Time series analysis comprises methods for analyzing time series data in order to extract meaningful statistics and other characteristics of the data. Time series forecasting is the use of a model to predict future values based on previously observed values.
Time series are widely used for non-stationary data, like economic, weather, stock price, and retail sales in this post. We will demonstrate different approaches for forecasting retail sales time series. Let’s get started!
-
Time Series Data Visualization
- Plotting of Pandas Df
- Adding title
- Adding Axis label
- X limits by slice
- X limit by argument
- Color and Style
- X ticks spacing
- Date formatting
- Major and Minor axis values
- Gridlines
-
Time Series EDA
- Introduction with time series data
- Time resampling
- Time downsampling/upsampling
- Time Shifting
- forward shift
- backward shift
- Rolling window mean
- Expanding window mean/cummulative mean
-
Time Series Data Analysis
- Introduction to statsmodels
- Hodrick Prescott filter - Trend/cyclical components
- Time Series Stationarity
- Augmented Dickey Fuller Test
- Granger Causality Tests
- Time series decomposition
- Additive/multiplicative models
- Moving Average
- Simple Exponentially weighted moving average(EWMA)
- Double EWMA
- Holt-Winters Method(Triple EWMA)
-
Time Series Forecasting Classical Methods
- Forecasting with Holts-Winter Method
- Autocorrelation function(ACF)
- Partial autocorrelation function(PACF)
- Autocovariance for 1D
- Autocorrelation for 1D
- Autoregressive model(AR(p))
- Autoregressive Moving Average(ARMA) Model
- Autoregressive Integreted Moving Average(ARIMA)
- Error/Trend/Seasonal Decomposition(ETS Decomposition)
- Seasonal Autoregressive Integreted Moving Averages(SARIMA)
- Seasonal AutoRegressive Integreted Moving Average with EXogenous Variable.
-
Time Series Forecasting with Deep Learning
- LSTMs for time series forecasting