From 9838ad8f2181e1ba1cb4be44ec635d21d7968a8d Mon Sep 17 00:00:00 2001
From: Francois Vieille <vieille.francois@gmail.com>
Date: Sun, 31 Mar 2019 18:05:09 +0200
Subject: [PATCH] etapes du clustering simple : PCA + Kmeans + CAH

---
 iss/clustering/.gitkeep               |  0
 iss/clustering/AbstractClustering.py  | 12 ++++++
 iss/clustering/ClassicalClustering.py | 58 +++++++++++++++++++++++++++
 iss/clustering/__init__.py            |  1 +
 4 files changed, 71 insertions(+)
 create mode 100644 iss/clustering/.gitkeep
 create mode 100644 iss/clustering/AbstractClustering.py
 create mode 100644 iss/clustering/ClassicalClustering.py
 create mode 100644 iss/clustering/__init__.py

diff --git a/iss/clustering/.gitkeep b/iss/clustering/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/iss/clustering/AbstractClustering.py b/iss/clustering/AbstractClustering.py
new file mode 100644
index 0000000..6906082
--- /dev/null
+++ b/iss/clustering/AbstractClustering.py
@@ -0,0 +1,12 @@
+# -*- coding: utf-8 -*-
+
+class AbstractClustering:
+
+	def __init__(config, pictures_id, pictures_np):
+
+		self.config = config
+		self.pictures_id = pictures_id
+		self.pictures_np = pictures_np
+
+
+	
\ No newline at end of file
diff --git a/iss/clustering/ClassicalClustering.py b/iss/clustering/ClassicalClustering.py
new file mode 100644
index 0000000..1e62ce3
--- /dev/null
+++ b/iss/clustering/ClassicalClustering.py
@@ -0,0 +1,58 @@
+from iss.clustering import AbstractClustering
+from sklearn.decomposition import PCA
+from sklearn.cluster import KMeans
+from sklearn.cluster import AgglomerativeClustering
+
+class ClassicalClustering(AbstractClustering):
+
+	def __init__(config, pictures_id, pictures_np):
+
+		self.pca_fit = None
+		self.pca_args = self.config['PCA']
+		self.pca_reduction = None
+
+		self.kmeans_fit = None
+		self.kmeans_args = self.config['kmeans']
+		self.kmeans_labels = None
+		self.kmeans_centers = []
+
+		self.cah_fit = None
+		self.cah_args = self.config['CAH']
+		self.cah_labels = None
+
+		self.final_labels = None
+
+		super().__init__(config, pictures_id, pictures_np)
+
+
+	def pca_fit(self):
+
+		self.pca_fit = PCA(**self.pca_args**)
+		self.pca_fit.fit(self.pictures_np)
+		self.pca_reduction = self.pca_fit.transform(self.pictures_np)
+
+		return self
+
+	def kmeans_fit(self):
+		self.kmeans_fit = KMeans(self.kmeans_args**)
+		self.kmeans_fit.fit(self.pca_reduction)
+		self.kmeans_labels = self.kmeans_fit.labels_
+		return self
+
+	def compute_kmeans_centers(self):
+		for cl in range(self.kmeans_args['n_clusters']):
+			tmp = self.[np.where(self.kmeans_labels == cl)]
+			self.kmeans_centers.append(np.mean(tmp, axis = 0))
+		return self
+
+	def cah_fit(self):
+
+		self.cah_fit = AgglomerativeClustering(self.cah_args**)
+		self.cah_fit.fit_predict(self.kmeans_centers)
+		self.cah_labels = self.cah_fit.labels_
+		return self
+
+	def compute_cah_labels(self):
+		self.final_labels = [self.cah_labels[old_cl] for old_cl in self.kmeans_labels]
+
+
diff --git a/iss/clustering/__init__.py b/iss/clustering/__init__.py
new file mode 100644
index 0000000..6f511a1
--- /dev/null
+++ b/iss/clustering/__init__.py
@@ -0,0 +1 @@
+from .AbstractClustering import AbstractClustering
\ No newline at end of file