isi-mube / patent-pending

To predict selling house prices based on historical data for Ironhack's mid-bootcamp project. Also, Linear Regression practice.

Patent-Pending

This is Ironhack's mid-bootcamp project, developed and (not-yet)completed by the knowledge triumvirate of Gladys, izzy & JC.

Ironhack storytelling: You are working as an analyst for a real estate company. Your company wants to build a machine learning model to predict the selling prices of houses based on a variety of features on which the value of the house is evaluated

Objectives:

Ironhack objectives:

• Build a model that will predict the price of a house based on features provided in the dataset.
• Use business intelligence tools to explore the characteristics of the houses.
• To know which factors are responsible for higher property value - $650K and above.

Group objectives:

• Be able to organize and divide the work equally accordingly to each other skills.
• Document the process and keep everyone updated.
• Merging all files and discussing the changes together.
• Learn about AGILE methodology.
• Work on personal weak-points and try to learn from each other.
• Have fun ! :)

Project development:

Project deadline: 06 days (between 23/04/23 and 09/05/23)

Week 12:

• DAY 1 (25-04-2023) | Project discussion, tasks assignments** and division of the work.
• DAY 2 (27-04-2023) | Starting with Trello, merging python scripts, starting to work on SQL and storytelling-brainstorming.
• DAY 3 (29-04-2023) | Futher improvments to the code and opening discussions, more task assigments, SQL part done. Also;
  • We discussed about making “house_lifetime” based on the last year of the dataset, instead of the current year (2023).
  • We discussed about making year a continuous variable, (e.g, 2013,02 to represent february) to have a a single feature that represents yearly trends.

Week 13:

• DAY 4: (02-05-2023) | Presentation of the changes, brainstorming on how to improve the model, tasks division (Tableau, presentation, python fine-tunning)
• DAY 5: (04-05-2023) | Tasks division. Finishing with Tableau, presentation and python fine-tunning.
• DAY 6: (06-05-2023) | Presentation day

--> AGILE methods (Trello)

About the folders:

• 00_data --> data and datasets info.
• 01_usefulness --> tailor's drawer to quickly access to functions, libraries and a template.
• 02_project_info --> ironhack deliverables files.
• 03_python_scripts --> python source code.
• 04_sql_script --> sql source script.
• 05_sandboxes --> testing scripts and ideas.
• 06_tableau --> tableau exercise.
• 07_presentation --> presentation and conclusions.

Tools:

Enviornments

• JupyterLab: Python scripts.
• MySQL Workbench: SQL script.
• Tableau: Visualizations.
• Trello: Organization.
• Google Doc: Organization.
• Canva: Logo and presentation.

Libraries

• Pandas: Data manipulation.
• Os: File managment.
• Warnings: Roses are red. Violets are blue. Warnings are annoying.
• Datetime: To play with time.
• Matplotlib: 2D visualizations.
• Seaborn: High-resolution visualizations.
• Linear Regression model: From sklearn.
• Skew: Data asymmetry.
• StandardScaler: Data normalization.
• Train-test splits: Sets after X-Y split.
• Metrics: R2, RMSE, MSE, MAE.