data-analysis

Data Pre-Processing tools like annotation, metadata extraction, etc. for various data, including image files, audio, and video files.
Data Analysis tools like error calculation classified under linear and logistic regression for a dataset with numeric and categorical attributes.
Data Classification tools like ID3 Decision Trees, Naive Bayes Classification, K Means clustering.

---

Image-preprocessing

This program aims to recognize objects in any given picture and draw bounding boxes around the object.
The objective lies in identifying the objects for further data pre-processing !

For Windows

Step 1:

Install the respective dependencies:

• yolov3.weights
• yolov3.cfg
• coco.names

You may visit the official website of YOLO to get the dependencies, the command prompt commands are as follows for the respective dependencies:

1. for yolov3.weights
   

   wget https://pjreddie.com/media/files/yolov3.weights

2. for yolov3.cfg
   

   wget https://github.com/pjreddie/darknet/blob/master/cfg/yolov3.cfg?raw=true -O yolov3.cfg

3. for coco.names
   

   wget https://github.com/pjreddie/darknet/blob/master/data/coco.names?raw=true -O coco.names

For Mac

You may visit the official YOLO website to install the dependencies or use these terminal commands:

1. for yolov3.weights
   

   curl -O https://pjreddie.com/media/files/yolov3.weights

2. for yolov3.cfg
   

   curl -o yolov3.cfg https://raw.githubusercontent.com/pjreddie/darknet/master/cfg/yolov3.cfg

3. for coco.names
   

   curl -o coco.names https://raw.githubusercontent.com/pjreddie/darknet/master/data/coco.names

---

Step 2:

Place the Files:

Ensure these files are in the same directory as your Python script. The directory should look like this:

your_project_directory/
├── yolov3.weights
├── yolov3.cfg
├── coco.names
└── main.py

---

Step 3:

Add an image in the same directory as the main.py file and run the script

If you are running this in an IDE like PyCharm, install the modules ( headers like opencv, matplotlib, numpy, and pillow ) packages in your environment before running the script.

CLI command to install the 'cv2' module:

pip install opencv-python

Note: For Mac users, there might occur a warning after successfully running the programming explaining the warning is related to macOS's security features and how macOS applications handle restorable state (like remembering window positions, open documents, etc.) when they are relaunched.

The warning may look like this:

WARNING: Secure coding is not enabled for restorable state! Enable secure coding by implementing NSApplicationDelegate.applicationSupportsSecureRestorableState: and returning YES.

This warning goes away if the program is run online through platforms like Google Colab or Jupyter Notebook.

---

Performance-Metrics

This repository displays how one performs the multiple performance metrics classified under both multiple linear and logistic regression on a dataset consisting of both numeric and categorical attributes

For Linear Regression Metrics

Respective Performance Metrics used:

• Mean Squared Error (MSE)
• Root Mean Squared Error (RMSE)
• Mean Absolute Error (MAE)
• R Squared Error
• Adjusted R Squared Error

Libraries Required:

1. numpy
2. pandas

Install the libraries if not already installed on the system using:

pip install numpy pandas

For Logistic Regression Metrics

Respective Performance Metrics used:

• Mean Squared Logarithmic Error (MSLE)
• Mean Absolute Percentage Error (MAPE)

Additional Library used:

• Streamlit

Streamlit is an open-source Python framework that allows users to create and share interactive web apps for data science and machine learning

Provides our code with a clean visualization feature.

Install it in your system with the command

pip install streamlit

Finally, open the directory where your file lies using the command:

cd path-to-dir/folder-where-your-file-lies

Run the code through the terminal with the command:

streamlit run filename.py

Feel free to add to this repository, Happy Coding !