Iris Dataset¶

In [1]:

#Uncomment the next line and run this cell to install sorix
#!pip install 'sorix @ git+https://github.com/Mitchell-Mirano/sorix.git@main'

#Uncomment the next line and run this cell to install sorix #!pip install 'sorix @ git+https://github.com/Mitchell-Mirano/sorix.git@main'

In [2]:

import pandas as pd
import matplotlib.pyplot as plt
from sorix.clustering import Kmeans
from sorix import tensor

import pandas as pd import matplotlib.pyplot as plt from sorix.clustering import Kmeans from sorix import tensor

In [3]:

data=pd.read_csv("../data/Iris.csv")
data.head()

data=pd.read_csv("../data/Iris.csv") data.head()

Out[3]:

	Id	SepalLengthCm	SepalWidthCm	PetalLengthCm	PetalWidthCm	Species
0	1	5.1	3.5	1.4	0.2	Iris-setosa
1	2	4.9	3.0	1.4	0.2	Iris-setosa
2	3	4.7	3.2	1.3	0.2	Iris-setosa
3	4	4.6	3.1	1.5	0.2	Iris-setosa
4	5	5.0	3.6	1.4	0.2	Iris-setosa

In [4]:

data['labels'] = data.Species.map({'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2})
data.head()

data['labels'] = data.Species.map({'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}) data.head()

Out[4]:

	Id	SepalLengthCm	SepalWidthCm	PetalLengthCm	PetalWidthCm	Species	labels
0	1	5.1	3.5	1.4	0.2	Iris-setosa	0
1	2	4.9	3.0	1.4	0.2	Iris-setosa	0
2	3	4.7	3.2	1.3	0.2	Iris-setosa	0
3	4	4.6	3.1	1.5	0.2	Iris-setosa	0
4	5	5.0	3.6	1.4	0.2	Iris-setosa	0

In [5]:

plt.figure(figsize=(12,8))
plt.scatter(data['PetalLengthCm'],data['PetalWidthCm'],s=80, c=data['labels'])

plt.figure(figsize=(12,8)) plt.scatter(data['PetalLengthCm'],data['PetalWidthCm'],s=80, c=data['labels'])

Out[5]:

<matplotlib.collections.PathCollection at 0x7fd200b0bcb0>

In [6]:

X=data[['PetalLengthCm','PetalWidthCm','PetalLengthCm','PetalWidthCm']].to_numpy()
X = tensor(X)
X

X=data[['PetalLengthCm','PetalWidthCm','PetalLengthCm','PetalWidthCm']].to_numpy() X = tensor(X) X

Out[6]:

