aman

  import numpy as np import matplotlib.pyplot as plt from collections import Counter # Generate random data and labels data = np.random.rand(100) labels = ["Class1" if x <= 0.5 else "Class2" for x in data[:50]] # Euclidean distance function def euclidean_distance(x1, x2): return abs(x1 - x2) # k-NN classifier 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 -> ...

  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] = '?' return hypothesis file_path = 'training_data.csv' hypothesis = find_s_algorithm(file_path) print("\nThe final hypothesis is:", hypothesis)

  import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.datasets import load_iris from sklearn.preprocessing import StandardScaler from sklearn.decomposition import PCA # Load and prepare the data iris = load_iris() df = pd.DataFrame(data=iris.data, columns=iris.feature_names) df['target'] = iris.target df['target_names'] = pd.Categorical.from_codes(iris.target, iris.target_names) # Standardize the features and perform PCA X = df[iris.feature_names] X_scaled = StandardScaler().fit_transform(X) pca = PCA(n_components=2) X_pca = pca.fit_transform(X_scaled) # Plot PCA results plt.figure(figsize=(10, 8)) for target, target_name in zip(sorted(df['target'].unique()), sorted(df['target_names'].unique())): mask = df['target'] == target plt.scatter(X_pca[mask, 0], X_pca[mask, 1], label=target_name, alpha=0.8) plt.xlabel(f'PC1 ({pca.explained_variance_ratio_[0]:.2%} variance)')...

  import pandas as pd import seaborn as sns import matplotlib.pyplot as plt from sklearn.datasets import fetch_california_housing # Step 1: Load the California Housing dataset california_housing = fetch_california_housing() df = pd.DataFrame(california_housing.data, columns=california_housing.feature_names) # Include target variable in the DataFrame df['target'] = california_housing.target # Step 2: Compute the correlation matrix correlation_matrix = df.corr() # Step 3: Visualize the correlation matrix using a heatmap plt.figure(figsize=(12, 8)) sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', cbar=True) plt.title("Correlation Matrix Heatmap") plt.show() # Step 4: Create a pair plot to visualize pairwise relationships between features sns.pairplot(df, height=2.5, plot_kws={'alpha':0.7}) plt.suptitle("Pair Plot of California Housing Dataset", y=1.02) plt.show()  

  Step 1: Import Required Libraries import pandas as pd from sklearn.datasets import fetch_california_housing california_housing = fetch_california_housing() print(california_housing.DESCR) Step 2: Convert to DataFrame df = pd.DataFrame(california_housing.data, columns=california_housing.feature_names) Step 3: Include target variable in the DataFrame df['target'] = california_housing.target Step 4: View the first few rows of the dataset using the head() method print("First 5 rows of the dataset:") print(df.head()) # Display the first 5 rows Step 5: # Plot histograms for all numerical features def plot_histograms(df): df.hist(bins=30, figsize=(12, 10)) plt.suptitle("Histograms of Numerical Features", fontsize=16) plt.show() Step6:# Plot box plots for all numerical features to detect outliers def plot_boxplots(df): plt.figure(figsize=(12, 10)) for i, feature in enumerate(df.columns): plt.subplot(3, 4, i+1) # Adjust the...