tprdb-utilities 0.1.0__tar.gz

tprdb_utilities-0.1.0/.gitignore

@@ -0,0 +1,16 @@
+# Virtual environment
+.venv/
+
+# Build output
+dist/
+build/
+*.egg-info/
+
+# Python cache
+__pycache__/
+*.pyc
+*.pyo
+.pytest_cache/
+
+# OS
+.DS_Store

tprdb_utilities-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Critt-Kent
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

tprdb_utilities-0.1.0/PKG-INFO

@@ -0,0 +1,166 @@
+Metadata-Version: 2.4
+Name: tprdb-utilities
+Version: 0.1.0
+Summary: A toolkit for accessing and working with data from the CRITT Translation Process Research Database (TPR-DB).
+Project-URL: Homepage, https://github.com/Critt-Kent/tprdb-utilities
+Project-URL: Issues, https://github.com/Critt-Kent/tprdb-utilities/issues
+Author-email: Devin Gilbert <DevinG@uvu.edu>
+License: MIT
+License-File: LICENSE
+Requires-Python: >=3.9
+Requires-Dist: pandas
+Requires-Dist: requests
+Description-Content-Type: text/markdown
+
+# tprdb-utilities
+
+[![PyPI version](https://img.shields.io/pypi/v/tprdb-utilities.svg)](https://pypi.org/project/tprdb-utilities/)
+[![Python](https://img.shields.io/pypi/pyversions/tprdb-utilities.svg)](https://pypi.org/project/tprdb-utilities/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+A Python toolkit for downloading and reading data tables from the
+[CRITT Translation Process Research Database (TPR-DB)](https://critt.as.kent.edu/tpr/).
+
+Two functions cover the full workflow:
+
+| Function | What it does |
+|---|---|
+| `fetch_TPRDB_tables` | Downloads study tables from the CRITT API and saves them to a local directory structure |
+| `read_TPRDB_tables` | Reads those tables (locally or on the CRITT server) into a single `pandas.DataFrame` |
+
+---
+
+## Installation
+
+```bash
+# pip
+pip install tprdb-utilities
+
+# uv
+uv add tprdb-utilities
+
+# poetry
+poetry add tprdb-utilities
+```
+
+---
+
+## Quick Start
+
+### 1 — Download data (fetcher)
+
+**Public study** (no credentials needed):
+
+```python
+from tprdb_utilities import fetch_TPRDB_tables
+
+fetch_TPRDB_tables(
+    path="/path/to/local/data",
+    StudyID="DG21",
+    extension=["kd", "ss"],
+    public=True,
+)
+```
+
+**Private study** (requires your TPR-DB username and API token):
+
+```python
+from tprdb_utilities import fetch_TPRDB_tables
+
+fetch_TPRDB_tables(
+    path="/path/to/local/data",
+    StudyID="MYSTUDY",
+    extension=["kd"],
+    public=False,
+    username="myTPRDBusername",   # case-sensitive, must match your account
+    token="my-api-token",
+)
+```
+
+After downloading, the function always prints a summary like this:
+
+```
+=== fetch_TPRDB_tables Summary ===
+StudyID  : DG21
+Clone dir: /path/to/local/data/tprdb-mothership-clone
+User dir : TPRDB
+
+Extension  Status      Time
+---------  ----------  ------
+kd         Downloaded  1.23s
+ss         Downloaded  0.98s
+
+To read these files with read_TPRDB_tables:
+  path      = "/path/to/local/data/tprdb-mothership-clone"
+  user      = "TPRDB"
+  studies   = ["DG21"]
+```
+
+Copy those argument values directly into `read_TPRDB_tables`.
+
+---
+
+### 2 — Read data (reader)
+
+**From a local clone** (`mothership=False`) — after running `fetch_TPRDB_tables`:
+
+```python
+from tprdb_utilities import read_TPRDB_tables
+
+df = read_TPRDB_tables(
+    studies=["DG21", "AR22"],
+    extension="kd",
+    mothership=False,
+    path="/path/to/local/data/tprdb-mothership-clone",
+    user="TPRDB",
+)
+```
+
+**Directly on the CRITT TPR-DB server** (`mothership=True`):
+
+```python
+from tprdb_utilities import read_TPRDB_tables
+
+df = read_TPRDB_tables(
+    studies=["DG21", "AR22"],
+    extension="kd",
+    mothership=True,   # path is set automatically; no path argument needed
+)
+```
+
+---
+
+## Directory Structure
+
+`fetch_TPRDB_tables` creates the following layout under `path`:
+
+```
+<path>/
+└── tprdb-mothership-clone/
+    ├── TPRDB/                  ← public studies
+    │   └── <StudyID>/
+    │       └── Tables/
+    │           ├── session1.kd
+    │           └── ...
+    └── <username>/             ← private studies
+        └── <StudyID>/
+            └── Tables/
+                ├── session1.kd
+                └── ...
+```
+
+`read_TPRDB_tables` with `mothership=False` expects this exact layout, so the
+two functions are designed to work together seamlessly.
+
+---
+
+## Supported Table Extensions
+
+`ss`, `sg`, `st`, `tt`, `kd`, `fd`, `au`, `pu`, `hof`, `pol`
+
+---
+
+## License
+
+MIT — see [LICENSE](LICENSE).
+

