{"id":23670167,"url":"https://github.com/codewithdark-git/ai-ml-intern-tasks","last_synced_at":"2026-04-12T02:36:27.862Z","repository":{"id":269821473,"uuid":"908562101","full_name":"codewithdark-git/AI-ML-Intern-tasks","owner":"codewithdark-git","description":"Welcome to the AI/ML Internship repository. This repository outlines a structured 3-week program designed to enhance your skills in machine learning and deep learning, focusing on medical data analysis and disease prediction.","archived":false,"fork":false,"pushed_at":"2025-01-25T05:16:26.000Z","size":112299,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-21T04:13:13.886Z","etag":null,"topics":["cnn","cnn-classification","decision-trees","image-processing","logistic-regression","machine","machine-learning","python","random-forest","sklearn","svm-classifier","torch","torchvision"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/codewithdark-git.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-12-26T11:25:51.000Z","updated_at":"2025-01-25T05:16:30.000Z","dependencies_parsed_at":"2024-12-26T12:25:17.313Z","dependency_job_id":"4dddf477-1f8d-418f-a42a-e864f709c13e","html_url":"https://github.com/codewithdark-git/AI-ML-Intern-tasks","commit_stats":null,"previous_names":["codewithdark-git/ai-ml-intern-tasks"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/codewithdark-git/AI-ML-Intern-tasks","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithdark-git%2FAI-ML-Intern-tasks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithdark-git%2FAI-ML-Intern-tasks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithdark-git%2FAI-ML-Intern-tasks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithdark-git%2FAI-ML-Intern-tasks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/codewithdark-git","download_url":"https://codeload.github.com/codewithdark-git/AI-ML-Intern-tasks/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithdark-git%2FAI-ML-Intern-tasks/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273539219,"owners_count":25123494,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-03T02:00:09.631Z","response_time":76,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cnn","cnn-classification","decision-trees","image-processing","logistic-regression","machine","machine-learning","python","random-forest","sklearn","svm-classifier","torch","torchvision"],"created_at":"2024-12-29T09:31:59.528Z","updated_at":"2026-04-12T02:36:22.623Z","avatar_url":"https://github.com/codewithdark-git.png","language":"Jupyter Notebook","readme":"# AI/ML Internship Tasks\n\nWelcome to the AI/ML Internship repository. This repository outlines a structured 3-week program designed to enhance your skills in machine learning and deep learning, focusing on medical data analysis and disease prediction.\n\n\n## Table of Contents\n\n- [AI/ML Internship Tasks](#aiml-internship-tasks)\n  - [Table of Contents](#table-of-contents)\n  - [Repository Structure](#repository-structure)\n  - [Week 1: Disease Prediction Using Patient Data](#week-1-disease-prediction-using-patient-data)\n  - [Week 2: Cancer Detection Using Histopathological Images](#week-2-cancer-detection-using-histopathological-images)\n  - [Week 3: Medical Image Classification](#week-3-medical-image-classification)\n    - [1. Skin Cancer Detection](#1-skin-cancer-detection)\n    - [2. Pneumonia Detection from Chest X-Rays](#2-pneumonia-detection-from-chest-x-rays)\n  - [Learning Goals](#learning-goals)\n  - [Tools \\\u0026 Libraries](#tools--libraries)\n  - [Submission Requirements](#submission-requirements)\n  - [Bonus Task](#bonus-task)\n  - [Getting Started](#getting-started)\n  - [Prerequisites](#prerequisites)\n  - [Installation](#installation)\n  - [Usage](#usage)\n  - [Contributing](#contributing)\n  - [License](#license)\n  - [Contact](#contact)\n\n## Repository Structure\n```python\nAI-ML-Intern-ta\n├── Week_1/\n│   ├── Diabetes_prediction/\n│   │   ├── data/\n│   │   │   └── diabetes.csv\n│   │   ├── diabetes_prediction.ipynb\n│   │   |── app.py # The Streamlit Ui for testing save models\n│   │   ├── models/\n│   │   │   └── # Trained models saved here\n│   │   └── README.md  # Documentation about the model