kumoai 2.13.0.dev202512040649__cp313-cp313-win_amd64.whl → 2.14.0.dev202512211732__cp313-cp313-win_amd64.whl

kumoai/experimental/rfm/base/table.py

@@ -1,23 +1,20 @@
 from abc import ABC, abstractmethod
-from collections import defaultdict
+from collections.abc import Sequence
 from functools import cached_property
-from typing import Dict, List, Optional, Sequence, Set
 
 import pandas as pd
+from kumoapi.model_plan import MissingType
 from kumoapi.source_table import UnavailableSourceTable
 from kumoapi.table import Column as ColumnDefinition
 from kumoapi.table import TableDefinition
 from kumoapi.typing import Stype
 from typing_extensions import Self
 
-from kumoai import in_notebook
-from kumoai.experimental.rfm.base import Column, SourceColumn, SourceForeignKey
+from kumoai import in_notebook, in_snowflake_notebook
+from kumoai.experimental.rfm.base import Column, DataBackend, SourceColumn
 from kumoai.experimental.rfm.infer import (
-    contains_categorical,
-    contains_id,
-    contains_multicategorical,
-    contains_timestamp,
     infer_primary_key,
+    infer_stype,
     infer_time_column,
 )
 
@@ -38,44 +35,32 @@ class Table(ABC):
     def __init__(
         self,
         name: str,
-        columns: Optional[Sequence[str]] = None,
-        primary_key: Optional[str] = None,
-        time_column: Optional[str] = None,
-        end_time_column: Optional[str] = None,
+        columns: Sequence[str] | None = None,
+        primary_key: MissingType | str | None = MissingType.VALUE,
+        time_column: str | None = None,
+        end_time_column: str | None = None,
     ) -> None:
 
         self._name = name
-        self._primary_key: Optional[str] = None
-        self._time_column: Optional[str] = None
-        self._end_time_column: Optional[str] = None
+        self._primary_key: str | None = None
+        self._time_column: str | None = None
+        self._end_time_column: str | None = None
 
-        if len(self._source_column_dict) == 0:
-            raise ValueError(f"Table '{name}' does not hold any column with "
-                             f"a supported data type")
+        if columns is None:
+            columns = list(self._source_column_dict.keys())
 
-        primary_keys = [
-            column.name for column in self._source_column_dict.values()
-            if column.is_primary_key
-        ]
-        if len(primary_keys) == 1:  # NOTE No composite keys yet.
-            if primary_key is not None and primary_key != primary_keys[0]:
-                raise ValueError(f"Found duplicate primary key "
-                                 f"definition '{primary_key}' and "
-                                 f"'{primary_keys[0]}' in table '{name}'")
-            primary_key = primary_keys[0]
-
-        unique_keys = [
-            column.name for column in self._source_column_dict.values()
-            if column.is_unique_key
-        ]
-        if primary_key is None and len(unique_keys) == 1:
-            primary_key = unique_keys[0]
-
-        self._columns: Dict[str, Column] = {}
-        for column_name in columns or list(self._source_column_dict.keys()):
+        self._columns: dict[str, Column] = {}
+        for column_name in columns:
             self.add_column(column_name)
 
-        if primary_key is not None:
+        if isinstance(primary_key, MissingType):
+            # Inference from source column metadata:
+            if '_source_column_dict' in self.__dict__:
+                primary_key = self._source_primary_key
+                if (primary_key is not None and primary_key in self
+                        and self[primary_key].is_physical):
+                    self.primary_key = primary_key
+        elif primary_key is not None:
             if primary_key not in self:
                 self.add_column(primary_key)
             self.primary_key = primary_key
@@ -95,7 +80,7 @@ class Table(ABC):
         r"""The name of this table."""
         return self._name
 
-    # Data column #############################################################
+    # Column ##################################################################
 
     def has_column(self, name: str) -> bool:
         r"""Returns ``True`` if this table holds a column with name ``name``;
@@ -117,7 +102,7 @@ class Table(ABC):
         return self._columns[name]
 
