| # Script for populating the database. You can run it as: | |
| # | |
| # mix run priv/repo/seeds.exs | |
| # | |
| # Inside the script, you can read and write to any of your | |
| # repositories directly: | |
| # | |
| # Medicode.Repo.insert!(%Medicode.SomeSchema{}) | |
| # | |
| # We recommend using the bang functions (`insert!`, `update!` | |
| # and so on) as they will fail if something goes wrong. | |
| # Populate code_vectors with cached version of ICD-9 codes | |
| code_vectors = | |
| "../../code_vectors.csv" | |
| |> Path.expand(__DIR__) | |
| |> File.stream!() | |
| |> CSV.decode(headers: true) | |
| |> Enum.map(fn {:ok, | |
| %{ | |
| "code" => code, | |
| "description" => description, | |
| "description_vector" => description_vector | |
| }} -> | |
| vector = | |
| description_vector | |
| |> String.replace_prefix("[", "") | |
| |> String.replace_suffix("]", "") | |
| |> String.split(",") | |
| |> Enum.map(&String.to_float/1) | |
| |> Pgvector.new() | |
| %{code: code, description: description, description_vector: vector} | |
| end) | |
| Medicode.Repo.insert_all( | |
| Medicode.Coding.CodeVector, | |
| code_vectors | |
| ) | |