February vs July Average Temperatures

Well, as you remember, there are no 100% correct answers to clustering problems. For the last task you solved it seems like 5 clusters might be a good option.

Let's visualize the results of clustering into 5 groups by building the scatter plot for average February vs July temperatures, which are one of the coldest and hottest months respectively.

Opgave

Swipe to start coding

Create a KMeans model named model with 5 clusters.
Fit the numerical columns of data (2 - 13 indices) to model.
Add the 'prediction' column to the data DataFrame with predicted by model labels.
Build a scatter plot of average 'Feb' vs 'Jul' temperatures, having each point colored with respect to the 'prediction' column of the data DataFrame.

Løsning

# Import the libraries

import pandas as pd

import seaborn as sns

import matplotlib.pyplot as plt

from sklearn.cluster import KMeans

# Read the data

data = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/138ab9ad-aa37-4310-873f-0f62abafb038/Cities+weather.csv', index_col = 0)

# Create KMeans model

model = KMeans(n_clusters = 5)

# Fit the data to model

model.fit(data.iloc[:,2:14])

# Predict the labels

data['prediction'] = model.predict(data.iloc[:,2:14])

# Visualize the results

sns.scatterplot(x = 'Feb', y = 'Jul', hue = 'prediction', data = data)

plt.show()

Var alt klart?

Tak for dine kommentarer!

Sektion 1. Kapitel 7

single

# Import the libraries

import pandas as pd

import seaborn as sns

import matplotlib.pyplot as plt

from sklearn.cluster import KMeans

# Read the data

data = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/138ab9ad-aa37-4310-873f-0f62abafb038/Cities+weather.csv', index_col = 0)

# Create KMeans model

model = ___(___ = ___)

# Fit the data to model

___.___(data.iloc[:,2:14])

# Predict the labels

data['prediction'] = ___.___(data.___[___])

# Visualize the results

sns.scatterplot(x = '___', y = '___', hue = '___', data = ___)

plt.show()

Spørg AI

Spørg om hvad som helst eller prøv et af de foreslåede spørgsmål for at starte vores chat