Notice: This page requires JavaScript to function properly.
Please enable JavaScript in your browser settings or update your browser.Aprenda Clustering Weather Data | K-Means Algorithm
Cluster Analysis in Python
course content

Conteúdo do Curso

Cluster Analysis in Python

Cluster Analysis in Python

1. K-Means Algorithm
Exploratory Data AnalysisWhat is a K-Means Algorithm?Defining the Number of ClustersCase 1: Three Distinct ClustersCase 2: Four Distinct ClustersClustering Weather DataFebruary vs July Average TemperaturesVisualizing the Dynamics Across Clusters
2. K-Medoids Algorithm
What is a K-Medoids Algorithm?Cluster CentersSilhouette ScoresK-Medoids and the Weather DataMean Yearly Temperatures Across ClustersComparing the Dynamics
3. Hierarchical Clustering
What is a Hierarchical Clustering?DendrogramsSetting Parameters: LinkageRand IndexThe Weather Data and LinkagesDeciding the Number of ClustersWeather Data: Complete and Ward LinkagesHow Similar are the Results?
4. Spectral Clustering
What is a Spectral Clustering?Peculiarity of Spectral ClusteringSetting Parameters: AffinityDefining the Number of ClustersIs 4 the Optimal Number of Clusters?Comparing the Trends Across Clusters

book
Clustering Weather Data

Let's work with some real data. If you passed the 'Visualization in Python with matplotlib' course you might remember the USA cities' weather data. We will use an expanded version of this dataset there.

First, let's describe our dataset. It contains 15 columns: Country, City, All the 12 months, and Continent. Obviously, the months' columns are numerical and contain the average monthly temperature in Fahrenheit. For example, each row of this DataFrame looks like this.

We may guess that it would be logical to cluster by continent. But let's remind, that all the continents combine different climate types, which depend on proximity to the sea, to the ocean, to mountains, and so on. So, let's find out how will K-Means algorithm divide the observations.

Tarefa

Swipe to start coding

Given DataFrame data. Watch out, that numerical columns have indices 2 - 13! Table

  1. Import the pandas, seaborn libraries with their standard aliases (pd and sns respectively), and KMeans from sklearn.clusters.
  2. Create range object with integers from 2 to 9 assigned to clusters variable.
  3. Iterate over clusters values. At each step:
  • Initialize KMeans model with new number of clusters (i).
  • Fit the model to 2-13 (indices) columns of data. Remember .iloc[] method of DataFrame. You can pass the first parameter to access certain rows, and the second to access columns.
  • Add model total within sum of squares value (value of .inertia_ attribute of model) to variances list.
  1. Display the seaborn lineplot "number of clusters vs total within sum of squares" (clusters - x-axis vs variances - y-axis).

Solução

Switch to desktopMude para o desktop para praticar no mundo realContinue de onde você está usando uma das opções abaixo
Tudo estava claro?

Como podemos melhorá-lo?

Obrigado pelo seu feedback!

Seção 1. Capítulo 6
toggle bottom row

book
Clustering Weather Data

Let's work with some real data. If you passed the 'Visualization in Python with matplotlib' course you might remember the USA cities' weather data. We will use an expanded version of this dataset there.

First, let's describe our dataset. It contains 15 columns: Country, City, All the 12 months, and Continent. Obviously, the months' columns are numerical and contain the average monthly temperature in Fahrenheit. For example, each row of this DataFrame looks like this.

We may guess that it would be logical to cluster by continent. But let's remind, that all the continents combine different climate types, which depend on proximity to the sea, to the ocean, to mountains, and so on. So, let's find out how will K-Means algorithm divide the observations.

Tarefa

Swipe to start coding

Given DataFrame data. Watch out, that numerical columns have indices 2 - 13! Table

  1. Import the pandas, seaborn libraries with their standard aliases (pd and sns respectively), and KMeans from sklearn.clusters.
  2. Create range object with integers from 2 to 9 assigned to clusters variable.
  3. Iterate over clusters values. At each step:
  • Initialize KMeans model with new number of clusters (i).
  • Fit the model to 2-13 (indices) columns of data. Remember .iloc[] method of DataFrame. You can pass the first parameter to access certain rows, and the second to access columns.
  • Add model total within sum of squares value (value of .inertia_ attribute of model) to variances list.
  1. Display the seaborn lineplot "number of clusters vs total within sum of squares" (clusters - x-axis vs variances - y-axis).

Solução

Switch to desktopMude para o desktop para praticar no mundo realContinue de onde você está usando uma das opções abaixo
Tudo estava claro?

Como podemos melhorá-lo?

Obrigado pelo seu feedback!

Seção 1. Capítulo 6
Switch to desktopMude para o desktop para praticar no mundo realContinue de onde você está usando uma das opções abaixo
Sentimos muito que algo saiu errado. O que aconteceu?
some-alt