mathdatech/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-03-15 02:59:50 +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] 2024-10-02 10:33:28 +00:00
parent 249b0e8871
commit 4d76e8236b
1 changed files with 72 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

110
machine_learning/dbscan.py
View File

@ -2,8 +2,10 @@ import math
from typing import dict, list, optional from typing import dict, list, optional
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import pandas as pd import pandas as pd
class DbScan: class DbScan:
''' """
DBSCAN Algorithm : DBSCAN Algorithm :
Density-Based Spatial Clustering Of Applications With Noise Density-Based Spatial Clustering Of Applications With Noise
Refer this website for more details : https://en.wikipedia.org/wiki/DBSCAN Refer this website for more details : https://en.wikipedia.org/wiki/DBSCAN
@ -23,14 +25,28 @@ class DbScan:
obj = dbscan.DbScan(minpts, radius, file) obj = dbscan.DbScan(minpts, radius, file)
obj.print_dbscan() obj.print_dbscan()
obj.plot_dbscan() obj.plot_dbscan()
''' """
def __init__(self, minpts : int, radius : int, file : optional[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: optional[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 Constructor
Args: Args:
@ -58,13 +74,14 @@ class DbScan:
6 | 4 6 | 4
7 | 3 7 | 3
----- -----
''' """
self.minpts = minpts self.minpts = minpts
self.radius = radius self.radius = radius
self.file = file self.file = file
self.dict1 = self.perform_dbscan() self.dict1 = self.perform_dbscan()
def perform_dbscan(self) -> dict[int, list[int]]: def perform_dbscan(self) -> dict[int, list[int]]:
''' """
Args: Args:
----------- -----------
None None
@ -90,25 +107,30 @@ class DbScan:
11 [2, 10, 11, 12] 11 [2, 10, 11, 12]
12 [9, 11, 12] 12 [9, 11, 12]
''' """
if type(self.file) is str: if type(self.file) is str:
data = pd.read_csv(self.file) data = pd.read_csv(self.file)
else: else:
data = pd.DataFrame(list(self.file)) data = pd.DataFrame(list(self.file))
e = self.radius e = self.radius
dict1 = {} dict1 = {}
for i in range(len(data)): for i in range(len(data)):
for j 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 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: else:
dict1[i+1] = [j+1,] dict1[i + 1] = [
j + 1,
]
return dict1 return dict1
def print_dbscan(self) -> None: def print_dbscan(self) -> None:
''' """
Outputs: Outputs:
-------- --------
Prints each point and if it is a core or a noise (w/ border) Prints each point and if it is a core or a noise (w/ border)
@ -126,24 +148,25 @@ class DbScan:
10 [1, 10, 11] ---> Noise ---> Border 10 [1, 10, 11] ---> Noise ---> Border
11 [2, 10, 11, 12] ---> Core 11 [2, 10, 11, 12] ---> Core
12 [9, 11, 12] ---> Noise ---> Border 12 [9, 11, 12] ---> Noise ---> Border
''' """
for i in self.dict1: for i in self.dict1:
print(i," ",self.dict1[i], end=' ---> ') print(i, " ", self.dict1[i], end=" ---> ")
if len(self.dict1[i]) >= self.minpts: if len(self.dict1[i]) >= self.minpts:
print("Core") print("Core")
else: else:
for j in self.dict1: for j in self.dict1:
if ( if (
i != j i != j
and len(self.dict1[j]) >= self.minpts and len(self.dict1[j]) >= self.minpts
and i in self.dict1[j] and i in self.dict1[j]
): ):
print("Noise ---> Border") print("Noise ---> Border")
break break
else: else:
print("Noise") print("Noise")
def plot_dbscan(self) -> None: def plot_dbscan(self) -> None:
''' """
Output: Output:
------- -------
A matplotlib plot that show points as core and noise along A matplotlib plot that show points as core and noise along
@ -151,27 +174,38 @@ class DbScan:
>>> DbScan(4,1.9).plot_dbscan() >>> DbScan(4,1.9).plot_dbscan()
Plotted Successfully Plotted Successfully
''' """
if type(self.file) is str: if type(self.file) is str:
data = pd.read_csv(self.file) data = pd.read_csv(self.file)
else: else:
data = pd.DataFrame(list(self.file)) data = pd.DataFrame(list(self.file))
e = self.radius e = self.radius
for i in self.dict1: for i in self.dict1:
if len(self.dict1[i]) >= self.minpts: 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.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: 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() plt.show()
print("Plotted Successfully") print("Plotted Successfully")