feat: add analytics

docs/advanced_settings/analytics.md

@@ -0,0 +1,42 @@
+# Analytics & Telemetry
+
+## Overview
+
+`ydata-profiling` is a powerful library designed to generate profile reports from pandas and Spark Dataframe objects. 
+As part of our ongoing efforts to improve user experience and functionality, `ydata-profiling` 
+includes a telemetry feature. This feature collects anonymous usage data, helping us understand how the
+library is used and identify areas for improvement.
+
+The primary goal of collecting telemetry data is to:
+
+- Enhance the functionality and performance of the ydata-profiling library
+- Prioritize new features based on user engagement
+- Identify common issues and bugs to improve overall user experience
+
+### Data Collected
+
+The telemetry system collects non-personal, anonymous information such as:
+
+- Python version
+- `ydata-profiling` version
+- Frequency of use of `ydata-profiling` features
+- Errors or exceptions thrown within the library
+
+## Disabling usage analytics
+
+We respect your choice to not participate in our telemetry collection. If you prefer to disable telemetry, you can do so
+by setting an environment variable on your system. Disabling telemetry will not affect the functionality 
+of the ydata-profiling library, except for the ability to contribute to its usage analytics.
+
+
+### Set an Environment Variable
+
+Open your terminal or command prompt and set the YDATA_PROFILING_NO_ANALYTICS environment variable to false.
+
+````python
+    import os 
+
+    os.environ['YDATA_PROFILING_NO_ANALYTICS'] = 'True'
+````
+
+

mkdocs.yml

@@ -25,6 +25,7 @@ nav:
     -  General settings: 'advanced_settings/available_settings.md'
     -  Changing settings: 'advanced_settings/changing_settings.md'
     -  Caching: 'advanced_settings/caching.md'
+    -  Analytics: 'advanced_settings/analytics.md'
   - Integrations:
     -  Other dataframes: 'integrations/other_dataframe_libraries.md'
     -  Pyspark: 'integrations/pyspark.md'

src/ydata_profiling/utils/common.py

@@ -1,5 +1,8 @@
 """Common util functions (e.g. missing in Python)."""
 import collections.abc
+import os
+import platform
+import subprocess
 import zipfile
 from datetime import datetime, timedelta
 
@@ -8,6 +11,10 @@
 from pathlib import Path
 from typing import Mapping
 
+import requests
+
+from ydata_profiling.version import __version__
+
 
 def update(d: dict, u: Mapping) -> dict:
     """Recursively update a dict.
@@ -88,3 +95,32 @@ def convert_timestamp_to_datetime(timestamp: int) -> datetime:
         return datetime.fromtimestamp(timestamp)
     else:
         return datetime(1970, 1, 1) + timedelta(seconds=int(timestamp))
+
+
+def analytics_features(dataframe, datatype: bool, report_type: bool):
+    endpoint = "https://packages.ydata.ai/ydata-profiling?"
+
+    if os.getenv("YDATA_PROFILING_NO_ANALYTICS") != True:
+        package_version = __version__
+        try:
+            subprocess.check_output("nvidia-smi")
+            gpu_present = True
+        except Exception:
+            gpu_present = False
+
+        python_version = ".".join(platform.python_version().split(".")[:2])
+
+        try:
+            request_message = (
+                f"{endpoint}version={package_version}"
+                f"&python_version={python_version}"
+                f"&report_type={report_type}"
+                f"&dataframe={dataframe}"
+                f"&datatype={datatype}"
+                f"&os={platform.system()}"
+                f"&gpu={str(gpu_present)}"
+            )
+
+            requests.get(request_message)
+        except Exception:
+            pass

src/ydata_profiling/utils/logger.py

@@ -0,0 +1,42 @@
+"""
+    Logger function for ydata-profiling reports
+"""
+
+import logging
+
+import pandas as pd
+
+from ydata_profiling.utils.common import analytics_features
+
+
+class ProfilingLogger(logging.Logger):
+    def __init__(self, name, level=logging.INFO):
+        super().__init__(name, level)
+
+    def info(
+        self,
+        msg: object,
+    ) -> None:
+        super().info(f"[PROFILING] - {msg}.")
+
+    def info_def_report(self, dataframe, timeseries: bool):
+        if dataframe == pd.DataFrame:
+            dataframe = "pandas"
+            report_type = "regular"
+        elif dataframe == type(None):
+            dataframe = "pandas"
+            report_type = "compare"
+        else:
+            dataframe = "spark"
+            report_type = "regular"
+
+        datatype = "timeseries" if timeseries else "tabular"
+
+        analytics_features(
+            dataframe=dataframe, datatype=datatype, report_type=report_type
+        )
+
+        super().info(
+            f"[PROFILING] Calculating profile with the following characteristics "
+            f"- {dataframe} | {datatype} | {report_type}."
+        )