ds-proj-cc 0.1.3__tar.gz

ds_proj_cc-0.1.3/.github/workflows/ci.yml

@@ -0,0 +1,28 @@
+name: CI
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.11', '3.12', '3.13']
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+
+      - name: Install Python
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync --all-groups
+
+      - name: Run tests
+        run: uv run pytest -v

ds_proj_cc-0.1.3/.github/workflows/release.yml

@@ -0,0 +1,80 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - 'v*'       # v0.1.0, v1.2.3, ...
+
+jobs:
+  build:
+    name: Build distribution
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+
+      - name: Set up Python
+        run: uv python install 3.13
+
+      - name: Build
+        run: uv build
+
+      - name: Smoke test (wheel)
+        run: uv run --isolated --no-project --with dist/*.whl python -c "from ds_proj_cc import profile; print(profile([{'name':'Alice','age':21},{'name':'Bob','age':22}])['rows'])"
+
+      - name: Upload dist/
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish-testpypi:
+    name: Publish to TestPyPI
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/project/ds-proj-cc/
+    permissions:
+      id-token: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Download dist/
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+
+      - name: Publish
+        run: uv publish --index testpypi dist/*
+
+  publish-pypi:
+    name: Publish to PyPI
+    needs: publish-testpypi
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/project/ds-proj-cc/
+    permissions:
+      id-token: write
+    steps:
+      - name: Download dist/
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+
+      - name: Publish
+        run: uv publish dist/*

ds_proj_cc-0.1.3/.gitignore

@@ -0,0 +1,10 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv

ds_proj_cc-0.1.3/.python-version

@@ -0,0 +1 @@
+3.13

ds_proj_cc-0.1.3/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2026 Chirantan Chakraborty
+
+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.
+

ds_proj_cc-0.1.3/PKG-INFO

@@ -0,0 +1,51 @@
+Metadata-Version: 2.5
+Name: ds-proj-cc
+Version: 0.1.3
+Summary: A lightweight dataset profiling toolkit
+Project-URL: Homepage, https://github.com/WeiWuxian0609/ds-proj-cc
+Project-URL: Issues, https://github.com/WeiWuxian0609/ds-proj-cc/issues
+Author-email: Chirantan Chakraborty <cchirantan1@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: dataset profiler,tds
+Classifier: Development Status :: 3 - Alpha
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Education
+Description-Content-Type: text/markdown
+
+# ds-proj-cc
+
+**DS Profiler**
+
+A lightweight Python toolkit for *dataset profiling, statistical summaries, missing-value detection, duplicate detection, and numerical anomaly detection.*
+
+## Install
+
+```bash
+pip install ds-proj-cc
+```
+
+## Usage
+
+```python
+from ds_proj_cc import profile, summarize, detect_anomalies
+
+data = [
+    {"name": "Alice", "age": 21, "score": 85},
+    {"name": "Bob", "age": 22, "score": 91},
+    {"name": "Charlie", "age": None, "score": 78},
+]
+
+print(profile(data))
+print(summarize(data))
+print(detect_anomalies(data))
+```
+
+## Author
+
+**Chirantan Chakraborty**

ds_proj_cc-0.1.3/README.md

@@ -0,0 +1,31 @@
+# ds-proj-cc
+
+**DS Profiler**
+
+A lightweight Python toolkit for *dataset profiling, statistical summaries, missing-value detection, duplicate detection, and numerical anomaly detection.*
+
+## Install
+
+```bash
+pip install ds-proj-cc
+```
+
+## Usage
+
+```python
+from ds_proj_cc import profile, summarize, detect_anomalies
+
+data = [
+    {"name": "Alice", "age": 21, "score": 85},
+    {"name": "Bob", "age": 22, "score": 91},
+    {"name": "Charlie", "age": None, "score": 78},
+]
+
+print(profile(data))
+print(summarize(data))
+print(detect_anomalies(data))
+```
+
+## Author
+
+**Chirantan Chakraborty**

ds_proj_cc-0.1.3/pyproject.toml

@@ -0,0 +1,40 @@
+[project]
+name = "ds-proj-cc"
+version = "0.1.3"
+description = "A lightweight dataset profiling toolkit"
+readme = "README.md"
+license = "MIT"
+authors = [
+    { name = "Chirantan Chakraborty", email = "cchirantan1@gmail.com" }
+]
+keywords = ["tds", "dataset profiler"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Education",
+]
+dependencies = []
+
+[project.urls]
+Homepage = "https://github.com/WeiWuxian0609/ds-proj-cc"
+Issues   = "https://github.com/WeiWuxian0609/ds-proj-cc/issues"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[[tool.uv.index]]
+name = "testpypi"
+url = "https://test.pypi.org/simple/"
+publish-url = "https://test.pypi.org/legacy/"
+explicit = true
+
+[dependency-groups]
+dev = [
+    "pytest>=9.1.1",
+]

