Pandas 模糊查询与替换的操作

#!/usr/bin/python
# -*- encoding: utf-8 
import numpy as np
import pandas as pd
from fuzzywuzzy import fuzz
from fuzzywuzzy import process 
 
def enum_row(row):
 print(row['state']) #对state这一列做枚举 
 
def find_state_code(row):
 if row['state'] != 0:  # 如果这个state的名字存在，就用state的名字与states列表中的值选择一个最接近的，如果小于80分，直接舍弃，大于80才返回
 print(process.extractOne(row['state'], states, score_cutoff=80)) 
 
def capital(str): # 把str这个字符串，第一个字母大写，其余小写
 return str.capitalize() 
 
def correct_state(row):
 if row['state'] != 0: # 如果这个state的名字存在，就用state的名字与states列表中的值选择一个最接近的，如果小于80分，直接舍弃，大于80才返回
 state = process.extractOne(row['state'], states, score_cutoff=80)
 if state: # 如果为真，则找到了一个相关性的州名
  state_name = state[0] # 选择用找到的这个州名数据
  return ' '.join(map(capital, state_name.split(' '))) # 先按空格分开（有的州名中间有空格）单词，然后每个单词首字母大写
 return row['state'] 
 
def fill_state_code(row):
 if row['state'] != 0:
 state = process.extractOne(row['state'], states, score_cutoff=80)
 if state:
  state_name = state[0]
  return state_to_code[state_name] # 返回这个州名的value，即缩写
 return '' 
 
if __name__ == "__main__":
 pd.set_option('display.width', 200) # 横向最多显示多少个字符， 一般80不适合横向的屏幕，平时多用200.
 data = pd.read_excel('sales.xlsx', sheetname='sheet1', header=0) # 读取excel表
 print('data.head() = \n', data.head()) # 默认显示前五行
 print('data.tail() = \n', data.tail()) # tail显示后五行
 print('data.dtypes = \n', data.dtypes) # 数据类型
 print('data.columns = \n', data.columns)# 显示第一行行名
 for c in data.columns:
 print(c, end=' ') # 输出第一行行名，中间以空格隔开
 print() #相当于回车
 data['total'] = data['Jan'] + data['Feb'] + data['Mar'] # Jan、Feb、Mar三列的值相加得到一个total
 print(data.head())
 print(data['Jan'].sum()) # Jan这一列的值相加
 print(data['Jan'].min()) # Jan这一列的最小值
 print(data['Jan'].max()) # Jan这一列的最大值
 print(data['Jan'].mean()) # Jan这一列的平均值
 
 print('=============')
 # 添加一行
 s1 = data[['Jan', 'Feb', 'Mar', 'total']].sum() # s1包含四个值，分别是这四列的和
 print(s1)
 s2 = pd.DataFrame(data=s1)
 print(s2)
 print(s2.T)
 print(s2.T.reindex(columns=data.columns)) # 将s2进行转置输出
 # 即：
 s = pd.DataFrame(data=data[['Jan', 'Feb', 'Mar', 'total']].sum()).T
 s = s.reindex(columns=data.columns, fill_value=0)
 print(s)
 data = data.append(s, ignore_index=True)
 data = data.rename(index={15:'Total'})
 print(data.tail())
 
 # apply的使用
 print('==============apply的使用==========')
 data.apply(enum_row, axis=1)  # axis=0时对每一列做变换，axis=1时对每一行做变换
 
 # 事先写好以state为单位的编码字典
 state_to_code = {"VERMONT": "VT", "GEORGIA": "GA", "IOWA": "IA", "Armed Forces Pacific": "AP", "GUAM": "GU",
   "KANSAS": "KS", "FLORIDA": "FL", "AMERICAN SAMOA": "AS", "NORTH CAROLINA": "NC", "HAWAII": "HI",
   "NEW YORK": "NY", "CALIFORNIA": "CA", "ALABAMA": "AL", "IDAHO": "ID",
   "FEDERATED STATES OF MICRONESIA": "FM",
   "Armed Forces Americas": "AA", "DELAWARE": "DE", "ALASKA": "AK", "ILLINOIS": "IL",
   "Armed Forces Africa": "AE", "SOUTH DAKOTA": "SD", "CONNECTICUT": "CT", "MONTANA": "MT",
   "MASSACHUSETTS": "MA",
   "PUERTO RICO": "PR", "Armed Forces Canada": "AE", "NEW HAMPSHIRE": "NH", "MARYLAND": "MD",
   "NEW MEXICO": "NM",
   "MISSISSIPPI": "MS", "TENNESSEE": "TN", "PALAU": "PW", "COLORADO": "CO",
   "Armed Forces Middle East": "AE",
   "NEW JERSEY": "NJ", "UTAH": "UT", "MICHIGAN": "MI", "WEST VIRGINIA": "WV", "WASHINGTON": "WA",
   "MINNESOTA": "MN", "OREGON": "OR", "VIRGINIA": "VA", "VIRGIN ISLANDS": "VI",
   "MARSHALL ISLANDS": "MH",
   "WYOMING": "WY", "OHIO": "OH", "SOUTH CAROLINA": "SC", "INDIANA": "IN", "NEVADA": "NV",
   "LOUISIANA": "LA",
   "NORTHERN MARIANA ISLANDS": "MP", "NEBRASKA": "NE", "ARIZONA": "AZ", "WISCONSIN": "WI",
   "NORTH DAKOTA": "ND",
   "Armed Forces Europe": "AE", "PENNSYLVANIA": "PA", "OKLAHOMA": "OK", "KENTUCKY": "KY",
   "RHODE ISLAND": "RI",
   "DISTRICT OF COLUMBIA": "DC", "ARKANSAS": "AR", "MISSOURI": "MO", "TEXAS": "TX", "MAINE": "ME"}
 states = list(state_to_code.keys()) # 把字典中的key拿出来放到states列表中
 print(fuzz.ratio('Python Package', 'PythonPackage')) #计算Python Package与PythonPackage的相似度
 print(process.extract('Mississippi', states)) # Mississippi与states中哪个最接近，并且列出相似比，不考虑大小写
 print(process.extract('Mississipi', states, limit=1)) # limit=1代表只取最接近的一个
 print(process.extractOne('Mississipi', states)) # extractOne代表只取最接近的一个
 data.apply(find_state_code, axis=1) #apply表示对每一行（axis=1）的数据做find_state_code的变换
 
 print('Before Correct State:\n', data['state']) # 打印修改之前的state
 data['state'] = data.apply(correct_state, axis=1) # 检测每一行，并对其修改
 print('After Correct State:\n', data['state'])
 data.insert(5, 'State Code', np.nan) # 插入State Code这一列，为这一列州名的缩写
 data['State Code'] = data.apply(fill_state_code, axis=1)
 print(data)
 
 # group by
 print('==============group by================')
 print(data.groupby('State Code'))
 print('All Columns:\n')
 print(data.groupby('State Code').sum()) # 按州名缩写划分，并将同样州名的数字相加
 print('Short Columns:\n')
 print(data[['State Code', 'Jan', 'Feb', 'Mar', 'total']].groupby('State Code').sum())
 
 # 写入文件
 data.to_excel('sales_result.xls', sheet_name='Sheet1', index=False)