matomo integration

examples/matomo integration.ipynb

@@ -0,0 +1,254 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You need this if you are running the notebook from repo"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "sys.path.append(\"../\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Please note, that it is necessary to adjust this notebook according to your Matomo configuration and data structure. Please check Readme file to check the data structure expectation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "import pandas as pd\n",
+    "\n",
+    "from variatio import VariatioAnalyzer"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Configuration for Matomo API access\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "MATOMO_URL = 'https://your-matomo-domain.com'  # Replace with your Matomo domain\n",
+    "TOKEN_AUTH = 'your_matomo_api_token'  # Replace with your API token\n",
+    "SITE_ID = 'your_site_id'  # Replace with your site ID in Matomo\n",
+    "DATE_RANGE = '2023-01-01,2023-01-31'  # Define the date range for data extraction\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def fetch_from_matomo(method, params):\n",
+    "    \"\"\"\n",
+    "    Generic function to fetch data from the Matomo API.\n",
+    "    - method: Matomo API method to be called\n",
+    "    - params: Additional parameters for the API call\n",
+    "    Returns: JSON response from the API\n",
+    "    \"\"\"\n",
+    "    api_params = {\n",
+    "        'module': 'API',\n",
+    "        'method': method,\n",
+    "        'idSite': SITE_ID,\n",
+    "        'period': 'range',\n",
+    "        'date': DATE_RANGE,\n",
+    "        'format': 'JSON',\n",
+    "        'token_auth': TOKEN_AUTH,\n",
+    "        **params,\n",
+    "    }\n",
+    "    response = requests.get(MATOMO_URL, params=api_params)\n",
+    "    return response.json()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Fetching event data\n",
+    "Here we're fetching event categories, adjusting parameters as needed for your events\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "event_data_response = fetch_from_matomo('Events.getCategory', {'secondaryDimension': 'eventName'})\n",
+    "event_data_df = pd.json_normalize(event_data_response)  # Normalize JSON response into a flat table\n",
+    "event_data_df = event_data_df[['label', 'nb_visits', 'nb_events']]  # Select relevant columns\n",
+    "event_data_df.columns = ['event_name', 'visits', 'events_count']  # Rename columns for clarity\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Fetching A/B test allocation events example\n",
+    "Assuming A/B test allocations are events with a specific naming pattern\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ab_test_response = fetch_from_matomo('Events.getCategory', {'secondaryDimension': 'eventAction', 'label': 'ABTest Allocation'})\n",
+    "ab_test_df = pd.json_normalize(ab_test_response)\n",
+    "ab_test_df = ab_test_df[['label', 'subtable']]  # 'subtable' might contain more detailed data requiring further processing\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Fetching user properties example (custom dimensions)\n",
+    "Replace 'ID_OF_YOUR_DIMENSION' with the actual ID of the custom dimension representing user properties\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "user_properties_response = fetch_from_matomo('CustomDimensions.getCustomDimension', {'idDimension': 'ID_OF_YOUR_DIMENSION'})\n",
+    "user_properties_df = pd.json_normalize(user_properties_response)  # Flatten the JSON response into a DataFrame\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "analyzer = VariatioAnalyzer(event_data: event_data_df, \n",
+    "                            ab_test_allocations: ab_test_df, \n",
+    "                            \"A\", \n",
+    "                            user_properties: user_properties_df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Metrics were calculated\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Calculate the count of 'purchase' events per user\n",
+    "analyzer.calculate_event_count_per_user('purchase')\n",
+    "\n",
+    "# Calculate the sum of 'purchase_value' for 'purchase' events per user\n",
+    "analyzer.calculate_event_attribute_sum_per_user('purchase', 'purchase_value')\n",
+    "\n",
+    "# Calculate the conversion rate to 'login' events\n",
+    "analyzer.calculate_conversion('login')\n",
+    "\n",
+    "print(\"Metrics were calculated\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "analyzer.save_report(\"abtest_report.html\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}