AI / ML·shipped
No-Code ML Environment
Flask app that wraps common supervised-learning pipelines behind a UI: CSV upload, column picker, sklearn regressors or Keras LSTM, then MAE/MSE/RMSE plus a prediction plot.
Date2022-03
Reading TimeN/A
Statusshipped
StackPython, Flask, scikit-learn+2
What it does
Domain experts often need a regression answer without writing pandas. This app:
- Accepts a CSV (or URL)
- Lets you drop columns and choose a target
- Trains a selected model (sklearn regressors or LSTM)
- Returns error metrics, a plot, and a downloadable model file
flowchart LR
A[CSV / URL] --> B[Preview and drop columns]
B --> C[Target + model pick]
C --> D[Train]
D --> E[Metrics + plot + download]Tradeoffs worth knowing
- LSTM in the same dropdown as linear regression is powerful and easy to misuse — sequential framing is not obvious to every user.
- A single global training object means concurrent users would collide. Fine for a solo demo; production needs per-session state or a job queue.
What it demonstrates
- Product framing of ML: hide the library surface, expose the decisions people actually make
- Composing preprocess → split → fit → metrics → viz as separate steps
- Honesty about demo vs multi-user product gaps