DeConveil 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

deconveil/__version__.py

@@ -1 +1 @@
-__version__ = "0.1.2"
+__version__ = "0.1.4"

deconveil/dds.py

@@ -18,6 +18,7 @@ from deconveil.utils_fit import fit_moments_dispersions2
 from deconveil.utils_fit import grid_fit_beta
 from deconveil.utils_fit import irls_glm
 from deconveil.utils_fit import build_design_matrix
+from deconveil.utils_processing import replace_underscores
 
 from pydeseq2.preprocessing import deseq2_norm_fit
 from pydeseq2.preprocessing import deseq2_norm_transform
@@ -25,7 +26,6 @@ from pydeseq2.utils import dispersion_trend
 from pydeseq2.utils import mean_absolute_deviation
 from pydeseq2.utils import n_or_more_replicates
 from pydeseq2.utils import nb_nll
-from pydeseq2.utils import replace_underscores
 from pydeseq2.utils import robust_method_of_moments_disp
 from pydeseq2.utils import test_valid_counts
 from pydeseq2.utils import trimmed_mean

deconveil/utils_processing.py

@@ -5,11 +5,93 @@ from pathlib import Path
 
 import numpy as np
 import pandas as pd
+import deconveil
 
 from typing import List, Literal, Optional, Dict, Any, cast
 
 
 
+def load_test_data(
+    modality: Literal["rna", "cnv", "metadata", "cnv_tumor"] = "rna",
+    dataset: Literal["tcga_brca"] = "tcga_brca",
+    debug: bool = False,
+    debug_seed: int = 42,
+) -> pd.DataFrame:
+    """Load TCGA-BRCA example data from the DeConveil package.
+
+    Parameters
+    ----------
+    modality : {"rna", "cnv", "metadata", "cnv_tumor"}
+        Type of data to load.
+
+    dataset : {"tcga_brca"}
+        Dataset name. Only "tcga_brca" is currently supported.
+
+    debug : bool, optional
+        If True, randomly subsample 10 samples and 100 features (if applicable).
+        Default is False.
+
+    debug_seed : int, optional
+        Random seed for reproducibility of debug subsampling. Default is 42.
+
+    Returns
+    -------
+    pandas.DataFrame
+        The requested data modality as a DataFrame.
+    """
+    assert modality in ["rna", "cnv", "metadata", "cnv_tumor"], (
+        "modality must be one of: 'rna', 'cnv', 'metadata', 'cnv_tumor'"
+    )
+    assert dataset in ["tcga_brca"], (
+        "dataset must be one of: 'tcga_brca'"
+    )
+
+    # Locate data within the package
+    datasets_path = Path(__file__).resolve().parent.parent / "datasets" / dataset
+
+    # Construct file paths
+    file_map = {
+        "rna": datasets_path / "rna.csv",
+        "cnv": datasets_path / "cnv.csv",
+        "metadata": datasets_path / "metadata.csv",
+        "cnv_tumor": datasets_path / "cnv_tumor.csv",
+    }
+
+    data_path = file_map[modality]
+    if not data_path.exists():
+        raise FileNotFoundError(f"Data file not found: {data_path}")
+
+    # Load the CSV
+    df = pd.read_csv(data_path, index_col=0)
+
+    # Apply debug mode subsampling
+    if debug:
+        df = df.sample(n=min(10, df.shape[0]), random_state=debug_seed)
+        if modality in ["rna", "cnv"]:
+            df = df.sample(n=min(100, df.shape[1]), axis=1, random_state=debug_seed)
+
+    return df
+
+
+def replace_underscores(factors: List[str]):
+    """Replace all underscores from strings in a list by hyphens.
+
+    To be used on design factors to avoid bugs due to the reliance on
+    ``str.split("_")`` in parts of the code.
+
+    Parameters
+    ----------
+    factors : list
+        A list of strings which may contain underscores.
+
+    Returns
+    -------
+    list
+        A list of strings in which underscores were replaced by hyphens.
+    """
+    return [factor.replace("_", "-") for factor in factors]
+
+
 def filter_low_count_genes(
     df: pd.DataFrame,
     other_dfs: Optional[List[pd.DataFrame]] = None,

