Python使用树状图实现可视化聚类详解

import pandasaspd
import requests
 
 companies={'Apple':'AAPL','Amazon':'AMZN','Facebook':'META','Tesla':'TSLA','Alphabet (Google)':'GOOGL','Shell':'SHEL','Suncor Energy':'SU',
            'Exxon Mobil Corp':'XOM','Lululemon':'LULU','Walmart':'WMT','Carters':'CRI','Childrens Place':'PLCE','TJX Companies':'TJX',
            'Victorias Secret':'VSCO','MACYs':'M','Wayfair':'W','Dollar Tree':'DLTR','CVS Caremark':'CVS','Walgreen':'WBA','Curaleaf':'CURLF'}

import time
 
 all_data={}
 forkey,valueincompanies.items():  
 # Replace YOUR_API_KEY with your Alpha Vantage API key
   url=f'https://www.alphavantage.co/query?function=TIME_SERIES_DAILY_ADJUSTED&symbol={value}&apikey=<YOUR_API_KEY>&outputsize=full'
   response=requests.get(url)
   data=response.json()
   time.sleep(15)
   if'Time Series (Daily)'indataanddata['Time Series (Daily)']:
     df=pd.DataFrame.from_dict(data['Time Series (Daily)'], orient='index')
     print(f'Received data for {key}')
   else:
     print("Time series data is empty or not available.")
   df.rename(columns= {'1. open':key}, inplace=True)
   all_data[key]=df[key]

# find common dates among all data frames
 common_dates=None
 fordf_key, dfinall_data.items():
     ifcommon_datesisNone:
         common_dates=set(df.index)
     else:
         common_dates=common_dates.intersection(df.index)
 
 common_dates=sorted(list(common_dates))
 
 # create new data frame with common dates as index
 df_combined=pd.DataFrame(index=common_dates)
 
 # reindex each data frame with common dates and concatenate horizontally
 fordf_key, dfinall_data.items():
     df_combined=pd.concat([df_combined, df.reindex(common_dates)], axis=1)

import numpyasnp
import scipy.cluster.hierarchyassch
import matplotlib.pyplotasplt
 
 # Convert correlation matrix to distance matrix
 dist_mat=1-df_combined.corr()
 
 # Perform top-down clustering
 clustering=sch.linkage(dist_mat, method='complete')
 cuts=sch.cut_tree(clustering, n_clusters=[3, 4])
 
 # Plot dendrogram
 plt.figure(figsize=(10, 5))
 sch.dendrogram(clustering, labels=list(df_combined.columns), leaf_rotation=90)
 plt.title('Dendrogram of Company Correlations (Top-Down Clustering)')
 plt.xlabel('Companies')
 plt.ylabel('Distance')
 plt.show()

import numpyasnp
import scipy.cluster.hierarchyassch
import matplotlib.pyplotasplt
 
 # Convert correlation matrix to distance matrix
 dist_mat=1-df_combined.corr()
 
 # Perform bottom-up clustering
 clustering=sch.linkage(dist_mat, method='ward')
 
 # Plot dendrogram
 plt.figure(figsize=(10, 5))
 sch.dendrogram(clustering, labels=list(df_combined.columns), leaf_rotation=90)
 plt.title('Dendrogram of Company Correlations (Bottom-Up Clustering)')
 plt.xlabel('Companies')
 plt.ylabel('Distance')
 plt.show()