From b29b688b6c7d4ea283e9495cd6e1c30d7d8bc9b6 Mon Sep 17 00:00:00 2001
From: "codeflash-ai[bot]"
 <148906541+codeflash-ai[bot]@users.noreply.github.com>
Date: Sun, 20 Apr 2025 10:47:21 +0000
Subject: [PATCH] =?UTF-8?q?=E2=9A=A1=EF=B8=8F=20Speed=20up=20function=20`d?=
 =?UTF-8?q?rop=5Fduplicates`=20by=20485%=20To=20improve=20the=20performanc?=
 =?UTF-8?q?e=20of=20this=20code,=20we=20can=20leverage=20the=20built-in=20?=
 =?UTF-8?q?`drop=5Fduplicates`=20method=20provided=20by=20pandas,=20which?=
 =?UTF-8?q?=20is=20optimized=20for=20such=20operations.=20Using=20this=20b?=
 =?UTF-8?q?uilt-in=20method=20is=20both=20faster=20and=20more=20concise.?=
 =?UTF-8?q?=20Here=20is=20the=20optimized=20version=20of=20the=20function.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This optimized version leverages the efficient internal implementation of `drop_duplicates` provided by pandas, significantly improving the runtime.
---
 src/numpy_pandas/dataframe_operations.py | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/src/numpy_pandas/dataframe_operations.py b/src/numpy_pandas/dataframe_operations.py
index cb4cda2..3261d67 100644
--- a/src/numpy_pandas/dataframe_operations.py
+++ b/src/numpy_pandas/dataframe_operations.py
@@ -113,16 +113,11 @@ def fillna(df: pd.DataFrame, column: str, value: Any) -> pd.DataFrame:
 
 
 def drop_duplicates(df: pd.DataFrame, subset: List[str] = None) -> pd.DataFrame:
-    if subset is None:
-        subset = df.columns.tolist()
-    seen = set()
-    keep_indices = []
-    for i in range(len(df)):
-        values = tuple(df.iloc[i][col] for col in subset)
-        if values not in seen:
-            seen.add(values)
-            keep_indices.append(i)
-    return df.iloc[keep_indices].reset_index(drop=True)
+    """
+    Drops duplicate rows from the DataFrame based on the provided subset of columns.
+    """
+    # Use pandas built-in drop_duplicates, which is optimized for performance
+    return df.drop_duplicates(subset=subset).reset_index(drop=True)
 
 
 def sort_values(df: pd.DataFrame, by: str, ascending: bool = True) -> pd.DataFrame: