The Interactive Parent-Child Activity Planner is a web-based application that recommends activities for parents and children to enjoy together. By analyzing shared hobbies and interests, the platform provides tailored suggestions to enhance family bonding and create memorable experiences.
The key objectives of this project are as follows:
- User Input Collection: Gather details about the child’s interests, age, and preferences.
- ML Model Integration: Utilize a trained machine learning model to predict suitable hobbies.
- Activity Retrieval from Database: Fetch activities from MongoDB based on predicted hobby and age group.
- Personalized Recommendations: Generate customized activity suggestions.
- Interactive UI: Provide an intuitive and user-friendly interface for parents.
Experience the live application: Interactive Parent-Child Activity Planner
The dataset used for training the model contains various child interests, age groups, and activity preferences. The structured data allows the model to identify patterns and suggest the most relevant activities.
- Dataset Source: Hobby Prediction Dataset
- Features:
- Child’s age (categorized into 4-5 and 6-8 years)
- Interests (Arts, Sports, Academics)
- Preferred activity type (indoor, outdoor)
- Time availability
- Parental participation level
- User Input Handling: Collects child-related details through a form.
- ML Model Prediction: The trained model predicts the child's hobby (Arts, Sports, or Academics).
- Fetching Data from MongoDB: Based on the predicted hobby and age group, the system retrieves activity recommendations from the MongoDB database.
- Recommendation Display: Presents the personalized recommendations (videos, descriptions, required materials) on the web interface.
The database stores activities under three categories: Arts, Sports, and Academics, further classified into two age groups (4-5 and 6-8). Each activity entry includes:
- URL: A link to an instructional video.
- Title: Activity name.
- Description: Brief details about the activity.
- Image: Stored as a Base64 binary.
- Materials: List of required materials.
- Duration: Estimated time to complete the activity.
- Age Group: Either 4-5 or 6-8.
The machine learning models used in this project were trained using a dataset from Kaggle.
- Dataset: Hobby Prediction Dataset
- Libraries Used: pandas, numpy, matplotlib, seaborn, sklearn
- RandomForestClassifier (Primary Model)
- Logistic Regression
-
Metrics Used:
- Accuracy Score
- Classification Report
- Confusion Matrix
-
Performance on Test Data:
- Achieved 91% accuracy
- Used GridSearchCV to optimize the model parameters.
- Improved model performance by tuning hyperparameters for better accuracy.
To set up and run the project:
- Clone the repository:
git clone https://github.com/PriyanshuLathi/Interactive-Parent-Child-Activity-Planner.git
cd Interactive-Parent-Child-Activity-Planner- Create and Activate a Virtual Environment:
python3 -m venv venv
source venv/bin/activate # On Windows, use venv\Scripts\activate- Install Dependencies:
pip install -r requirements.txt- Run the Application:
python app.pyAccess the application at http://127.0.0.1:5000/ in your browser.
This project aims to enhance parent-child engagement by leveraging machine learning to recommend personalized activities. The combination of a user-friendly web interface, an optimized ML model, and a structured MongoDB database ensures a seamless experience for parents looking to spend quality time with their children.
Contributions are welcome! To contribute:
- Fork the repository.
- Create a new branch: git checkout -b feature-branch-name.
- Make your changes and commit them: git commit -m 'Add new feature'.
- Push to the branch: git push origin feature-branch-name.
- Submit a pull request detailing your changes.
This project is licensed under the MIT License - see the LICENSE file for details.
For questions or feedback:
- LinkedIn: Priyanshu Lathi
- GitHub: Priyanshu Lathi
- Priyanshu Lathi