly clipped) date.

DATE: shifted (and optionally clipped) date VALUE: number of days between the base date and the final date

Parameters:

Name	Type	Description	Default
name		The name of the phenotype.	required
phenotype	Optional[Phenotype]	Optional phenotype whose EVENT_DATE is used as the base date.	None
domain	Optional[str]	Required when phenotype is None. The domain table whose INDEX_DATE column is used as the base date.	None
days	int	The number of days to shift. Positive shifts forward, negative backward.	required
date_range	Optional[DateFilter]	Optional DateFilter. The shifted date is clipped to [min_date, max_date].	None

Examples:

Example: Shift an existing phenotype forward by one year

    pt_one_year_after_af = TimeShiftPhenotype(
        name="one_year_after_af",
        phenotype=pt_af,
        days=365,
    )

Example: Shift INDEX_DATE forward by one year, clipped to study end

    pt_one_year_from_index = TimeShiftPhenotype(
        name="one_year_from_index",
        domain="PERSON",
        days=365,
        date_range=DateFilter(max_date=BeforeOrOn("2023-12-31")),
    )

Source code in phenex/phenotypes/time_shift_phenotype.py

class TimeShiftPhenotype(Phenotype):
    """
    TimeShiftPhenotype shifts a base date by the defined number of days.

    The base date is determined as follows:
    - If ``phenotype`` is provided, the base date is ``phenotype.EVENT_DATE``.
    - If ``phenotype`` is ``None``, the base date is the ``INDEX_DATE`` column of the
      domain table identified by ``domain``. A ``ValueError`` is raised at execution
      time if the table has no ``INDEX_DATE`` column.

    If a ``date_range`` is provided, the shifted date is additionally clipped to stay
    within that range. The VALUE column is the number of days between the base date and
    the final (possibly clipped) date.

    DATE: shifted (and optionally clipped) date
    VALUE: number of days between the base date and the final date

    Parameters:
        name: The name of the phenotype.
        phenotype: Optional phenotype whose EVENT_DATE is used as the base date.
        domain: Required when ``phenotype`` is ``None``. The domain table whose
            ``INDEX_DATE`` column is used as the base date.
        days: The number of days to shift. Positive shifts forward, negative backward.
        date_range: Optional DateFilter. The shifted date is clipped to [min_date, max_date].

    Examples:

    Example: Shift an existing phenotype forward by one year
    ```python
        pt_one_year_after_af = TimeShiftPhenotype(
            name="one_year_after_af",
            phenotype=pt_af,
            days=365,
        )
    ```

    Example: Shift INDEX_DATE forward by one year, clipped to study end
    ```python
        pt_one_year_from_index = TimeShiftPhenotype(
            name="one_year_from_index",
            domain="PERSON",
            days=365,
            date_range=DateFilter(max_date=BeforeOrOn("2023-12-31")),
        )
    ```
    """

    output_display_type = "value"

    def __init__(
        self,
        days: int,
        phenotype: Optional[Phenotype] = None,
        domain: Optional[str] = None,
        date_range: Optional[DateFilter] = None,
        **kwargs,
    ):
        super(TimeShiftPhenotype, self).__init__(**kwargs)
        if days is None:
            raise ValueError("days parameter is required")
        if phenotype is None and domain is None:
            raise ValueError("Either phenotype or domain must be provided")
        self.phenotype = phenotype
        self.domain = domain
        self.days = days
        self.date_range = date_range
        if self.phenotype is not None:
            self.add_children(self.phenotype)

    def _execute(self, tables) -> PhenotypeTable:
        if self.phenotype is not None:
            self.phenotype.execute(tables)
            table = self.phenotype.table
            base_date = table.EVENT_DATE
        else:
            table = tables[self.domain]
            if "INDEX_DATE" not in table.columns:
                raise ValueError(
                    f"TimeShiftPhenotype '{self.name}': domain table '{self.domain}' "
                    f"has no INDEX_DATE column."
                )
            table = table.select(["PERSON_ID", "INDEX_DATE"]).distinct()
            base_date = table.INDEX_DATE

        # Preserve base date for VALUE computation
        table = table.mutate(_BASE_DATE=base_date)

        # Shift the date
        shifted = base_date + ibis.interval(days=self.days)

        # Clip to date_range if provided
        if self.date_range is not None:
            if self.date_range.min_value is not None:
                shifted = ibis.greatest(
                    shifted, ibis.literal(self.date_range.min_value.value)
                )
            if self.date_range.max_value is not None:
                shifted = ibis.least(
                    shifted, ibis.literal(self.date_range.max_value.value)
                )

        table = table.mutate(EVENT_DATE=shifted)

        # VALUE = days from base date to the final (possibly clipped) date
        table = table.mutate(
            VALUE=table.EVENT_DATE.cast("date")
            .delta(table._BASE_DATE.cast("date"), "day")
            .cast("float64")
        )

        table = table.drop("_BASE_DATE")
        table = select_phenotype_columns(table)
        return self._perform_final_processing(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)

copy()

Return a deep copy of this node with _table_name_prefix cleared on all nodes.