ds_proj_cc-0.1.3/src/ds_proj_cc/__init__.py

@@ -0,0 +1,248 @@
+"""
+ds_proj_cc — a lightweight dataset profiling toolkit.
+
+Provides utilities for inspecting tabular data, including:
+- Dataset dimensions
+- Missing values
+- Duplicate rows
+- Column names
+- Basic numerical statistics
+"""
+
+from importlib.metadata import version as _v
+from pathlib import Path
+import csv
+import statistics
+
+
+__version__ = _v("ds-proj-cc")
+
+
+def _load_csv(path: str) -> list[dict]:
+    """Load a CSV file into a list of dictionaries."""
+
+    file_path = Path(path)
+
+    if not file_path.exists():
+        raise FileNotFoundError(f"File not found: {path}")
+
+    if not file_path.is_file():
+        raise ValueError(f"Not a file: {path}")
+
+    with file_path.open("r", newline="", encoding="utf-8") as file:
+        return list(csv.DictReader(file))
+
+
+def _validate_data(data: list[dict]) -> None:
+    """Validate dataset structure."""
+
+    if not isinstance(data, list):
+        raise TypeError("data must be a list")
+
+    if not all(isinstance(row, dict) for row in data):
+        raise TypeError("each row must be a dictionary")
+
+
+def _prepare_data(data_or_path) -> list[dict]:
+    """Accept either a list of dictionaries or a CSV path."""
+
+    if isinstance(data_or_path, (str, Path)):
+        return _load_csv(str(data_or_path))
+
+    _validate_data(data_or_path)
+    return data_or_path
+
+
+def profile(data_or_path) -> dict:
+    """
+    Generate a statistical profile of a tabular dataset.
+
+    Parameters
+    ----------
+    data_or_path:
+        Either:
+        - a list of dictionaries, or
+        - a path to a CSV file.
+
+    Returns
+    -------
+    dict
+        Dataset statistics.
+    """
+
+    data = _prepare_data(data_or_path)
+
+    if not data:
+        return {
+            "rows": 0,
+            "columns": 0,
+            "missing_values": 0,
+            "duplicate_rows": 0,
+            "column_names": [],
+            "numerical_summary": {},
+        }
+
+    # Collect all column names.
+    columns = set()
+
+    for row in data:
+        columns.update(row.keys())
+
+    columns = sorted(columns)
+
+    # Count missing values.
+    missing_values = sum(
+        1
+        for row in data
+        for column in columns
+        if row.get(column) in (None, "")
+    )
+
+    # Count duplicate rows.
+    row_signatures = [
+        tuple(sorted(row.items()))
+        for row in data
+    ]
+
+    duplicate_rows = len(data) - len(set(row_signatures))
+
+    # Numerical statistics.
+    numerical_summary = {}
+
+    for column in columns:
+        values = []
+
+        for row in data:
+            value = row.get(column)
+
+            if value in (None, ""):
+                continue
+
+            try:
+                values.append(float(value))
+            except (ValueError, TypeError):
+                pass
+
+        if values:
+            numerical_summary[column] = {
+                "count": len(values),
+                "mean": round(statistics.mean(values), 2),
+                "median": round(statistics.median(values), 2),
+                "minimum": min(values),
+                "maximum": max(values),
+            }
+
+    return {
+        "rows": len(data),
+        "columns": len(columns),
+        "missing_values": missing_values,
+        "duplicate_rows": duplicate_rows,
+        "column_names": columns,
+        "numerical_summary": numerical_summary,
+    }
+
+
+def summarize(data_or_path) -> str:
+    """
+    Generate a human-readable dataset summary.
+    """
+
+    result = profile(data_or_path)
+
+    lines = [
+        "Dataset Profile",
+        "────────────────────────────",
+        f"Rows:              {result['rows']}",
+        f"Columns:           {result['columns']}",
+        f"Missing values:    {result['missing_values']}",
+        f"Duplicate rows:    {result['duplicate_rows']}",
+        "",
+        "Columns",
+        "────────────────────────────",
+    ]
+
+    for column in result["column_names"]:
+        lines.append(f"- {column}")
+
+    if result["numerical_summary"]:
+        lines.extend([
+            "",
+            "Numerical Summary",
+            "────────────────────────────",
+        ])
+
+        for column, stats in result["numerical_summary"].items():
+            lines.extend([
+                f"{column}:",
+                f"  Count:   {stats['count']}",
+                f"  Mean:    {stats['mean']}",
+                f"  Median:  {stats['median']}",
+                f"  Min:     {stats['minimum']}",
+                f"  Max:     {stats['maximum']}",
+            ])
+
+    return "\n".join(lines)
+
+
+def detect_anomalies(data_or_path) -> dict:
+    """
+    Detect simple anomalies in numerical columns.
+
+    Uses the IQR (Interquartile Range) method.
+    """
+
+    data = _prepare_data(data_or_path)
+
+    if not data:
+        return {}
+
+    columns = set()
+
+    for row in data:
+        columns.update(row.keys())
+
+    anomalies = {}
+
+    for column in sorted(columns):
+
+        values = []
+
+        for row in data:
+            value = row.get(column)
+
+            if value in (None, ""):
+                continue
+
+            try:
+                values.append(float(value))
+            except (ValueError, TypeError):
+                continue
+
+        if len(values) < 4:
+            continue
+
+        values.sort()
+
+        q1 = statistics.quantiles(values, n=4)[0]
+        q3 = statistics.quantiles(values, n=4)[2]
+
+        iqr = q3 - q1
+
+        lower_bound = q1 - 1.5 * iqr
+        upper_bound = q3 + 1.5 * iqr
+
+        outliers = [
+            value
+            for value in values
+            if value < lower_bound or value > upper_bound
+        ]
+
+        if outliers:
+            anomalies[column] = {
+                "outliers": outliers,
+                "count": len(outliers),
+                "lower_bound": round(lower_bound, 2),
+                "upper_bound": round(upper_bound, 2),
+            }
+
+    return anomalies

