Bots From Extension: cfxai_classification
CloudFabrix ML - Classification
This extension provides 2 bots.
Bot @cfxsml:classify-predict
Bot Position In Pipeline: Sink
CFX ML Classification prediction
This bot expects a Restricted CFXQL.
Each parameter may be specified using '=' operator and AND logical operation
Following are the parameters expected for this Bot
| Parameter Name | Type | Default Value | Description |
|---|---|---|---|
| nlp_columns | Text | Comma separated list of columns to be vectorized using NLP techniques | |
| category_columns | Text | Comma separated list of category columns (at least one of nlp or category must be specified) | |
| numeric_columns | Text | Comma separated list of Numeric columns (at least one of nlp or category or numeric must be specified) |
|
| model_name | Text | default | Name of the model for trained data. Default model name is 'default' |
| remove_vars | Text | yes | De-variabilize NLP columns. Allowed values 'yes' or 'no' |
Example Pipelines Using this Bot
Bot @cfxsml:classify-train
Bot Position In Pipeline: Sink
CFX ML Classification training
This bot expects a Restricted CFXQL.
Each parameter may be specified using '=' operator and AND logical operation
Following are the parameters expected for this Bot
| Parameter Name | Type | Default Value | Description |
|---|---|---|---|
| nlp_columns | Text | Comma separated list of columns to be vectorized using NLP techniques | |
| category_columns | Text | Comma separated list of category columns (at least one of nlp or category must be specified) | |
| numeric_columns | Text | Comma separated list of numeric columns | |
| target_column* | Text | Column or Columns that identifies the Class label. Can be single or multiplr (comma separated list) |
|
| model_name | Text | default | Name of the model for trained data. Default model name is 'default' |
| remove_vars | Text | yes | De-variabilize NLP columns. Allowed values 'yes' or 'no' |
| job_name | Text | default | Name of the Job to be created. Default job name is 'default' |
| skip_errors | Text | no | Specify 'yes' or 'no'. If 'yes', do not bailout if regression results in error. Check 'reason' field when it continues with an error. |