{deconveil-0.1.2.dist-info → deconveil-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: DeConveil
-Version: 0.1.2
+Version: 0.1.4
 Summary: An extension of PyDESeq2/DESeq2 designed to account for genome aneuploidy
 Home-page: https://github.com/caravagnalab/DeConveil
 Author: Katsiaryna Davydzenka

{deconveil-0.1.2.dist-info → deconveil-0.1.4.dist-info}/RECORD

@@ -1,6 +1,6 @@
 deconveil/__init__.py,sha256=_6FL_AYiycv9nP3mKJiQ4zl4aU83YSWnV2YoIZr9Mv0,188
-deconveil/__version__.py,sha256=K5SiDdEGYMpdqXThrqwTqECJJBOQNTQDrnpc2K5mzKs,21
-deconveil/dds.py,sha256=0MNwtDzCjqjoJR-rrCmVu3JOaDd3gXuToOzTBXJMxak,49039
+deconveil/__version__.py,sha256=Wzf5T3NBDfhQoTnhnRNHSlAsE0XMqbclXG-M81Vas70,22
+deconveil/dds.py,sha256=FlZ9Cm92oKmsuOmhP9XWrQaz9cWT37s4ZVxTElI0J8w,49051
 deconveil/default_inference.py,sha256=J40O0-qZChLnLrLGmhwxjaTVsV7REWAUQOTf8qSwWk0,9466
 deconveil/ds.py,sha256=Vb9p152U1KXltrXFpMoBxY6YRW25dP4CO26_osbz6Aw,29476
 deconveil/grid_search.py,sha256=iOHR8ur10MyrrfEZHr409lGulGxODufsjG6j7lQ7tWs,5181
@@ -8,9 +8,9 @@ deconveil/inference.py,sha256=B3zf3q_mbCTX3gHJwuXnTuy9uyXOxEjuWyaSR6VtVEo,10429
 deconveil/utils_clustering.py,sha256=twspPvXQ6pvw_NaY1ebyvswuH3ZvVBGn7DeOpZ1XatI,5939
 deconveil/utils_fit.py,sha256=SdGcBQjN3cyzbSFessufYOOOJAQCOjNcy3etbwmodsM,21583
 deconveil/utils_plot.py,sha256=1JQthYXaEUKUWa0fy8owkyJ1CTkQxlrSRAqPkXMk7Us,9857
-deconveil/utils_processing.py,sha256=CB99CwQst7eUiIgE58yl7_3E6uD9CgQoU_Qmprjyt-s,4141
-deconveil-0.1.2.dist-info/licenses/LICENSE,sha256=BJ0f3JRteiF7tjiARi8syxiu4yKmckc0nWlHCKXttKQ,1078
-deconveil-0.1.2.dist-info/METADATA,sha256=JqHZYXo0lLvPjoj_cDT-IwHADSKdESJQxorDbpsk3-k,1097
-deconveil-0.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-deconveil-0.1.2.dist-info/top_level.txt,sha256=yAWZbw0eg8XpbMsswoq-VzBGfQHrfWOqNHnu2qQ2xO4,10
-deconveil-0.1.2.dist-info/RECORD,,
+deconveil/utils_processing.py,sha256=9j35FAfQ7oNjdH1FWHP90DBTyL5RwlgdVbbW9de10VI,6560
+deconveil-0.1.4.dist-info/licenses/LICENSE,sha256=BJ0f3JRteiF7tjiARi8syxiu4yKmckc0nWlHCKXttKQ,1078
+deconveil-0.1.4.dist-info/METADATA,sha256=uxr_y-JarwDKuEbzC3kdN_W-Wf-X-G2fELNvH0HwwM4,1097
+deconveil-0.1.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+deconveil-0.1.4.dist-info/top_level.txt,sha256=yAWZbw0eg8XpbMsswoq-VzBGfQHrfWOqNHnu2qQ2xO4,10
+deconveil-0.1.4.dist-info/RECORD,,