[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

machine_learning/dbscan.py

@@ -1,18 +1,19 @@
-'''
+"""
 
 Author : Gowtham Kamalasekar
 LinkedIn : https://www.linkedin.com/in/gowtham-kamalasekar/
 
-'''
+"""
+
 import math
 
 import matplotlib.pyplot as plt
 import pandas as pd
 from typing import dict, list
 
-class DbScan:
 
-    '''
+class DbScan:
+    """
     DBSCAN Algorithm :
     Density-Based Spatial Clustering Of Applications With Noise
     Refer this website for more details : https://en.wikipedia.org/wiki/DBSCAN
@@ -32,14 +33,28 @@ class DbScan:
     obj = dbscan.DbScan(minpts, radius, file)
     obj.print_dbscan()
     obj.plot_dbscan()
-    '''
+    """
-    def __init__(self, minpts : int, radius : int, file : str =
+
-                 ({'x': 3, 'y': 7}, {'x': 4, 'y': 6}, {'x': 5, 'y': 5},
+    def __init__(
-                  {'x': 6, 'y': 4},{'x': 7, 'y': 3}, {'x': 6, 'y': 2},
+        self,
-                  {'x': 7, 'y': 2}, {'x': 8, 'y': 4},{'x': 3, 'y': 3},
+        minpts: int,
-                  {'x': 2, 'y': 6}, {'x': 3, 'y': 5}, {'x': 2, 'y': 4})
+        radius: int,
-                 ) -> None:
+        file: str = (
-        '''
+            {"x": 3, "y": 7},
+            {"x": 4, "y": 6},
+            {"x": 5, "y": 5},
+            {"x": 6, "y": 4},
+            {"x": 7, "y": 3},
+            {"x": 6, "y": 2},
+            {"x": 7, "y": 2},
+            {"x": 8, "y": 4},
+            {"x": 3, "y": 3},
+            {"x": 2, "y": 6},
+            {"x": 3, "y": 5},
+            {"x": 2, "y": 4},
+        ),
+    ) -> None:
+        """
         Constructor
 
         Args:
@@ -67,13 +82,14 @@ class DbScan:
             6 | 4
             7 | 3
             -----
-        '''
+        """
         self.minpts = minpts
         self.radius = radius
         self.file = file
         self.dict1 = self.perform_dbscan()
+
     def perform_dbscan(self) -> dict[int, list[int]]:
-        '''
+        """
         Args:
         -----------
             None
@@ -99,7 +115,7 @@ class DbScan:
         11 [2, 10, 11, 12]
         12 [9, 11, 12]
 
-        '''
+        """
         if type(self.file) is str:
             data = pd.read_csv(self.file)
         else:
@@ -108,16 +124,21 @@ class DbScan:
         dict1 = {}
         for i in range(len(data)):
             for j in range(len(data)):
-                dist = math.sqrt(pow(data['x'][j] - data['x'][i],2)
+                dist = math.sqrt(
-                                 + pow(data['y'][j] - data['y'][i],2))
+                    pow(data["x"][j] - data["x"][i], 2)
+                    + pow(data["y"][j] - data["y"][i], 2)
+                )
                 if dist < e:
-                    if i+1 in dict1:
+                    if i + 1 in dict1:
-                        dict1[i+1].append(j+1)
+                        dict1[i + 1].append(j + 1)
                     else:
-                        dict1[i+1] = [j+1,]
+                        dict1[i + 1] = [
+                            j + 1,
+                        ]
         return dict1
+
     def print_dbscan(self) -> None:
-        '''
+        """
         Outputs:
         --------
         Prints each point and if it is a core or a noise (w/ border)
@@ -135,9 +156,9 @@ class DbScan:
         10   [1, 10, 11] ---> Noise ---> Border
         11   [2, 10, 11, 12] ---> Core
         12   [9, 11, 12] ---> Noise ---> Border
-        '''
+        """
         for i in self.dict1:
-            print(i," ",self.dict1[i], end=' ---> ')
+            print(i, " ", self.dict1[i], end=" ---> ")
             if len(self.dict1[i]) >= self.minpts:
                 print("Core")
             else:
@@ -151,8 +172,9 @@ class DbScan:
                         break
                 else:
                     print("Noise")
+
     def plot_dbscan(self) -> None:
-        '''
+        """
         Output:
         -------
         A matplotlib plot that show points as core and noise along
@@ -160,7 +182,7 @@ class DbScan:
 
         >>> DbScan(4,1.9).plot_dbscan()
         Plotted Successfully
-        '''
+        """
         if type(self.file) is str:
             data = pd.read_csv(self.file)
         else:
@@ -168,23 +190,36 @@ class DbScan:
         e = self.radius
         for i in self.dict1:
             if len(self.dict1[i]) >= self.minpts:
-                plt.scatter(data['x'][i-1], data['y'][i-1], color='red')
+                plt.scatter(data["x"][i - 1], data["y"][i - 1], color="red")
-                circle = plt.Circle((data['x'][i-1], data['y'][i-1]),
+                circle = plt.Circle(
-                                    e, color='blue', fill=False)
+                    (data["x"][i - 1], data["y"][i - 1]), e, color="blue", fill=False
+                )
                 plt.gca().add_artist(circle)
-                plt.text(data['x'][i-1], data['y'][i-1],
+                plt.text(
-                         'P'+str(i), ha='center', va='bottom')
+                    data["x"][i - 1],
+                    data["y"][i - 1],
+                    "P" + str(i),
+                    ha="center",
+                    va="bottom",
+                )
             else:
-                plt.scatter(data['x'][i-1], data['y'][i-1], color='green')
+                plt.scatter(data["x"][i - 1], data["y"][i - 1], color="green")
-                plt.text(data['x'][i-1], data['y'][i-1],
+                plt.text(
-                         'P'+str(i), ha='center', va='bottom')
+                    data["x"][i - 1],
-        plt.xlabel('X')
+                    data["y"][i - 1],
-        plt.ylabel('Y')
+                    "P" + str(i),
-        plt.title('DBSCAN Clustering')
+                    ha="center",
-        plt.legend(['Core','Noise'])
+                    va="bottom",
+                )
+        plt.xlabel("X")
+        plt.ylabel("Y")
+        plt.title("DBSCAN Clustering")
+        plt.legend(["Core", "Noise"])
         plt.show()
         print("Plotted Successfully")
 
+
 if __name__ == "__main__":
     import doctest
+
     doctest.testmod()