from sklearn.datasets import load_iris
from sklearn.decomposition import PCA
from sklearn.cluster import DBSCAN
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
iris_database=load_iris();
data=iris_database["data"];
target=iris_database["target"]
print("target=",target);
print("\n");
iris_df = pd.DataFrame(iris_database.data, columns=['Sepal_Length',
'Sepal_Width', 'Patal_Length', 'Petal_Width'])
print(iris_df);
iris_df['Target'] = iris_database.target
iris_df['Target'].replace([0], 'Iris_Setosa', inplace=True)
iris_df['Target'].replace([1], 'Iris_Vercicolor', inplace=True)
iris_df['Target'].replace([2], 'Iris_Virginica', inplace=True)
sns.kdeplot(iris_df.loc[(iris_df['Target']=='Iris_Setosa'),
'Sepal_Length'], color='r', fill=True);
sns.kdeplot(iris_df.loc[(iris_df['Target']=='Iris_Vercicolor'),
'Sepal_Length'], color='b', fill=True);
sns.kdeplot(iris_df.loc[(iris_df['Target']=='Iris_Virginica'),
'Sepal_Length'], color='r', fill=True)
plt.xlabel('Sepal Length')
plt.ylabel('Probability Density')
fig, axs = plt.subplots(2, 2)
nu=0;
for i in axs:
i[nu%2].boxplot(data[:,nu]);
part1=i[nu%2].violinplot(data[:,nu], widths=0.15)
nu=nu+1
i[nu%2].boxplot(data[:,nu]);
i[nu%2].violinplot(data[:,nu], widths=0.15)
nu=nu+1
plt.tight_layout()
plt.show();
basic=DBSCAN(eps=0.4,min_samples=3);
basic.fit(data);
basic_label=basic.labels_;
print("db.labels_(eps=0.4,min_simples=3)=",basic_label);
print("\n");
pca=PCA(n_components=3);
newx=pca.fit_transform(data);
fig_0=plt.figure();
ax_0 =plt.axes(projection ='3d');
ax_0.scatter(newx[:,0],newx[:,1],newx[:,2],c=target);
ax_0.set_title("3d Scatter plot for PCA");
plt.show();
db=DBSCAN(eps=0.5,min_samples=4).fit(newx);
labels=db.labels_;
print("db.labels_(eps=0.5,min_simples=4)=",db.labels_);
fig_1 = plt.figure();
ax_1 = plt.axes(projection ='3d');
ax_1.scatter(newx[:,0],newx[:,1], newx[:,2],c=labels);
ax_1.set_title('3d Scatter plot for DBSCAN');
plt.show();
target= [0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2
2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
2 2]
Sepal_Length Sepal_Width Patal_Length Petal_Width
0 5.1 3.5 1.4 0.2
1 4.9 3.0 1.4 0.2
2 4.7 3.2 1.3 0.2
3 4.6 3.1 1.5 0.2
4 5.0 3.6 1.4 0.2
.. ... ... ... ...
145 6.7 3.0 5.2 2.3
146 6.3 2.5 5.0 1.9
147 6.5 3.0 5.2 2.0
148 6.2 3.4 5.4 2.3
149 5.9 3.0 5.1 1.8
[150 rows x 4 columns]
C:\Users\tyq17\AppData\Local\Temp\ipykernel_22328\4175703781.py:27: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.
The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.
For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.
iris_df['Target'].replace([0], 'Iris_Setosa', inplace=True)
db.labels_(eps=0.4,min_simples=3)= [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 -1 0 0 0 0 0 0 0 -1 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 -1 0 0 0 0 0 0
0 0 1 1 1 1 1 1 1 2 1 1 2 1 -1 1 -1 1 1 1 -1 1 3 1
3 1 1 1 1 1 1 1 1 1 1 3 1 1 1 -1 1 1 1 1 1 2 1 1
1 1 2 1 -1 3 3 3 3 -1 -1 -1 -1 -1 3 3 3 3 -1 3 3 -1 -1 -1
3 3 -1 3 3 3 3 3 3 3 -1 -1 3 3 -1 -1 3 3 3 3 3 3 3 3
3 3 3 3 3 3]
db.labels_(eps=0.5,min_simples=4)= [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 -1 0 0 0 0 0 0
0 0 1 1 1 1 1 1 1 2 1 1 2 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1
1 1 2 1 1 1 1 1 1 1 -1 1 -1 -1 1 1 1 1 1 1 1 -1 -1 1
1 1 -1 1 1 1 1 1 1 1 1 -1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1]
