Add new methods for dropping output parameters and columns

src/f3dasm/_src/design/domain.py

@@ -428,7 +428,7 @@ def add(self, name: str,
                 f"Unknown type {type}!"
                 f"Possible types are: 'float', 'int', 'category', 'constant'.")
 
-    def add_output(self, name: str, to_disk: bool):
+    def add_output(self, name: str, to_disk: bool, exist_ok=False):
         """Add a new output parameter to the domain.
 
         Parameters
@@ -446,9 +446,11 @@ def add_output(self, name: str, to_disk: bool):
         {'param1': OutputParameter(to_disk=True)}
         """
         if name in self.output_space:
-            raise KeyError(
-                f"Parameter {name} already exists in the domain! \
-                     Choose a different name.")
+            if not exist_ok:
+                raise KeyError(
+                    f"Parameter {name} already exists in the domain! \
+                        Choose a different name.")
+            return
 
         self.output_space[name] = _OutputParameter(to_disk)
 #                                                                       Getters
@@ -724,6 +726,41 @@ def select(self, names: str | Iterable[str]) -> Domain:
 
         return Domain(space={key: self.space[key] for key in names})
 
+    def drop_output(self, names: str | Iterable[str]) -> Domain:
+        """Drop a subset of output parameters from the domain.
+
+        Parameters
+        ----------
+
+        names : str or Iterable[str]
+            The names of the output parameters to drop.
+
+        Returns
+        -------
+        Domain
+            A new domain with the dropped output parameters.
+
+        Example
+        -------
+        >>> domain = Domain()
+        >>> domain.output_space = {
+        ...     'param1': _OutputParameter(to_disk=True),
+        ...     'param2': _OutputParameter(to_disk=True),
+        ...     'param3': _OutputParameter(to_disk=True)
+        ... }
+        >>> domain.drop_output(['param1', 'param3'])
+        Domain({'param2': _OutputParameter(to_disk=True)})
+        """
+
+        if isinstance(names, str):
+            names = [names]
+
+        return Domain(
+            space=self.space,
+            output_space={key: self.output_space[key]
+                          for key in self.output_space
+                          if key not in names})
+
 #                                                                 Miscellaneous
 # =============================================================================
 

src/f3dasm/_src/experimentdata/_data.py

@@ -351,6 +351,29 @@ def select_columns(self, columns: Iterable[str] | str) -> _Data:
         return _Data(
             self.data[self.columns.iloc(columns)], columns=_selected_columns)
 
+    def drop(self, columns: Iterable[str] | str) -> _Data:
+        """Drop the selected columns from the data.
+
+        Parameters
+        ----------
+        columns : Iterable[str] | str
+            The columns to drop.
+
+        Returns
+        -------
+        _Data
+            The data without the selected columns
+        """
+        if isinstance(columns, str):
+            columns = [columns]
+        _selected_columns = _Columns(
+            {
+                name: None for name in self.columns.columns
+                if name not in columns})
+        return _Data(
+            data=self.data.drop(columns=self.columns.iloc(columns)),
+            columns=_selected_columns)
+
 #                                                        Append and remove data
 # =============================================================================
 
@@ -381,7 +404,14 @@ def add_empty_rows(self, number_of_rows: int):
             np.nan, index=new_indices, columns=self.data.columns)
         self.data = pd.concat([self.data, empty_data], ignore_index=False)
 
-    def add_column(self, name: str):
+    def add_column(self, name: str, exist_ok: bool = False):
+        if name in self.columns.names:
+            if not exist_ok:
+                raise ValueError(
+                    f"Column {name} already exists in the data. "
+                    "Set exist_ok to True to allow skipping existing columns.")
+            return
+
         if self.data.columns.empty:
             new_columns_index = 0
         else:
@@ -454,6 +484,16 @@ def is_empty(self) -> bool:
         """Check if the data is empty."""
         return self.data.empty
 
+    def get_index_with_nan(self) -> pd.Index:
+        """Get the indices with NaN values.
+
+        Returns
+        -------
+        pd.Index
+            The indices with NaN values.
+        """
+        return self.indices[self.data.isna().any(axis=1)]
+
     def has_columnnames(self, names: Iterable[str]) -> bool:
         return set(names).issubset(self.names)
 

src/f3dasm/_src/experimentdata/experimentdata.py

@@ -329,12 +329,17 @@ def from_yaml(cls, config: DictConfig) -> ExperimentData:
         ExperimentData
             ExperimentData object containing the loaded data.
         """
+        # Option 0: Both existing and sampling
+        if 'from_file' in config and 'from_sampling' in config:
+            return cls.from_file(config.from_file) + cls.from_sampling(
+                **config.from_sampling)
+
         # Option 1: From exisiting ExperimentData files
         if 'from_file' in config:
             return cls.from_file(config.from_file)
 
         # Option 2: Sample from the domain
-        elif 'from_sampling' in config:
+        if 'from_sampling' in config:
             return cls.from_sampling(**config.from_sampling)
 
         else:
@@ -395,6 +400,25 @@ def select(self, indices: int | Iterable[int]) -> ExperimentData:
                               jobs=self._jobs[indices],
                               domain=self.domain, project_dir=self.project_dir)
 
+    def drop_output(self, names: Iterable[str] | str) -> ExperimentData:
+        """Drop a column from the output data
+
+        Parameters
+        ----------
+        names : Iteraeble | str
+            The names of the columns to drop.
+
+        Returns
+        -------
+        ExperimentData
+            The ExperimentData object with the column dropped.
+        """
+        return ExperimentData(input_data=self._input_data,
+                              output_data=self._output_data.drop(names),
+                              jobs=self._jobs, domain=self.domain.drop_output(
+                                  names),
+                              project_dir=self.project_dir)
+
     def select_with_status(self, status: Literal['open', 'in progress',
                                                  'finished', 'error']
                            ) -> ExperimentData:
@@ -763,7 +787,8 @@ def add_input_parameter(
         self._input_data.add_column(name)
         self.domain.add(name=name, type=type, **kwargs)
 
-    def add_output_parameter(self, name: str, is_disk: bool) -> None:
+    def add_output_parameter(
+            self, name: str, is_disk: bool, exist_ok: bool = False) -> None:
         """Add a new output column to the ExperimentData object.
 
         Parameters
@@ -772,9 +797,12 @@ def add_output_parameter(self, name: str, is_disk: bool) -> None:
             name of the new output column
         is_disk
             Whether the output column will be stored on disk or not
+        exist_ok
+            If True, it will not raise an error if the output column already
+            exists, by default False
         """
-        self._output_data.add_column(name)
-        self.domain.add_output(name, is_disk)
+        self._output_data.add_column(name, exist_ok=exist_ok)
+        self.domain.add_output(name=name, to_disk=is_disk, exist_ok=exist_ok)
 
     def remove_rows_bottom(self, number_of_rows: int):
         """
@@ -1018,6 +1046,13 @@ def mark_all_in_progress_open(self) -> None:
         Mark all the experiments that have the status 'in progress' open
         """
         self._jobs.mark_all_in_progress_open()
+
+    def mark_all_nan_open(self) -> None:
+        """
+        Mark all the experiments that have 'nan' in output open
+        """
+        indices = self._output_data.get_index_with_nan()
+        self.mark(indices=indices, status='open')
     #                                                            Datageneration
     # =========================================================================