The HMMUnsupervisedLearner function outputs console messages and generates the following three tables through JDBC:
- Initial-state probability table
- State-transition probability table
- Emission probability table
Column | Data Type | Description |
---|---|---|
message | VARCHAR | Console message that describes the output. |
Column | Data Type | Description |
---|---|---|
model_attribute | BIGINT, INTEGER, or VARCHAR | The name of the column that contains the model attribute, specified by the ModelColumn attribute. |
state | VARCHAR | The hidden state of the learned HMM. |
probability | DOUBLE PRECISION | The initial state probability determined by the function. |
Column | Data Type | Description |
---|---|---|
model_attribute | BIGINT, INTEGER, or VARCHAR | The name of the column that contains the model attribute, specified by the ModelColumn attribute. |
from_state | VARCHAR | The hidden state of the learned HMM, from which a transition emanates. |
to_state | VARCHAR | The hidden state of the learned HMM, to which a transition is made. |
probability | DOUBLE PRECISION | The probability of a transition from the from_state to the to_state. |
Column | Data Type | Description |
---|---|---|
model_attribute | BIGINT, INTEGER, or VARCHAR | The name of the column that contains the model attribute, specified by the ModelColumn attribute. |
state | VARCHAR | The hidden state of the learned HMM. |
observed_key_attribute | VARCHAR | An observed symbol found in the observed_id column of the input table. |
probability | DOUBLE PRECISION | The probability of emitting an observed symbol given that the HMM is in a hidden state. |