A Streamlit-based AI Task Management dashboard that classifies, visualizes, and analyzes tasks using machine learning.
Live Demo: Click Here
“Where Artificial Intelligence meets Productivity.”
An enterprise-level AI-driven platform that intelligently classifies, prioritizes, and assigns tasks using NLP and Machine Learning — designed to supercharge teams with data-driven automation.
| 🌟 Feature | 💡 Description |
|---|---|
| 🧠 AI-Driven Task Allocation | Automatically assigns and prioritizes tasks using workload, deadlines, and behavioral analytics. |
| 📊 Interactive Dashboard | Explore real-time visual analytics — task status, team performance, and model insights in one view. |
| ⚙️ Adaptive Machine Learning Model | Continuously learns from user data to refine task predictions and improve accuracy over time. |
| 📝 Dual-Mode Task Control | Seamlessly switch between manual edits and automated AI-based task assignment. |
| 📈 Comprehensive Analytics | Gain deep insights into productivity trends, overdue tasks, and efficiency ratios. |
| 🚀 Future-Ready Integrations | Designed for smooth integration with Trello, Jira, and Slack APIs for enterprise workflows. |
| 🔧 Category | 🧩 Tools & Technologies |
|---|---|
| 💻 Languages & Libraries | Python · Pandas · Streamlit · NumPy · Matplotlib · Scikit-learn |
| 🤖 Machine Learning | Classification models using Scikit-learn for task priority prediction and behavioral analysis |
| 📊 Data Handling | Structured CSV datasets (tasks_cleaned.csv, user_data.csv, model_predictions.csv) for reproducible results |
| 🎨 UI & Visualization | Streamlit for the dashboard UI with responsive layouts and real-time visual components |
| 🧠 Analytics & Insights | Matplotlib/Seaborn for performance graphs and prediction visualization |
| ⚙️ Environment Management | Virtual environments (venv) and requirements.txt for dependency reproducibility |
| ☁️ Platform Compatibility | Works seamlessly across Windows, macOS, and Linux environments |
AI_TASK_MANAGER_2.8/
│
├── .gitignore
├── README.md
├── requirements.txt
│
├── app/
│ ├── main.py
│ └── routes/
│ └── task_dashboard.py
│
├── assets/
│ └── (images, icons, UI files)
│
├── docs/
│ ├── CODE_OF_CONDUCT.md
│ ├── CONTRIBUTING.md
│ ├── SECURITY.md
│ └── project_overview.docx
│
├── src/
│ │
│ ├── data/
│ │ ├── users.csv
│ │ ├── user_data.csv
│ │ ├── tasks.csv
│ │ ├── tasks_cleaned.csv
│ │ └── model_predictions.csv
│ │
│ ├── preprocessing/
│ │ ├── check_columns.py
│ │ ├── eda_analysis.py
│ │ └── eda_cleaning.py
│ │
│ ├── model/
│ │ ├── task_classifier.py
│ │ ├── predict_task.py
│ │ ├── smart_assigner.py
│ │ ├── assign_tasks.py
│ │ ├── task_predictor.py
│ │ ├── update_user_performance.py
│ │ ├── priority_model.pkl
│ │ └── vectorizer.pkl
│ │
│ └── utils/
│ ├── models.py
│ └── user_tracker.py
│
└── tests/
└── (placeholder for test scripts)Follow these steps to set up and run AI Task Manager 2.8 on your local machine:
# Use the below command to clone the Repo
git clone https://github.com/ABHIJEET-0001/AI_TASK_MANAGER_2.8.git
# Open your folder using the below command
cd AI_TASK_MANAGER_2.8# Create a virtual environment
python -m venv venv
# Activate the environment
venv\Scripts\activate # 🪟 Windows
source venv/bin/activate # 🍎 macOS / 🐧 Linux
pip install --upgrade pip
pip install -r requirements.txttasks_cleaned.csv
user_data.csv
model_predictions.csvstreamlit run dashboard.pyThen open your browser and go to 👉 http://localhost:8501
| 💡 Solution | |
|---|---|
ModuleNotFoundError |
Run pip install -r requirements.txt again inside the activated virtual environment. |
OSError: Port 8501 already in use |
Run the app on a different port using streamlit run dashboard.py --server.port 8502. |
| 📂 Missing CSV files | Ensure all required dataset files (tasks_cleaned.csv, user_data.csv, model_predictions.csv) are present in the project root. |
| ⚙️ Virtual environment not activating | Recheck your Python installation path or restart your terminal, then try activating the environment again. |
✅ Once the app starts successfully, you’ll see the AI Task Manager Dashboard running locally — ready for exploration!
The AI Task Manager Dashboard provides an interactive and data-driven interface that blends machine learning insights with intuitive visualization. Each module is designed to give users a holistic view of team productivity and task prioritization.
- 📋 Task Overview Table: Displays all active, pending, and completed tasks with quick filters and sorting by user, priority, and status.
- 🥧 Priority Distribution Chart: Visualizes how tasks are spread across High, Medium, and Low priorities — helping identify workload balance.
- 📈 User Performance Analytics: Tracks user efficiency, completed task ratios, and behavioral performance metrics in real-time.
- 🧩 Model Accuracy Tracker: Monitors how well the ML model predicts priorities compared to actual user decisions, with precision and confidence scores.
- 🤖 Smart Task Auto-Assigner: Automatically assigns new or unassigned tasks using workload, behavior analytics, and priority logic.
- ✏️ Add/Edit Task Interface: Lets users manually create, update, or reassign tasks directly from the dashboard — no coding required.
- 🔍 Summary Metrics Panel: Offers quick insights into total tasks, overdue count, completion rate, and pending workload.
💡 These modules work together to create a unified, intelligent workflow — enabling data-driven decision-making and time-efficient task management.
The AI Task Manager relies on structured CSV datasets that feed data into the ML models and dashboard visualizations. Each file plays a unique role in tracking tasks, user performance, and model predictions.
Stores individual user statistics to measure productivity and workload distribution.
Username,CurrentTasks,CompletedTasks,PendingTasks,BehaviorScore
Alice,3,15,2,85
Bob,5,10,3,78
Carol,2,20,1,92
- Username: Identifier for each user.
- CurrentTasks: Number of active tasks assigned.
- CompletedTasks: Total completed tasks.
- PendingTasks: Tasks awaiting completion.
- BehaviorScore: ML-derived performance score (0–100).
Represents the main dataset for task tracking and ML classification. It contains information about deadlines, assignments, and status.
TaskID,Description,Deadline,AssignedTo,Priority,Status
T001,Fix login bug,2025-11-10,Alice,High,In Progress
T002,Update documentation,2025-11-15,Bob,Medium,Pending
T003,Deploy to production,2025-11-08,Carol,High,Completed
- TaskID: Unique task identifier.
- Description: Short summary of the task.
- Deadline: Due date in
YYYY-MM-DDformat. - AssignedTo: User responsible for completion.
- Priority: ML-assigned or user-defined level (High, Medium, Low).
- Status: Task progress (Pending, In Progress, Completed).
Captures the AI model’s prediction results compared to the actual outcomes for model evaluation and tuning.
TaskID,PredictedPriority,ActualPriority,Confidence
T001,High,High,0.92
T002,Medium,Medium,0.85
T003,High,High,0.88
- TaskID: Reference to the task from
tasks_cleaned.csv. - PredictedPriority: AI-predicted priority category.
- ActualPriority: Ground truth assigned manually or from data.
- Confidence: Model’s confidence score (0–1 scale).
AI Task Manager 2.8 is designed with scalability in mind. The following roadmap outlines upcoming features aimed at improving automation, collaboration, and cloud readiness.
- 🔗 Integration with Trello, Jira & Slack APIs: Seamless synchronization with popular project management and communication tools for unified task tracking.
- 💬 Smart Notifications via Email & Chatbot: Real-time alerts for deadlines, task updates, and status changes using conversational AI.
- 🔐 Role-Based Authentication & Multi-User Access: Secure user management system with admin and member privileges for collaborative task handling.
- ☁️ Real-Time Cloud Sync: Enable persistent data storage, cloud-hosted dashboards, and live updates across distributed teams.
- 📱 Mobile-Responsive Dashboard: Optimized layout for smartphones and tablets to manage tasks on the go.
- 🧩 Enhanced AI Models: Implement deep learning for smarter task prediction and improved accuracy in prioritization.
