5

 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 <= 0.5 else "Class2" for x in train_data])


# k-NN function

def knn(train_data, train_labels, test_point, k):

    distances = np.abs(train_data - test_point)

    nearest_labels = train_labels[np.argsort(distances)[:k]]

    return Counter(nearest_labels).most_common(1)[0][0]


# k values to test

k_values = [1, 2, 3, 4, 5, 20, 30]


# Loop over each k

for k in k_values:

    predictions = np.array([knn(train_data, train_labels, x, k) for x in test_data])

    

    class1 = test_data[predictions == "Class1"]

    class2 = test_data[predictions == "Class2"]


    plt.figure(figsize=(8, 3))

    plt.scatter(train_data, np.zeros_like(train_data), c="black", label="Train", marker="x")

    if len(class1) > 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()


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