     @property
-    def columns(self) -> List[Column]:
+    def columns(self) -> list[Column]:
         r"""Returns a list of :class:`Column` objects that represent the
         columns in this table.
         """
@@ -140,36 +125,22 @@ class Table(ABC):
             raise KeyError(f"Column '{name}' does not exist in the underlying "
                            f"source table")
 
-        try:
-            dtype = self._source_column_dict[name].dtype
-        except Exception as e:
-            raise RuntimeError(f"Could not obtain data type for column "
-                               f"'{name}' in table '{self.name}'. Change "
-                               f"the data type of the column in the source "
-                               f"table or remove it from the table.") from e
+        dtype = self._source_column_dict[name].dtype
 
+        ser = self._source_sample_df[name]
         try:
-            ser = self._sample_df[name]
-            if contains_id(ser, name, dtype):
-                stype = Stype.ID
-            elif contains_timestamp(ser, name, dtype):
-                stype = Stype.timestamp
-            elif contains_multicategorical(ser, name, dtype):
-                stype = Stype.multicategorical
-            elif contains_categorical(ser, name, dtype):
-                stype = Stype.categorical
-            else:
-                stype = dtype.default_stype
+            stype = infer_stype(ser, name, dtype)
         except Exception as e:
             raise RuntimeError(f"Could not obtain semantic type for column "
-                               f"'{name}' in table '{self.name}'. Change "
-                               f"the data type of the column in the source "
-                               f"table or remove it from the table.") from e
+                               f"'{name}' with data type '{dtype}' in table "
+                               f"'{self.name}'. Change the data type of the "
+                               f"column in the source table or remove it from "
+                               f"this table.") from e
 
         self._columns[name] = Column(
             name=name,
-            dtype=dtype,
             stype=stype,
+            dtype=dtype,
         )
 
         return self._columns[name]
@@ -205,7 +176,7 @@ class Table(ABC):
         return self._primary_key is not None
 
     @property
-    def primary_key(self) -> Optional[Column]:
+    def primary_key(self) -> Column | None:
         r"""The primary key column of this table.
 
         The getter returns the primary key column of this table, or ``None`` if
@@ -220,7 +191,7 @@ class Table(ABC):
         return self[self._primary_key]
 
     @primary_key.setter
-    def primary_key(self, name: Optional[str]) -> None:
+    def primary_key(self, name: str | None) -> None:
         if name is not None and name == self._time_column:
             raise ValueError(f"Cannot specify column '{name}' as a primary "
                              f"key since it is already defined to be a time "
@@ -250,7 +221,7 @@ class Table(ABC):
         return self._time_column is not None
 
     @property
-    def time_column(self) -> Optional[Column]:
+    def time_column(self) -> Column | None:
         r"""The time column of this table.
 
         The getter returns the time column of this table, or ``None`` if no
@@ -265,7 +236,7 @@ class Table(ABC):
         return self[self._time_column]
 
     @time_column.setter
-    def time_column(self, name: Optional[str]) -> None:
+    def time_column(self, name: str | None) -> None:
         if name is not None and name == self._primary_key:
             raise ValueError(f"Cannot specify column '{name}' as a time "
                              f"column since it is already defined to be a "
@@ -295,7 +266,7 @@ class Table(ABC):
         return self._end_time_column is not None
 
     @property
-    def end_time_column(self) -> Optional[Column]:
+    def end_time_column(self) -> Column | None:
         r"""The end time column of this table.
 
         The getter returns the end time column of this table, or ``None`` if no
@@ -311,7 +282,7 @@ class Table(ABC):
         return self[self._end_time_column]
 
     @end_time_column.setter
-    def end_time_column(self, name: Optional[str]) -> None:
+    def end_time_column(self, name: str | None) -> None:
         if name is not None and name == self._primary_key:
             raise ValueError(f"Cannot specify column '{name}' as an end time "
                              f"column since it is already defined to be a "
@@ -384,7 +355,12 @@ class Table(ABC):
         if self._num_rows is not None:
             num_rows_repr = ' ({self._num_rows:,} rows)'
 
-        if in_notebook():
+        if in_snowflake_notebook():
+            import streamlit as st
+            md_repr = f"### 🏷️ Metadata of Table `{self.name}`{num_rows_repr}"
+            st.markdown(md_repr)
+            st.dataframe(self.metadata, hide_index=True)
+        elif in_notebook():
             from IPython.display import Markdown, display
             md_repr = f"### 🏷️ Metadata of Table `{self.name}`{num_rows_repr}"
             display(Markdown(md_repr))
@@ -400,8 +376,91 @@ class Table(ABC):
             print(f"🏷️ Metadata of Table '{self.name}'{num_rows_repr}")
             print(self.metadata.to_string(index=False))
 
+    def infer_primary_key(self, verbose: bool = True) -> Self:
+        r"""Infers the primary key in this table.
+
+        Args:
+            verbose: Whether to print verbose output.
+        """
+        if self.has_primary_key():
+            return self
+
+        def _set_primary_key(primary_key: str) -> None:
+            self.primary_key = primary_key
+            if verbose:
+                print(f"Detected primary key '{primary_key}' in table "
+                      f"'{self.name}'")
+
+        # Inference from source column metadata:
+        if '_source_column_dict' in self.__dict__:
+            primary_key = self._source_primary_key
+            if (primary_key is not None and primary_key in self
+                    and self[primary_key].is_physical):
+                _set_primary_key(primary_key)
+                return self
+
+            unique_keys = [
+                column.name for column in self._source_column_dict.values()
+                if column.is_unique_key
+            ]
+            if (len(unique_keys) == 1  # NOTE No composite keys yet.
+                    and unique_keys[0] in self
+                    and self[unique_keys[0]].is_physical):
+                _set_primary_key(unique_keys[0])
+                return self
+
+        # Heuristic-based inference:
+        candidates = [
+            column.name for column in self.columns if column.stype == Stype.ID
+        ]
+        if len(candidates) == 0:
+            for column in self.columns:
+                if self.name.lower() == column.name.lower():
+                    candidates.append(column.name)
+                elif (self.name.lower().endswith('s')
+                      and self.name.lower()[:-1] == column.name.lower()):
+                    candidates.append(column.name)
+
+        if primary_key := infer_primary_key(
+                table_name=self.name,
+                df=self._sample_current_df(columns=candidates),
+                candidates=candidates,
+        ):
+            _set_primary_key(primary_key)
+            return self
+
+        return self
+
+    def infer_time_column(self, verbose: bool = True) -> Self:
+        r"""Infers the time column in this table.
+
+        Args:
+            verbose: Whether to print verbose output.
+        """
+        if self.has_time_column():
+            return self
+
+        # Heuristic-based inference:
+        candidates = [
+            column.name for column in self.columns
+            if column.stype == Stype.timestamp
+            and column.name != self._end_time_column
+        ]
+
+        if time_column := infer_time_column(
+                df=self._sample_current_df(columns=candidates),
+                candidates=candidates,
+        ):
+            self.time_column = time_column
+
+            if verbose:
+                print(f"Detected time column '{time_column}' in table "
+                      f"'{self.name}'")
+
+        return self
+
     def infer_metadata(self, verbose: bool = True) -> Self:
-        r"""Infers metadata, *i.e.*, primary keys and time columns, in the
+        r"""Infers metadata, *i.e.*, primary keys and time columns, in this
         table.
 
         Args:
@@ -409,45 +468,15 @@ class Table(ABC):
         """
         logs = []
 
-        # Try to detect primary key if not set:
         if not self.has_primary_key():
+            self.infer_primary_key(verbose=False)
+            if self.has_primary_key():
+                logs.append(f"primary key '{self._primary_key}'")
 
