Speaker notes and additional resources for the Python Time Series course
- TimeStamp Object: Stores a date / time value. Plays nice with Python datetime functionality.
- TiemDelta: Stores a time period value.
- DateTimeIndex: A series of individual TimeStamp objects. Can be incorporated into a DataFrame, ideally as an index.
- Resampling: Transforming a time series to change the frequency. There are two types of resampling:
- Upsampling: Increasing the frequency of the samples
- Downsampliong: Decreasing the frequency of the samples
- Decomposition: Breaking the time series down into the underliying componenents (e.g. trend, seasonal, residuals)
- Autocorrelation: Shows the degree of similarity between the values in a time series.
- Python Date / Time Formats
- Pandas Frequency Codes
- Pandas Time Series / Date Functionality
- Pandas Date Offset
- Pandas Timestamp Reference
- Pandas date_range Reference
- Pandas Timedelta Reference
- Pandas Date Offset Reference
- Python datetime Reference
- What is Autocorrelation?
- Autocorrelation Plot (Correlogram)
- Autocorrelation in Python
- A Gentle Introduction to Exponential Smoothing
- Introduction to Simple Exponential Smoothing (SES)
- Holt Winters Forecasting for Dummies
- Autoregression Models for Time Series Forecasting With Python
- Time Series Analysis in Python
- A Gentle Introduction to Autocorrelation and Partial Autocorrelation
- ARIMA models in Python
- What a p-value tells you about Statistical Data
- How to read and write scientific notation
- A Gentle Introduction to Box-Jenkins Models
- Forecasting: Principles and Practice Book
- DataQuest Time Series Tutorial
- A comprehensive beginner’s guide to create a Time Series Forecast (with Codes in Python)
- Time Series Forecasting in Python Cheat Sheet
- Kaggle Time Series Analysis in Python (Part 1)
- Kaggle Time Series Analysis with Facebook Prophet
- Example Notebook with Prophet