Utilisation du jeu de données réel

mydatalib.py

@@ -11,6 +11,7 @@ import time
 from sklearn import cluster, metrics, preprocessing
 import pandas as pd
 
+
 def extract_data_2d(data_path):
     databrut = arff.loadarff(open(data_path + ".arff", 'r'))
     return np.array([[x[0], x[1]] for x in databrut[0]])
@@ -31,8 +32,12 @@ def extract_data_txt(data_path):
 
 
 def extract_data_csv(data_path: str, first_col: int, last_col: int):
-    data = pd.read_csv(data_path + ".csv")
-    return data.iloc[:, last_col]
+    databrut = pd.read_csv(data_path + ".csv")
+    ret = []
+    for x in range(first_col, last_col+1):
+        ret += [databrut.iloc[:, x]]
+    ret = np.array(ret)
+    return (list(databrut.iloc[:, 0]), np.array(list(map(list, zip(*ret)))))
 
 
 def scale_data(data):

tp-preprocessing

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Sun Jan  9 11:12:30 2022
+
+@author: pfaure
+"""
+from sklearn.neighbors import NearestNeighbors
+import numpy as np
+
+from myplotlib import print_1d_data, print_2d_data
+from mydatalib import extract_data_csv, scale_data
+
+path = './new-data/'
+dataset_name = "pluie"
+save = False
+
+print("-----------------------------------------------------------")
+print("     Chargement du dataset : " + dataset_name)
+(villes, data) = extract_data_csv(path + dataset_name, 13, 13)
+print(data)
+# print_2d_data(data, dataset_name=dataset_name +
+#              "_brutes", stop=False, save=save)
+
+print("-----------------------------------------------------------")
+print("     Mise à l'échelle")
+data_scaled = scale_data(data)
+# print_2d_data(data_scaled, dataset_name=dataset_name +
+#              "_scaled", stop=False, save=save)
+
+print("-----------------------------------------------------------")
+print("     Calcul du voisinage")
+n = 5
+neighbors = NearestNeighbors(n_neighbors=n)
+neighbors.fit(data_scaled)
+distances, indices = neighbors.kneighbors(data_scaled)
+distances = list(map(lambda x: sum(x[1:n-1])/(len(x)-1), distances))
+distances = np.sort(distances, axis=0)
+print_1d_data(distances, range(1, len(distances)+1), x_name="distance_moyenne",
+              y_name="nombre_de_points", stop=False, save=save)

tp5-preprocessing.py

@@ -13,12 +13,13 @@ from myplotlib import print_1d_data, print_2d_data
 from mydatalib import extract_data_txt, scale_data
 
 path = './new-data/'
-dataset_name = "d32"
+dataset_name = "w2"
 save = False
 
 print("-----------------------------------------------------------")
 print("     Chargement du dataset : " + dataset_name)
 data = extract_data_txt(path + dataset_name)
+print(data)
 print_2d_data(data, dataset_name=dataset_name +
               "_brutes", stop=False, save=save)
 

tp6-preprocessing

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Sun Jan  9 11:12:30 2022
+
+@author: pfaure
+"""
+from sklearn.neighbors import NearestNeighbors
+import numpy as np
+
+from myplotlib import print_1d_data, print_2d_data
+from mydatalib import extract_data_csv, scale_data
+
+path = './new-data/'
+dataset_name = "pluie"
+save = False
+
+print("-----------------------------------------------------------")
+print("     Chargement du dataset : " + dataset_name)
+(villes, data) = extract_data_csv(path + dataset_name, 13, 13)
+print(data)
+# print_2d_data(data, dataset_name=dataset_name +
+#              "_brutes", stop=False, save=save)
+
+print("-----------------------------------------------------------")
+print("     Mise à l'échelle")
+data_scaled = scale_data(data)
+# print_2d_data(data_scaled, dataset_name=dataset_name +
+#              "_scaled", stop=False, save=save)
+
+print("-----------------------------------------------------------")
+print("     Calcul du voisinage")
+n = 5
+neighbors = NearestNeighbors(n_neighbors=n)
+neighbors.fit(data_scaled)
+distances, indices = neighbors.kneighbors(data_scaled)
+distances = list(map(lambda x: sum(x[1:n-1])/(len(x)-1), distances))
+distances = np.sort(distances, axis=0)
+print_1d_data(distances, range(1, len(distances)+1), x_name="distance_moyenne",
+              y_name="nombre_de_points", stop=False, save=save)

tp6-real-dataset.py

@@ -10,18 +10,17 @@ from sklearn.neighbors import NearestNeighbors
 import numpy as np
 
 from myplotlib import print_1d_data, print_2d_data
-from mydatalib import  scale_data, apply_DBSCAN, evaluate, extract_data_csv, apply_kmeans, \
+from mydatalib import scale_data, apply_DBSCAN, evaluate, extract_data_csv, apply_kmeans, \
     apply_agglomerative_clustering, apply_mean_shift
 
 path = './new-data/'
 dataset_name = "pluie"
-save = True
-eps = 0.8
-
+save = False
+eps = 0.6
 
 print("-----------------------------------------------------------")
 print("     Chargement du dataset : " + dataset_name)
-data = extract_data_csv(path + dataset_name, 1, 5)
+(villes, data) = extract_data_csv(path + dataset_name, 1, 12)
 
 print(data)
 
@@ -29,7 +28,7 @@ print("-----------------------------------------------------------")
 print("     Mise à l'échelle")
 data_scaled = scale_data(data)
 
-k_max = 10
+k_max = 20
 print("-----------------------------------------------------------")
 print("     Application de k-means")
 # Application de k-means pour plusieurs valeurs de k