|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
import pandas as pd import numpy as np beer=pd.read_csv('data.txt',sep=' ') # print(beer) X=beer[["calories","sodium","alcohol","cost"]] # print(X) from sklearn.cluster import KMeans km=KMeans(n_clusters=3).fit(X) km2=KMeans(n_clusters=2).fit(X) # print(km.labels_) beer["cluster"]=km.labels_ beer["cluster2"]=km2.labels_ # print(beer.sort_values('cluster')) # print(beer.groupby("cluster").mean().reset_index()) import matplotlib.pyplot as plt colors=np.array(['red','green','blue','yellow']) # plt.scatter(beer['calories'],beer["alcohol"],c=colors[beer["cluster"]]) # plt.xlabel('Calories') # plt.ylabel('Alcohol') # plt.show() # pd.scatter_matrix(beer[["calories","sodium","alcohol","cost"]],c=colors[beer["cluster"]], figsize=(10, 6)) # plt.show() # Scaled data from sklearn.preprocessing import StandardScaler scaler=StandardScaler() X_scaled=scaler.fit_transform(X) # print(X_scaled) km3=KMeans(n_clusters=3).fit(X_scaled) beer["scale_cluster"]=km3.labels_ # print(beer.sort_values('scale_cluster')) from sklearn import metrics score_scaled=metrics.silhouette_score(X,beer.scale_cluster) score=metrics.silhouette_score(X,beer.cluster) # print(score_scaled,score) scores=[] for k in range(2,20): labels=KMeans(n_clusters=k).fit(X).labels_ score=metrics.silhouette_score(X,labels) scores.append(score) plt.plot(list(range(2,20)),scores) plt.xlabel("Number of Clusters Initialized") plt.ylabel("Sihouette Score") plt.xticks(np.arange(2,20,1)) plt.show() from sklearn.cluster import DBSCAN db=DBSCAN(eps=10,min_samples=2).fit(X) labels=db.labels_ beer['cluster_db']=labels beer.sort_values('cluster_db') print(beer) |