Tuesday, 30 January 2024

Distance Measures in Data Science with Algorithms

Python Coding January 30, 2024 Data Science No comments

Distance Measures in data science with algorithms

1. Euclidean Distance:import numpy as np

def euclidean_distance(p1, p2):
    return np.sqrt(np.sum((p1 - p2) ** 2))

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Euclidean distance:", euclidean_distance(point1, point2))

#clcoding.com
Euclidean distance: 2.8284271247461903


2. Manhattan Distance:import numpy as np

def manhattan_distance(p1, p2):
    return np.sum(np.abs(p1 - p2))

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Manhattan distance:", manhattan_distance(point1, point2))

#clcoding.com
Manhattan distance: 4



3. Cosine Similarity:from scipy.spatial import distance

def cosine_similarity(p1, p2):
    return 1 - distance.cosine(p1, p2)

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Cosine similarity:", cosine_similarity(point1, point2))

#clcoding.com
Cosine similarity: 0.9838699100999074
4. Minkowski Distance:import numpy as np

def minkowski_distance(p1, p2, r):
    return np.power(np.sum(np.power(np.abs(p1 - p2), r)), 1/r)

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Minkowski distance:", minkowski_distance(point1, point2, 3))

#clcoding.com
Minkowski distance: 2.5198420997897464



5. Chebyshev Distance:import numpy as np

def chebyshev_distance(p1, p2):
    return np.max(np.abs(p1 - p2))

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Chebyshev distance:", chebyshev_distance(point1, point2))

#clcoding.com
Chebyshev distance: 2


6. Hamming Distance:import jellyfish

def hamming_distance(s1, s2):
    return jellyfish.hamming_distance(s1, s2)

# Example usage
string1 = "hello"
string2 = "hallo"
print("Hamming distance:", hamming_distance(string1, string2))

#clcoding.com
Hamming distance: 1



7. Jaccard Similarity:def jaccard_similarity(s1, s2):
    set1 = set(s1)
    set2 = set(s2)
    intersection = set1.intersection(set2)
    union = set1.union(set2)
    return len(intersection) / len(union)

# Example usage
string1 = "hello"
string2 = "hallo"
print("Jaccard similarity:", jaccard_similarity(string1, string2))

#clcoding.com
Jaccard similarity: 0.6
8. Sørensen-Dice Index:def sorensen_dice_index(s1, s2):
    set1 = set(s1)
    set2 = set(s2)
    intersection = set1.intersection(set2)
    return (2 * len(intersection)) / (len(set1) + len(set2))

# Example usage
string1 = "hello"
string2 = "hallo"
print("Sørensen-Dice index:", sorensen_dice_index(string1, string2))

#clcoding.com
Sørensen-Dice index: 0.75



9. Haversine Distance:def haversine_distance(lat1, lon1, lat2, lon2):
    R = 6371.0  # Radius of the earth in km
    dLat = np.deg2rad(lat2 - lat1)
    dLon = np.deg2rad(lon2 - lon1)
    a = np.sin(dLat / 2)**2 + np.cos(np.deg2rad(lat1)) * np.cos(np.deg2rad(lat2)) * np.sin(dLon / 2)**2
    c = 2 * np.arctan2(np.sqrt(a), np.sqrt(1 - a))
    return R * c

# Example usage
print("Haversine distance:", haversine_distance(51.5074, 0.1278, 40.7128, -74.0060))

#clcoding.com
  Input In [14]
    a = np.sin(dLat / 2)**2 + np.cos(np.deg2rad(lat1)) *
                                                         ^
SyntaxError: invalid syntax
10. Mahalanobis Distance:from scipy.spatial.distance import cdist

def mahalanobis_distance(X, Y):
    return cdist(X.reshape(1,-1), Y.reshape(1,-1), 'mahalanobis', VI=np.cov(X))

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Mahalanobis distance:", mahalanobis_distance(point1, point2))

#clcoding.com
Mahalanobis distance: [[1.41421356]]



11. Pearson Correlation:from scipy.stats import pearsonr

def pearson_correlation(X, Y):
    return pearsonr(X, Y)[0]

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Pearson correlation:", pearson_correlation(point1, point2))

#clcoding.com
Pearson correlation: 1.0
12. Squared Euclidean Distance:def squared_euclidean_distance(X, Y):
    return euclidean_distance(X, Y)**2

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Squared Euclidean distance:", squared_euclidean_distance(point1, point2))

#clcoding.com
Squared Euclidean distance: 8.000000000000002



13. Jensen-Shannon Divergence:def jensen_shannon_divergence(X, Y):
    M = 0.5 * (X + Y)
    return np.sqrt(0.5 * (rel_entr(X, M).sum() + rel_entr(Y, M).sum()))

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Jensen-Shannon divergence:", jensen_shannon_divergence(point1, point2))

#clcoding.com
Jensen-Shannon divergence: 0.6569041853099059
14. Chi-Square Distance:def chi_square_distance(X, Y):
    X = X / np.sum(X)
    Y = Y / np.sum(Y)
    return np.sum((X - Y) ** 2 / (X + Y))

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Chi-Square distance:", chi_square_distance(point1, point2))

#clcoding.com
Chi-Square distance: 0.01923076923076923



15. Spearman Correlation:from scipy.stats import spearmanr

def spearman_correlation(X, Y):
    return spearmanr(X, Y)[0]

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Spearman correlation:", spearman_correlation(point1, point2))

#clcoding.com
Spearman correlation: 0.9999999999999999
16. Canberra Distance:from scipy.spatial.distance import canberra

def canberra_distance(X, Y):
    return canberra(X, Y)

# Example usage
point1 = np.array([1, 2])
point2 = np.array([3, 4])
print("Canberra distance:", canberra_distance(point1, point2))

#clcoding.com
Canberra distance: 0.8333333333333333