Source code in phenex/node.py

def copy(self):
    """Return a deep copy of this node with _table_name_prefix cleared on all nodes."""
    clone = copy.deepcopy(self)
    clone._table_name_prefix = None
    for dep in clone.dependencies:
        dep._table_name_prefix = None
    return clone

delete_table(con, table_name_prefix=None)

Delete this node's materialized table from the destination database.

Parameters:

Name	Type	Description	Default
con		Database connector.	required
table_name_prefix	Optional[str]	Optional prefix. If None, uses the prefix from the last execution.	None

Returns:

Name	Type	Description
bool	bool	True if the table was dropped, False if it didn't exist.

Source code in phenex/node.py

def delete_table(self, con, table_name_prefix: Optional[str] = None) -> bool:
    """
    Delete this node's materialized table from the destination database.

    Parameters:
        con: Database connector.
        table_name_prefix: Optional prefix. If None, uses the prefix from the last execution.

    Returns:
        bool: True if the table was dropped, False if it didn't exist.
    """
    db_name = self.get_table_name(table_name_prefix)
    try:
        con.drop_table(db_name)
        logger.info(f"Node '{self.name}': dropped table '{db_name}'")
        return True
    except Exception as e:
        logger.warning(f"Node '{self.name}': could not drop table '{db_name}': {e}")
        return False

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

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_name_prefix: Optional[str] = None,
) -> 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.
    """
    if table_name_prefix:
        table_name_prefix = re.sub(r"[^A-Za-z0-9_]", "_", table_name_prefix).upper()

    # Store prefix on all nodes so get_table_name() works after execution
    all_deps = self.dependencies
    for dep in all_deps:
        dep._table_name_prefix = table_name_prefix
    self._table_name_prefix = table_name_prefix

    # 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 _restore_phenex_wrapper(materialized, original):
        # Re-wrap: get_dest_table() strips PhenexTable metadata, restore the original subclass.
        if isinstance(original, PhenexTable) and not isinstance(
            materialized, PhenexTable
        ):
            return type(original)(
                materialized, name=original.NAME_TABLE, column_mapping={}
            )
        return materialized

    def _run_and_materialise(node, node_name):
        """Execute *node*, materialise the result, record timing, and update the run hash."""
        db_name = node.get_table_name(table_name_prefix)
        node.lastexecution_start_time = datetime.now()
        table = node._execute(tables)
        # Save the generating query before create_table() materializes it (to_sql layer 1).
        node._expression = table
        if table is not None:
            original = table
            con.create_table(table, db_name, overwrite=overwrite)
            table = _restore_phenex_wrapper(con.get_dest_table(db_name), original)
        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."
                        )

                    # Sampler nodes write no dest table (the SAMPLER_STAGE group returns
                    # None; a fraction=1.0 node is a no-op via _skip_cache). Skip the cache
                    # for them — with no table to look up they would perpetually MISS.
                    is_sampler_group = (
                        isinstance(node, NodeGroup)
                        and "SAMPLER_STAGE" in node.name.upper()
                    )
                    if is_sampler_group or getattr(node, "_skip_cache", False):
                        table = node._execute(tables)
                    elif Node._node_manager.should_rerun(node, con):
                        table = _run_and_materialise(node, node_name)
                    else:
                        db_name = node.get_table_name(table_name_prefix)
                        try:
                            table = con.get_dest_table(db_name)
                        except Exception:
                            # Cached table was dropped or is inaccessible; recompute.
                            logger.warning(
                                f"Cached table for '{node_name}' not found at {db_name}; recomputing."
                            )
                            table = _run_and_materialise(node, node_name)
                else:
                    # Time the execution
                    node.lastexecution_start_time = datetime.now()
                    table = node._execute(tables)
                    # Save the generating query before create_table() materializes it (to_sql layer 1).
                    node._expression = table

                    if (
                        con and table is not None
                    ):  # Only create table if _execute returns something
                        original = table
                        db_name = node.get_table_name(table_name_prefix)
                        logger.info(
                            f"Thread {threading.current_thread().name}: materializing '{node_name}' to database ..."
                        )
                        _t_mat = datetime.now()
                        con.create_table(table, db_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 = _restore_phenex_wrapper(
                            con.get_dest_table(db_name), original
                        )

                    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

get_sql_filename()

Filesystem-safe .sql filename for this node's table.

<>:"/\|?* become _, plus a short hash when that changed the name so two names that clean up alike never collide. Filenames longer than 250 characters (including .sql) are truncated with the same hash suffix, staying below the common 255-character per-filename filesystem limit. Only the filename changes, not the SQL.

Source code in phenex/node.py

def get_sql_filename(self) -> str:
    """Filesystem-safe `.sql` filename for this node's table.