-            def is_candidate(column: Column) -> bool:
-                if column.stype == Stype.ID:
-                    return True
-                if all(column.stype != Stype.ID for column in self.columns):
-                    if self.name == column.name:
-                        return True
-                    if (self.name.endswith('s')
-                            and self.name[:-1] == column.name):
-                        return True
-                return False
-
-            candidates = [
-                column.name for column in self.columns if is_candidate(column)
-            ]
-
-            if primary_key := infer_primary_key(
-                    table_name=self.name,
-                    df=self._sample_df,
-                    candidates=candidates,
-            ):
-                self.primary_key = primary_key
-                logs.append(f"primary key '{primary_key}'")
-
-        # Try to detect time column if not set:
         if not self.has_time_column():
-            candidates = [
-                column.name for column in self.columns
-                if column.stype == Stype.timestamp
-                and column.name != self._end_time_column
-            ]
-            if time_column := infer_time_column(
-                    df=self._sample_df,
-                    candidates=candidates,
-            ):
-                self.time_column = time_column
-                logs.append(f"time column '{time_column}'")
+            self.infer_time_column(verbose=False)
+            if self.has_time_column():
+                logs.append(f"time column '{self._time_column}'")
 
         if verbose and len(logs) > 0:
             print(f"Detected {' and '.join(logs)} in table '{self.name}'")
@@ -468,6 +497,36 @@ class Table(ABC):
             end_time_col=self._end_time_column,
         )
 
+    @cached_property
+    def _source_column_dict(self) -> dict[str, SourceColumn]:
+        source_columns = self._get_source_columns()
+        if len(source_columns) == 0:
+            raise ValueError(f"Table '{self.name}' does not hold any column "
+                             f"with a supported data type")
+        return {column.name: column for column in source_columns}
+
+    @cached_property
+    def _source_sample_df(self) -> pd.DataFrame:
+        return self._get_source_sample_df()
+
+    @property
+    def _source_primary_key(self) -> str | None:
+        primary_keys = [
+            column.name for column in self._source_column_dict.values()
+            if column.is_primary_key
+        ]
+        if len(primary_keys) == 1:  # NOTE No composite keys yet.
+            return primary_keys[0]
+
+        return None
+
+    @cached_property
+    def _num_rows(self) -> int | None:
+        return self._get_num_rows()
+
+    def _sample_current_df(self, columns: Sequence[str]) -> pd.DataFrame:
+        return self._source_sample_df[columns]
+
     # Python builtins #########################################################
 
     def __hash__(self) -> int:
@@ -496,45 +555,21 @@ class Table(ABC):
                 f'  end_time_column={self._end_time_column},\n'
                 f')')
 
-    # Abstract method #########################################################
-
-    @cached_property
-    def _source_column_dict(self) -> Dict[str, SourceColumn]:
-        return {col.name: col for col in self._get_source_columns()}
+    # Abstract Methods ########################################################
 
+    @property
     @abstractmethod
-    def _get_source_columns(self) -> List[SourceColumn]:
-        pass
-
-    @cached_property
-    def _source_foreign_key_dict(self) -> Dict[str, SourceForeignKey]:
-        fkeys = self._get_source_foreign_keys()
-        # NOTE Drop all keys that link to different primary keys in the same
-        # table since we don't support composite keys yet:
-        table_pkeys: Dict[str, Set[str]] = defaultdict(set)
-        for fkey in fkeys:
-            table_pkeys[fkey.dst_table].add(fkey.primary_key)
-        return {
-            fkey.name: fkey
-            for fkey in fkeys if len(table_pkeys[fkey.dst_table]) == 1
-        }
+    def backend(self) -> DataBackend:
+        r"""The data backend of this table."""
 
     @abstractmethod
-    def _get_source_foreign_keys(self) -> List[SourceForeignKey]:
+    def _get_source_columns(self) -> list[SourceColumn]:
         pass
 
-    @cached_property
-    def _sample_df(self) -> pd.DataFrame:
-        return self._get_sample_df()
-
     @abstractmethod
-    def _get_sample_df(self) -> pd.DataFrame:
+    def _get_source_sample_df(self) -> pd.DataFrame:
         pass
 
-    @cached_property
-    def _num_rows(self) -> Optional[int]:
-        return self._get_num_rows()
-
     @abstractmethod
-    def _get_num_rows(self) -> Optional[int]:
+    def _get_num_rows(self) -> int | None:
         pass