The way we treat quantity units (as of February 26th 2018)

The retranscribed variable is “quantity_unit” (1,538 different values).

 Orthographic Normalization

The file “Units_Normalisation_Orthographique.dta” establishes a correspondance between the variable “quantity_unit” and the variable “quantity_unit_ortho” (701 values). 210,000 observations have “livres” in “quantity_unit_ortho” and 160,000 have “unité manquante” (out of 510,000).

Simplification and single-key conversion

The file “Units_Normalisation_Métrique1” establishes a correspondance between the variable “quantity_unit_ortho” and either
– 1. the variables “quantity_unit_ajustees” (simplifying the “quantity_unit_ortho”), “u_conv” (a metric unit of quantity) and “q_conv” (the number of u_conv in “quantity_unit_ortho”). e.g. “quantity_unit_orth” “douzaine de paires” has “douzaine de paires” as “quantity_unit_ajustees”, “pièce” as u_conv and “24” as “q_conv”.
– 2. a variable “needs_more_details” which indicate that we cannot know the metric equivalent without using more variables.

Simplification and Multi-key conversion

The file “Units_Normalisation_Métrique2” establishes a correspondance between :
exportsimports + pays_grouping + direction + marchandises_simplification + quantity_unit_ortho and “quantity_unit_ajustees” (simplifying the “quantity_unit_ortho”), “u_conv” (a metric unit of quantity) and “q_conv” (the number of u_conv in “quantity_unit_ortho”).


Laisser un commentaire

Votre adresse de messagerie ne sera pas publiée. Les champs obligatoires sont indiqués avec *

Ce site utilise Akismet pour réduire les indésirables. En savoir plus sur comment les données de vos commentaires sont utilisées.