mathdatech/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2024-10-06 05:39:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2024-10-01 15:51:03 +00:00
parent 12ac966b63
commit a393075ede
1 changed files with 55 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
machine_learning/dbscan.py
View File

@ -2,8 +2,10 @@ import pandas as pd
import math
import matplotlib.pyplot as plt
from typing import dict, list
class DbScan:
'''
"""
DBSCAN Algorithm :
Density-Based Spatial Clustering Of Applications With Noise
Refer this website for more details : https://en.wikipedia.org/wiki/DBSCAN
@ -21,9 +23,10 @@ class DbScan:
obj = dbscan.DbScan(minpts, radius, file)
obj.print_dbscan()
obj.plot_dbscan()
'''
"""
def __init__(self, minpts: int, radius: int, file: str) -> None:
'''
"""
Constructor
Attributes:
@ -51,13 +54,14 @@ 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]]:
'''
"""
Parameters:
-----------
None
@ -66,56 +70,81 @@ class DbScan:
--------
Dictionary with points and the list of points
that lie in its radius
'''
"""
data = pd.read_csv(self.file)
e = self.radius
dict1 = {}
for i in range(len(data)):
for j in range(len(data)):
dist = math.sqrt(pow(data['x'][j] - data['x'][i],2) + pow(data['y'][j] - data['y'][i],2))
dist = math.sqrt(
pow(data["x"][j] - data["x"][i], 2)
+ pow(data["y"][j] - data["y"][i], 2)
)
if dist < e:
if i + 1 in dict1:
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)
'''
"""
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:
for j in self.dict1:
if i != j and len(self.dict1[j]) >= self.minpts and i in self.dict1[j]:
if (
i != j
and len(self.dict1[j]) >= self.minpts
and i in self.dict1[j]
):
print("Noise ---> Border")
break
else:
print("Noise")
def plot_dbscan(self) -> None:
'''
"""
Output:
-------
A matplotlib plot that show points as core and noise along
with the circle that lie within it.
'''
"""
data = pd.read_csv(self.file)
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')
circle = plt.Circle((data['x'][i-1], data['y'][i-1]), e, color='blue', fill=False)
plt.scatter(data["x"][i - 1], data["y"][i - 1], color="red")
circle = plt.Circle(
(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], 'P'+str(i), ha='center', va='bottom')
plt.text(
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.text(data['x'][i-1], data['y'][i-1], 'P'+str(i), ha='center', va='bottom')
plt.xlabel('X')
plt.ylabel('Y')
plt.title('DBSCAN Clustering')
plt.legend(['Core','Noise'])
plt.scatter(data["x"][i - 1], data["y"][i - 1], color="green")
plt.text(
data["x"][i - 1],
data["y"][i - 1],
"P" + str(i),
ha="center",
va="bottom",
)
plt.xlabel("X")
plt.ylabel("Y")
plt.title("DBSCAN Clustering")
plt.legend(["Core", "Noise"])
plt.show()