pgm3

 #pgm3

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.datasets import load_iris

from sklearn.decomposition import PCA



iris = load_iris()

data = iris.data

labels = iris.target

label_names = iris.target_names



iris_df = pd.DataFrame(data, columns=iris.feature_names)



pca = PCA(n_components=2)

data_reduced = pca.fit_transform(data)



reduced_df = pd.DataFrame(data_reduced, columns=['Principal Component 1', 'Principal Component 2'])

reduced_df['Label'] = labels



plt.figure(figsize=(8, 6))

colors = ['r', 'g', 'b']


for i, label in enumerate(np.unique(labels)):

    plt.scatter(

        reduced_df[reduced_df['Label'] == label]['Principal Component 1'],

        reduced_df[reduced_df['Label'] == label]['Principal Component 2'],

        label=label_names[label],

        color=colors[i]

    )


plt.title('PCA on Iris Dataset')

plt.xlabel('Principal Component 1')

plt.ylabel('Principal Component 2')

plt.legend()

plt.grid()

plt.show()



plt.figure(figsize=(10, 6))

plt.plot(np.cumsum(pca.explained_variance_ratio_), 'bo-')

plt.xlabel('Number of Components')

plt.ylabel('Cumulative Explained Variance')

plt.title('Explained Variance vs. Number of Components')

plt.grid(True, alpha=0.3)

plt.show()


Comments

Post a Comment

Popular posts from this blog

pgm 2

  #pgm2 import pandas as pd import seaborn as sns import matplotlib.pyplot as plt from sklearn.datasets import fetch_california_housing california_housing = fetch_california_housing() df = pd.DataFrame(california_housing.data, columns=california_housing.feature_names) df['target'] = california_housing.target correlation_matrix = df.corr() plt.figure(figsize=(12, 8)) sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', cbar=True) plt.title("Correlation Matrix Heatmap") plt.show() sns.pairplot(df, height=2.5, plot_kws={'alpha':0.7}) plt.suptitle("Pair Plot of California Housing Dataset", y=1.02) plt.show()
Read more

pgm5

 import numpy as np import matplotlib.pyplot as plt from collections import Counter # --- Data Setup --- np.random.seed(42) data = np.random.rand(100) train, test = data[:50], data[50:] train_labels = ["Class1" if x <= 0.5 else "Class2" for x in train] true_labels = ["Class1" if x <= 0.5 else "Class2" for x in test] # --- KNN Function --- def knn(x, train_data, labels, k):     distances = sorted(((abs(x - xi), yi) for xi, yi in zip(train_data, labels)))     nearest = distances[:k]     return Counter(yi for _, yi in nearest).most_common(1)[0][0] # --- Classification and Plotting --- k_values = [1, 3, 5, 20, 30] for k in k_values:     predictions = [knn(x, train, train_labels, k) for x in test]     accuracy = round(np.mean([pred == true for pred, true in zip(predictions, true_labels)]), 2)          print(f"\n--- k = {k} | Accuracy: {accuracy} ---")     for i, (x, p) in enumerate(zip(test, predi...
Read more

pgm 4

 #pgm4 import pandas as pd def find_s_algorithm(data):     print("Training data:")     print(data)     attributes = data.columns[:-1]     class_label = data.columns[-1]       hypothesis = None     for index, row in data.iterrows():         if row[class_label] == 'Yes':  # only consider positive examples             if hypothesis is None:                 hypothesis = list(row[attributes])             else:                 for i, value in enumerate(row[attributes]):                     if hypothesis[i] != value:                         hypothesis[i] = '?'  # generalize the hypothesis     if hypothesis is None:      ...
Read more