Pgr-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

data = load_breast_cancer()
X = data.data
y = data.target
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
kmeans = KMeans(n_clusters=2, random_state=42)
y_kmeans = kmeans.fit_predict(X_scaled)
print("Confusion Matrix:")
print(confusion_matrix(y, y_kmeans))
print("\nClassification Report:")
print(classification_report(y, y_kmeans))
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_scaled)

df = pd.DataFrame(X_pca, columns=['PC1', 'PC2'])
df['Cluster'] = y_kmeans // cluster label Kmeans
df['True Label'] = y

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 of Breast Cancer Dataset')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title="Cluster")
plt.show()

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 of Breast Cancer Dataset')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title="True Label")
plt.show()

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 Clustering with Centroids')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title="Cluster")
plt.show()

Comments

Post a Comment

Popular posts from this blog

Pgr-1

import pandas as pd from sklearn.datasets import fetch_california_housing california_housing = fetch_california_housing() print(california_housing.DESCR) df = pd.DataFrame(california_housing.data, columns=california_housing.feature_names) df['target'] = california_housing.target print("First 5 rows of the dataset:") print(df.head()) # Display the first 5 rows def plot_histograms(df):  df.hist(bins=30, figsize=(12, 10))  plt.suptitle("Histograms of Numerical Features", fontsize=16)  plt.show() def plot_boxplots(df):  plt.figure(figsize=(12, 10))  for i, feature in enumerate(df.columns):   plt.subplot(3, 4, i+1) # Adjust the number of rows and columns accordingly   sns.boxplot(df[feature])   plt.title(f'Box Plot of {feature}')  plt.tight_layout()  plt.show() import matplotlib.pyplot as plt plot_histograms(df) plot_boxplots(df) print("Outliers Detection:") outliers_summary = {} numerical_features = df.select_dtypes(include=['float64', ...
Read more

Pgr-4

 import pandas as pd def find_s_algorithm(file_path):  data = pd.read_csv(file_path)  print("Training data:")  print(data)  attributes = data.columns[:-1]   class_label = data.columns[-1]   for index, row in data.iterrows():  if row[class_label] == 'Yes':   hypothesis = list(row[attributes])    break  for index, row in data.iterrows():  if row[class_label] == 'Yes':   for i, value in enumerate(row[attributes]):    if hypothesis[i] != value:      hypothesis[i] = '?' # Generalize hypothesis return hypothesis file_path = 'training_data.csv' # Provide the file path hypothesis = find_s_algorithm(file_path) print("\nThe final hypothesis is:", hypothesis)
Read more

Pgr-5

import numpy as np import matplotlib.pyplot as plt from collections import Counter data = np.random.rand(100) labels = ["Class1" if x <= 0.5 else "Class2" for x in data[:50]] def euclidean_distance(x1, x2):  return abs(x1 - x2) def knn_classifier(train_data, train_labels, test_point, k):  distances = [(euclidean_distance(test_point, train_data[i]), train_labels[i]) for i in   range(len(train_data))]  distances.sort(key=lambda x: x[0])  k_nearest_neighbors = distances[:k]  k_nearest_labels = [label for _, label in k_nearest_neighbors]  return Counter(k_nearest_labels).most_common(1)[0][0]  train_data = data[:50]  train_labels = labels  test_data = data[50:]  k_values = [1, 2, 3, 4, 5, 20, 30]  print("--- k-Nearest Neighbors Classification ---")  print("Training dataset: First 50 points labeled based on the rule (x <= 0.5 -> Class1, x > 0.5 ->  Class2)")  print("Testing dataset: Remaining 50 poi...
Read more