dfflow 0.1.0__tar.gz

dfflow-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Suresh 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.

dfflow-0.1.0/PKG-INFO

@@ -0,0 +1,184 @@
+Metadata-Version: 2.4
+Name: dfflow
+Version: 0.1.0
+Summary: Lightweight pandas DataFrame logging and flow tracker
+Home-page: https://github.com/suressssz/dfflow
+Author: Suresh K
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=1.3
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# dfflow
+
+Lightweight pandas DataFrame logging and flow pipeline tracker.
+
+---
+
+## 📌 What is this?
+
+**dfflow** is a simple, easy-to-use Python package for:
+- Logging pandas DataFrame transformations step by step
+- Saving logs in text or JSON format
+- Building reusable pipeline-style data flows
+
+---
+
+## 📌 Features
+
+✅ Automatic DataFrame transformation logging  
+✅ Text and JSON log formats supported  
+✅ Easy pipeline-style processing  
+✅ Customizable logging  
+
+---
+
+## 📌 Installation
+
+```bash
+pip install dfflow
+```
+
+---
+
+## 📌 Requirements
+
+- Python >=3.7
+- pandas >=1.3
+
+To install requirements:
+
+```bash
+pip install -r requirements.txt
+```
+
+---
+
+## 📌 Usage Example 1
+
+```python
+import pandas as pd
+from dfflow import DFLogger, FlowPipeline, drop_nulls
+import os
+os.makedirs('examples', exist_ok=True)
+
+logger = DFLogger()
+pipe = FlowPipeline(logger=logger)
+
+pipe.add_step("Drop Nulls", drop_nulls)
+
+df = pd.DataFrame({
+    'name': ['Suresh', None, 'Jerry', 'Sunil', 'Linga'],
+    'age': [23, 26, None, 23, 24]
+})
+
+pipe.run(df)
+
+```
+---
+## 📌 Usage Example 2
+
+```python
+import pandas as pd
+from dfflow import DFLogger, FlowPipeline
+from dfflow.cleaning import drop_nulls, lowercase_columns
+from dfflow.profile import profile_summary
+
+# Create a sample DataFrame
+data = {
+    "Name": ["Suresh", None, "Sunil", "Shiva", "Linga"],
+    "Age": [23, 26, 23, 24, None]
+}
+df = pd.DataFrame(data)
+
+print("Original DataFrame:")
+print(df)
+print("\n")
+
+# Setup the DFLogger
+logger = DFLogger(
+    log_file='dfflow_log2.txt',  # Log file path
+    mode='text'                          # 'text' or 'json'
+)
+
+# Create the FlowPipeline
+pipe = FlowPipeline(logger=logger)
+
+# Add cleaning steps
+pipe.add_step("Drop Nulls", drop_nulls)
+pipe.add_step("Lowercase Columns", lowercase_columns)
+
+# Run the pipeline
+result_df = pipe.run(df)
+
+print("Final Cleaned DataFrame:")
+print(result_df)
+print("\n")
+
+# Profile Summary
+summary = profile_summary(result_df)
+print("Profile Summary:")
+print(summary)
+
+```
+---
+
+## 📌 Project Structure
+
+```
+dfflow/              # Main package folder
+│
+├── __init__.py
+├── logger.py        # Core logging class (DFLogger)
+├── decorators.py    # log_step decorator
+├── flow.py          # FlowPipeline logic
+├── cleaning.py      # Cleaning steps (drop_nulls, lowercase_columns)
+├── profile.py       # Profile utilities
+├── utils.py         # Helper functions
+│
+examples/            # Usage demos
+│   ├── dfflow_log.txt
+│   ├── dfflow_log2.txt
+│   ├── flow_demo.py
+│   └── flow_demo2.py
+│
+tests/               # Unit tests
+│   ├── __init__.py
+│   ├── test_cleaning.py
+│   ├── test_flow.py
+│   ├── test_logger.py
+│   └── test_profile.py
+│
+LICENSE              # MIT License
+README.md            # Project description
+requirements.txt     # Dependencies
+setup.py             # Packaging configuration
+
+```
+
+
+---
+
+## 📌 Author
+
+Maintained by **Suresh K**  
+📧 Email: sureshstr38@gmail.com  
+🌐 GitHub: [suressssz](https://github.com/suressssz)
+
+---
+
+## 📌 License
+
+This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

