Analysis¶
Details and available models¶
See the API documentation for further details on available analysis tools:
|
Enum for different aggregation modes. |
|
ModelRelevanceTable builds feature relevance table using feature relevance values obtained from model. |
|
Abstract class for relevance table computation. |
|
StatisticsRelevanceTable builds feature relevance table with tsfresh statistics. |
|
Calculate distance for |
|
Autocorrelation and partial autocorrelation plot for multiple timeseries. |
Cross-correlation plot between multiple timeseries. |
|
Distribution of z-values grouped by segments and time frequency. |
|
|
Find trend change points using ruptures models. |
|
Compute outliers according to density rule. |
Get point outliers in time series using histogram model. |
|
|
Get point outliers in time series using median model (estimation model-based method). |
|
Get point outliers in time series using prediction intervals (estimation model-based method). |
Compute pairwise correlation of timeseries for selected segments. |
|
|
Calculate relevance table with feature importance from model. |
Get residuals for further analysis. |
|
|
Calculate relevance table with p-values from tsfresh. |
|
Plot per-segment metrics distribution. |
Plot a time series with indicated anomalies. |
|
|
Plot a time series with indicated anomalies. |
Plot targets and forecast for backtest pipeline. |
|
Plot targets and forecast for backtest pipeline using plotly. |
|
|
Plot a time series with indicated change points. |
Plot clusters [with centroids]. |
|
Plot pairwise correlation heatmap for selected segments. |
|
|
Plot relevance of the features. |
Plot of prediction for forecast pipeline. |
|
|
Plot of prediction and its components. |
Plot holidays for segments. |
|
Plot the result of imputation by a given imputer. |
|
Plot barplot with per-segment metrics. |
|
Plot the periodogram using |
|
Plot residuals for predictions from backtest against some feature. |
|
|
Plot segments with their trend change points. |
Plot series and trend from trend transform for this series. |
|
|
Plot scatter plot with forecasted/actual values for segments. |
|
Plot Q-Q plots for segments. |
Plot each season on one canvas for each segment. |
|
Plot STL decomposition for segments. |