From d18871dd06149b6033b31b03c19a3e25e8f10e4f Mon Sep 17 00:00:00 2001
From: Nicolas Barthes <nicolas.barthes@cnrs.fr>
Date: Fri, 19 Apr 2024 13:56:34 +0200
Subject: [PATCH] LWPLSR as a documented class
---
docs/index.md | 5 ++-
docs/model_creation.md | 7 +++
mkdocs.yml | 1 +
src/Class_Mod/HDBSCAN_Clustering.py | 3 +-
src/Class_Mod/LWPLSR_.py | 69 ++++++++++++++++++++---------
5 files changed, 61 insertions(+), 24 deletions(-)
create mode 100644 docs/model_creation.md
diff --git a/docs/index.md b/docs/index.md
index 17a491a..10504b2 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -8,4 +8,7 @@ This workflow aims at ...
## Clustering
[K-Means](Clustering.md#k-means-clustering)
-[HDBSCAN](Clustering.md#hdbscan-clustering)
\ No newline at end of file
+[HDBSCAN](Clustering.md#hdbscan-clustering)
+
+## Models Creation
+[lwPlsR from Jchemo (Julia)](model_creation.md)
\ No newline at end of file
diff --git a/docs/model_creation.md b/docs/model_creation.md
new file mode 100644
index 0000000..09695a6
--- /dev/null
+++ b/docs/model_creation.md
@@ -0,0 +1,7 @@
+# Models creation
+
+## PLSR from Pinard (scikit learn)
+::: src.Class_Mod.KMEANS_.Sk_Kmeans
+
+## lwPlsR from Jchemo (Julia)
+::: src.Class_Mod.LWPLSR_.LWPLSR
\ No newline at end of file
diff --git a/mkdocs.yml b/mkdocs.yml
index fd8d5d9..445e28b 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -4,6 +4,7 @@ nav:
- Home: 'index.md'
- Dimensionality Reduction: 'Dimensionality_Reduction.md'
- Clustering Methods: 'Clustering.md'
+ - Models Creation: 'model_creation.md'
theme:
diff --git a/src/Class_Mod/HDBSCAN_Clustering.py b/src/Class_Mod/HDBSCAN_Clustering.py
index 9f64bce..ccecf5f 100644
--- a/src/Class_Mod/HDBSCAN_Clustering.py
+++ b/src/Class_Mod/HDBSCAN_Clustering.py
@@ -132,7 +132,8 @@ class Hdbscan:
dist_function (func): function to determine distance between objects
func args must be [np.array, np.array] where each array is a point
- Returns: mutual_reachability (float)
+ Returns:
+ mutual_reachability (float)
mutual reachability between points i and j
"""
diff --git a/src/Class_Mod/LWPLSR_.py b/src/Class_Mod/LWPLSR_.py
index 18c6755..b5c7e49 100644
--- a/src/Class_Mod/LWPLSR_.py
+++ b/src/Class_Mod/LWPLSR_.py
@@ -1,25 +1,50 @@
from Packages import *
from Class_Mod.Miscellaneous import *
-def LWPLSR(x_train, x_test, y_train, y_test):
- # prepare to send dataframes to julia and Jchemo
- Main.x_train,Main.y_train,Main.x_test,Main.y_test = x_train, y_train, x_test, y_test
- Main.eval("""
- #convert python pd.dataframes to julia dataframes
- x_train_j = Main.x_train |> Pandas.DataFrame|> DataFrames.DataFrame;
- y_train_j = Main.y_train |> Pandas.DataFrame|> DataFrames.DataFrame;
- x_test_j = Main.x_test |> Pandas.DataFrame|> DataFrames.DataFrame;
- y_test_j = Main.y_test |> Pandas.DataFrame|> DataFrames.DataFrame;
- # Compute model
- nlvdis = 5 ; metric = :mah
- h = 1 ; k = 200 ; nlv = 15 #; scal = true
- mod = Main.Jchemo.model(Main.Jchemo.lwplsr; nlvdis, metric, h, k, nlv)
- Main.Jchemo.fit!(mod, X_train_j, y_train_j)
- # predictions on test data calculation
- res = Main.Jchemo.predict(mod, X_test_j) ;
- score = Main.Jchemo.rmsep(res.pred, y_test_j)
- resjp = Pandas.DataFrame(res.pred);
- """)
- score = Main.score
- predicted_results_on_test = pd.DataFrame(Main.resjp)
- return score, predicted_results_on_test
\ No newline at end of file
+class LWPLSR:
+ """
+ The UMAP dimension reduction algorithm from scikit learn
+ """
+ def __init__(self, x_train, x_test, y_train, y_test):
+ """Initiate the LWPLSR and prepare data for Julia computing."""
+ self.x_train, self.y_train, self.x_test, self.y_test = x_train, x_test, y_train, y_test
+ # prepare to send dataframes to julia and Jchemo
+ self.Main.x_train,self.Main.y_train,self.Main.x_test,self.Main.y_test = self.x_train, self.y_train, self.x_test, self.y_test
+
+ def Jchemo_lwplsr(self):
+ """Send data to Julia to compute lwplsr.
+
+ Args:
+ self.Main.x_train (DataFrame):
+ self.Main.y_train (DataFrame):
+ self.Main.x_test (DataFrame):
+ self.Main.y_test (DataFrame):
+
+ Returns:
+ self.scores (DataFrame): various metrics and scores
+ self.predicted_results_on_test (DataFrame):
+ """
+ # launch Julia Jchemo lwplsr
+ Main.eval("""
+ #convert python pd.dataframes to julia dataframes
+ x_train_j = self.Main.x_train |> Pandas.DataFrame|> DataFrames.DataFrame;
+ y_train_j = self.Main.y_train |> Pandas.DataFrame|> DataFrames.DataFrame;
+ x_test_j = self.Main.x_test |> Pandas.DataFrame|> DataFrames.DataFrame;
+ y_test_j = self.Main.y_test |> Pandas.DataFrame|> DataFrames.DataFrame;
+ # Compute model
+ nlvdis = 5 ; metric = :mah
+ h = 1 ; k = 200 ; nlv = 15 #; scal = true
+ mod = Main.Jchemo.model(Main.Jchemo.lwplsr; nlvdis, metric, h, k, nlv)
+ Main.Jchemo.fit!(mod, X_train_j, y_train_j)
+ # predictions on test data calculation
+ res = Main.Jchemo.predict(mod, X_test_j) ;
+ scores = Main.Jchemo.mse(res.pred, y_test_j)
+ scoresjp = Pandas.DataFrame(scores);
+ resjp = Pandas.DataFrame(res.pred);
+ """)
+ self.scores = self.Main.scoresjp
+ self.predicted_results_on_test = pd.DataFrame(self.Main.resjp)
+
+ @property
+ def scores_(self):
+ return self.scores, self.predicted_results_on_test
\ No newline at end of file
--
GitLab