Im doing some analytics using python 3.5 and anaconda.

in K means Clustering python will not recognise ggplot, even after importing.

any alternatives to ggplot?

this is my code

_{import pandas as pd import numpy as np from sklearn.cluster import KMeans from sklearn.decomposition import PCA from ggplot import aes from ggplot import *}

_{data = pd.read_csv(r'C:\Users\user\Anaconda3\envs\assign\land-area-population-density-london.csv') data.columns = ["Codes","Ward names" ,"Borough", "Hectares", "Square Kilometres", "Population 2015", "Population per hectare 2015", "Population per square kilometre 2015", "Census population(2011)", "Population per hectare 2011"]}

_{#creating a matrix table}

_{matrix = data.pivot_table(index=['Ward names'], columns=['Borough','Population per hectare 2015', 'Population per hectare 2011']) print(matrix)}

_{matrix = matrix.fillna(0).reset_index() x_cols = matrix.columns[1:]}

_{cluster = KMeans(n_clusters=5)}

_{matrix['cluster']= cluster.fit_predict(matrix[matrix.columns[3:]])}

_{pca = PCA(n_components=2)}

_{matrix['x'] = pca.fit_transform(matrix[x_cols])[:,0] matrix['y'] = pca.fit_transform(matrix[x_cols])[:,1]}

_{matrix = matrix.reset_index()}

_{customer_clusters = matrix [['Ward names', 'cluster', 'x', 'y']] #works up to here}

_{g = ggplot(data, aes(x='x', y='y',color='cluster')) +\ geom_point(size=75) +\ ggtitle("Clustering based on Area")}