feat: created analytics sheets notebook for hca browser (#4317)

DataBiosphere · Jan 27, 2025 · 70482a8 · 70482a8
1 parent e0ce2c7
commit 70482a8
Show file tree

Hide file tree

Showing 4 changed files with 153 additions and 1 deletion.
diff --git a/analytics/hca-explorer-sheets/constants.py b/analytics/hca-explorer-sheets/constants.py
@@ -0,0 +1,20 @@
+# CHANGE THESE VALUES TO GENERATE NEW REPORTS
+# The start and end dates of the current month (yyyy-mm-dd)
+START_DATE_CURRENT = "2024-12-01"
+END_DATE_CURRENT = "2024-12-31"
+# The start and end dates of the prior months
+START_DATE_PRIOR = "2024-11-01"
+END_DATE_PRIOR = "2024-11-30"
+# The name of the folder in which to save the report
+PARENT_FOLDER_NAME = "December 2024 (demos)"
+
+# The name of the spreadsheet with the report
+SHEET_NAME = "HCA Explorer"
+
+HCA_PORTAL_ID = "361323030"
+# Filter to exclude the Data Explorer
+HCA_BROWSER_EXCLUDE_FILTER = {"filter": {"fieldName": "hostName", "stringFilter": {"matchType": "EXACT", "value": "explore.data.humancellatlas.org"}}}
+SECRET_NAME = "HCA_ANALYTICS_REPORTING_CLIENT_SECRET_PATH"
+ANALYTICS_START = "2021-01-01"
+
+OAUTH_PORT = 8082
diff --git a/analytics/hca-explorer-sheets/generate_sheets_report.ipynb b/analytics/hca-explorer-sheets/generate_sheets_report.ipynb
@@ -0,0 +1,116 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from analytics import sheets_api as sheets\n",
+    "from analytics import sheets_elements as elements\n",
+    "from analytics import api as ga\n",
+    "import pandas as pd\n",
+    "from constants import *"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Please visit this URL to authorize this application: https://accounts.google.com/o/oauth2/auth?response_type=code&client_id=425030666072-vun85q7nt3038skng8gs0f03juh97e17.apps.googleusercontent.com&redirect_uri=http%3A%2F%2Flocalhost%3A8082%2F&scope=https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdrive+https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fanalytics.readonly+https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fspreadsheets&state=gQXcCGWIVhfxgIYwz935kc6SSgk4Wp&access_type=offline\n"
+     ]
+    }
+   ],
+   "source": [
+    "ga_authentication, drive_authentication = ga.authenticate(\n",
+    "    SECRET_NAME,\n",
+    "    ga.ga4_service_params,\n",
+    "    ga.drive_service_params,\n",
+    "    port=OAUTH_PORT\n",
+    ")\n",
+    "\n",
+    "date_string = f\"{START_DATE_CURRENT} - {END_DATE_CURRENT}\"\n",
+    "\n",
+    "default_params = {\n",
+    "    \"service_system\": ga_authentication,\n",
+    "    \"start_date\": START_DATE_CURRENT,\n",
+    "    \"end_date\": END_DATE_CURRENT,\n",
+    "}\n",
+    "\n",
+    "hca_portal_params = {\n",
+    "    **default_params,\n",
+    "    \"base_dimension_filter\": HCA_BROWSER_EXCLUDE_FILTER,\n",
+    "    \"property\": HCA_PORTAL_ID,\n",
+    "}\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pageviews = elements.get_page_views_change(hca_portal_params, START_DATE_CURRENT, END_DATE_CURRENT, START_DATE_PRIOR, END_DATE_PRIOR) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dict_spreadsheet = {\n",
+    "    \"Page Views\": df_pageviews,\n",
+    "}\n",
+    "sheets.fill_spreadsheet_with_df_dict(\n",
+    "    sheets.create_sheet_in_folder(\n",
+    "        drive_authentication,\n",
+    "        SHEET_NAME,\n",
+    "        PARENT_FOLDER_NAME,\n",
+    "        override_behavior=sheets.FILE_OVERRIDE_BEHAVIORS.OVERRIDE_IF_IN_SAME_PLACE\n",
+    "    ),\n",
+    "    dict_spreadsheet,\n",
+    "    sheets.FILE_OVERRIDE_BEHAVIORS.OVERRIDE_IF_IN_SAME_PLACE,\n",
+    "    column_formatting_options={\n",
+    "        \"Outbound Links\": {\n",
+    "            \"Total Clicks Percent Change\": sheets.COLUMN_FORMAT_OPTIONS.PERCENT_COLORED,\n",
+    "            \"Total Users Percent Change\": sheets.COLUMN_FORMAT_OPTIONS.PERCENT_COLORED,\n",
+    "        },\n",
+    "        \"Page Views\": {\n",
+    "            \"Total Views Percent Change\": sheets.COLUMN_FORMAT_OPTIONS.PERCENT_COLORED,\n",
+    "            \"Total Users Percent Change\": sheets.COLUMN_FORMAT_OPTIONS.PERCENT_COLORED,\n",
+    "        }\n",
+    "\n",
+    "    }\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/analytics/hca-explorer-sheets/readme.md b/analytics/hca-explorer-sheets/readme.md
@@ -0,0 +1,16 @@
+## Installing the environment
+- Use Python 3.12.4
+- Run `python -m venv ./venv` to create a new environment under `./venv`.
+- Run `source ./venv/bin/activate` to activate the environment.
+- Run `pip install -r ./requirements.txt` to install requirements.
+
+## Deactivating/reactivating
+- To deactivate the environment, run `deactivate`.
+- To activate the environment again, run `source ./venv/bin/activate`.
+
+## Generating Reports
+- Update `constants.py` to reflect the date ranges and file name you would like for the report
+- Open `./generate_sheets_report.ipynb` using your favorite IDE or by running `jupyter notebook` and selecting it from the browser window that appears.
+- Add a path to your Google Cloud credentials in the first cell as instructed by the comments.
+- Run all cells in the Jupyter notebook by pressing the button with two arrows at the top. You will be prompted to log in to your Google Account, which must have access to the relevant analytics property.
+- Check your Google Drive to ensure that the desired spreadsheet is present.
diff --git a/analytics/requirements.txt b/analytics/requirements.txt
@@ -1,6 +1,6 @@
 accessible-pygments==0.0.5
 alabaster==0.7.16
--e git+https://github.com/DataBiosphere/data-browser.git@60dc83eb36468c1f8091136f8e0534b3cba81b44#egg=analytics&subdirectory=analytics/analytics_package
+-e git+https://github.com/DataBiosphere/data-browser.git@6d65fae358f74ca0c6f7fb817c4b0bf89336c5f8#egg=analytics&subdirectory=analytics/analytics_package
 appdirs==1.4.4
 appnope==0.1.4
 asttokens==2.4.1