You guys have asked for it, so here's my StreamProphet app in early Beta! 🤗
With this app you can:
Connect to Google Search Console and visualise your forecasted SEO traffic in just a few clicks
Visualise your time series' trends and seasonality
Export your predictions to CSV and your models to JSON! 🔥
How to get started!
Click the 'sign-in with Google' button to reach the consent screen
Copy the Oauth token and paste it back in the app
Type the Web Property
Define your forecast horizon (from 1 month to 1 year)
Press the 'Fetch GSC data & get predictions' button! 🔥
📈 Checking predictions
Once that's done, you can then visualise past data and predictions in the right-hand side chart
Left-hand side charts show you the decomposed trend, weekly and yearly seasonality (when available) of the time series
You can export predictions via CSV + your forecast model via JSON
🛠️ Here’s the stack I used:
Web framework: the mighty @streamlit! 🎈
Forecasting library: @fb_engineering Prophet
PyStan
Pandas
100% Python! 🐍🔥
🌅 Early Beta
StreamProphet's still in early beta, with possible rough edges! You. Have. Been. Warned! 😊
Issues, feedback or suggestions are welcome. Head-off to my Gitter page for a chat:
📝 To-Dos
Add session state so parameters can be tweaked w.o. having to re-authenticate
Add seasonality parameters
Holidays import so they can be factored in the forecast
Add cross-validation to optimise parameters
More forecasting models: ARIMA, HWAAS and more!🔥
🙌 Shout-outs!
Kudos to @JoshCarty and @_okld for their precious help!
Thanks also to @jakubmotyka, @KorayGubur, @periklispapanik and @RichardFergie for that early testing session! Lastly, this app is completely free. If it's useful to you, you can buy me a coffee to support my work! 🙏
Is there any git repo?