Make Simulated Data For Clustering

from sklearn.cluster import KMeans
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

# 3 clusters in 2D
d_means = {'cluster 1': [0, 0], 
           'cluster 2': [4, 5], 
           'cluster 3': [5, 0]}
d_covs = {'cluster 1': [[1, 1], 
                        [1, 4]], 
          'cluster 2': [[1, 1], 
                        [1, 3]], 
          'cluster 3': [[4, 2], 
                        [2, 2]]}

df_tmp.head()

# Generate data based on the above parameters
n_data = 1000

# Generate data based on the above parameters
l = []
for cluster in d_means.keys():
    arr = np.random.multivariate_normal(d_means[cluster], d_covs[cluster], n_data)
    df_tmp = pd.DataFrame(arr)
    df_tmp['label'] = cluster
    l.append(df_tmp)
    plt.plot(df_tmp[0], df_tmp[1], '.', label=cluster, alpha=0.5)

plt.legend()
plt.axis('off')
plt.show()

df_data.head()

df_data.shape

def create_clustered_data(d_means, d_covs, n_data=1000):
    """create artificial data for clustering
    
    Parameters
    ----------
    d_means : dict
        a dictionary of cluster means matrix. 
        The key is cluster name and the value.
        Each value will be passed to np.random.multivariate_normal as mean
    d_covs : dict
        a dictionary of cluster covariance matrix. 
        The key is cluster name and the value.
        Each value will be passed to np.random.multivariate_normal as covariance

    Returns
    -------
    pd.DataFrame
    
    """
    # Generate data based on the above parameters
    l = []
    for cluster in d_means.keys():
        arr = np.random.multivariate_normal(d_means[cluster], d_covs[cluster], n_data)
        df_tmp = pd.DataFrame(arr)
        df_tmp['label'] = cluster
        l.append(df_tmp)
    return pd.concat(l)
create_clustered_data(d_means, d_covs, n_data=1000).head()