tprdb_utilities-0.1.0/README.md

@@ -0,0 +1,152 @@
+# tprdb-utilities
+
+[![PyPI version](https://img.shields.io/pypi/v/tprdb-utilities.svg)](https://pypi.org/project/tprdb-utilities/)
+[![Python](https://img.shields.io/pypi/pyversions/tprdb-utilities.svg)](https://pypi.org/project/tprdb-utilities/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+A Python toolkit for downloading and reading data tables from the
+[CRITT Translation Process Research Database (TPR-DB)](https://critt.as.kent.edu/tpr/).
+
+Two functions cover the full workflow:
+
+| Function | What it does |
+|---|---|
+| `fetch_TPRDB_tables` | Downloads study tables from the CRITT API and saves them to a local directory structure |
+| `read_TPRDB_tables` | Reads those tables (locally or on the CRITT server) into a single `pandas.DataFrame` |
+
+---
+
+## Installation
+
+```bash
+# pip
+pip install tprdb-utilities
+
+# uv
+uv add tprdb-utilities
+
+# poetry
+poetry add tprdb-utilities
+```
+
+---
+
+## Quick Start
+
+### 1 — Download data (fetcher)
+
+**Public study** (no credentials needed):
+
+```python
+from tprdb_utilities import fetch_TPRDB_tables
+
+fetch_TPRDB_tables(
+    path="/path/to/local/data",
+    StudyID="DG21",
+    extension=["kd", "ss"],
+    public=True,
+)
+```
+
+**Private study** (requires your TPR-DB username and API token):
+
+```python
+from tprdb_utilities import fetch_TPRDB_tables
+
+fetch_TPRDB_tables(
+    path="/path/to/local/data",
+    StudyID="MYSTUDY",
+    extension=["kd"],
+    public=False,
+    username="myTPRDBusername",   # case-sensitive, must match your account
+    token="my-api-token",
+)
+```
+
+After downloading, the function always prints a summary like this:
+
+```
+=== fetch_TPRDB_tables Summary ===
+StudyID  : DG21
+Clone dir: /path/to/local/data/tprdb-mothership-clone
+User dir : TPRDB
+
+Extension  Status      Time
+---------  ----------  ------
+kd         Downloaded  1.23s
+ss         Downloaded  0.98s
+
+To read these files with read_TPRDB_tables:
+  path      = "/path/to/local/data/tprdb-mothership-clone"
+  user      = "TPRDB"
+  studies   = ["DG21"]
+```
+
+Copy those argument values directly into `read_TPRDB_tables`.
+
+---
+
+### 2 — Read data (reader)
+
+**From a local clone** (`mothership=False`) — after running `fetch_TPRDB_tables`:
+
+```python
+from tprdb_utilities import read_TPRDB_tables
+
+df = read_TPRDB_tables(
+    studies=["DG21", "AR22"],
+    extension="kd",
+    mothership=False,
+    path="/path/to/local/data/tprdb-mothership-clone",
+    user="TPRDB",
+)
+```
+
+**Directly on the CRITT TPR-DB server** (`mothership=True`):
+
+```python
+from tprdb_utilities import read_TPRDB_tables
+
+df = read_TPRDB_tables(
+    studies=["DG21", "AR22"],
+    extension="kd",
+    mothership=True,   # path is set automatically; no path argument needed
+)
+```
+
+---
+
+## Directory Structure
+
+`fetch_TPRDB_tables` creates the following layout under `path`:
+
+```
+<path>/
+└── tprdb-mothership-clone/
+    ├── TPRDB/                  ← public studies
+    │   └── <StudyID>/
+    │       └── Tables/
+    │           ├── session1.kd
+    │           └── ...
+    └── <username>/             ← private studies
+        └── <StudyID>/
+            └── Tables/
+                ├── session1.kd
+                └── ...
+```
+
+`read_TPRDB_tables` with `mothership=False` expects this exact layout, so the
+two functions are designed to work together seamlessly.
+
+---
+
+## Supported Table Extensions
+
+`ss`, `sg`, `st`, `tt`, `kd`, `fd`, `au`, `pu`, `hof`, `pol`
+
+---
+
+## License
+
+MIT — see [LICENSE](LICENSE).
+

