adds docstrings

app/analysis/data_utils.py

@@ -3,6 +3,20 @@ import os
 import pandas as pd
 
 def prepare_data(df):
+    """
+    Prepares the data for analysis by converting timestamps, calculating previous timestamps,
+    determining active status, and extracting the hour from the timestamp.
+
+    Parameters:
+    df (pd.DataFrame): The input DataFrame containing user activity data.
+
+    Returns:
+    pd.DataFrame: The processed DataFrame with additional columns for analysis.
+
+    The returned DataFrame will have the following columns:
+        user_id     name       last_action              status  timestamp                       prev_timestamp  was_active  hour
+    0   12345678    UserName   2025-02-08 17:58:11      Okay    2025-02-08 18:09:41.867984056   NaT             False       18
+    """
     df["timestamp"] = pd.to_datetime(df["timestamp"])
     df["last_action"] = pd.to_datetime(df["last_action"])
     df["prev_timestamp"] = df.groupby("user_id")["timestamp"].shift(1)
@@ -12,6 +26,15 @@ def prepare_data(df):
     return df
 
 def mk_plotdir(output_filename):
+    """
+    Creates the directory for storing plots and generates the output path and URL for the plot.
+
+    Parameters:
+    output_filename (str): The filename for the output plot.
+
+    Returns:
+    dict: A dictionary containing the output path and plot URL.
+    """
     plots_dir = os.path.join(current_app.root_path, "static", "plots")
     os.makedirs(plots_dir, exist_ok=True)
 
@@ -19,4 +42,4 @@ def mk_plotdir(output_filename):
     
     plot_url = url_for('static', filename=f'plots/{output_filename}', _external=True)
 
-    return {'output_path': output_path, 'plot_url': plot_url}
+    return {'output_path': output_path, 'plot_url': plot_url}