df = seaborn.load_dataset("iris")
df_features = df.drop(labels=["species"], axis=1)
df_target = df.filter(items=["species"])

Please note that the output labels are strings. But, a machine learning model understands only numbers. So, we need to label encode the target labels column. Here, we are label encoding the species column of df_target.

encoder = LabelEncoder()
df_target["species"] = encoder.fit_transform(df_target["species"])

Now, we are performing k-means clustering on the dataset. The number of clusters is 3 and the random_state=1 parameter controls the random number generator that is used to randomly initialize the k centroids of the clusters (How does k-means clustering work?)

The fit_predict() method learns from the dataset, performs clustering, and assigns labels to each of the datapoints depending on to which cluster the datapoint belongs.

kmeans = KMeans(n_clusters=3, random_state=1)
y_pred = kmeans.fit_predict(df_features)

Now, we can compare y_pred with the actual labels in df_target[“species”] and measure the clustering performance using the V-measure score.

score = v_measure_score(df_target["species"], y_pred)

The output of the above program will be:

   sepal_length  sepal_width  petal_length  petal_width species
0           5.1          3.5           1.4          0.2  setosa
1           4.9          3.0           1.4          0.2  setosa
2           4.7          3.2           1.3          0.2  setosa
3           4.6          3.1           1.5          0.2  setosa
4           5.0          3.6           1.4          0.2  setosa

V-measure Score:  0.7581756800057786