proformance and insights\n│   └── Heart_disease_prediction/\n│       ├── data/\n│       |   ├── heart-disease-dataset.zip\n│       │   └── heart.csv\n│       |   ├── heart-disease-dataset.zip\n│       |── app.py # The Streamlit Ui for testing save models\n|       |── heart_disease.ipynb\n│       ├── models/\n│       │   └── # Trained models saved here\n│       └── README.md  # Documentation about the model proformance and insights\n├── Week_2/\n│   ├── Cancer_detection/\n│   │   ├── data/\n│   │   │   └── histopathology_images/\n│   │   ├── notebooks/\n│   │   │   └── cancer_detection.ipynb\n│   │   ├── models/\n│   │   │   └── cnn_model.h5\n│   │   ├── reports/\n│   │   │   └── cancer_detection_report.pdf\n│   │   └── README.md\n├── Week_3/\n│   ├── Skin_cancer_detection/\n│   │   ├── melamoma_cancer_dataset\n|   |   |   ├── test\n|   │   │   |  ├── melanoma\n|   │   │   |  └── benign\n|   │   |   └── train\n|   |   |      ├── melanoma\n|   |   |      └── benign\n│   │   ├── skin_cancer_detection.ipynb\n│   │   ├── Models/\n│   │   │   └──             \n│   │   └── README.md       # full documentation for the Skin-Cancer-detection Pipeline \n│   └── Pneumonia_detection/\n│       ├── data/\n│       │   └── chest_xrays/\n│       ├── notebooks/\n│       │   └── pneumonia_detection.ipynb\n│       ├── models/\n│       │   └── mobilenet_model.h5\n│       ├── reports/\n│       │   └── pneumonia_detection_report.pdf\n│       └── README.md\n├── LICENSE\n├── requirements.txt\n└── README.md  # Main README file with an overview of the internship tasks\n```\n\n## Week 1: Disease Prediction Using Patient Data\n\n**Objective:** Train and evaluate machine learning models to predict diseases such as diabetes or heart disease.\n\n**Tasks:**\n\n1. **Dataset Acquisition:**\n   - Download the dataset from the [UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/index.php).\n\n2. **Data Preprocessing:**\n   - Handle missing values appropriately.\n   - Perform normalization of numerical features.\n   - Encode categorical features using suitable encoding techniques.\n\n3. **Exploratory Data Analysis (EDA):**\n   - Analyze feature distributions and correlations.\n   - Visualize data using histograms, scatter plots, and heatmaps.\n\n4. **Model Training:**\n   - Train models using Logistic Regression, Random Forest, and Support Vector Machine (SVM).\n\n5. **Model Evaluation:**\n   - Evaluate models with metrics such as accuracy, precision, recall, and F1-score.\n   - Compare model performances to identify the best-performing algorithm.\n\n**Outcome:** A comprehensive report summarizing the analysis, model performances, and insights.\n\n## Week 2: Cancer Detection Using Histopathological Images\n\n**Objective:** Utilize deep learning to detect cancerous cells from histopathological images.\n\n**Tasks:**\n\n1. **Dataset Acquisition:**\n   - Access the [Breast Cancer Histopathology Images Dataset](https://www.kaggle.com/paultimothymooney/breast-histopathology-images) from Kaggle.\n\n2. **Data Augmentation:**\n   - Apply techniques such as rotation, flipping, and scaling to balance the dataset and enhance generalization.\n\n3. **Model Implementation:**\n   - Implement a Convolutional Neural Network (CNN) using frameworks like TensorFlow or PyTorch.\n   - Explore Transfer Learning with pre-trained models such as ResNet or VGG16.\n\n4. **Visualization:**\n   - Highlight cancerous regions in images using Image Segmentation or Grad-CAM visualization techniques.\n\n**Outcome:** A deep learning model capable of accurately detecting and highlighting cancerous regions.\n\n## Week 3: Medical Image Classification\n\n### 1. Skin Cancer Detection\n\n**Objective:** Classify skin lesions into categories (e.g., benign or malignant).\n\n**Dataset:** [ISIC Skin Cancer Dataset](https://www.isic-archive.com/).\n\n**Steps:**\n\n1. **Data Preprocessing:**\n   - Load the dataset and normalize pixel values to [0, 1].\n   - Resize images to a fixed size (e.g., 224x224) for compatibility with CNNs.\n   - Split the dataset into training, validation, and testing sets.\n\n2. **Data Augmentation:**\n   - Apply techniques like random rotation, flipping, zooming, and brightness adjustment.\n\n3. **Model Development:**\n   - Utilize a pre-trained CNN model (e.g., ResNet50 or EfficientNet) with transfer learning.\n   - Fine-tune the model by replacing the last fully connected layer with a dense layer for binary classification.\n   - Use Binary Crossentropy as the loss function and Adam optimizer.\n\n4. **Evaluation:**\n   - Assess the model using accuracy, precision, recall, and F1-score.\n\n**Deliverables:**\n   - Code file (`skin_cancer_detection.py` or notebook).\n   - A short report (1-2 pages) detailing model performance and insights.\n\n### 2. Pneumonia Detection from Chest X-Rays\n\n**Objective:** Classify chest X-ray images as pneumonia-positive or negative.\n\n**Dataset:** [Chest X-Ray Images Dataset](https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia) from Kaggle.\n\n**Steps:**\n\n1. **Data Preprocessing:**\n   - Load and preprocess images (resize to 224x224, normalize pixel values).\n   - Divide the dataset into training, validation, and testing sets.\n\n2. **Data Augmentation:**\n   - Apply augmentation techniques (e.g., random cropping, rotation, and histogram equalization).\n\n3. **Model Development:**\n   - Implement a CNN architecture or fine-tune a pre-trained model (e.g., MobileNet or InceptionV3).\n   - Optimize the model with Categorical Crossentropy loss and Adam optimizer.\n\n4. **Evaluation:**\n   - Use metrics like sensitivity, specificity, and ROC-AUC score.\n   - Compare results on augmented vs. non-augmented datasets.\n\n**Deliverables:**\n   - Code file (`pneumonia_detection.py` or notebook).\n   - A summary report (1-2 pages) on model performance and challenges.\n\n## Learning Goals\n\n- Understand and apply Transfer Learning for medical image classification.\n- Gain hands-on experience with data preprocessing and augmentation techniques.\n- Comprehend evaluation metrics such as sensitivity, specificity, and F1-score.\n- Explore the impact of fine-tuning pre-trained models on performance.\n\n## Tools \u0026 Libraries\n\n- **Frameworks:** TensorFlow/Keras or PyTorch.\n- **Libraries:** OpenCV, NumPy, Pandas, Matplotlib, Scikit-learn.\n- **Hardware:** Google Colab or a local system with GPU support.\n\n## Submission Requirements\n\n1. Code files or notebooks for each task.\n2. Reports summarizing findings, challenges, and insights.\n3. Model files (optional) and visualizations (charts/graphs) demonstrating results.\n4. **Deadline:** End of Week 3.\n\n## Bonus Task\n\nFor enthusiastic internees:\n\n- Experiment with ensemble models combining multiple pre-trained CNNs.\n- Perform hyperparameter tuning (e.g., learning rate, batch size, epochs) to enhance performance.\n\n## Getting Started\n\nTo begin working on these tasks, clone the repository to your local machine:\n\n```bash\ngit clone https://github.com/codewithdark-git/AI-ML-Intern-tasks.git\n```\n\n## Prerequisites\n\nEnsure you have the following software installed:\n\n- Python 3.x\n- Jupyter Notebook\n- Necessary Python libraries (listed in `requirements.txt`)\n\n## Installation\n\nNavigate to the project directory and install the required dependencies:\n\n```bash\npip install -r requirements.txt\n```\n\n## Usage\n\nEach task is contained within its respective directory. Open the Jupyter Notebook files to explore the code and follow the instructions provided within each notebook.\n\nbash\njupyter notebook\n\n\n## Contributing\n\nContributions are welcome! Please fork the repository and create a pull request with your enhancements or bug fixes.\n\n## License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.\n\n## Contact\n\nFor any questions or suggestions, feel free to reach out:\n\n- **GitHub:** [codewithdark-git](https://github.com/codewithdark-git)\n- **LinkedIn:** [Ahsan Umar](https://www.linkedin.com/in/codewithdark)\n- **Kaggle:** [codewithdark](https://www.kaggle.com/codewithdark)\n- **Email:** [codewithdark](mailto:codewithdark90@gmail.com)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodewithdark-git%2Fai-ml-intern-tasks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodewithdark-git%2Fai-ml-intern-tasks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodewithdark-git%2Fai-ml-intern-tasks/lists"}