ds_proj_cc-0.1.3/tests/test_profiler.py

@@ -0,0 +1,97 @@
+import pytest
+
+from ds_proj_cc import profile, summarize, detect_anomalies
+
+
+def test_profile_basic_dataset():
+    data = [
+        {"name": "Alice", "age": 21},
+        {"name": "Bob", "age": 22},
+    ]
+
+    result = profile(data)
+
+    assert result["rows"] == 2
+    assert result["columns"] == 2
+    assert result["missing_values"] == 0
+    assert result["duplicate_rows"] == 0
+
+
+def test_profile_missing_values():
+    data = [
+        {"name": "Alice", "age": 21},
+        {"name": "Bob", "age": None},
+    ]
+
+    result = profile(data)
+
+    assert result["missing_values"] == 1
+
+
+def test_profile_duplicate_rows():
+    data = [
+        {"name": "Alice", "age": 21},
+        {"name": "Alice", "age": 21},
+        {"name": "Bob", "age": 22},
+    ]
+
+    result = profile(data)
+
+    assert result["duplicate_rows"] == 1
+
+
+def test_numerical_summary():
+    data = [
+        {"name": "Alice", "score": 80},
+        {"name": "Bob", "score": 90},
+        {"name": "Charlie", "score": 100},
+    ]
+
+    result = profile(data)
+
+    assert result["numerical_summary"]["score"]["mean"] == 90.0
+    assert result["numerical_summary"]["score"]["median"] == 90.0
+    assert result["numerical_summary"]["score"]["minimum"] == 80.0
+    assert result["numerical_summary"]["score"]["maximum"] == 100.0
+
+
+def test_summarize():
+    data = [
+        {"name": "Alice", "age": 21},
+        {"name": "Bob", "age": 22},
+    ]
+
+    result = summarize(data)
+
+    assert "Dataset Profile" in result
+    assert "Rows:" in result
+    assert "Columns:" in result
+
+def test_anomaly_detection():
+    data = [
+        {"score": 10},
+        {"score": 11},
+        {"score": 12},
+        {"score": 13},
+        {"score": 12},
+        {"score": 11},
+        {"score": 13},
+        {"score": 12},
+        {"score": 11},
+        {"score": 100},
+    ]
+
+    result = detect_anomalies(data)
+
+    assert "score" in result
+    assert 100.0 in result["score"]["outliers"]
+
+
+def test_invalid_file_path():
+    with pytest.raises(FileNotFoundError):
+        profile("not a dataset")
+
+
+def test_invalid_row_type():
+    with pytest.raises(TypeError):
+        profile([{"name": "Alice"}, "invalid row"])

