Methods and Tools for Time Series Data Science Problems
summary
Shows a concrete pipeline: data ingested by Telegraf execd processor, fed to a Python script using statsmodels to apply Holt Winters (double/triple exponential smoothing), forecasting with as few as ~10 points and predicting 3–4 (demo shows 28) steps ahead. Residuals produce simple anomaly detection (MAD and thresholds). A brewing temperature OCR example and an InfluxDB Cloud demo run end-to-end and produce usable forecasts and alerts. IOx and notebook integrations are mentioned.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 1:41Time series tools overview
- 5:41Time series and databases
- 7:26InfluxDB and Telegraf
- 10:39Forecasting with Telegraf
- 24:06Flux language
- 28:48Jupyter and Zeppelin
- 31:18Python libraries
- 33:23Live forecasting demo
- 37:39Learning resources
- 38:43Q&A
related talks
30mMethods & Tools For Time Series Data Science Problems With InfluxDB
28mTime series data science problems with InfluxDB
26mTime Series Analysis in Python: Easy Tools for Scientific Insight
01h 43m(Serious) Time for Time Series
01h 16mPredicting Weather Patterns using Time Series ML
19mForecasting for Everyone - Foundation Models and the Future of Time Series Prediction
01h 18m(Serious) Time for Time Series
29mA dive into time series for the energy sector