feat: Populate code vectors from cache csv file

mix.exs

@@ -65,7 +65,8 @@ defmodule MedicalTranscription.MixProject do
       {:progress_bar, "~> 3.0"},
       {:membrane_core, "~> 1.0"},
       {:membrane_raw_audio_format, "~> 0.12.0"},
-      {:kino, "~> 0.12.3"}
+      {:kino, "~> 0.12.3"},
+      {:csv, "~> 3.2"}
       # {:membrane_portaudio_plugin, "~> 0.18.0"}
     ]
   end

mix.lock

@@ -17,6 +17,7 @@
   "cowboy_telemetry": {:hex, :cowboy_telemetry, "0.4.0", "f239f68b588efa7707abce16a84d0d2acf3a0f50571f8bb7f56a15865aae820c", [:rebar3], [{:cowboy, "~> 2.7", [hex: :cowboy, repo: "hexpm", optional: false]}, {:telemetry, "~> 1.0", [hex: :telemetry, repo: "hexpm", optional: false]}], "hexpm", "7d98bac1ee4565d31b62d59f8823dfd8356a169e7fcbb83831b8a5397404c9de"},
   "cowlib": {:hex, :cowlib, "2.12.1", "a9fa9a625f1d2025fe6b462cb865881329b5caff8f1854d1cbc9f9533f00e1e1", [:make, :rebar3], [], "hexpm", "163b73f6367a7341b33c794c4e88e7dbfe6498ac42dcd69ef44c5bc5507c8db0"},
   "credo": {:hex, :credo, "1.7.3", "05bb11eaf2f2b8db370ecaa6a6bda2ec49b2acd5e0418bc106b73b07128c0436", [:mix], [{:bunt, "~> 0.2.1 or ~> 1.0", [hex: :bunt, repo: "hexpm", optional: false]}, {:file_system, "~> 0.2 or ~> 1.0", [hex: :file_system, repo: "hexpm", optional: false]}, {:jason, "~> 1.0", [hex: :jason, repo: "hexpm", optional: false]}], "hexpm", "35ea675a094c934c22fb1dca3696f3c31f2728ae6ef5a53b5d648c11180a4535"},
+  "csv": {:hex, :csv, "3.2.1", "6d401f1ed33acb2627682a9ab6021e96d33ca6c1c6bccc243d8f7e2197d032f5", [:mix], [], "hexpm", "8f55a0524923ae49e97ff2642122a2ce7c61e159e7fe1184670b2ce847aee6c8"},
   "db_connection": {:hex, :db_connection, "2.6.0", "77d835c472b5b67fc4f29556dee74bf511bbafecdcaf98c27d27fa5918152086", [:mix], [{:telemetry, "~> 0.4 or ~> 1.0", [hex: :telemetry, repo: "hexpm", optional: false]}], "hexpm", "c2f992d15725e721ec7fbc1189d4ecdb8afef76648c746a8e1cad35e3b8a35f3"},
   "decimal": {:hex, :decimal, "2.1.1", "5611dca5d4b2c3dd497dec8f68751f1f1a54755e8ed2a966c2633cf885973ad6", [:mix], [], "hexpm", "53cfe5f497ed0e7771ae1a475575603d77425099ba5faef9394932b35020ffcc"},
   "dns_cluster": {:hex, :dns_cluster, "0.1.1", "73b4b2c3ec692f8a64276c43f8c929733a9ab9ac48c34e4c0b3d9d1b5cd69155", [:mix], [], "hexpm", "03a3f6ff16dcbb53e219b99c7af6aab29eb6b88acf80164b4bd76ac18dc890b3"},

priv/repo/seeds.exs

@@ -9,3 +9,31 @@
 #
 # 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)
+
+MedicalTranscription.Repo.insert_all(
+  MedicalTranscription.Coding.CodeVector,
+  code_vectors
+)

test/support/fixtures/code_vectors_fixtures.ex

@@ -0,0 +1,39 @@
+defmodule MedicalTranscription.CodeVectorsFixtures do
+  @moduledoc """
+  This module defines test helpers for creating %CodeVector{}
+  entities via the `MedicalTranscription.Coding` context.
+  """
+
+  @doc """
+  Insert code vectors from cached csv file.
+  """
+  def insert_code_vector_fixtures(attrs \\ %{}) do
+    code_vectors =
+      "../../../code_vectors.csv"
+      |> Path.expand(__DIR__)
+      |> File.stream!()
+      |> CSV.decode(headers: true)
+      |> Enum.take(5)
+      |> 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)
+
+    MedicalTranscription.Repo.insert_all(
+      MedicalTranscription.Coding.CodeVector,
+      code_vectors
+    )
+  end
+end