From 9e2f7f1dc24468c4a45bffbcdccabef1394f7bd5 Mon Sep 17 00:00:00 2001
From: ammarcsj <70114795+ammarcsj@users.noreply.github.com>
Date: Tue, 13 Aug 2024 16:22:51 +0200
Subject: [PATCH] add dostring and type hints

---
 directlfq/utils.py | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/directlfq/utils.py b/directlfq/utils.py
index 4327d02..ba5734f 100644
--- a/directlfq/utils.py
+++ b/directlfq/utils.py
@@ -310,13 +310,26 @@ def index_and_log_transform_input_df(data_df):
 def remove_allnan_rows_input_df(data_df):
     return data_df.dropna(axis = 0, how = 'all')
 
-def remove_potential_quant_id_duplicates(data_df):
+def remove_potential_quant_id_duplicates(data_df : pd.DataFrame):
+    """
+    Remove duplicate entries from a DataFrame based on the QUANT_ID column.
+
+    This function removes duplicate rows from the input DataFrame, keeping only the first
+    occurrence of each unique QUANT_ID. It also logs a warning message if any duplicates
+    are found and removed.
+
+    Args:
+        data_df (pd.DataFrame): dataframe in directLFQ format
+
+    Returns:
+        pd.DataFrame: dataframe in directLFQ format w duplicate QUANT_ID entries removed.
+    """
     before_drop = len(data_df)
     data_df = data_df.drop_duplicates(subset=config.QUANT_ID, keep='first')
     after_drop = len(data_df)
     if before_drop != after_drop:
         entries_removed = before_drop - after_drop
-        LOGGER.info(f"Duplicate quant_ids detected. {entries_removed} rows removed from input df.")
+        LOGGER.warning(f"Duplicate quant_ids detected. {entries_removed} rows removed from input df.")
 
     return data_df