tensor([[1.4, 0.2, 1.4, 0.2],
        [1.4, 0.2, 1.4, 0.2],
        [1.3, 0.2, 1.3, 0.2],
        [1.5, 0.2, 1.5, 0.2],
        [1.4, 0.2, 1.4, 0.2],
        [1.7, 0.4, 1.7, 0.4],
        [1.4, 0.3, 1.4, 0.3],
        [1.5, 0.2, 1.5, 0.2],
        [1.4, 0.2, 1.4, 0.2],
        [1.5, 0.1, 1.5, 0.1],
        [1.5, 0.2, 1.5, 0.2],
        [1.6, 0.2, 1.6, 0.2],
        [1.4, 0.1, 1.4, 0.1],
        [1.1, 0.1, 1.1, 0.1],
        [1.2, 0.2, 1.2, 0.2],
        [1.5, 0.4, 1.5, 0.4],
        [1.3, 0.4, 1.3, 0.4],
        [1.4, 0.3, 1.4, 0.3],
        [1.7, 0.3, 1.7, 0.3],
        [1.5, 0.3, 1.5, 0.3],
        [1.7, 0.2, 1.7, 0.2],
        [1.5, 0.4, 1.5, 0.4],
        [1. , 0.2, 1. , 0.2],
        [1.7, 0.5, 1.7, 0.5],
        [1.9, 0.2, 1.9, 0.2],
        [1.6, 0.2, 1.6, 0.2],
        [1.6, 0.4, 1.6, 0.4],
        [1.5, 0.2, 1.5, 0.2],
        [1.4, 0.2, 1.4, 0.2],
        [1.6, 0.2, 1.6, 0.2],
        [1.6, 0.2, 1.6, 0.2],
        [1.5, 0.4, 1.5, 0.4],
        [1.5, 0.1, 1.5, 0.1],
        [1.4, 0.2, 1.4, 0.2],
        [1.5, 0.1, 1.5, 0.1],
        [1.2, 0.2, 1.2, 0.2],
        [1.3, 0.2, 1.3, 0.2],
        [1.5, 0.1, 1.5, 0.1],
        [1.3, 0.2, 1.3, 0.2],
        [1.5, 0.2, 1.5, 0.2],
        [1.3, 0.3, 1.3, 0.3],
        [1.3, 0.3, 1.3, 0.3],
        [1.3, 0.2, 1.3, 0.2],
        [1.6, 0.6, 1.6, 0.6],
        [1.9, 0.4, 1.9, 0.4],
        [1.4, 0.3, 1.4, 0.3],
        [1.6, 0.2, 1.6, 0.2],
        [1.4, 0.2, 1.4, 0.2],
        [1.5, 0.2, 1.5, 0.2],
        [1.4, 0.2, 1.4, 0.2],
        [4.7, 1.4, 4.7, 1.4],
        [4.5, 1.5, 4.5, 1.5],
        [4.9, 1.5, 4.9, 1.5],
        [4. , 1.3, 4. , 1.3],
        [4.6, 1.5, 4.6, 1.5],
        [4.5, 1.3, 4.5, 1.3],
        [4.7, 1.6, 4.7, 1.6],
        [3.3, 1. , 3.3, 1. ],
        [4.6, 1.3, 4.6, 1.3],
        [3.9, 1.4, 3.9, 1.4],
        [3.5, 1. , 3.5, 1. ],
        [4.2, 1.5, 4.2, 1.5],
        [4. , 1. , 4. , 1. ],
        [4.7, 1.4, 4.7, 1.4],
        [3.6, 1.3, 3.6, 1.3],
        [4.4, 1.4, 4.4, 1.4],
        [4.5, 1.5, 4.5, 1.5],
        [4.1, 1. , 4.1, 1. ],
        [4.5, 1.5, 4.5, 1.5],
        [3.9, 1.1, 3.9, 1.1],
        [4.8, 1.8, 4.8, 1.8],
        [4. , 1.3, 4. , 1.3],
        [4.9, 1.5, 4.9, 1.5],
        [4.7, 1.2, 4.7, 1.2],
        [4.3, 1.3, 4.3, 1.3],
        [4.4, 1.4, 4.4, 1.4],
        [4.8, 1.4, 4.8, 1.4],
        [5. , 1.7, 5. , 1.7],
        [4.5, 1.5, 4.5, 1.5],
        [3.5, 1. , 3.5, 1. ],
        [3.8, 1.1, 3.8, 1.1],
        [3.7, 1. , 3.7, 1. ],
        [3.9, 1.2, 3.9, 1.2],
        [5.1, 1.6, 5.1, 1.6],
        [4.5, 1.5, 4.5, 1.5],
        [4.5, 1.6, 4.5, 1.6],
        [4.7, 1.5, 4.7, 1.5],
        [4.4, 1.3, 4.4, 1.3],
        [4.1, 1.3, 4.1, 1.3],
        [4. , 1.3, 4. , 1.3],
        [4.4, 1.2, 4.4, 1.2],
        [4.6, 1.4, 4.6, 1.4],
        [4. , 1.2, 4. , 1.2],
        [3.3, 1. , 3.3, 1. ],
        [4.2, 1.3, 4.2, 1.3],
        [4.2, 1.2, 4.2, 1.2],
        [4.2, 1.3, 4.2, 1.3],
        [4.3, 1.3, 4.3, 1.3],
        [3. , 1.1, 3. , 1.1],
        [4.1, 1.3, 4.1, 1.3],
        [6. , 2.5, 6. , 2.5],
        [5.1, 1.9, 5.1, 1.9],
        [5.9, 2.1, 5.9, 2.1],
        [5.6, 1.8, 5.6, 1.8],
        [5.8, 2.2, 5.8, 2.2],
        [6.6, 2.1, 6.6, 2.1],
        [4.5, 1.7, 4.5, 1.7],
        [6.3, 1.8, 6.3, 1.8],
        [5.8, 1.8, 5.8, 1.8],
        [6.1, 2.5, 6.1, 2.5],
        [5.1, 2. , 5.1, 2. ],
        [5.3, 1.9, 5.3, 1.9],
        [5.5, 2.1, 5.5, 2.1],
        [5. , 2. , 5. , 2. ],
        [5.1, 2.4, 5.1, 2.4],
        [5.3, 2.3, 5.3, 2.3],
        [5.5, 1.8, 5.5, 1.8],
        [6.7, 2.2, 6.7, 2.2],
        [6.9, 2.3, 6.9, 2.3],
        [5. , 1.5, 5. , 1.5],
        [5.7, 2.3, 5.7, 2.3],
        [4.9, 2. , 4.9, 2. ],
        [6.7, 2. , 6.7, 2. ],
        [4.9, 1.8, 4.9, 1.8],
        [5.7, 2.1, 5.7, 2.1],
        [6. , 1.8, 6. , 1.8],
        [4.8, 1.8, 4.8, 1.8],
        [4.9, 1.8, 4.9, 1.8],
        [5.6, 2.1, 5.6, 2.1],
        [5.8, 1.6, 5.8, 1.6],
        [6.1, 1.9, 6.1, 1.9],
        [6.4, 2. , 6.4, 2. ],
        [5.6, 2.2, 5.6, 2.2],
        [5.1, 1.5, 5.1, 1.5],
        [5.6, 1.4, 5.6, 1.4],
        [6.1, 2.3, 6.1, 2.3],
        [5.6, 2.4, 5.6, 2.4],
        [5.5, 1.8, 5.5, 1.8],
        [4.8, 1.8, 4.8, 1.8],
        [5.4, 2.1, 5.4, 2.1],
        [5.6, 2.4, 5.6, 2.4],
        [5.1, 2.3, 5.1, 2.3],
        [5.1, 1.9, 5.1, 1.9],
        [5.9, 2.3, 5.9, 2.3],
        [5.7, 2.5, 5.7, 2.5],
        [5.2, 2.3, 5.2, 2.3],
        [5. , 1.9, 5. , 1.9],
        [5.2, 2. , 5.2, 2. ],
        [5.4, 2.3, 5.4, 2.3],
        [5.1, 1.8, 5.1, 1.8]], dtype=sorix.float64)