ds_proj_cc-0.1.3/uv.lock

@@ -0,0 +1,79 @@
+version = 1
+revision = 2
+requires-python = ">=3.13"
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d8/53/6f443c9a4a8358a93a6792e2acffb9d9d5cb0a5cfd8802644b7b1c9a02e4/colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44", size = 27697, upload-time = "2022-10-25T02:36:22.414Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" },
+]
+
+[[package]]
+name = "ds-proj-cc"
+version = "0.1.3"
+source = { editable = "." }
+
+[package.dev-dependencies]
+dev = [
+    { name = "pytest" },
+]
+
+[package.metadata]
+
+[package.metadata.requires-dev]
+dev = [{ name = "pytest", specifier = ">=9.1.1" }]
+
+[[package]]
+name = "iniconfig"
+version = "2.3.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/72/34/14ca021ce8e5dfedc35312d08ba8bf51fdd999c576889fc2c24cb97f4f10/iniconfig-2.3.0.tar.gz", hash = "sha256:c76315c77db068650d49c5b56314774a7804df16fee4402c1f19d6d15d8c4730", size = 20503, upload-time = "2025-10-18T21:55:43.219Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cb/b1/3846dd7f199d53cb17f49cba7e651e9ce294d8497c8c150530ed11865bb8/iniconfig-2.3.0-py3-none-any.whl", hash = "sha256:f631c04d2c48c52b84d0d0549c99ff3859c98df65b3101406327ecc7d53fbf12", size = 7484, upload-time = "2025-10-18T21:55:41.639Z" },
+]
+
+[[package]]
+name = "packaging"
+version = "26.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/7d/fa/3944b40b07da9ce895c0e6303a5ab7d53da063554f534556b134a54d6093/packaging-26.3.tar.gz", hash = "sha256:94edc256424af38762eb31306eed28beb9f0efc50a8837492c9d6fd6004aed79", size = 313412, upload-time = "2026-08-04T18:15:28.737Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/63/34/ba1c580383c9eada3711951fef0795c80b829a078d72188184bcab9dd527/packaging-26.3-py3-none-any.whl", hash = "sha256:d7193f7c8e4e93f444fde0262bf90af30e16fa0ad0ad44cb553c87339b23cd1c", size = 129956, upload-time = "2026-08-04T18:15:27.159Z" },
+]
+
+[[package]]
+name = "pluggy"
+version = "1.6.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f9/e2/3e91f31a7d2b083fe6ef3fa267035b518369d9511ffab804f839851d2779/pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3", size = 69412, upload-time = "2025-05-15T12:30:07.975Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538, upload-time = "2025-05-15T12:30:06.134Z" },
+]
+
+[[package]]
+name = "pygments"
+version = "2.21.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/49/2e/ced460408999b33da6b31b0021b0f37d329e202d4169aeb164493778f25b/pygments-2.21.0.tar.gz", hash = "sha256:610ca751c9bc2492b38eb9a38a7fbc93edbbb2d7182edaf34e66ae493dee5c8c", size = 5005329, upload-time = "2026-08-17T08:02:48.824Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/71/46/17f022dd3e953bf20a04a028a21ec746d942f8d2af30fa0f124fa0e6a684/pygments-2.21.0-py3-none-any.whl", hash = "sha256:2363c69b61c4a97c838da3b130dcd6468f4848992b21a82f2a63ec34377137d9", size = 1250147, upload-time = "2026-08-17T08:02:44.912Z" },
+]
+
+[[package]]
+name = "pytest"
+version = "9.1.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "iniconfig" },
+    { name = "packaging" },
+    { name = "pluggy" },
+    { name = "pygments" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e4/47/b9efed96c114afcfa3c9d3fe98a76a1d14c74a9e266d397cf6eb64be5e01/pytest-9.1.1.tar.gz", hash = "sha256:1088fbde8f2b49d95a549a195707afa7a76a3ce9bcadc26b6d71f0ffda5fe313", size = 1636369, upload-time = "2026-06-19T10:58:32.857Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/24/25/1de2678b631f5a49215c6c96fff41ba892b0a34df68d6d80292b1b48aa7f/pytest-9.1.1-py3-none-any.whl", hash = "sha256:37a86b45efb9a47a61a36449063e8e18d0cab3161329fc099eb21783169c4f0c", size = 386536, upload-time = "2026-06-19T10:58:31.347Z" },
+]