dfcleanerpro 0.1.0__tar.gz

dfcleanerpro-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Nishanth K
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

dfcleanerpro-0.1.0/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.4
+Name: dfcleanerpro
+Version: 0.1.0
+Summary: Simple DataFrame cleaning toolkit
+Home-page: https://github.com/Nishanth9696/dfcleaner
+Author: Nishanth K
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+License-File: LICENSE
+Requires-Dist: pandas
+Dynamic: author
+Dynamic: classifier
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary

dfcleanerpro-0.1.0/README.md

@@ -0,0 +1,26 @@
+# **dfcleaner**
+
+**dfcleaner** is a simple Python library to clean Pandas DataFrames quickly.
+
+**Features**
+- Remove duplicates
+- Convert column names to snake_case
+- Fill missing values
+
+**Installation**
+
+pip install dfcleaner
+
+**Example**
+
+```
+import pandas as pd
+from dfcleaner import clean_dataframe
+
+df = pd.read_csv("data.csv")
+
+df = clean_dataframe(df, fill_missing="mean")
+```
+
+**License**<br>
+MIT License

dfcleanerpro-0.1.0/dfcleanerpro/__init__.py

@@ -0,0 +1,3 @@
+from .cleaner import clean_dataframe
+
+__all__ = ["clean_dataframe"]

dfcleanerpro-0.1.0/dfcleanerpro/cleaner.py

@@ -0,0 +1,29 @@
+import pandas as pd
+
+def clean_dataframe(
+        df,
+        drop_duplicates=True,
+        snake_case_columns=True,
+        fill_missing=None
+):
+    df = df.copy()
+
+    # Drop duplicates
+    if drop_duplicates:
+        df = df.drop_duplicates()
+
+    # Convert column names to snake_case
+    if snake_case_columns:
+        df.columns = [
+            col.strip().lower().replace(" ", "_")
+            for col in df.columns
+        ]
+
+    # Fill missing values
+    if fill_missing == "zero":
+        df = df.fillna(0)
+
+    elif fill_missing == "mean":
+        df = df.fillna(df.mean(numeric_only=True))
+
+    return df

dfcleanerpro-0.1.0/dfcleanerpro/utils.py

@@ -0,0 +1,2 @@
+def snake_case(name):
+    return name.strip().lower().replace(" ", "_")

dfcleanerpro-0.1.0/dfcleanerpro.egg-info/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.4
+Name: dfcleanerpro
+Version: 0.1.0
+Summary: Simple DataFrame cleaning toolkit
+Home-page: https://github.com/Nishanth9696/dfcleaner
+Author: Nishanth K
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+License-File: LICENSE
+Requires-Dist: pandas
+Dynamic: author
+Dynamic: classifier
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary

dfcleanerpro-0.1.0/dfcleanerpro.egg-info/SOURCES.txt

@@ -0,0 +1,13 @@
+LICENSE
+README.md
+pyproject.toml
+setup.py
+dfcleanerpro/__init__.py
+dfcleanerpro/cleaner.py
+dfcleanerpro/utils.py
+dfcleanerpro.egg-info/PKG-INFO
+dfcleanerpro.egg-info/SOURCES.txt
+dfcleanerpro.egg-info/dependency_links.txt
+dfcleanerpro.egg-info/requires.txt
+dfcleanerpro.egg-info/top_level.txt
+tests/test_cleaner.py

dfcleanerpro-0.1.0/dfcleanerpro.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

dfcleanerpro-0.1.0/dfcleanerpro.egg-info/requires.txt

@@ -0,0 +1 @@
+pandas

dfcleanerpro-0.1.0/dfcleanerpro.egg-info/top_level.txt

@@ -0,0 +1 @@
+dfcleanerpro

dfcleanerpro-0.1.0/pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"

dfcleanerpro-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

dfcleanerpro-0.1.0/setup.py

@@ -0,0 +1,21 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="dfcleanerpro",
+    version="0.1.0",
+    author="Nishanth K",
+    description="Simple DataFrame cleaning toolkit",
+    Long_description=open('README.md').read(),
+    Long_description_content_type='text/markdown',
+    packages=find_packages(),
+    url='https://github.com/Nishanth9696/dfcleaner',
+    classifiers=[
+    'Programming Language :: Python :: 3',
+    'License :: OSI Approved :: MIT License',
+    'Operating System :: OS Independent',
+        ],
+    install_requires=[
+        "pandas"
+    ],
+    python_requires=">=3.8",
+)

dfcleanerpro-0.1.0/tests/test_cleaner.py

@@ -0,0 +1,45 @@
+import pandas as pd
+from dfcleanerpro import clean_dataframe
+
+
+def test_drop_duplicates():
+    df = pd.DataFrame({
+        "name": ["Alice", "Alice", "Bob"],
+        "age": [25, 25, 30]
+    })
+
+    result = clean_dataframe(df, drop_duplicates=True)
+
+    assert len(result) == 2
+
+
+def test_snake_case_columns():
+    df = pd.DataFrame({
+        "First Name": ["Alice"],
+        "Last Name": ["Smith"]
+    })
+
+    result = clean_dataframe(df, snake_case_columns=True)
+
+    assert "first_name" in result.columns
+    assert "last_name" in result.columns
+
+
+def test_fill_missing_zero():
+    df = pd.DataFrame({
+        "age": [25, None, 30]
+    })
+
+    result = clean_dataframe(df, fill_missing="zero")
+
+    assert result["age"].isnull().sum() == 0
+
+
+def test_fill_missing_mean():
+    df = pd.DataFrame({
+        "age": [20, None, 40]
+    })
+
+    result = clean_dataframe(df, fill_missing="mean")
+
+    assert result["age"].isnull().sum() == 0