python读取和保存为excel、csv、txt文件及对DataFrame文件的基本操作指南_python_

data_file = 'Pre_results.xlsx' # Excel文件存储位置 D = pd.read_excel('Pre_results.xlsx') print(D) 

# 生成一个2×2的类型为str的矩阵 import numpy as np datamatrix = np.zeros((2, 2),dtype = str) print(datamatrix) 

import numpy as np import xlrd def import_excel_matrix(path): table = xlrd.open_workbook(path).sheets()[0] # 获取第一个sheet表 row = table.nrows # 行数 #print(row) col = table.ncols # 列数 datamatrix = np.zeros((row, col),dtype = float) # 生成一个nrows行*ncols列的初始矩阵，在excel中，类型必须相同，否则需要自己指定dtype来强制转换。 for i in range(col): # 对列进行遍历 向矩阵中放入数据 #print(table.col_values(i)) #是矩阵 cols = np.matrix(table.col_values(i)) # 把list转换为矩阵进行矩阵操作 #print(cols) #cols = float(cols) datamatrix[:, i] = cols # 按列把数据存进矩阵中 return datamatrix data_file = 'to_matrix.xlsx' # Excel文件存储位置 data_matrix = import_excel_matrix(data_file) print(data_matrix) 

# 1.导入openpyxl模块 import openpyxl # 2.调用Workbook()方法 wb = openpyxl.Workbook() # 3. 新建一个excel文件，并且在单元表为"sheet1"的表中写入数据 ws = wb.create_sheet("sheet1") # 4.在单元格中写入数据 # ws.cell(row=m, column=n).value = *** 在第m行n列写入***数据 ws.cell(row=1, column=1).value = "时间" ws.cell(row=1, column=2).value = "零食" ws.cell(row=1, column=3).value = "是否好吃" # 5.保存表格 wb.save('嘿嘿.xlsx') print('保存成功！') 

import xlwt workbook=xlwt.Workbook(encoding='utf-8') booksheet=workbook.add_sheet('Sheet 1', cell_overwrite_ok=True) DATA=(('学号','姓名','年龄','性别','成绩'), ('1001','A','11','男','12'), ('1002','B','12','女','22'), ('1003','C','13','女','32'), ('1004','D','14','男','52'),) for i,row in enumerate(DATA): for j,col in enumerate(row): booksheet.write(i,j,col) workbook.save('grade.xls') 

import pandas as pd df = pd.read_csv('to_df.csv') #,nrows =6) nrows=6表示只读取前六行数据 print(df) 

df.to_csv('df_to_csv.csv') 

f=open('data.txt') print(f.read()) 

f = open('data.txt','w', encoding='utf-8') #打开文件，若文件不存在系统自动创建 #w只能写入操作 r只能读取 a向文件追加；w+可读可写 r+可读可写 a+可读可追加；wb+写入进制数据 #w模式打开文件，如果文件中有数据，再次写入内容，会把原来的覆盖掉 f.write('hello world! = %.3f' % data) #write写入 f.writelines(['hello!\n']) #writelines 将列表中的字符串写入文件 但不会换行 参数必须是一个只存放字符串的列表 f.close() #关闭文件 

save_path= 'save.txt' np.savetxt(save_path, data, fmt='%.6f')

data = { 'state':['Ohio','Ohio','Ohio','Nevada','Nevada'], 'year':[2000,2001,2002,2001,2002], 'pop':[1.5,1.7,3.6,2.4,2.9] } frame = pd.DataFrame(data) frame #输出 pop state year 0 1.5 Ohio 2000 1 1.7 Ohio 2001 2 3.6 Ohio 2002 3 2.4 Nevada 2001 4 2.9 Nevada 2002 

frame2 = pd.DataFrame(data,index=['one','two','three','four','five'],columns=['year','state','pop','debt']) frame2 #输出 year state pop debt one 2000 Ohio 1.5 NaN two 2001 Ohio 1.7 NaN three 2002 Ohio 3.6 NaN four 2001 Nevada 2.4 NaN five 2002 Nevada 2.9 NaN 

pop = {'Nevada':{2001:2.4,2002:2.9},'Ohio':{2000:1.5,2001:1.7,2002:3.6}} frame3 = pd.DataFrame(pop) frame3 #输出 Nevada Ohio 2000 NaN 1.5 2001 2.4 1.7 2002 2.9 3.6 

frame2.values frame2.values[0,1] 

frame2['year'] #索引列名 

data = pd.DataFrame(np.arange(16).reshape((4,4)),index = ['Ohio','Colorado','Utah','New York'],columns=['one','two','three','four']) data[['two','three']] 

data[:2] #第一行和第二行 #输出 one two three four Ohio 0 1 2 3 Colorado 4 5 6 7 

data.loc['Colorado',['two','three']] #输出 two 5 three 6 Name: Colorado, dtype: int64 data.iloc[0:3,2] #输出 Ohio 2 Colorado 6 Utah 10 Name: three, dtype: int64 

data = { 'state':['Ohio','Ohio','Ohio','Nevada','Nevada'], 'year':[2000,2001,2002,2001,2002], 'pop':[1.5,1.7,3.6,2.4,2.9] } frame2 = pd.DataFrame(data,index=['one','two','three','four','five'],columns=['year','state','pop','debt']) frame2 frame2['debt']=16.5