pandas的DataFrame的categeries

gzj137070928

pandas的DataFrame的categeries

1. import pandas as pd
   
2. import time
   
3. 
   
4. idx = [1,2,3,5,6,7,9,4,8]
   
5. name = ["apple","pearl","orange", "apple","orange","orange","apple","pearl","orange"]
   
6. price = [5.20,3.50,7.30,5.00,7.50,7.30,5.20,3.70,7.30]
   
7. N = 10  # 数据越大，内存差距越大
   
8. df = pd.DataFrame({ "fruit": name*N , "price" : price*N}, index = idx*N)
   
9. print (df,"\n")
   
10. print ('memory_usage',df.memory_usage(),"\n")
    
11. print (df.dtypes)
    
12. print ("*" * 20)
    
13. df['fruit'] = df['fruit'].astype('category')
    
14. # 将fruit列由Series改为了category类型,通过codes和categories组合出fruit的values
    
15. print (df)
    
16. print ('memory_usage',df.memory_usage(),"\n")
    
17. print (df.dtypes)
    
18. print('fruit.values:',df.fruit.values)
    
19. print('fruit.values.codes:',df.fruit.values.codes)
    
20. print('fruit.values.categories:',df.fruit.values.categories)

复制代码