tprdb_utilities-0.1.0/pyproject.toml

@@ -0,0 +1,25 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "tprdb-utilities"
+version = "0.1.0"
+description = "A toolkit for accessing and working with data from the CRITT Translation Process Research Database (TPR-DB)."
+readme = "README.md"
+license = { text = "MIT" }
+authors = [
+    { name = "Devin Gilbert", email = "DevinG@uvu.edu" }
+]
+requires-python = ">=3.9"
+dependencies = [
+    "pandas",
+    "requests",
+]
+
+[project.urls]
+Homepage = "https://github.com/Critt-Kent/tprdb-utilities"
+Issues = "https://github.com/Critt-Kent/tprdb-utilities/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/tprdb_utilities"]

tprdb_utilities-0.1.0/src/tprdb_utilities/__init__.py

@@ -0,0 +1,4 @@
+from tprdb_utilities.fetcher import fetch_TPRDB_tables
+from tprdb_utilities.reader import read_TPRDB_tables
+
+__all__ = ["fetch_TPRDB_tables", "read_TPRDB_tables"]

tprdb_utilities-0.1.0/src/tprdb_utilities/fetcher.py

@@ -0,0 +1,194 @@
+import glob
+import io
+import os
+import time
+import zipfile
+
+import requests
+
+
+def fetch_TPRDB_tables(
+    path, StudyID, extension, public, username=None, token=None, verbose=0
+):
+    """
+    Download TPR-DB data tables from the CRITT TPR-DB API and save them
+    locally in a directory structure that mirrors the TPR-DB server layout.
+
+    Makes one HTTP GET request per extension to the CRITT TPR-DB REST API,
+    receives a ``.zip`` archive, and extracts its contents directly into the
+    appropriate ``Tables/`` subdirectory.  The resulting file structure is
+    identical to the layout expected by ``read_TPRDB_tables``, so the two
+    functions are designed to be used in sequence.
+
+    **File structure created**::
+
+        <path>/
+        └── tprdb-mothership-clone/
+            ├── TPRDB/                  ← public studies
+            │   └── <StudyID>/
+            │       └── Tables/
+            │           ├── session1.<ext>
+            │           └── ...
+            └── <username>/             ← private studies (when public=False)
+                └── <StudyID>/
+                    └── Tables/
+                        ├── session1.<ext>
+                        └── ...
+
+    Parameters
+    ----------
+    path : str
+        Root directory in which the ``tprdb-mothership-clone`` folder will
+        be created (or appended to if it already exists).  After downloading,
+        pass ``os.path.join(path, "tprdb-mothership-clone")`` as the ``path``
+        argument to ``read_TPRDB_tables`` — or simply copy the value from
+        the summary printed by this function.
+    StudyID : str
+        Identifier of the study to download, e.g. ``"DG21"``.  Must match a
+        study registered in the TPR-DB exactly (case-sensitive).
+    extension : list of str
+        One or more table-type extensions to download, e.g.
+        ``["kd", "ss", "st"]``.  Valid values include ``"ss"``, ``"sg"``,
+        ``"st"``, ``"tt"``, ``"kd"``, ``"fd"``, ``"au"``, ``"pu"``,
+        ``"hof"``, and ``"pol"``.  One API request is made per extension;
+        extensions with files already present locally are skipped.
+    public : bool
+        Whether the requested study is publicly accessible.
+
+        ``True``
+            No credentials required.  Files are saved under
+            ``tprdb-mothership-clone/TPRDB/<StudyID>/Tables/``.
+
+        ``False``
+            Requires ``username`` and ``token``.  Files are saved under
+            ``tprdb-mothership-clone/<username>/<StudyID>/Tables/``.
+
+    username : str, optional
+        Your TPR-DB web application username.  **Required when**
+        ``public=False``.  Must match your registered username exactly
+        (case-sensitive).  Also determines the folder name used for private
+        study data, so it must be consistent across calls.
+    token : str, optional
+        Your TPR-DB API key (Bearer token).  **Required when**
+        ``public=False``.  Obtain this from your TPR-DB account settings.
+    verbose : int, optional
+        Verbosity level.  Default ``0``.
+
+        ``1`` or higher
+            Print the name of each file extracted from the zip archive for
+            every downloaded extension.
+
+    Returns
+    -------
+    None
+        This function saves files to disk and always prints a summary to
+        stdout.  It does not return data; use ``read_TPRDB_tables`` to load
+        the downloaded files into a DataFrame.
+
+    Raises
+    ------
+    ValueError
+        If ``public=False`` and ``username`` or ``token`` is not provided.
+    requests.HTTPError
+        If the API returns a non-2xx HTTP status code.  The error message
+        includes the status code and response body for diagnosis.
+
+    Notes
+    -----
+    A summary is always printed after all extensions have been processed,
+    regardless of the ``verbose`` setting.  The summary includes ready-to-use
+    argument values for ``read_TPRDB_tables`` so they can be copied directly
+    into your next call.
+
+    If files matching a given extension already exist in the ``Tables/``
+    directory, the API request for that extension is skipped entirely.
+
+    Examples
+    --------
+    **Downloading a public study:**
+
+    >>> from tprdb_utilities import fetch_TPRDB_tables
+    >>> fetch_TPRDB_tables(
+    ...     path="/path/to/local/data",
+    ...     StudyID="DG21",
+    ...     extension=["kd", "ss"],
+    ...     public=True,
+    ... )
+
+    **Downloading a private study:**
+
+    >>> from tprdb_utilities import fetch_TPRDB_tables
+    >>> fetch_TPRDB_tables(
+    ...     path="/path/to/local/data",
+    ...     StudyID="MYSTUDY",
+    ...     extension=["kd"],
+    ...     public=False,
+    ...     username="myTPRDBusername",
+    ...     token="my-api-token",
+    ... )
+    """
+    if not public and (username is None or token is None):
+        raise ValueError(
+            "username and token are required when public=False. "
+            "Provide your TPR-DB web app username (case-sensitive) and API token."
+        )
+
+    folder_name = "TPRDB" if public else username
+    clone_root = os.path.join(path, "tprdb-mothership-clone")
+    target_dir = os.path.join(clone_root, folder_name, StudyID, "Tables")
+    os.makedirs(target_dir, exist_ok=True)
+
+    # Strip any leading dots so extensions are consistently bare (e.g. "kd" not ".kd")
+    clean_extensions = [ext.lstrip(".") for ext in extension]
+
+    results = []  # list of (ext, status_str, elapsed_str)
+
+    for ext in clean_extensions:
+        # Skip if files for this extension are already present
+        existing = glob.glob(os.path.join(target_dir, f"*{ext}"))
+        if existing:
+            results.append((ext, "Skipped (already present)", "--"))
+            continue
+
+        url = (
+            "https://critt.as.kent.edu/tpr/api/tables/"
+            f"?studyID={StudyID}&extension={ext}&public={str(public).lower()}"
+        )
+        headers = {"Authorization": f"Bearer {token}"} if not public else {}
+
+        t0 = time.perf_counter()
+        response = requests.get(url, headers=headers)
+        if not response.ok:
+            raise requests.HTTPError(
+                f"HTTP {response.status_code} for extension '{ext}': {response.text}"
+            )
+
+        with zipfile.ZipFile(io.BytesIO(response.content)) as zf:
+            members = zf.namelist()
+            for name in members:
+                zf.extract(name, target_dir)
+            if verbose:
+                for name in members:
+                    print(f"  Extracted: {name}")
+
+        elapsed = f"{time.perf_counter() - t0:.2f}s"
+        results.append((ext, "Downloaded", elapsed))
+
+    # --- Always-printed summary ---
+    col_w = max(max((len(r[0]) for r in results), default=0), len("Extension"))
+    status_w = max(max((len(r[1]) for r in results), default=0), len("Status"))
+
+    print("=== fetch_TPRDB_tables Summary ===")
+    print(f"StudyID  : {StudyID}")
+    print(f"Clone dir: {clone_root}")
+    print(f"User dir : {folder_name}")
+    print()
+    print(f"{'Extension':<{col_w}}  {'Status':<{status_w}}  Time")
+    print(f"{'-' * col_w}  {'-' * status_w}  ------")
+    for ext, status, elapsed in results:
+        print(f"{ext:<{col_w}}  {status:<{status_w}}  {elapsed}")
+    print()
+    print("To read these files with read_TPRDB_tables:")
+    print(f'  path      = "{clone_root}"')
+    print(f'  user      = "{folder_name}"')
+    print(f'  studies   = ["{StudyID}"]')

tprdb_utilities-0.1.0/src/tprdb_utilities/reader.py

@@ -0,0 +1,153 @@
+import os
+import glob
+
+import pandas as pd
+
+
+def read_TPRDB_tables(studies, extension, mothership, path=None, user="TPRDB", verbose=0):
+    """
+    Load TPR-DB data tables into a single concatenated DataFrame.
+
+    Scans the expected TPR-DB directory layout for files matching the given
+    extension across one or more studies and concatenates them into one
+    ``pandas.DataFrame``.
+
+    The directory layout expected (and created by ``fetch_TPRDB_tables``) is::
+
+        <path>/
+        └── <user>/
+            └── <StudyID>/
+                └── Tables/
+                    ├── session1.<extension>
+                    ├── session2.<extension>
+                    └── ...
+
+    Parameters
+    ----------
+    studies : list of str
+        Study identifiers to load, e.g. ``["BML12", "SG12", "AR22"]``.
+        Each must correspond to a subfolder under ``<path>/<user>/``.
+    extension : str
+        File extension identifying the table type, e.g. ``"kd"``, ``"ss"``,
+        ``"sg"``, ``"st"``, ``"tt"``, ``"fd"``, ``"au"``, ``"pu"``,
+        ``"hof"``, or ``"pol"``.  A leading dot is not required.
+    mothership : bool
+        **Required.**  Controls how the root path is resolved.
+
+        ``True``
+            You are running this function directly on the **CRITT TPR-DB
+            server** (the "mothership").  The path is automatically set to
+            ``/data/critt/tprdb/`` and the ``path`` argument is ignored.
+            The ``user`` argument still applies (default ``"TPRDB"`` for
+            the public corpus).
+
+        ``False``
+            You are working from a **local clone** of the TPR-DB structure,
+            either assembled manually or downloaded via
+            ``fetch_TPRDB_tables``.  You *must* supply the ``path``
+            argument pointing to the root of that clone (i.e. the
+            ``tprdb-mothership-clone`` directory created by
+            ``fetch_TPRDB_tables``).
+
+    path : str, optional
+        Root directory of the local TPR-DB clone.  **Required when**
+        ``mothership=False``; ignored when ``mothership=True``.
+        This should be the ``tprdb-mothership-clone`` folder — i.e. the
+        full path *including* the ``tprdb-mothership-clone`` segment — that
+        was created by ``fetch_TPRDB_tables``.
+    user : str, optional
+        Name of the user sub-folder directly under ``path``.  Default is
+        ``"TPRDB"``, which corresponds to the public corpus.  When working
+        with private studies downloaded via ``fetch_TPRDB_tables``, set
+        this to your TPR-DB username (the same value passed as ``username``
+        to ``fetch_TPRDB_tables``).
+    verbose : int, optional
+        Verbosity level.  Default ``0`` (silent).
+
+        ``1``
+            Print the study name and the number of table files found for
