from sklearn.cluster import KMeans
import numpy as np
x = np.random.random(10000)
y = x.reshape(-1,1)
km = KMeans()
km.fit(y)

  
  
from jenkspy import jenks_breaks
import numpy as np
 
 
def goodness_of_variance_fit(array, classes):
    # get the break points
    classes = jenks_breaks(array, classes)
 
    # do the actual classification
    classified = np.array([classify(i, classes) for i in array])
 
    # max value of zones
    maxz = max(classified)
 
    # nested list of zone indices
    zone_indices = [[idx for idx, val in enumerate(classified) if zone + 1  val] for zone in range(maxz)]
 
    # sum of squared deviations from array mean
    sdam = np.sum((array - array.mean())  2)
 
    # sorted polygon stats
    array_sort = [np.array([array[index] for index in zone]) for zone in zone_indices]
 
    # sum of squared deviations of class means
    sdcm = sum([np.sum((classified - classified.mean())  2) for classified in array_sort])
 
    # goodness of variance fit
    gvf = (sdam - sdcm) / sdam
 
    return gvf
 
 
def classify(value, breaks):
    for i in range(1, len(breaks)):
        if value < breaks[i]:
            return i
    return len(breaks) - 1
 
 
if name  ‘main’:
    gvf = 0.0
    nclasses = 2
    array = np.random.random(10000)
    while gvf < .8:
        gvf = goodness_of_variance_fit(array, nclasses)
        print(nclasses, gvf)
        nclasses += 1

  
  
import numpy as np
from scipy.signal import argrelextrema
import matplotlib.pyplot as plt
from sklearn.neighbors.kde import KernelDensity
 
a = np.array([10, 11, 9, 23, 21, 11, 45, 20, 11, 12]).reshape(-1, 1)
kde = KernelDensity(kernel=‘gaussian’, bandwidth=3).fit(a)
s = np.linspace(0, 50)
e = kde.score_samples(s.reshape(-1, 1))
plt.plot(s, e)
plt.show()
 
mi, ma = argrelextrema(e, np.less)[0], argrelextrema(e, np.greater)[0]
print(“Minima:”, s[mi])
print(“Maxima:”, s[ma])
print(a[a < mi[0]], a[(a >= mi[0]) * (a <= mi[1])], a[a >= mi[1]])
 
plt.plot(s[:mi[0] + 1], e[:mi[0] + 1], ‘r’,
         s[mi[0]:mi[1] + 1], e[mi[0]:mi[1] + 1], ‘g’,
         s[mi[1]:], e[mi[1]:], ‘b’,
         s[ma], e[ma], ‘go’,
         s[mi], e[mi], ‘ro’)
plt.show()

  
  
Minima: [17.34693878 33.67346939]
Maxima: [10.20408163 21.42857143 44.89795918]
[10 11  9 11 11 12] [23 21 20] [45]