main.py

@@ -1,12 +1,23 @@
 #!/usr/bin/env python3
+
 import sys
 sys.path.append('./src/back/')
 
 import load_csv as l 
+import show_csv as s 
+import clustering_csv as c
 
 df = l.return_csv("./data.csv")
 l.csv_value(df)
 
 l.csv_value(df)
 
-l.csv_stadadisation_Z(df,"Vehicle Year")
+# l.csv_standardisation_Z(df,"Vehicle Year")
+
+# l.csv_robust_normalize(df,"Speed Limit")
+
+# s.histo_col(df,"Speed Limit")
+
+# s.plotBoxWhisker(df)
+
+c.launch_cluster(df,['Speed Limit','Vehicle Year'])

src/back/clustering_csv.py

@@ -0,0 +1,83 @@
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.cluster import KMeans, DBSCAN
+from sklearn.datasets import make_blobs, make_moons
+from mpl_toolkits.mplot3d import Axes3D
+
+def visualize_clusters_2d(X, labels, centers=None, title="Clusters"):
+    plt.figure(figsize=(10, 7))
+    plt.scatter(X[:, 0], X[:, 1], c=labels, s=50, cmap='viridis')
+    if centers is not None:
+        plt.scatter(centers[:, 0], centers[:, 1], c='red', s=200, alpha=0.75)
+    plt.title(title)
+    plt.xlabel("Feature 1")
+    plt.ylabel("Feature 2")
+    plt.show()
+
+def visualize_clusters_3d(X, labels, centers=None, title="Clusters"):
+    fig = plt.figure(figsize=(10, 7))
+    ax = fig.add_subplot(111, projection='3d')
+    ax.scatter(X[:, 0], X[:, 1], X[:, 2], c=labels, s=50, cmap='viridis')
+    if centers is not None:
+        ax.scatter(centers[:, 0], centers[:, 1], centers[:, 2], c='red', s=200, alpha=0.75)
+    ax.set_title(title)
+    ax.set_xlabel("Feature 1")
+    ax.set_ylabel("Feature 2")
+    ax.set_zlabel("Feature 3")
+    plt.show()
+
+def calculate_cluster_statistics_kmeans(X, labels, centers):
+    unique_labels = np.unique(labels)
+    stats = []
+    for label in unique_labels:
+        cluster_points = X[labels == label]
+        num_points = len(cluster_points)
+        center = centers[label]
+        stats.append({
+            'cluster': label,
+            'num_points': num_points,
+            'center': center
+        })
+    return stats
+
+def calculate_cluster_statistics_dbscan(X, labels):
+    unique_labels = np.unique(labels)
+    stats = []
+    for label in unique_labels:
+        if label == -1:
+            continue  # Ignore noise
+        cluster_points = X[labels == label]
+        num_points = len(cluster_points)
+        density = num_points / (np.max(cluster_points, axis=0) - np.min(cluster_points, axis=0)).prod()
+        stats.append({
+            'cluster': label,
+            'num_points': num_points,
+            'density': density
+        })
+    return stats
+
+def launch_cluster(df,array_columns):
+    X = df[array_columns].values
+    
+    kmeans = KMeans(n_clusters=4, random_state=42)
+    labels_kmeans = kmeans.fit_predict(X)
+    centers_kmeans = kmeans.cluster_centers_
+     
+    stats_kmeans = calculate_cluster_statistics_kmeans(X, labels_kmeans, centers_kmeans)
+    # for stat in stats_kmeans:
+    #     print(f"Cluster {stat['cluster']}: {stat['num_points']} points, Center: {stat['center']}")
+
+    # Appliquer DBSCAN
+    dbscan = DBSCAN(eps=0.2, min_samples=5)
+    labels_dbscan = dbscan.fit_predict(X)
+    stats_dbscan = calculate_cluster_statistics_dbscan(X, labels_dbscan)
+        # for stat in stats_dbscan:
+        #     print(f"Cluster {stat['cluster']}: {stat['num_points']} points, Density: {stat['density']}")
+    if len(array_columns) == 3:
+        visualize_clusters_3d(X, labels_kmeans, centers_kmeans, title="K-Means Clustering 3D")
+        visualize_clusters_3d(X, labels_dbscan, title="DBSCAN Clustering 3D")
+    else: 
+        visualize_clusters_2d(X, labels_kmeans, centers_kmeans, title="K-Means Clustering")
+        visualize_clusters_2d(X, labels_dbscan, title="DBSCAN Clustering")
+    return stats_kmeans,stats_dbscan
+    

src/back/load_csv.py

@@ -1,5 +1,6 @@
 import pandas as pd
 import numpy  as np
+import matplotlib.pyplot as plt
 
 def return_csv(path):
     df = pd.read_csv(path)
@@ -27,9 +28,21 @@ def csv_norm_min_max(df,col):
     df[col] = (df[col] - df[col].min()) / (df[col].max() - df[col].min())
     return df
 
-def csv_stadadisation_Z(df,col):
+def csv_standardisation_Z(df,col):
     mean_col1 = df[col].mean()
     std_col1 = df[col].std()
     df[col] = (df[col] - mean_col1) / std_col1
     return df[col]
-    
+
+def csv_robust_normalize(df, column):
+    # Calcul de la médiane et de l'IQR
+    median = df[column].median()
+    q1 = df[column].quantile(0.25)
+    q3 = df[column].quantile(0.75)
+    iqr = q3 - q1
+
+    # Application de la normalisation robuste
+    normalized_column = (df[column] - median) / iqr
+    df[column] = normalized_column
+    print (normalized_column)
+    return normalized_column

src/back/show_csv.py

@@ -0,0 +1,16 @@
+import pandas as pd
+import numpy  as np
+import matplotlib.pyplot as plt
+
+def histo_col(df,colonne):
+    plt.figure()
+    plt.hist(df[colonne], bins=int(df[colonne].nunique()/4), alpha=0.7, color='blue', edgecolor='black')
+    plt.title(f"Histogramme de la colonne '{colonne}'")
+    plt.xlabel(colonne)
+    plt.ylabel("Fréquence")
+    plt.grid(True)
+    plt.show()
+
+def plotBoxWhisker(df):
+    df.plot(kind='box', subplots=True, sharex=False, sharey=False)
+    plt.show()