From 5c400f40d258c989659daefab030efcb24cec823 Mon Sep 17 00:00:00 2001
From: gaxler <g.axler@gmail.com>
Date: Wed, 27 Jan 2021 19:36:38 -0800
Subject: [PATCH] Scaffold for turniing floats to hashable and fittinng to
 columns

---
 src/preprocessing/categorical_encoders.rs | 27 +++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 src/preprocessing/categorical_encoders.rs

diff --git a/src/preprocessing/categorical_encoders.rs b/src/preprocessing/categorical_encoders.rs
new file mode 100644
index 0000000..828eeef
--- /dev/null
+++ b/src/preprocessing/categorical_encoders.rs
@@ -0,0 +1,27 @@
+#![allow(clippy::ptr_arg)]
+//! # Encode categorical features as a one-hot numeric array.
+
+use crate::error::Failed;
+use crate::linalg::{BaseVector, Matrix};
+use crate::math::num::RealNumber;
+
+use crate::preprocessing::series_encoder::SeriesOneHotEncoder;
+
+pub type HashableReal = u32;
+
+fn hashable_num<T: RealNumber>(v: &T) -> HashableReal {
+    // gaxler: If first 32 bits are the same, assume numbers are the same for the categorical coercion
+    v.to_f32_bits()
+}
+
+#[derive(Debug, Clone)]
+pub struct OneHotEncoderParams {
+    pub categorical_param_idxs: Option<Vec<usize>>,
+    pub infer_categorical: bool,
+}
+/// Encode Categorical variavbles of data matrix to one-hot
+pub struct OneHotEncoder {
+    series_encoders: Vec<SeriesOneHotEncoder<HashableReal>>,
+    categorical_param_idxs: Vec<usize>,
+}
+