10

 import numpy as np 

import pandas as pd 

import matplotlib.pyplot as plt 

import seaborn as sns 

from sklearn.datasets import load_breast_cancer 

from sklearn.cluster import KMeans 

from sklearn.preprocessing import StandardScaler 

from sklearn.decomposition import PCA 

from sklearn.metrics import confusion_matrix, classification_report 

# Load dataset 

data = load_breast_cancer() 

X, y = data.data, data.target 

# Standardize features 

X_scaled = StandardScaler().fit_transform(X) 

# Apply KMeans clustering 

kmeans = KMeans(n_clusters=2, random_state=42, n_init=10) 

y_kmeans = kmeans.fit_predict(X_scaled) 

# Evaluate clustering 

print("Confusion Matrix:") 

print(confusion_matrix(y, y_kmeans)) 

print("\nClassification Report:") 

print(classification_report(y, y_kmeans)) 

# Reduce dimensions for visualization 

pca = PCA(n_components=2) 

X_pca = pca.fit_transform(X_scaled) 

# Prepare DataFrame for plotting 

df = pd.DataFrame(X_pca, columns=['PC1', 'PC2']) 

df['Cluster'] = y_kmeans 

df['True Label'] = y 

# Plot: K-Means Clusters 

plt.figure(figsize=(8, 6)) 

sns.scatterplot(data=df, x='PC1', y='PC2', hue='Cluster', 

palette='Set1', s=100, edgecolor='black', alpha=0.7) 

plt.title('K-Means Clustering') 

plt.xlabel('PC1') 

plt.ylabel('PC2') 

plt.legend(title="Cluster") 

plt.show() 

# Plot: True Labels 

plt.figure(figsize=(8, 6)) 

sns.scatterplot(data=df, x='PC1', y='PC2', hue='True Label', 

palette='coolwarm', s=100, edgecolor='black', alpha=0.7) 

plt.title('True Labels') 

plt.xlabel('PC1') 

plt.ylabel('PC2') 

plt.legend(title="True Label") 

plt.show() 

# Plot: Clusters with Centroids 

plt.figure(figsize=(8, 6)) 

sns.scatterplot(data=df, x='PC1', y='PC2', hue='Cluster', 

palette='Set1', s=100, edgecolor='black', alpha=0.7) 

centers = pca.transform(kmeans.cluster_centers_) 

plt.scatter(centers[:, 0], centers[:, 1], s=200, c='red', marker='X', 

label='Centroids') 

plt.title('K-Means Clusters with Centroids') 

plt.xlabel('PC1') 

plt.ylabel('PC2') 

plt.legend(title="Cluster") 

plt.show()

Comments

Post a Comment

Popular posts from this blog

2

import pandas as pd import numpy as np import seaborn as sns import matplotlib.pyplot as plt from sklearn.datasets import fetch_california_housing # Load dataset and convert to DataFrame data = fetch_california_housing() df = pd.DataFrame(data.data, columns=data.feature_names) df['MedHouseVal'] = data.target # Add target column # 1. Correlation Matrix correlation_matrix = df.corr() print("\nCorrelation Matrix:") print(correlation_matrix) # 2. Heatmap of Correlation Matrix plt.figure(figsize=(10, 8)) sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5) plt.title('Correlation Matrix of California Housing Features') plt.tight_layout() plt.show() # 3. Pair Plot for Selected Features selected_features = ['MedInc', 'HouseAge', 'AveRooms', 'AveOccup', 'MedHouseVal'] sns.pairplot(df[selected_features], diag_kind='kde', plot_kws={'alpha': ...
Read more

3

 import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.datasets import load_iris from sklearn.decomposition import PCA # Load the Iris dataset iris = load_iris() data = iris.data labels = iris.target label_names = iris.target_names # Reduce dimensionality to 2 using PCA pca = PCA(n_components=2) reduced_data = pca.fit_transform(data) # Create DataFrame for visualization df_pca = pd.DataFrame(reduced_data, columns=['PC1', 'PC2']) df_pca['Label'] = labels # Plot PCA result plt.figure(figsize=(8, 6)) colors = ['r', 'g', 'b'] for i, label in enumerate(np.unique(labels)): subset = df_pca[df_pca['Label'] == label] plt.scatter(subset['PC1'], subset['PC2'], color=colors[i], label=label_names[label], alpha=0.7) plt.title('PCA on Iris Dataset') plt.xlabel('Principal Component 1') plt.ylabel('Principal Component 2') plt.legend() plt.grid(True) p...
Read more

1

 import numpy as np  import pandas as pd  import matplotlib.pyplot as plt  import seaborn as sns  from sklearn.datasets import fetch_california_housing  # Load California housing dataset  housing_data = fetch_california_housing()  df = pd.DataFrame(housing_data.data,  columns=housing_data.feature_names)  # 1. Display First Five Rows  print("First five rows of the dataset:")  print(df.head())  # 2. Dataset Summary  print("\nDataset Summary:")  print(df.describe())  # 3. Histograms for All Features  df.hist(figsize=(12, 8), bins=30, edgecolor='black')  plt.suptitle("Histograms for All Numerical Features", fontsize=16)  plt.show()  # 4. Boxplots for All Features  plt.figure(figsize=(12, 6))  df.boxplot(rot=45)  plt.title("Box Plots for All Numerical Features", fontsize=16)  plt.show()  # 5. Outlier Detection using IQR  Q1 = df.quantile(0.25)  Q3 = df.quanti...
Read more