In [7]:

model= Kmeans(n_clusters=3)
model.fit(X)

model= Kmeans(n_clusters=3) model.fit(X)

In [8]:

pred_labels = model.predict(X)
plt.figure(figsize=(12,8))
plt.scatter(data['PetalLengthCm'],data['PetalWidthCm'],s=80, c=pred_labels)

for centroid in model.centroids:
    plt.scatter(centroid[0],centroid[1], s=150)

pred_labels = model.predict(X) plt.figure(figsize=(12,8)) plt.scatter(data['PetalLengthCm'],data['PetalWidthCm'],s=80, c=pred_labels) for centroid in model.centroids: plt.scatter(centroid[0],centroid[1], s=150)

In [9]:

pred_labels = model.predict(X)
plt.figure(figsize=(12,8))
plt.scatter(data['PetalLengthCm'],data['PetalWidthCm'],s=80, c=pred_labels)

for centroid in model.centroids:
    plt.scatter(centroid[0],centroid[1], s=150)

pred_labels = model.predict(X) plt.figure(figsize=(12,8)) plt.scatter(data['PetalLengthCm'],data['PetalWidthCm'],s=80, c=pred_labels) for centroid in model.centroids: plt.scatter(centroid[0],centroid[1], s=150)

In [10]:

inertias = []

for i in range(2,11):
    model = Kmeans(n_clusters=i)
    model.fit(X)
    inertias.append(model.get_inertia(X))

import matplotlib.pyplot as plt
plt.plot(range(2,11), inertias, marker='o')

inertias = [] for i in range(2,11): model = Kmeans(n_clusters=i) model.fit(X) inertias.append(model.get_inertia(X)) import matplotlib.pyplot as plt plt.plot(range(2,11), inertias, marker='o')

Out[10]:

[<matplotlib.lines.Line2D at 0x7fd20033cf50>]