cleanup / removal of outdated functions

Author: ymahlich

coderdata/utils/stats.py

@@ -135,48 +135,6 @@ def plot_response_metric(
     p.set_title(title_)
 
 
-def split_experiments_by_study(data: cd.Dataset) -> dict:
-    """
-    Splits the CoderData object into multiple smaller CoderData objects
-    according to the `study` recorded in the ``.experiments`` table in 
-    the CoderData object.
-
-    Parameters
-    ----------
-    data : cd.Dataset
-        The CoderData object containing the data set loaded into memory
-        via ``coderdata.cd.Dataset()``.
-
-    Returns
-    -------
-    dict
-        A dictionary dict[study, data] where keys `study` are the names 
-        of the study in the ``.experiments`` part of the imported 
-        CoderData object and values `data` are the filtered smaller
-        CoderData objects containing only data corresponding to the 
-        study. 
-    """
-
-    df_ret = {}
-    experiments = data.experiments
-    
-    # creating the groups based on 'study' to itterate over 
-    groups = experiments.groupby('study')
-    for name, group in groups:
-
-        # extracting improve sample and drug ids from the provided split
-        sample_ids = list(np.unique(group['improve_sample_id'].values))
-        drug_ids = list(np.unique(group['improve_drug_id'].values))
-        
-        # creating new CoderData objects that contain only data
-        # pertaining to the study defined by the previous grouping
-        df_ret[name] = _filter(
-            data=data, sample_ids=sample_ids, drug_ids=drug_ids, study=name
-            )
-    
-    return df_ret
-
-
 def summarize_response_metric(data: cd.Dataset) -> pd.DataFrame:
     """
     Helper function to extract basic statistics for the `experiments`
@@ -224,99 +182,6 @@ def summarize_response_metric(data: cd.Dataset) -> pd.DataFrame:
     return df_ret
 
 
-def _filter(
-        data: cd.Dataset,
-        sample_ids: list,
-        drug_ids: list,
-        study: str=None,
-        ) -> cd.Dataset:
-    """
-    Helper function to filter down the CoderData object(s) to create
-    independent more concise CoderData objects for further processing.
-    This can be either splitting a dataset according to the different 
-    drug response studies (e.g. the broad_sanger dataset) or if small 
-    subsets need to be extracted (e.g. training / testing splits for 
-    machine learning)
-
-    Parameters
-    ----------
-    data : cd.Dataset
-        Contains a full CoderData object imported/loaded via 
-        ``cd.DataLoader``
-    sample_ids : list
-        A list of improve_sample_id[s] that the CoderData object should
-        be filtered to
-    drug_ids : list
-        A list of improve_drug_id[s] that the CoderData object should 
-        be filtered to
-    study : str, default = None
-        The drug response study that the CoderData object should be 
-        filtered to. This argument is only important for filtering the
-        broad_sanger dataset if the splitting / filtering of the data 
-        set is based on the drug response study
-
-    Returns
-    -------
-    cd.Dataset
-        The filtered CoderData object
-    
-    Notes
-    -----
-
-    Different data types of the CoderData object are going to be 
-    filtered using either the improve_sample_id or the improve_drug_id.
-    
-    - cd.copynumber -> reduce based on ``improve_sample_id``
-    - cd.drugs -> reduce based on ``improve_drug_id``
-    - cd.experiments -> reduce based on ``study`` (only applicable if 
-      the dataset is broad_sanger)
-    - cd.mutations -> reduce based on ``improve_sample_id``
-    - cd.proteomics -> reduce based on ``improve_sample_id``
-    - cd.samples -> reduce based on ``improve_sample_id``
-    - cd.transcriptomics -> reduce based on ``improve_sample_id``
-    
-    """
-
-    # creating a deep copy of the CoderData object such that any 
-    # further operations on the object are not changing the original
-    # object / data
-    data_ret = deepcopy(data)
-
-    # filtering each individual data type down by only the improve 
-    # sample / drug ids that are present in the study
-    if not data_ret.copy_number.empty:
-        data_ret.copy_number = data_ret.copy_number[
-            data_ret.copy_number['improve_sample_id'].isin(sample_ids)
-        ]
-    if not data_ret.drugs.empty:
-        data_ret.drugs = data_ret.drugs[
-            data_ret.drugs['improve_drug_id'].isin(drug_ids)
-            ]
-    if not data_ret.mutations.empty:
-        data_ret.mutations = data_ret.mutations[
-            data_ret.mutations['improve_sample_id'].isin(sample_ids)
-            ]
-    if not data_ret.proteomics.empty:
-        data_ret.proteomics = data_ret.proteomics[
-            data_ret.proteomics['improve_sample_id'].isin(sample_ids)
-            ]
-    if not data_ret.samples.empty:
-        data_ret.samples = data_ret.samples[
-            data_ret.samples['improve_sample_id'].isin(sample_ids)
-            ]
-    if not data_ret.transcriptomics.empty:
-        data_ret.transcriptomics = data_ret.transcriptomics[
-            data_ret.transcriptomics['improve_sample_id'].isin(sample_ids)
-            ]
-    if not data_ret.experiments.empty:
-        data_ret.experiments = data_ret.experiments[
-            data_ret.experiments['study'] == study
-        ]
-    # TODO: do we also need to split the gene table?
-    
-    return data_ret
-
-
 def _prepare_2d_hist_data(
         data: pd.DataFrame,
         metrics: list[str]=[