Merge pull request #14 from thomasthaddeus/dev

v1.2.0

.github/workflows/python-publish.yml

@@ -1,4 +1,4 @@
-name: Upload Python Package
+name: Publish Python 🐍 distribution 📦 to PyPI
 
 on:
   release:
@@ -8,7 +8,8 @@ permissions:
   contents: read
 
 jobs:
-  deploy:
+  build:
+    name: Build distribution 📦
     runs-on: ubuntu-latest
 
     steps:
@@ -27,8 +28,80 @@ jobs:
     - name: Build package
       run: python -m build
 
-    - name: Publish package
-      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+    - name: Store the distribution packages
+      uses: actions/upload-artifact@v3
+      with:
+        name: python-package-distributions
+        path: dist/
+
+  publish-to-pypi:
+    name: >-
+      Publish Python 🐍 distribution 📦 to PyPI
+    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
+    needs:
+    - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/dataanalysistoolkit   # Replace <package-name> with your PyPI project name
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v3
+      with:
+        name: python-package-distributions
+        path: dist/
+
+    - name: Publish distribution 📦 to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
       with:
         user: __token__
         password: ${{ secrets.PYPI_API_TOKEN }}
+
+  github-release:
+    name: >-
+      Sign the Python 🐍 distribution 📦 with Sigstore
+      and upload them to GitHub Release
+    needs:
+    - publish-to-pypi
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write  # IMPORTANT: mandatory for making GitHub Releases
+      id-token: write  # IMPORTANT: mandatory for sigstore
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+
+    - name: Sign the dists with Sigstore
+      uses: sigstore/[email protected]
+      with:
+        inputs: >-
+          ./dist/*.tar.gz
+          ./dist/*.whl
+
+    - name: Create GitHub Release
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+      run: >-
+        gh release create
+        '${{ github.ref_name }}'
+        --repo '${{ github.repository }}'
+        --notes ""
+
+    - name: Upload artifact signatures to GitHub Release
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+      # Upload to GitHub Release using the `gh` CLI.
+      # `dist/` contains the built packages, and the
+      # sigstore-produced signatures and certificates.
+      run: >-
+        gh release upload
+        '${{ github.ref_name }}' dist/**
+        --repo '${{ github.repository }}'

docs/source/AdditionalResources/tutorials/tutorial_data_import.ipynb

@@ -47,14 +47,10 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "vscode": {
-     "languageId": "shellscript"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "pip install dataanalysistoolkit"
+    "%pip install dataanalysistoolkit\n"
    ]
   },
   {
@@ -66,14 +62,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'src'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[3], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;66;03m# Importing necessary libraries from the toolkit\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msrc\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdata_sources\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mexcel_connector\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m ExcelConnector\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msrc\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdata_sources\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01msql_connector\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m SQLConnector\n\u001b[0;32m      4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msrc\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdata_sources\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mapi_connector\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m APIConnector\n",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'src'"
+     ]
+    }
+   ],
    "source": [
     "# Importing necessary libraries from the toolkit\n",
-    "from src.data_sources.excel_connector import ExcelConnector\n",
-    "from src.data_sources.sql_connector import SQLConnector\n",
-    "from src.data_sources.api_connector import APIConnector\n",
+    "from src.data_sources import ExcelConnector\n",
+    "from src.data_sources import SQLConnector\n",
+    "from src.data_sources import APIConnector\n",
     "from src.integrators.data_integrator import DataIntegrator\n",
     "from src.formatters.data_formatter import DataFormatter\n",
     "\n",
@@ -138,7 +146,7 @@
     "df_sheet_index = excel_connector.load_data(sheet_name=1)\n",
     "\n",
     "# Display the first few rows of the dataframe\n",
-    "print(df_sheet_name.head())"
+    "print(df_sheet_name.head())\n"
    ]
   },
   {
@@ -155,7 +163,7 @@
    "outputs": [],
    "source": [
     "excel_connector = ExcelConnector('path/to/excel.xlsx')\n",
-    "df_excel = excel_connector.load_data(sheet_name='Sheet1')"
+    "df_excel = excel_connector.load_data(sheet_name='Sheet1')\n"
    ]
   },
   {
@@ -188,7 +196,7 @@
     "df_sql = sql_connector.query_data(query)\n",
     "\n",
     "# Display the result\n",
-    "print(df_sql.head())"
+    "print(df_sql.head())\n"
    ]
   },
   {
@@ -369,7 +377,7 @@
    "outputs": [],
    "source": [
     "# Custom method for time-series data integration (hypothetical example)\n",
-    "time_aligned_df = integrator.integrate_time_series('timestamp_column')"
+    "time_aligned_df = integrator.integrate_time_series('timestamp_column')\n"
    ]
   },
   {
@@ -484,7 +492,7 @@
     "formatter.fill_missing_values('another_column', method='ffill')\n",
     "\n",
     "# Checking for missing values\n",
-    "print(combined_df.isnull().sum())"
+    "print(combined_df.isnull().sum())\n"
    ]
   },
   {
@@ -508,7 +516,7 @@
     "formatter.custom_transform('numeric_column', lambda x: x ** 2)\n",
     "\n",
     "# Viewing the transformed data\n",
-    "print(combined_df['numeric_column'].head())"
+    "print(combined_df['numeric_column'].head())\n"
    ]
   },
   {
@@ -621,8 +629,22 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/source/conf.py

@@ -13,7 +13,7 @@
 project = 'Data Analysis Toolkit'
 copyright = '2024, Thaddeus Thomas'
 author = 'Thaddeus Thomas'
-release = '1.1.1'
+release = '1.2.0'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration