Skip to content
This repository has been archived by the owner on Sep 3, 2020. It is now read-only.

Model.json changes #1

Open
brichnim opened this issue Oct 8, 2018 · 0 comments
Open

Model.json changes #1

brichnim opened this issue Oct 8, 2018 · 0 comments

Comments

@brichnim
Copy link

brichnim commented Oct 8, 2018

Hello,
I am currently testing the best drug selection Watson app. I followed the steps described in https://github.com/pmservice/best-heart-drug-selection/blob/master/README.md.
For this app example, everything runs very well
However, I adapt the test the code of best-heart-drug-selection to another problem which is the heart disease prediction. So, I changed in the source code the model.json (in /config) to correspond to my model schema, as follows:

{
"model-schema": [
{"name": "AGE", "type": "decimal(4,1)"},
{"name": "SEX", "type": "decimal(2,1)"},
{"name": "chest_pain", "type": "decimal(12,6)"},
{"name": "blood pressure", "type": "decimal(12,6)"},
{"name": "serum_cholestoral", "type": "decimal(12,6)"},
{"name": "fasting_blood_sugar", "type": "decimal(12,6)"},
{"name": "electrocardiographic", "type": "decimal(12,6)"},
{"name": "max_heart_rate", "type": "decimal(12,6)"},
{"name": "induced_angina", "type": "decimal(12,6)"},
{"name": "ST_depression", "type": "decimal(12,6)"},
{"name": "slope", "type": "decimal(12,6)"},
{"name": "vessels", "type": "decimal(12,6)"},
{"name": "thal", "type": "decimal(12,6)"}
],
"label": "diagnosis",
"label-values": [
{"title": "Level 0", "value": 0},
{"title": "Level 1", "value": 1},
{"title": "Level 2", "value": 2},
{"title": "Level 3", "value": 3},
{"title": "Level 4", "value": 4}
],
"model-input": [
{"name": "Gregory", "icon": "gregory", "data": [63.0,1.0,1.0,145.0,233.0,1.0,2.0,150.0,0.0,2.3,3.0,0.0,6.0]},
{"name": "Alice", "icon": "alice", "data": [41.0,0.0,2.0,130.0,204.0,0.0,2.0,172.0,0.0,1.4,1.0,0.0,3.0]},
{"name": "Joanna", "icon": "joanna", "data": [48.0,0.0,3.0,130.0,275.0,0.0,0.0,139.0,0.0,0.2,1.0,0.0,3.0]},
{"name": "Alexander", "icon": "alexander", "data": [53.0,1.0,4.0,140.0,203.0,1.0,2.0,155.0,1.0,3.1,3.0,0.0,7.0]},
{"name": "Bill", "icon": "alexander", "data": [52.0,1.0,3.0,172.0,199.0,1.0,0.0,162.0,0.0,0.5,1.0,0.0,7.0]},
{"name": "Olivia", "icon": "alice", "data": [65.0,0.0,4.0,150.0,225.0,0.0,2.0,114.0,0.0,1.0,2.0,3.0,7.0]},
{"name": "Mark", "icon": "gregory", "data": [59.0,1.0,3.0,150.0,212.0,1.0,0.0,157.0,0.0,1.6,1.0,0.0,3.0]},
{"name": "Emma", "icon": "joanna", "data": [61.0,0.0,4.0,130.0,330.0,0.0,2.0,169.0,0.0,0.0,1.0,0.0,3.0]}
],
"model-prediction-mapping": {
"0": "Level 0",
"1": "Level 1",
"2": "Level 2",
"3": "Level 3",
"4": "Level 4"
}
}

I deployed the corresponding model for heart disease that is actually displayed in my app screen (in addition to the drug selection deployed model). However, I can not select it because it says (when I put the cursor on): "Data schema of this model is incompatible with data schema expected by the application".

What should I change too in the app code to make it working with the suitable deployed model and schema.

PS: I prefer to make it working via the devops and not locally.
Thank you so much for your help.

Manel

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant