https://github.com/jamesnw/goshen-trains

https://github.com/jamesnw/goshen-trains

Last synced: about 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/jamesnw/goshen-trains
• Owner: jamesnw
• Created: 2017-11-06T13:22:13.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2022-12-07T23:46:23.000Z (about 2 years ago)
• Last Synced: 2023-04-16T07:17:29.967Z (almost 2 years ago)
• Language: Jupyter Notebook
• Size: 3.24 MB
• Stars: 1
• Watchers: 1
• Forks: 2
• Open Issues: 13
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Goshen Trains

Check it out live at http://is-it-training.herokuapp.com/.

This project uses data collected at https://sites.google.com/site/goshentrains/ by Douglas Miller. Check out his site to see some really interesting techniques and other analysis.

## Files

### Load

This file scrapes the directory listing of the csv for a list of csvs. It then compares the list against the list of csvs already pulled, and adds any new ones to the dataframe. The dataframe is saved to `data/trains.pkl`, and can be loaded into other files.

### MakeModel

This file loads the data, preprocesses it, and uses a Random Forest Classifier to build a model. It saves the model to the models folder, with some identifiers in the name about how the model was built and the date. It also outputs some model accuracy analysis.

### Explore

Some basic data exploration

### PredictForTime

Loads the model, and predicts whether a train is present or not for a given time (default now)

### Flask app

```

$ python app.py

```

Open http://localhost:5000/prediction/

### Deploying to heroku

First, install the heroku command line tools.

Setup:

```

$ heroku login

$ heroku git:remote -a is-it-training

```

Deploying:

```

$ git push heroku master

```