Build a Machine Learning Model - Unsupervised Learning

                                

# Calculate the distance between two points
import numpy as np

def calculate_distance(a, b):
  return np.sqrt((a[0] - b[0]) ** 2 + (a[1] - b[1]) ** 2)

point1 = [1, 2]
point2 = [4, 6]
print(calculate_distance(point1, point2))
# Output will be the distance between the two points


                              

                                

from sklearn.cluster import KMeans

# Example data
data_samples = [[1, 2], [2, 3], [5, 6], [8, 9]]

# Create and fit K-Means model
model = KMeans(n_clusters=2)
model.fit(data_samples)
labels = model.predict(data_samples)
print(labels)
# Output will show the cluster each sample belongs to


                              

                                

import matplotlib.pyplot as plt
from sklearn.cluster import KMeans

# Sample data
data_samples = [[1, 2], [2, 3], [5, 6], [8, 9]]

# Calculate inertia for different K values
inertia = []
for k in range(1, 5):
    model = KMeans(n_clusters=k)
    model.fit(data_samples)
    inertia.append(model.inertia_)

# Plot the Elbow graph
plt.plot(range(1, 5), inertia, marker='o')
plt.xlabel('Number of Clusters')
plt.ylabel('Inertia')
plt.title('Elbow Method')
plt.show()


                              

                                

from sklearn.cluster import KMeans

# Sample data
data_samples = [[1, 2], [2, 3], [5, 6], [8, 9]]

# Create and fit K-Means model
model = KMeans(n_clusters=2)
model.fit(data_samples)
print(model.cluster_centers_)
# Output will show the center points of each cluster


                              

                                

from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans

# Generate sample data
data_samples, _ = make_blobs(n_samples=300, centers=4)

# Create and fit K-Means model
model = KMeans(n_clusters=4)
model.fit(data_samples)
labels = model.predict(data_samples)
print(labels)
# Output will show the cluster assignments for each data point


                              

                                

import pandas as pd

# Sample data with predicted and actual labels
pred_labels = [1, 0, 1, 0]
user_labels = [1, 0, 1, 0]

# Create a cross-tabulation
cross_tab = pd.crosstab(pd.Series(pred_labels), pd.Series(user_labels))
print(cross_tab)
# Output will show a table comparing predicted vs actual labels