add doc_sphinx workflow

.github/workflows/doc_sphinx.yml

@@ -0,0 +1,27 @@
+name: Docs
+on:
+    push:
+        branches: ['main']
+permissions:
+    contents: write
+jobs:
+  docs:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v3
+      - name: Install dependencies
+        run: |
+          pip install sphinx sphinx_rtd_theme
+      - name: Sphinx build
+        run: |
+          cd docs
+          make html
+      - name: Deploy to Github Pages
+        uses: peaceiris/actions-gh-pages@v3
+        if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' }}
+        with:
+          publish_branch: gh-pages
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: docs/build # the path of doc
+          force_orphan: true

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/source/conf.py

@@ -0,0 +1,46 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+import os
+import sys
+sys.path.insert(0, os.path.abspath('../..'))
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+project = 'pyGA4'
+copyright = '2023, Lin-jun-xiang'
+author = 'Lin-jun-xiang'
+release = '0.1.0'
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = [
+    'sphinx.ext.intersphinx',
+    'sphinx.ext.autodoc',
+    'sphinx.ext.autosummary',
+    'sphinx.ext.mathjax',
+    'sphinx.ext.viewcode',
+    'sphinx_rtd_theme',
+    'sphinx.ext.githubpages',
+]
+
+templates_path = ['_templates']
+exclude_patterns = []
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = "sphinx_rtd_theme"
+html_static_path = ['_static']
+
+# Replace 'view source code' with 'Edit on Github'
+# https://stackoverflow.com/questions/62904172/how-do-i-replace-view-page-source-with-edit-on-github-links-in-sphinx-rtd-th
+html_context = {
+  'display_github': True,
+  'github_user': 'Lin-jun-xiang',
+  'github_repo': 'pyGA4',
+  'github_version': 'main/doc/',
+}

docs/source/index.rst

@@ -0,0 +1,22 @@
+.. pyGA4 documentation master file, created by
+   sphinx-quickstart on Mon Sep 18 17:02:12 2023.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+pyGA4's documentation!
+======================
+
+.. automodule:: ga4.model.bigquery
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: ga4.analytic.analytic
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: ga4.analytic.data_transform
+   :members:
+   :undoc-members:
+   :show-inheritance:

ga4/analytic/analytic.py

@@ -5,6 +5,9 @@
 
 
 class BaseAnalytic:
+    def __init__(self, table: Ga4Table) -> None:
+        self.table = table
+
     @staticmethod
     def attribute_distribution(table: Ga4Table, attribute_name: str) -> Counter:
         attribute_list = getattr(table, attribute_name)
@@ -17,7 +20,13 @@ class UserAnalytic(BaseAnalytic):
     """The features of user"""
 
     def __init__(self, table: Ga4Table) -> None:
-        self.table = table
+        super().__init__(table)
+
+    @property
+    def user_id_distribution(self) -> Counter:
+        return self.attribute_distribution(
+            self.table, 'user_id_list'
+        )
 
     @property
     def countries_distribution(self) -> Counter:
@@ -30,7 +39,7 @@ class DeviceAnalytic(BaseAnalytic):
     """The features of technology"""
 
     def __init__(self, table: Ga4Table) -> None:
-        self.table = table
+        super().__init__(table)
 
     @property
     def os_distribution(self) -> Counter:
@@ -67,7 +76,7 @@ class EventAnalytic(BaseAnalytic):
     """The features of event"""
 
     def __init__(self, table: Ga4Table) -> None:
-        self.table = table
+        super().__init__(table)
 
     @property
     def pages_distribution(self) -> Counter:

ga4/model/bigquery.py

@@ -29,22 +29,22 @@ class Client:
     Examples
     --------
     ```python
-    # Setup dry_run = True
     Client().query_config.dry_run = True
     ```
     """
     query_config = bigquery.QueryJobConfig(
         dry_run = False,
         use_query_cache = False
     )
-    def __init__(self, client) -> None:
+    def __init__(self, client, project_id: str) -> None:
         self.client = client
+        self.project_id = project_id
 
 
 class BaseTable(Client):
     """Connect to the data set from bigquery"""
-    def __init__(self, client, dataset_name: str) -> None:
-        super().__init__(client)
+    def __init__(self, client, project_id: str, dataset_name: str) -> None:
+        super().__init__(client, project_id)
         self.dataset_name = dataset_name
         self._table_id = None
 
@@ -78,8 +78,7 @@ def to_dataframe(self):
 
 class Ga4Table(BaseTable):
     def __init__(self, client, project_id: str, dataset_name: str) -> None:
-        super().__init__(client, dataset_name)
-        self.project_id = project_id
+        super().__init__(client, project_id, dataset_name)
         self._query_job = None
 
     def _query_template(self, query_target: str) -> list:
@@ -204,17 +203,17 @@ def page_location_list(self) -> list:
         """Return all event of page location from data table"""
         query = f"""
             SELECT
-                event_params.value.string_value AS param_string_value
+                param.value.string_value AS param_string_value
             FROM
-                `{self.project_id}.{self.dataset_name}.{self.table_id}`
-                UNNEST(event_params) AS event_params
+                `{self.project_id}.{self.dataset_name}.{self.table_id}`,
+                UNNEST(event_params) AS param
             WHERE
-                event_params.key = "page_location"
+                param.key = "page_location" OR param.key IS NULL
         """
         self._query_job = self.client.query(query, job_config=self.query_config)
         results = self._query_job.result()
 
-        return [row.page_location for row in results]
+        return [row.param_string_value for row in results]
 
     @calculate_bytes_processed
     def query(self, query: str) -> list:

pyproject.toml

@@ -1,5 +1,5 @@
 [tool.poetry]
-name = "pyga4"
+name = "pyGA4"
 version = "0.1.0"
 description = "Python Google Analytics 4 (GA4) Data Extraction and Analysis Toolkit"
 authors = ["Lin-jun-xiang <[email protected]>"]