dfflow-0.1.0/README.md

@@ -0,0 +1,161 @@
+# dfflow
+
+Lightweight pandas DataFrame logging and flow pipeline tracker.
+
+---
+
+## 📌 What is this?
+
+**dfflow** is a simple, easy-to-use Python package for:
+- Logging pandas DataFrame transformations step by step
+- Saving logs in text or JSON format
+- Building reusable pipeline-style data flows
+
+---
+
+## 📌 Features
+
+✅ Automatic DataFrame transformation logging  
+✅ Text and JSON log formats supported  
+✅ Easy pipeline-style processing  
+✅ Customizable logging  
+
+---
+
+## 📌 Installation
+
+```bash
+pip install dfflow
+```
+
+---
+
+## 📌 Requirements
+
+- Python >=3.7
+- pandas >=1.3
+
+To install requirements:
+
+```bash
+pip install -r requirements.txt
+```
+
+---
+
+## 📌 Usage Example 1
+
+```python
+import pandas as pd
+from dfflow import DFLogger, FlowPipeline, drop_nulls
+import os
+os.makedirs('examples', exist_ok=True)
+
+logger = DFLogger()
+pipe = FlowPipeline(logger=logger)
+
+pipe.add_step("Drop Nulls", drop_nulls)
+
+df = pd.DataFrame({
+    'name': ['Suresh', None, 'Jerry', 'Sunil', 'Linga'],
+    'age': [23, 26, None, 23, 24]
+})
+
+pipe.run(df)
+
+```
+---
+## 📌 Usage Example 2
+
+```python
+import pandas as pd
+from dfflow import DFLogger, FlowPipeline
+from dfflow.cleaning import drop_nulls, lowercase_columns
+from dfflow.profile import profile_summary
+
+# Create a sample DataFrame
+data = {
+    "Name": ["Suresh", None, "Sunil", "Shiva", "Linga"],
+    "Age": [23, 26, 23, 24, None]
+}
+df = pd.DataFrame(data)
+
+print("Original DataFrame:")
+print(df)
+print("\n")
+
+# Setup the DFLogger
+logger = DFLogger(
+    log_file='dfflow_log2.txt',  # Log file path
+    mode='text'                          # 'text' or 'json'
+)
+
+# Create the FlowPipeline
+pipe = FlowPipeline(logger=logger)
+
+# Add cleaning steps
+pipe.add_step("Drop Nulls", drop_nulls)
+pipe.add_step("Lowercase Columns", lowercase_columns)
+
+# Run the pipeline
+result_df = pipe.run(df)
+
+print("Final Cleaned DataFrame:")
+print(result_df)
+print("\n")
+
+# Profile Summary
+summary = profile_summary(result_df)
+print("Profile Summary:")
+print(summary)
+
+```
+---
+
+## 📌 Project Structure
+
+```
+dfflow/              # Main package folder
+│
+├── __init__.py
+├── logger.py        # Core logging class (DFLogger)
+├── decorators.py    # log_step decorator
+├── flow.py          # FlowPipeline logic
+├── cleaning.py      # Cleaning steps (drop_nulls, lowercase_columns)
+├── profile.py       # Profile utilities
+├── utils.py         # Helper functions
+│
+examples/            # Usage demos
+│   ├── dfflow_log.txt
+│   ├── dfflow_log2.txt
+│   ├── flow_demo.py
+│   └── flow_demo2.py
+│
+tests/               # Unit tests
+│   ├── __init__.py
+│   ├── test_cleaning.py
+│   ├── test_flow.py
+│   ├── test_logger.py
+│   └── test_profile.py
+│
+LICENSE              # MIT License
+README.md            # Project description
+requirements.txt     # Dependencies
+setup.py             # Packaging configuration
+
+```
+
+
+---
+
+## 📌 Author
+
+Maintained by **Suresh K**  
+📧 Email: sureshstr38@gmail.com  
+🌐 GitHub: [suressssz](https://github.com/suressssz)
+
+---
+
+## 📌 License
+
+This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

dfflow-0.1.0/dfflow/__init__.py

@@ -0,0 +1,5 @@
+from .logger import DFLogger
+from .decorators import log_step
+from .flow import FlowPipeline
+from .cleaning import drop_nulls, lowercase_columns
+from .profile import profile_summary

dfflow-0.1.0/dfflow/cleaning.py

@@ -0,0 +1,10 @@
+from .decorators import log_step
+
+@log_step("Drop Nulls")
+def drop_nulls(df):
+    return df.dropna()
+
+@log_step("Lowercase Columns")
+def lowercase_columns(df):
+    df.columns = [col.lower() for col in df.columns]
+    return df

dfflow-0.1.0/dfflow/decorators.py

@@ -0,0 +1,8 @@
+def log_step(step_name):
+    def decorator(func):
+        def wrapper(df, *args, **kwargs):
+            result = func(df, *args, **kwargs)
+            print(f"[dfflow] Step: {step_name} completed.")
+            return result
+        return wrapper
+    return decorator

dfflow-0.1.0/dfflow/flow.py

@@ -0,0 +1,14 @@
+class FlowPipeline:
+    def __init__(self, logger=None):
+        self.steps = []
+        self.logger = logger
+
+    def add_step(self, name, func):
+        self.steps.append((name, func))
+
+    def run(self, df):
+        for name, func in self.steps:
+            df = func(df)
+            if self.logger:
+                self.logger.log(f"Step: {name}", df)
+        return df

dfflow-0.1.0/dfflow/logger.py

@@ -0,0 +1,34 @@
+import datetime
+import json
+
+class DFLogger:
+    def __init__(self, log_file='dfflow_log.txt', mode='text'):
+        self.log_file = log_file
+        self.mode = mode
+
+    def log(self, message, df, level="INFO"):
+        timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        if self.mode == 'json':
+            self._log_json(timestamp, message, df, level)
+        else:
+            self._log_text(timestamp, message, df, level)
+
+    def _log_text(self, timestamp, message, df, level):
+        with open(self.log_file, 'a') as f:
+            f.write("="*50 + "\n")
+            f.write(f"Timestamp : {timestamp}\n")
+            f.write(f"Level     : {level}\n")
+            f.write(f"Message   : {message}\n")
+            f.write("DataFrame :\n")
+            f.write(df.to_string())
+            f.write("\n\n")
+
+    def _log_json(self, timestamp, message, df, level):
+        log_entry = {
+            "timestamp": timestamp,
+            "level": level,
+            "message": message,
+            "dataframe": df.to_dict(orient="records")
+        }
+        with open(self.log_file, 'a') as f:
+            f.write(json.dumps(log_entry) + "\n")

dfflow-0.1.0/dfflow/profile.py

@@ -0,0 +1,6 @@
+def profile_summary(df):
+    return {
+        "shape": df.shape,
+        "columns": list(df.columns),
+        "null_counts": df.isnull().sum().to_dict()
+    }

dfflow-0.1.0/dfflow/utils.py

@@ -0,0 +1,4 @@
+from datetime import datetime
+
+def current_timestamp():
+    return datetime.now().strftime("%Y-%m-%d %H:%M:%S")

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

@@ -0,0 +1,184 @@
+Metadata-Version: 2.4
+Name: dfflow
+Version: 0.1.0
+Summary: Lightweight pandas DataFrame logging and flow tracker
+Home-page: https://github.com/suressssz/dfflow
+Author: Suresh K
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=1.3
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# dfflow
+
+Lightweight pandas DataFrame logging and flow pipeline tracker.
+
+---
+
+## 📌 What is this?
+
+**dfflow** is a simple, easy-to-use Python package for:
+- Logging pandas DataFrame transformations step by step
+- Saving logs in text or JSON format
+- Building reusable pipeline-style data flows
+
+---
+
+## 📌 Features
+
+✅ Automatic DataFrame transformation logging  
+✅ Text and JSON log formats supported  
+✅ Easy pipeline-style processing  
+✅ Customizable logging  
+
+---
+
+## 📌 Installation
+
+```bash
+pip install dfflow
+```
+
+---
+
+## 📌 Requirements
+
+- Python >=3.7
+- pandas >=1.3
+
+To install requirements:
+
+```bash
+pip install -r requirements.txt
+```
+
+---
+
+## 📌 Usage Example 1
+
+```python
+import pandas as pd
+from dfflow import DFLogger, FlowPipeline, drop_nulls
+import os
+os.makedirs('examples', exist_ok=True)
+
+logger = DFLogger()
+pipe = FlowPipeline(logger=logger)
+
+pipe.add_step("Drop Nulls", drop_nulls)
+
+df = pd.DataFrame({
+    'name': ['Suresh', None, 'Jerry', 'Sunil', 'Linga'],
+    'age': [23, 26, None, 23, 24]
+})
+
+pipe.run(df)
+
+```
+---
+## 📌 Usage Example 2
+
+```python
+import pandas as pd
+from dfflow import DFLogger, FlowPipeline
+from dfflow.cleaning import drop_nulls, lowercase_columns
+from dfflow.profile import profile_summary
+
+# Create a sample DataFrame
+data = {
+    "Name": ["Suresh", None, "Sunil", "Shiva", "Linga"],
+    "Age": [23, 26, 23, 24, None]
+}
+df = pd.DataFrame(data)
+
+print("Original DataFrame:")
+print(df)
+print("\n")
+
+# Setup the DFLogger
+logger = DFLogger(
+    log_file='dfflow_log2.txt',  # Log file path
+    mode='text'                          # 'text' or 'json'
+)
+
+# Create the FlowPipeline
+pipe = FlowPipeline(logger=logger)
+
+# Add cleaning steps
+pipe.add_step("Drop Nulls", drop_nulls)
+pipe.add_step("Lowercase Columns", lowercase_columns)
+
+# Run the pipeline
+result_df = pipe.run(df)
+
+print("Final Cleaned DataFrame:")
+print(result_df)
+print("\n")
+
+# Profile Summary
+summary = profile_summary(result_df)
+print("Profile Summary:")
+print(summary)
+
+```
+---
+
+## 📌 Project Structure
+
+```
+dfflow/              # Main package folder
+│
+├── __init__.py
+├── logger.py        # Core logging class (DFLogger)
+├── decorators.py    # log_step decorator
+├── flow.py          # FlowPipeline logic
+├── cleaning.py      # Cleaning steps (drop_nulls, lowercase_columns)
+├── profile.py       # Profile utilities
+├── utils.py         # Helper functions
+│
+examples/            # Usage demos
+│   ├── dfflow_log.txt
+│   ├── dfflow_log2.txt
+│   ├── flow_demo.py
+│   └── flow_demo2.py
+│
+tests/               # Unit tests
+│   ├── __init__.py
+│   ├── test_cleaning.py
+│   ├── test_flow.py
+│   ├── test_logger.py
+│   └── test_profile.py
+│
+LICENSE              # MIT License
+README.md            # Project description
+requirements.txt     # Dependencies
+setup.py             # Packaging configuration
+
+```
+
+
+---
+
+## 📌 Author
+
+Maintained by **Suresh K**  
+📧 Email: sureshstr38@gmail.com  
+🌐 GitHub: [suressssz](https://github.com/suressssz)
+
+---
+
+## 📌 License
+
+This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

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

@@ -0,0 +1,20 @@
+LICENSE
+README.md
+setup.py
+dfflow/__init__.py
+dfflow/cleaning.py
+dfflow/decorators.py
+dfflow/flow.py
+dfflow/logger.py
+dfflow/profile.py
+dfflow/utils.py
+dfflow.egg-info/PKG-INFO
+dfflow.egg-info/SOURCES.txt
+dfflow.egg-info/dependency_links.txt
+dfflow.egg-info/requires.txt
+dfflow.egg-info/top_level.txt
+tests/__init__.py
+tests/test_cleaning.py
+tests/test_flow.py
+tests/test_logger.py
+tests/test_profile.py

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

@@ -0,0 +1 @@
+

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

@@ -0,0 +1 @@
+pandas>=1.3

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

@@ -0,0 +1,2 @@
+dfflow
+tests

dfflow-0.1.0/setup.cfg

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

dfflow-0.1.0/setup.py

@@ -0,0 +1,21 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="dfflow",
+    version="0.1.0",
+    author="Suresh K",
+    description="Lightweight pandas DataFrame logging and flow tracker",
+    long_description=open("README.md").read(),
+    long_description_content_type="text/markdown",
+    url="https://github.com/suressssz/dfflow",
+    packages=find_packages(),
+    install_requires=[
+        "pandas>=1.3"
+    ],
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.7',
+)

dfflow-0.1.0/tests/test_cleaning.py

@@ -0,0 +1,21 @@
+# tests/test_cleaning.py
+
+import pandas as pd
+from dfflow.cleaning import drop_nulls, lowercase_columns
+
+def test_drop_nulls():
+    df = pd.DataFrame({
+        'A': [1, None, 3],
+        'B': [4, 5, None]
+    })
+    result = drop_nulls(df)
+    assert result.isnull().sum().sum() == 0
+
+def test_lowercase_columns():
+    df = pd.DataFrame({
+        'FirstName': [1, 2],
+        'AGE': [3, 4]
+    })
+    result = lowercase_columns(df)
+    for col in result.columns:
+        assert col.islower()

dfflow-0.1.0/tests/test_flow.py

@@ -0,0 +1,30 @@
+# tests/test_flow.py
+
+import pandas as pd
+from dfflow import DFLogger, FlowPipeline, drop_nulls, lowercase_columns
+
+def test_flow_pipeline(tmp_path):
+    log_file = tmp_path / "flow_log.txt"
+    logger = DFLogger(log_file=str(log_file), mode='text')
+
+    df = pd.DataFrame({
+        'Name': ['Tom', None],
+        'Age': [25, 22]
+    })
+
+    pipe = FlowPipeline(logger=logger)
+    pipe.add_step("Drop Nulls", drop_nulls)
+    pipe.add_step("Lowercase Columns", lowercase_columns)
+
+    result = pipe.run(df)
+
+    # Check nulls dropped
+    assert result.isnull().sum().sum() == 0
+    # Check columns lowercased
+    for col in result.columns:
+        assert col.islower()
+
+    # Check log created
+    with open(log_file) as f:
+        content = f.read()
+        assert "Drop Nulls" in content

dfflow-0.1.0/tests/test_logger.py

@@ -0,0 +1,28 @@
+# tests/test_logger.py
+
+import pandas as pd
+import os
+from dfflow.logger import DFLogger
+
+def test_text_logging(tmp_path):
+    log_file = tmp_path / "test_log.txt"
+    logger = DFLogger(log_file=str(log_file), mode='text')
+    df = pd.DataFrame({'A': [1, 2]})
+    logger.log("Test log message", df)
+
+    assert log_file.exists()
+    with open(log_file) as f:
+        content = f.read()
+        assert "Test log message" in content
+        assert "A" in content
+
+def test_json_logging(tmp_path):
+    log_file = tmp_path / "test_log.json"
+    logger = DFLogger(log_file=str(log_file), mode='json')
+    df = pd.DataFrame({'B': [3, 4]})
+    logger.log("JSON log message", df)
+
+    assert log_file.exists()
+    with open(log_file) as f:
+        content = f.read()
+        assert "JSON log message" in content

dfflow-0.1.0/tests/test_profile.py

@@ -0,0 +1,15 @@
+# tests/test_profile.py
+
+import pandas as pd
+from dfflow.profile import profile_summary
+
+def test_profile_summary():
+    df = pd.DataFrame({
+        'X': [1, None],
+        'Y': [3, 4]
+    })
+    summary = profile_summary(df)
+    assert 'shape' in summary
+    assert 'columns' in summary
+    assert 'null_counts' in summary
+    assert summary['null_counts']['X'] == 1