数据清洗小项目

目的:Learn to use string methods

daily_sales = \
"""Edith Mcbride   ;,;$1.21   ;,;   white ;,; 
09/15/17   ,Herbert Tran   ;,;   $7.29;,; 
white&blue;,;   09/15/17 ,Paul Clarke ;,;$12.52 
;,;   white&blue ;,; 09/15/17 ,Lucille Caldwell   
;,;   $5.13   ;,; white   ;,; 09/15/17,
Eduardo George   ;,;$20.39;,; white&yellow 
;,;09/15/17   ,   Danny Mclaughlin;,;$30.82;,;   
purple ;,;09/15/17 ,Stacy Vargas;,; $1.85   ;,; 
purple&yellow ;,;09/15/17,   Shaun Brock;,; 
$17.98;,;purple&yellow ;,; 09/15/17 , 
Erick Harper ;,;$17.41;,; blue ;,; 09/15/17, 
Michelle Howell ;,;$28.59;,; blue;,;   09/15/17   , 
Carroll Boyd;,; $14.51;,;   purple&blue   ;,;   
09/15/17   , Teresa Carter   ;,; $19.64 ;,; 
white;,;09/15/17   ,   Jacob Kennedy ;,; $11.40   
;,; white&red   ;,; 09/15/17, Craig Chambers;,; 
$8.79 ;,; white&blue&red   ;,;09/15/17   , Peggy Bell;,; $8.65 ;,;blue   ;,; 09/15/17,   Kenneth Cunningham ;,;   $10.53;,;   green&blue   ;,; 
09/15/17   ,   Marvin Morgan;,;   $16.49;,; 
green&blue&red   ;,;   09/15/17 ,Marjorie Russell 
;,; $6.55 ;,;   green&blue&red;,;   09/15/17 ,
Israel Cummings;,;   $11.86   ;,;black;,;  
09/15/17,   June Doyle   ;,;   $22.29 ;,;  
black&yellow ;,;09/15/17 , Jaime Buchanan   ;,;   
$8.35;,;   white&black&yellow   ;,;   09/15/17,   
Rhonda Farmer;,;$2.91 ;,;   white&black&yellow   
;,;09/15/17, Darren Mckenzie ;,;$22.94;,;green 
;,;09/15/17,Rufus Malone;,;$4.70   ;,; green&yellow 
;,; 09/15/17   ,Hubert Miles;,;   $3.59   
;,;green&yellow&blue;,;   09/15/17   , Joseph Bridges  ;,;$5.66   ;,; green&yellow&purple&blue 
;,;   09/15/17 , Sergio Murphy   ;,;$17.51   ;,;   
black   ;,;   09/15/17 , Audrey Ferguson ;,; 
$5.54;,;black&blue   ;,;09/15/17 ,Edna Williams ;,; 
$17.13;,; black&blue;,;   09/15/17,   Randy Fleming;,;   $21.13 ;,;black ;,;09/15/17 ,Elisa Hart;,; $0.35   ;,; black&purple;,;   09/15/17   ,
Ernesto Hunt ;,; $13.91   ;,;   black&purple ;,;   
09/15/17,   Shannon Chavez   ;,;$19.26   ;,; 
yellow;,; 09/15/17   , Sammy Cain;,; $5.45;,;   
yellow&red ;,;09/15/17 ,   Steven Reeves ;,;$5.50   
;,;   yellow;,;   09/15/17, Ruben Jones   ;,; 
$14.56 ;,;   yellow&blue;,;09/15/17 , Essie Hansen;,;   $7.33   ;,;   yellow&blue&red
;,; 09/15/17   ,   Rene Hardy   ;,; $20.22   ;,; 
black ;,;   09/15/17 ,   Lucy Snyder   ;,; $8.67   
;,;black&red  ;,; 09/15/17 ,Dallas Obrien ;,;   
$8.31;,;   black&red ;,;   09/15/17,   Stacey Payne 
;,;   $15.70   ;,;   white&black&red ;,;09/15/17   
,   Tanya Cox   ;,;   $6.74   ;,;yellow   ;,; 
09/15/17 , Melody Moran ;,;   $30.84   
;,;yellow&black;,;   09/15/17 , Louise Becker   ;,; 
$12.31 ;,; green&yellow&black;,;   09/15/17 ,
Ryan Webster;,;$2.94 ;,; yellow ;,; 09/15/17 
,Justin Blake ;,; $22.46   ;,;white&yellow ;,;   
09/15/17,   Beverly Baldwin ;,;   $6.60;,;   
white&yellow&black ;,;09/15/17   ,   Dale Brady   
;,;   $6.27 ;,; yellow   ;,;09/15/17 ,Guadalupe Potter ;,;$21.12   ;,; yellow;,; 09/15/17   , 
Desiree Butler ;,;$2.10   ;,;white;,; 09/15/17  
,Sonja Barnett ;,; $14.22 ;,;white&black;,;   
09/15/17, Angelica Garza;,;$11.60;,;white&black   
;,;   09/15/17   ,   Jamie Welch   ;,; $25.27   ;,; 
white&black&red ;,;09/15/17   ,   Rex Hudson   
;,;$8.26;,;   purple;,; 09/15/17 ,   Nadine Gibbs 
;,;   $30.80 ;,;   purple&yellow   ;,; 09/15/17   , 
Hannah Pratt;,;   $22.61   ;,;   purple&yellow   
;,;09/15/17,Gayle Richards;,;$22.19 ;,; 
green&purple&yellow ;,;09/15/17   ,Stanley Holland 
;,; $7.47   ;,; red ;,; 09/15/17 , Anna Dean;,;$5.49 ;,; yellow&red ;,;   09/15/17   ,
Terrance Saunders ;,;   $23.70  ;,;green&yellow&red 
;,; 09/15/17 ,   Brandi Zimmerman ;,; $26.66 ;,; 
red   ;,;09/15/17 ,Guadalupe Freeman ;,; $25.95;,; 
green&red ;,;   09/15/17   ,Irving Patterson 
;,;$19.55 ;,; green&white&red ;,;   09/15/17 ,Karl Ross;,;   $15.68;,;   white ;,;   09/15/17 , Brandy Cortez ;,;$23.57;,;   white&red   ;,;09/15/17, 
Mamie Riley   ;,;$29.32;,; purple;,;09/15/17 ,Mike Thornton   ;,; $26.44 ;,;   purple   ;,; 09/15/17, 
Jamie Vaughn   ;,; $17.24;,;green ;,; 09/15/17   , 
Noah Day ;,;   $8.49   ;,;green   ;,;09/15/17   
,Josephine Keller ;,;$13.10 ;,;green;,;   09/15/17 ,   Tracey Wolfe;,;$20.39 ;,; red   ;,; 09/15/17 ,
Ignacio Parks;,;$14.70   ;,; white&red ;,;09/15/17 
, Beatrice Newman ;,;$22.45   ;,;white&purple&red 
;,;   09/15/17, Andre Norris   ;,;   $28.46   ;,;   
red;,;   09/15/17 ,   Albert Lewis ;,; $23.89;,;   
black&red;,; 09/15/17,   Javier Bailey   ;,;   
$24.49   ;,; black&red ;,; 09/15/17   , Everett Lyons ;,;$1.81;,;   black&red ;,; 09/15/17 ,   
Abraham Maxwell;,; $6.81   ;,;green;,;   09/15/17   
,   Traci Craig ;,;$0.65;,; green&yellow;,; 
09/15/17 , Jeffrey Jenkins   ;,;$26.45;,; 
green&yellow&blue   ;,;   09/15/17,   Merle Wilson 
;,;   $7.69 ;,; purple;,; 09/15/17,Janis Franklin   
;,;$8.74   ;,; purple&black   ;,;09/15/17 ,  
Leonard Guerrero ;,;   $1.86   ;,;yellow  
;,;09/15/17,Lana Sanchez;,;$14.75   ;,; yellow;,;   
09/15/17   ,Donna Ball ;,; $28.10  ;,; 
yellow&blue;,;   09/15/17   , Terrell Barber   ;,; 
$9.91   ;,; green ;,;09/15/17   ,Jody Flores;,; 
$16.34 ;,; green ;,;   09/15/17,   Daryl Herrera 
;,;$27.57;,; white;,;   09/15/17   , Miguel Mcguire;,;$5.25;,; white&blue   ;,;   09/15/17 ,   
Rogelio Gonzalez;,; $9.51;,;   white&black&blue   
;,;   09/15/17   ,   Lora Hammond ;,;$20.56 ;,; 
green;,;   09/15/17,Owen Ward;,; $21.64   ;,;   
green&yellow;,;09/15/17,Malcolm Morales ;,;   
$24.99   ;,;   green&yellow&black;,; 09/15/17 ,   
Eric Mcdaniel ;,;$29.70;,; green ;,; 09/15/17 
,Madeline Estrada;,;   $15.52;,;green;,;   09/15/17 
, Leticia Manning;,;$15.70 ;,; green&purple;,; 
09/15/17 ,   Mario Wallace ;,; $12.36 ;,;green ;,; 
09/15/17,Lewis Glover;,;   $13.66   ;,;   
green&white;,;09/15/17,   Gail Phelps   ;,;$30.52   
;,; green&white&blue   ;,; 09/15/17 , Myrtle Morris 
;,;   $22.66   ;,; green&white&blue;,;09/15/17"""

#------------------------------------------------
# Start coding below!

daily_sales_replaced=daily_sales.replace(';,;',';')
daily_transactions=daily_sales_replaced.split(',')
#print(daily_transactions)
daily_transactions_split=[]
for item in daily_transactions:
  daily_transactions_split.append(item.split(';'))
#print(daily_transactions_split)
transactions_clean=[]
for i in daily_transactions_split:
  for j in i:
    transactions_clean.append(j.strip())
#print(transactions_clean)
customers=[]
sales=[]
thread_sold=[]
for i in range(len(transactions_clean)):
  if i % 4 ==0:
    customers.append(transactions_clean[i])
  elif i % 4 ==1:
    sales.append(transactions_clean[i])
  elif i % 4 ==2:
    thread_sold.append(transactions_clean[i])
total_sales =0
new_sales=[]
for item in sales:
  total_sales+=float(item.strip('$'))
print(thread_sold )
thread_sold_split=[]
for item in thread_sold:
  if item.find('&')==0:
    thread_sold_split.append(item)
  else:
    thread_sold_split.append(item.split('&'))
#print(thread_sold_split)
def color_count(color):
  count=0
  for item in thread_sold_split:
    for element in item:
      if element==color:
        count+=1
  return count
print(color_count('white'))
colors = ['red','yellow','green','white','black','blue','purple']
for color in colors:
  print("Thread Shed sold {num} threads of {color} thread today.".format(num=color_count(color),color=color))
  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Python数据清洗项目实战是指使用Python编程语言进行数据清洗的实际项目数据清洗是指对原始数据进行处理和转换,以便于后续分析和建模。下面是一个简单的Python数据清洗项目实战的介绍: 项目名称:电商销售数据清洗 项目描述:该项目的目标是对电商销售数据进行清洗,以便于后续的分析和可视化展示。原始数据包含了订单信息、产品信息、客户信息等多个表格,需要进行数据清洗和整合。 项目步骤: 1. 数据导入:使用Python的pandas库读取原始数据文件,将数据加载到DataFrame中进行后续处理。 2. 数据预览:查看数据的前几行、列名、数据类型等信息,了解数据的结构和内容。 3. 缺失值处理:检查数据中是否存在缺失值,根据业务需求选择合适的方法进行处理,如删除缺失值、填充缺失值等。 4. 重复值处理:检查数据中是否存在重复值,根据业务需求选择合适的方法进行处理,如删除重复值、保留唯一值等。 5. 数据类型转换:根据需要将数据中的某些列转换为合适的数据类型,如日期时间类型、数值类型等。 6. 数据整合:根据业务需求将多个表格进行合并,使用合适的连接方式(如内连接、外连接等)将相关数据整合到一张表中。 7. 数据清洗:根据业务需求进行数据清洗,如去除异常值、修正错误数据等。 8. 数据导出:将清洗后的数据导出为新的文件,以便于后续的分析和可视化展示。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值