9/23/24, 4:39 PM 21BCE2920.

ipynb - Colab

import math
import os
import gc
import random

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns
import pprint

from sklearn.cluster import KMeans

from sklearn.preprocessing import StandardScaler

input_data = pd.read_csv("Iris.csv")
input_data.head()

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

Next steps: Generate code with input_data

toggle_off View recommended plots New interactive sheet

input_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 6 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Id 150 non-null int64
1 SepalLengthCm 150 non-null float64
2 SepalWidthCm 150 non-null float64
3 PetalLengthCm 150 non-null float64
4 PetalWidthCm 150 non-null float64
5 Species 150 non-null object
dtypes: float64(4), int64(1), object(1)
memory usage: 7.2+ KB

input_data = pd.get_dummies(input_data)
input_data = input_data.drop(['Id'], axis = 1)
input_data

Species_Iris- Species_Iris- Species_Iris-

SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm
setosa versicolor virginica

0 5.1 3.5 1.4 0.2 True False False

1 4.9 3.0 1.4 0.2 True False False

2 4.7 3.2 1.3 0.2 True False False

3 4.6 3.1 1.5 0.2 True False False

4 5.0 3.6 1.4 0.2 True False False

... ... ... ... ... ... ... ...

145 6.7 3.0 5.2 2.3 False False True

146 6.3 2.5 5.0 1.9 False False True

147 6.5 3.0 5.2 2.0 False False True

148 6.2 3.4 5.4 2.3 False False True

149 5.9 3.0 5.1 1.8 False False True

Next steps: Generate code with input_data

toggle_off View recommended plots New interactive sheet

scaled_data = StandardScaler().fit_transform(input_data)
scaled_data[:10]

https://colab.research.google.com/drive/1FoEQ0l5WVUciLo7jL2A2eWqAuGB1pwE_#scrollTo=SPDHHI7Miz6h&printMode=true 1/3
9/23/24, 4:39 PM 21BCE2920.ipynb - Colab

array([[-0.90068117, 1.03205722, -1.3412724 , -1.31297673, 1.41421356,

-0.70710678, -0.70710678],
[-1.14301691, -0.1249576 , -1.3412724 , -1.31297673, 1.41421356,
-0.70710678, -0.70710678],
[-1.38535265, 0.33784833, -1.39813811, -1.31297673, 1.41421356,
-0.70710678, -0.70710678],
[-1.50652052, 0.10644536, -1.2844067 , -1.31297673, 1.41421356,
-0.70710678, -0.70710678],
[-1.02184904, 1.26346019, -1.3412724 , -1.31297673, 1.41421356,
-0.70710678, -0.70710678],
[-0.53717756, 1.95766909, -1.17067529, -1.05003079, 1.41421356,
-0.70710678, -0.70710678],
[-1.50652052, 0.80065426, -1.3412724 , -1.18150376, 1.41421356,
-0.70710678, -0.70710678],
[-1.02184904, 0.80065426, -1.2844067 , -1.31297673, 1.41421356,
-0.70710678, -0.70710678],
[-1.74885626, -0.35636057, -1.3412724 , -1.31297673, 1.41421356,
-0.70710678, -0.70710678],
[-1.14301691, 0.10644536, -1.2844067 , -1.4444497 , 1.41421356,
-0.70710678, -0.70710678]])

kmeans_kwargs = {
"init": "random",
"n_init": 10,
"random_state": 1,
}

sse = []
for k in range(1, 11):
kmeans = KMeans(n_clusters=k, **kmeans_kwargs)
kmeans.fit(scaled_data)
sse.append(kmeans.inertia_)
plt.plot(range(1, 11), sse)
plt.xticks(range(1, 11))
plt.xlabel("Number of Clusters")
plt.ylabel("SSE")
plt.show()

kmeans = KMeans(init="random", n_clusters=4, n_init=10, random_state=1)

kmeans.fit(scaled_data)
kmeans.labels_

array([2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 3, 1, 3, 1, 1, 3, 1, 3, 1,
1, 3, 1, 3, 3, 1, 1, 1, 1, 3, 1, 3, 1, 3, 1, 1, 3, 3, 3, 1, 1, 1,
3, 3, 3, 1, 1, 1, 3, 1, 1, 1, 3, 1, 1, 1, 3, 1, 1, 3], dtype=int32)

Start coding or generate with AI.

https://colab.research.google.com/drive/1FoEQ0l5WVUciLo7jL2A2eWqAuGB1pwE_#scrollTo=SPDHHI7Miz6h&printMode=true 2/3
9/23/24, 4:39 PM 21BCE2920.ipynb - Colab

https://colab.research.google.com/drive/1FoEQ0l5WVUciLo7jL2A2eWqAuGB1pwE_#scrollTo=SPDHHI7Miz6h&printMode=true 3/3