python数据分析与可视化（第2版）——2.7本章实训

2.7本章实训

#读取数据
import csv               
f=open("D:\python test\white_wine.csv","r")   
reader=csv.reader(f)     
content=[]              
for row in reader:     
    content.append(row)    
f.close()                  
for i in range(5):        
    print(content[i])  

#查看白葡萄酒总共分为几种品质等级
quality_list=[]                               
for row in content[1: ]:                     
    quality_list.append(int(row[-1]))       
quality_count=set(quality_list)            
print("白葡萄酒共有%d种等级，分别是：%r"  
     %(len(quality_count),quality_count))

#按照白葡萄酒等级将数据集划分为7个子集，并统计每种等级的数量
content_dict={}                                     
for row in content[1:]:                             
    quality=int(row[-1])                           
    if quality not in content_dict.keys():        
        #用字典保存每个子集
        content_dict[quality]=[row]
    else:                                         
        content_dict[quality].append(row)
for key in content_dict:                          
    print(key,":",len(content_dict[key]))  

#计算每个数据集中fixed acidity的均值（列表）
mean_list=[]                                 
for key,value in content_dict.items():      
    sum=0
    for row in value:         
        sum+=float(row[0])    #fixed acidity是第一列数据
    mean_list.append((key,sum/len(value)))   
for item in mean_list:     
    print(item[0],":",item[1]) 

#计算每个数据集中fixed acidity的均值（字典）
mean_dict={}                              
for key,value in content_dict.items():
    sum=0
    for row in value:                
        sum+=float(row[0])               
        mean_dict[key]=sum/len(value)    
for key,mean in mean_dict.items():
    print(key,":",mean)                

#求方差
var_list=[]                                    
for key,value in content_dict.items():
    sum=0
    mean=mean_dict[key]
    for row in value:
        sum+=(float(row[0])-mean)**2          
    var_list.append((key,sum/len(value)))     
for item in var_list:
    print(item[0],":",item[1])