Trane issues

Setting the ML Type for 1 column in 1 table should set it for same column if present in another table

Add n_entities to generate function

Add n_problems to generate function

Add having in prediction problem generation

In the store dataset, the target entity is orderlines. Currently, we can generate a problem like - Predict the number of records with greater than 22.99 in next 1m days...

PatrikDurdevic

Auto sort values on time column (if the user has not)

gsheni

Add complex prediction problem generation with multiple filter operations

- All prediction problems must end with an aggregation op at the end (can have more than 1 aggregation op?) - They can have 1 or more filter operations

gsheni

Determine how denormalize information can be passed to table meta (primary key, foreign keys)

gsheni

Set primary key to be the index of dataframe in denormalize

gsheni

Trane
Trane copied to clipboard

Metadata

Fix op hash function to properly has using column name, type and threshold

Add better auto threshold generation

Setting the ML Type for 1 column in 1 table should set it for same column if present in another table

Add n_entities to generate function

Add n_problems to generate function

Add having in prediction problem generation

Auto sort values on time column (if the user has not)

Add complex prediction problem generation with multiple filter operations

Determine how denormalize information can be passed to table meta (primary key, foreign keys)

Set primary key to be the index of dataframe in denormalize

← Metadata

Owner

Metadata

Trane Trane copied to clipboard

Metadata

← Metadata

Owner

Metadata

Trane
Trane copied to clipboard