    `<>:"/\\|?*` become `_`, plus a short hash when that changed the name so two
    names that clean up alike never collide. Filenames longer than 250 characters
    (including `.sql`) are truncated with the same hash suffix, staying below the
    common 255-character per-filename filesystem limit. Only the filename changes,
    not the SQL.
    """
    MAX_FILENAME_LEN = 250  # includes ".sql"
    name = self.get_table_name()
    safe = re.sub(r'[<>:"/\\|?*]', "_", name)
    if safe != name:
        safe = f"{safe}__{hashlib.md5(name.encode()).hexdigest()[:8]}"
    if len(safe) + len(".sql") > MAX_FILENAME_LEN:
        digest = hashlib.md5(name.encode()).hexdigest()[:8]
        keep = MAX_FILENAME_LEN - len(".sql") - len("__") - len(digest)
        safe = f"{safe[:keep]}__{digest}"
    return f"{safe}.sql"

get_table_name(table_name_prefix=None)

Get the table name used in the destination database for this node.

Parameters:

Name	Type	Description	Default
table_name_prefix	Optional[str]	Optional prefix. If None, uses the prefix from the last execution.	None

Returns:

Name	Type	Description
str	str	The table name in the destination database.

Source code in phenex/node.py

def get_table_name(self, table_name_prefix: Optional[str] = None) -> str:
    """
    Get the table name used in the destination database for this node.

    Parameters:
        table_name_prefix: Optional prefix. If None, uses the prefix from the last execution.

    Returns:
        str: The table name in the destination database.
    """
    prefix = table_name_prefix or self._table_name_prefix
    if prefix:
        prefix = re.sub(r"[^A-Za-z0-9_]", "_", prefix).upper()
        if not self.name.startswith(prefix):
            return f"{prefix}__{self.name}"
    return self.name

to_sql(sql_dir='./sql', connector=None)

Return the SQL that produces this node's table, read-only (execute() writes it).

Returns the first source available, in order: the in-memory expression (this session), the saved {sql_dir}/{name}.sql file, the phenex.db cache, or a recompile from dependency tables. Pass connector to pin the dialect.

Raises:

Type	Description
RuntimeError	If required upstream tables are missing, call execute() first.

Source code in phenex/node.py

def to_sql(self, sql_dir: str = "./sql", connector=None) -> str:
    """Return the SQL that produces this node's table, read-only (execute() writes it).

    Returns the first source available, in order: the in-memory expression (this
    session), the saved `{sql_dir}/{name}.sql` file, the `phenex.db` cache, or a
    recompile from dependency tables. Pass `connector` to pin the dialect.

    Raises:
        RuntimeError: If required upstream tables are missing, call `execute()` first.
    """
    # Explicit compile target when a connector is given; else each layer self-identifies.
    target_dialect = (
        ibis_dialect_of_connector(connector) if connector is not None else None
    )
    name = self.get_table_name()  # cohort-prefixed; matches the written filename

    # 1. in-memory expression: compile + stamp in the target (or its own backend) dialect.
    if self._expression is not None:
        logger.info(f"to_sql('{name}') ← memory (this session)")
        return compile_sql(self._expression, dialect=target_dialect)

    # 2. saved file, keyed by name (cohort-prefixed) to match the written filename.
    # sql_dir=None means "no directory to read from", skip straight to the cache.
    if sql_dir is not None:
        filepath = os.path.join(sql_dir, self.get_sql_filename())
        if os.path.exists(filepath):
            file_sql = read_sql_file(filepath)
            # Use the file unless it's stamped for a different backend (wrong dialect).
            stamp = read_dialect_stamp(file_sql)
            if target_dialect is None or stamp is None or stamp == target_dialect:
                logger.info(f"to_sql('{name}') ← file: {filepath}")
                return file_sql

    # 3. phenex.db SQL dialect-aware with a connector (only its SQL), else hash-only lookup.
    try:
        sql = Node._node_manager.get_sql(self, con=connector)
    except Exception:
        sql = None
    if sql is not None:
        logger.info(f"to_sql('{name}') ← phenex.db cache")
        return sql

    # 4. auto-collect dependency tables and recompile
    collected = {dep.name: dep.table for dep in self.dependencies}
    missing = [dep_name for dep_name, tbl in collected.items() if tbl is None]
    if missing:
        raise RuntimeError(
            f"Node '{self.name}' cannot compile SQL. Missing upstream tables: "
            f"{', '.join(missing)}. Call `load()` or `execute()` first."
        )
    # KeyError = a missing source table -> clear error; a real node bug -> re-raise.
    try:
        # Recompiled from dependency tables: compile + stamp in the target (or backend) dialect.
        recompiled = compile_sql(self._execute(collected), dialect=target_dialect)
        logger.info(
            f"to_sql('{self.get_table_name()}') ← recompiled from dependencies"
        )
        return recompiled
    except KeyError as e:
        key = e.args[0]
        if key not in collected:
            raise RuntimeError(
                f"Node '{self.name}' cannot compile SQL. "
                f"Missing source-domain table: '{key}'. "
                "Call `load()` or `execute()` first."
            ) from e
        raise

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)