If you run into issues while setting up or running the app, here are some common errors and their quick fixes:
| 💡 Solution | |
|---|---|
| ModuleNotFoundError | Ensure your virtual environment is activated, then run:pip install -r requirements.txt |
| OSError: Port 8501 already in use | Run the app on a different port:streamlit run dashboard.py --server.port 8502 |
| Missing CSV Files | Verify that tasks_cleaned.csv, user_data.csv, and model_predictions.csv exist in the project root folder. |
| Virtual Environment Not Activating | Recheck your Python installation path or restart your terminal session. |
| Streamlit Version Error | Use Python 3.10–3.12 and install the correct version:pip install streamlit==1.39.0 |
| File Path Errors | Run the app from the project root:streamlit run dashboard.py |
✅ Tip: Once the app launches successfully, open http://localhost:8501 to explore the AI Task Manager Dashboard locally.
We love and welcome contributions from everyone — whether you’re fixing bugs, improving documentation, or adding powerful new features! 💡
- 🌱 Explore Issues: Browse open issues and choose one that aligns with your interest or skill set.
- 🛠️ Enhance Features: Improve machine learning models, optimize data pipelines, or refine the dashboard UI for better UX.
- 📝 Improve Documentation: Clarify setup steps, add code examples, or contribute visual guides and screenshots.
- 🧪 Write or Improve Tests: Help strengthen reliability and performance through meaningful test coverage.
- 💬 Suggest Ideas: Share feedback and new feature proposals in the Discussions tab.
# 1️⃣ Fork the repository
# This creates your personal copy under your GitHub account
https://github.com/ABHIJEET-0001/AI_TASK_MANAGER_2.8/fork
# 2️⃣ Clone your fork locally
git clone https://github.com/<your-username>/AI_TASK_MANAGER_2.8.git
cd AI_TASK_MANAGER_2.8
# 3️⃣ Create a new branch for your contribution
git checkout -b docs/enhance-readme-contrib
# 4️⃣ Make your changes
# Example: edit README.md, improve documentation, or enhance features
# You can open the folder in VS Code:
code .
# 5️⃣ Stage your changes
git add .
# 6️⃣ Commit with a meaningful message
Example: git commit -m "docs: enhance README with setup, contribution, and reproducibility details"
# 7️⃣ Push your branch to your fork
Example: git push origin docs/enhance-readme-contrib
# 8️⃣ Open a Pull Request (PR)
# Go to your forked repository on GitHub
# Click “Compare & pull request”
# Add a clear title, description, and mention the related issue number if applicable
- ✅ Keep your PRs focused — smaller, well-defined changes are easier to review.
- 📄 Follow the existing CONTRIBUTING.md file for detailed workflow and coding standards.
- 💬 Communicate early — comment on issues before starting to avoid duplicate work.
- 🔍 Always test your changes locally before committing.
💡 Every contribution matters — from improving a single line of documentation to building new features. Let’s make AI Task Manager smarter, together! 🚀
- 🧑🎓 Students & Learners: Gain hands-on experience in AI, Machine Learning, and NLP by exploring practical task management and automation workflows.
- 💻 Developers & Engineers: Build and enhance intelligent productivity tools — from task prioritization systems to data-driven dashboards.
- 🌍 Open Source Contributors: Collaborate on a real-world ML project, sharpen your Git and documentation skills, and make meaningful contributions to an evolving AI tool.
- 🚀 Data Enthusiasts: Experiment with structured datasets, train predictive models, and visualize insights through an interactive Streamlit interface.
- 🧠 Researchers & Innovators: Prototype new ideas around smart automation, workload prediction, and adaptive decision-making systems.
- 👨💻 Created & Maintained by: Abhijeet Kasera
- 💡 Inspiration: Driven by a passion to combine Artificial Intelligence with Task Management — empowering smarter prioritization, automation, and productivity through data-driven insights.
- 🌍 Community: A heartfelt thanks to all open-source contributors, testers, and collaborators who help make AI Task Manager smarter with every release.
This project is licensed under the MIT License — you’re free to use, modify, and distribute this software, provided appropriate credit is given.
💡 Crafted with precision, powered by AI, and designed for innovation.
Made with ❤️ by Abhijeet Kasera