| thresh_rel | float | `0.1` | Minimum relative difference between two values to consider the latter as a break candidate. See condition (1) |
| thresh_abs | float | `0.01` | Minimum absolute difference between two values to consider the latter as a break candidate. See condition (2) |
| first_der_factor | float | `10` | Multiplication factor for arithmetic mean of the first derivatives surrounding a break candidate. See condition (3). |
| first_der_factor | float | `10` | Multiplication factor for the arithmetic mean of the first derivatives surrounding a break candidate. See condition (3). |
| first_der_window | [offset string](docs/ParameterDescriptions.md#offset-strings) | `"12h"` | Window around a break candidate for which the arithmetic mean is calculated. See condition (3) |
| scnd_der_ratio_range | float | `0.05` | Range of the area, covering all the values of the second derivatives quotient, that are regarded "sufficiently close to 1" for signifying a break. See condition (5). |
| scnd_der_ratio_thresh | float | `10.0` | Threshold for the ratio of the second derivatives succeeding a break. See condition (5). |
...
...
@@ -30,19 +30,27 @@ The function flags breaks (jumps/drops) by evaluating the derivatives of a time
A value $`x_k`$ of a time series $`x_t`$ with timestamps $`t_i`$, is considered to be a break, if:
1. $`x_k`$ represents a sufficiently large relative jump:
* $`|\frac{x_k - x_{k-1}}{x_k}| >`$ `thresh_rel`
$`|\frac{x_k - x_{k-1}}{x_k}| >`$ `thresh_rel`
2. $`x_k`$ represents a sufficient absolute jump:
* $`|x_k - x_{k-1}| >`$ `thresh_abs`
3. The dataset $`X = x_i, ..., x_{k-1}, x_{k+1}, ..., x_j`$, with
$`|t_{k-1} - t_i| = |t_j - t_{k+1}| =`$ `first_der_window` fulfills the following condition: