import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.cluster import KMeans

# Sample data $($replace this with your actual data$)$

data $=\{$

"Passenger Count": $[27271,29131,5415,35156,34090],$

"Price Category Code$\_$Low Fare": $[$True$,$ True, True, False, False$],$

"Price Category Code$\_$Other": $[$False$,$ False, False, True, True$],$

"GEO Summary$\_$Domestic": $[$True$,$ True, True, False, False$],$

"GEO Summary$\_$International": $[$False$,$ False, False, True, True$],$

"Cluster": $[0,0,0,3,3]$

$\}$

# Create a DataFrame

df $=$ pd$.$DataFrame$($data$)$

# Extract features for clustering $($you can select specific columns based on your requirement$)$

features $=$ df$[["$Passenger Count", "Price Category Code$\_$Low Fare", "Price Category Code$\_$Other", "GEO Summary$\_$Domestic", "GEO Summary$\_$International"$]]$

# Fit K$-$means clustering model

kmeans $=$ KMeans$($n$\_$clusters$=4)$ # Change the number of clusters as per your analysis

kmeans.fit$($features$)$

# Add cluster labels to the DataFrame

df$[\text{'}$Cluster$\text{'}]=$ kmeans.labels$\_$

# Visualize the clusters for all pairs of features

fig, axs $=$ plt$.$subplots$(2,3,$ figsize$=(18,12))$

# Flatten the axs array for easy iteration

axs $=$ axs.flatten$()$

# Initialize a counter for the subplot index

subplot$\_$index $=0$

# Plot each pair of features with color$-$coded clusters

for i$,$ feature$1$ in enumerate$($features$.$columns$)$:

for j$,$ feature$2$ in enumerate$($features$.$columns$)$:

if i $<$ j: # This ensures that each pair is plotted only once

ax $=$ axs$[$subplot$\_$index$]$

ax$.$scatter$($df$[$feature$1],$ df$[$feature$2],$ c$=$df$[\text{'}$Cluster$\text{'}],$ cmap$=$'viridis', s$=50,$ alpha$=0\mathrm{.}7)$

ax$.$set$\_$xlabel$($feature$1)$

ax$.$set$\_$ylabel$($feature$2)$

subplot$\_$index $+=1$ # Increment the subplot index

# Plot cluster centroids for each pair of features

for cluster in range$($kmeans$.$n$\_$clusters$)$:

subplot$\_$index $=0$ # Reset the subplot index for centroids

for i$,$ feature$1$ in enumerate$($features$.$columns$)$:

for j$,$ feature$2$ in enumerate$($features$.$columns$)$:

if i $<$ j: # This ensures that each pair is plotted only once

ax $=$ axs$[$subplot$\_$index$]$

ax$.$scatter$($kmeans$.$cluster$\_$centers$\_[$cluster$][$i$],$ kmeans.cluster$\_$centers$\_[$cluster$][$j$],$ c$=$'red', marker$=\text{'}$x$\text{'},$ s$=200,$ label$=$f'Cluster $\{$cluster$\}\text{'})$

subplot$\_$index $+=1$ # Increment the subplot index

plt$.$tight$\_$layout$()$

plt$.$show$()$

For the above code i am getting the below error

$\{$

"name": "IndexError",

"message": "index $6$ is out of bounds for axis $0$ with size $6",$

"stack": $"---------------------------------------------------------------------------$

IndexError Traceback $($most recent call last$)$

Cell In$[178],$ line $42$

$40$ for j$,$ feature$2$ in enumerate$($features$.$columns$)$:

$41$ if i $<$ j: # This ensures that each pair is plotted only once

$--->42$ ax $=$ axs$[$subplot$\_$index$]$

$43$ ax$.$scatter$($df$[$feature$1],$ df$[$feature$2],$ c$=$df$[\text{'}$Cluster$\text{'}],$ cmap$=$'viridis', s$=50,$ alpha$=0\mathrm{.}7)$

$44$ ax$.$set$\_$xlabel$($feature$1)$

IndexError: index $6$ is out of bounds for axis $0$ with size $6"$

Kindly resolve this $.$ also i am sharing the dataframe information : Dimensions of DataFrame $($rows$,$ columns$)$: $(5,6)$

Column labels: Index$([\text{'}$Passenger Count', 'Price Category Code$\_$Low Fare',

'Price Category Code$\_$Other', 'GEO Summary$\_$Domestic',

'GEO Summary$\_$International', 'Cluster'$],$

dtype$=$'object'$)$