https://github.com/jlenon7/housing-model

🤖 Model that predicts the worth of a housing according to it geolocation, number of bedrooms, number of bathrooms and more.
https://github.com/jlenon7/housing-model

Last synced: 9 days ago
JSON representation

🤖 Model that predicts the worth of a housing according to it geolocation, number of bedrooms, number of bathrooms and more.

• Host: GitHub
• URL: https://github.com/jlenon7/housing-model
• Owner: jlenon7
• License: mit
• Created: 2024-03-21T15:40:09.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-03-22T22:36:37.000Z (9 months ago)
• Last Synced: 2024-10-05T23:41:44.976Z (3 months ago)
• Language: Python
• Size: 1.31 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Housing Model 🤖

> Model that predicts what will be the price of a housing based on the number of bedrooms, bathrooms, square footage, etc.

## Results

> Verify that train/test data is not over fitting:



> Real prices vs predictions done by the model:



## Train/Test data analytics

> Count how many data we have with determined number of bedrooms



> Price distribution in **King County** city. This plot has been created

> by using the `lat` and `long` fields to create the map of the city.

> Greener values mean higher prices, redder means cheaper.



> Price distribution by the number of bedrooms:



> Price distribution by month:



> Price distribution by year:



> Price distribution by if the house/apartment is waterfront or not:



## Running

To run the model first create a new Python environment and activate it. I'm using [Anaconda](https://www.anaconda.com/) for that. The command bellow will

automatically setup the environment with conda and pipenv:

```shell

make env

```

Now install all the project dependencies:

```shell

make install-all

```

And run the model:

```shell

make model

```

After running you model, it will be saved inside `storage/housing-model.keras`.

To just run your recent created model and predict a random value from our data set,

use the following script:

```shell

make predict 

```

Remember that for this to work, you need to run `make model` first to create your model.