+            each study.
+
+        ``2`` or higher
+            Also print the full path of each file as it is read.
+
+    Returns
+    -------
+    pandas.DataFrame
+        Concatenated DataFrame containing all rows from all matching table
+        files across every requested study.  Column names and dtypes are
+        inferred automatically.  Returns an empty DataFrame if no matching
+        files are found.
+
+    Raises
+    ------
+    ValueError
+        If ``mothership=False`` and ``path`` is not provided.
+
+    Notes
+    -----
+    Files are expected to be tab-separated values (TSV).  Each file
+    corresponds to one recording session.
+
+    The ``extension`` argument is matched as a file-name suffix, so passing
+    ``"kd"`` will match any file whose name ends with ``"kd"``
+    (e.g. ``"P01_DG21_EN-DE.kd"``).
+
+    Examples
+    --------
+    **Use case 1 — Running on the CRITT TPR-DB server (mothership=True):**
+
+    Users with direct access to the CRITT server do not need to specify a
+    path; it is resolved automatically.
+
+    >>> from tprdb_utilities import read_TPRDB_tables
+    >>> df = read_TPRDB_tables(
+    ...     studies=["DG21", "AR22"],
+    ...     extension="kd",
+    ...     mothership=True,
+    ... )
+
+    **Use case 2 — Reading from a local clone (mothership=False):**
+
+    Data must have been previously downloaded with ``fetch_TPRDB_tables``
+    (or arranged manually in the identical directory structure).  Use the
+    ``path`` and ``user`` values printed by ``fetch_TPRDB_tables`` at the
+    end of its summary output.
+
+    >>> from tprdb_utilities import read_TPRDB_tables
+    >>> df = read_TPRDB_tables(
+    ...     studies=["DG21"],
+    ...     extension="kd",
+    ...     mothership=False,
+    ...     path="/path/to/tprdb-mothership-clone",
+    ...     user="TPRDB",
+    ... )
+    """
+    if mothership:
+        path = "/data/critt/tprdb/"
+    elif path is None:
+        raise ValueError(
+            "path is required when mothership=False. "
+            "Provide the full path to your local TPR-DB clone root — "
+            "this is the 'tprdb-mothership-clone' directory created by "
+            "fetch_TPRDB_tables. Example: "
+            "path='/your/local/data/tprdb-mothership-clone'"
+        )
+
+    df = pd.DataFrame()
+    for study in studies:
+        pattern = os.path.join(path, user, study, "Tables", f"*{extension}")
+        files = glob.glob(pattern)
+        if verbose:
+            print(f"Reading: {study}\twith {len(files)} '{extension}' Tables")
+        for fn in files:
+            if verbose > 1:
+                print(f"\t{fn}")
+            df = pd.concat(
+                [df, pd.read_csv(fn, sep="\t", dtype=None)],
+                ignore_index=True,
+            )
+
+    if verbose:
+        print(f"Total '{extension}' data rows: {df.shape[0]}, columns: {df.shape[1]}")
+    return df