programs

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']...

import numpy as np import matplotlib.pyplot as plt from sklearn.datasets import fetch_olivetti_faces from sklearn.model_selection import train_test_split, cross_val_score from sklearn.naive_bayes import GaussianNB from sklearn.metrics import accuracy_score, classification_report, confusion_matrix # Load dataset data = fetch_olivetti_faces(shuffle=True, random_state=42) X, y = data.data, data.target # Train-test split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42) # Train Naive Bayes model model = GaussianNB() model.fit(X_train, y_train) y_pred = model.predict(X_test) # Evaluation print(f'Accuracy: {accuracy_score(y_test, y_pred) * 100:.2f}%') print("\nClassification Report:") print(classification_report(y_test, y_pred, zero_division=0)) print("\nConfusion Matrix:") print(confusion_matrix(y_test, y_pred)) # Cross-validation cv_score = cross_val_score(model, X, y, cv=5).mean() print(f'\nCr...

import numpy as np import matplotlib.pyplot as plt from sklearn.datasets import load_breast_cancer from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeClassifier, plot_tree from sklearn.metrics import accuracy_score # Load dataset data = load_breast_cancer() X, y = data.data, data.target # Train-test split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # Train Decision Tree clf = DecisionTreeClassifier(random_state=42) clf.fit(X_train, y_train) # Accuracy y_pred = clf.predict(X_test) print(f"Accuracy: {accuracy_score(y_test, y_pred) * 100:.2f}%") # Predict one sample sample = X_test[0] predicted_label = clf.predict([sample])[0] print("Predicted Class:", "Benign" if predicted_label == 1 else "Malignant") # Plot tree plt.figure(figsize=(12, 8)) plot_tree(clf, filled=True, feature_names=data.feature_names, class_names=data.target_names) plt.ti...

import pandas as pd import matplotlib.pyplot as plt from sklearn.datasets import fetch_california_housing from sklearn.linear_model import LinearRegression from sklearn.model_selection import train_test_split from sklearn.metrics import mean_squared_error, r2_score from sklearn.pipeline import make_pipeline from sklearn.preprocessing import PolynomialFeatures, StandardScaler def linear_regression_california(): data = fetch_california_housing(as_frame=True) X = data.data[["AveRooms"]] y = data.target X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0) model = LinearRegression() model.fit(X_train, y_train) y_pred = model.predict(X_test) sorted_idx = X_test.values.flatten().argsort() plt.scatter(X_test, y_test, color="blue", label="Actual") plt.plot(X_test.values[sorted_idx], y_pred[sorted_idx], color="red", label="Predicted") plt.xlabel("AveRooms...

import numpy as np import matplotlib.pyplot as plt def weight(x, xi, tau): return np.exp(-np.sum((x - xi) ** 2) / (2 * tau ** 2)) def predict(x, X, y, tau): W = np.diag([weight(x, xi, tau) for xi in X]) theta = np.linalg.pinv(X.T @ W @ X) @ X.T @ W @ y return x @ theta # Generate training data X = np.linspace(0, 2 * np.pi, 100) y = np.sin(X) + 0.1 * np.random.randn(100) X_ = np.c_[np.ones(X.shape), X] # Add bias term # Generate test data x_test = np.linspace(0, 2 * np.pi, 200) x_test_ = np.c_[np.ones(x_test.shape), x_test] # Predict tau = 0.5 y_pred = [predict(xi, X_, y, tau) for xi in x_test_] # Plot plt.scatter(X, y, alpha=0.6, label="Data") plt.plot(x_test, y_pred, color="red", label="LWR Prediction") plt.legend() plt.title("Locally Weighted Regression") plt.show()

import numpy as np import matplotlib.pyplot as plt from collections import Counter np.random.seed(42) # Generate data data = np.random.rand(100) train_data = data[:50] test_data = data[50:] train_labels = np.array(["Class1" if x 0: plt.scatter(class1, np.ones_like(class1), c="blue", label="Class1 (Test)") if len(class2) > 0: plt.scatter(class2, np.ones_like(class2), c="red", label="Class2 (Test)") plt.title(f"k-NN Classification (k={k})") plt.yticks([]) plt.legend() plt.tight_layout() plt.show()

import pandas as pd def find_s_algorithm(file_path): # Load the dataset data = pd.read_csv(file_path) print("\nTraining Data:\n", data) attributes = data.columns[:-1] # All columns except the target target = data.columns[-1] # Target column (last one) # Step 1: Initialize hypothesis with the first positive example hypothesis = None for _, row in data.iterrows(): if row[target] == 'Yes': hypothesis = list(row[attributes]) break # If no positive examples found if hypothesis is None: print("No positive examples in the dataset.") return None # Step 2: Generalize the hypothesis using other positive examples for _, row in data.iterrows(): if row[target] == 'Yes': for i in range(len(attributes)): if hypothesis[i] != row[attributes[i]]: hypothesis[i] = '?' ...

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) pl...

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': ...

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.quantile(0.75) IQR = Q3 - Q1 lower_bound = Q1 - 1.5 * IQR upper_bound = Q3 + 1.5 * IQR ou...