Commit a9db2c6a authored by DAUXAIS Yann's avatar DAUXAIS Yann

add discriminant episode mining in README

parent a01cd778
......@@ -11,12 +11,12 @@ The extraction is done from set of temporal sequences.
- **Discriminant chronicle mining**: The main purpose of DCM is to extract
discriminant chronicles from a positive dataset in comparison to a negative dataset.
A chronicle will be considered discriminant if its support in the positive dataset
is greater than `$g_{min}$` times its support in the negative dataset.
The parameter `$g_{min}$` has to be defined by the user before the run.
is greater than $g_{min}$ times its support in the negative dataset.
The parameter $g_{min}$ has to be defined by the user before the run.
The implementation of this task in DCM is not complete as it will not extract
the whole set of discriminant chronicles.
This task has been detailed in
[**Discriminant chronicle mining: Application to care pathways**](#disc).
[**Discriminant chronicle mining: Application to care pathways**](#disc).
- **Frequent chronicle mining**: DCM contains also an implementation of the frequent
chronicle mining task. The implementation of this task is complete according to the
definition that the bounds used for the temporal intervals of the chronicles must
......@@ -43,7 +43,7 @@ make
cd ..
```
If the compilation is successful, the executable **_Extract_** will be present in the **_bin_**
If the compilation is successful, the executable **_DCM_** will be present in the **_bin_**
directory.
......@@ -71,7 +71,7 @@ More information on this base in the [citations part](#bide-d).
The sequences in those datasets are represented using the line format.
The uses of the command
`./bin/Extract examples/ECG/d214lbbb_H141.dat -d examples/ECG/d214pvc.dat -f 0.8 -g 2`
`./bin/DCM examples/ECG/d214lbbb_H141.dat -d examples/ECG/d214pvc.dat -f 0.8 -g 2`
will return 4 discriminant chronicles:
```
......@@ -130,6 +130,21 @@ first and the second occurrences of `qrs[abnormal]`. The temporal interval is de
`"qrs[abnormal]" [686, 881] "qrs[abnormal]"`.
Finally, `f:125/20` corresponds to a positive support of 125 and a negative support of 20.
The discriminant episodes extracted with the `-e` option are represented like the chronicles.
For example, the command line `./bin/DCM examples/BIDE-D/blocks/stack.dat -d examples/BIDE-D/blocks/unstack.dat -f 0.9 -g 2 -e --maxcs 3` will produce episodes such that:
```
C: {["ATTACHED-GREEN-REDe", "CONTACTS-GREEN-REDd", "CONTACTS-GREEN-REDe"]}
0, 1: (1, inf)
0, 2: (1, inf)
1, 2: (-inf, inf)
f: 30/1
```
The temporal constraints of this episode describe that `CONTACTS-GREEN-REDd` and `CONTACTS-GREEN-REDe` occur after `ATTACHED-GREEN-REDe`.
The extracted temporal constraints are here `(1, inf)` and they are interpreted as strictly after.
Temporal constraints of the form `(0, inf)` could also be extracted and, in this case, are interpreted as not before are at least at same time.
## <a name="args"></a>Argument options
The DCM parameters are listed in the help of the executable.
......@@ -164,7 +179,9 @@ General Options:
Discriminant chronicles Options:
-g [ --gmin ] arg Minimal growth threshold
default : 2
-e [ --episode ] Extract discriminant partially ordered patterns
(episodes) instead of chronicles
Frequent chronicles Options:
-a [ --all_different ] Extract chronicles with multisets containing at most
one occurrence of an event
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment