python 数据读写 IO

1   TXT读写

# 写入 txt_0=open('packages/txt_0.txt','w') # w 只写 r 只读 txt_0.write('写入数据到TXT') txt_0.close() # 读取 txt_1=open('packages/txt_0.txt','r') print(txt_1.read()) group = pd.read_table('bayes.txt',header=None,usecols = (0,1,3))

2  Excel 读写

# 1 xlsxwriter 读取写入 import xlsxwriter # 写入 workbook = xlsxwriter.Workbook('packages/写入的XLSX.xlsx') worksheet = workbook.add_worksheet() N=0 for i in range(101): # print(i) worksheet.write(N,0,i) N=N+1 workbook.close() print('写入成功') print('\n\n pandas读取写入 转为DataFrame用pd写入') # 读取 import pandas as pd excel_0=pd.read_excel('packages/写入的XLSX.xlsx') # print(excel_0) # 写入 import numpy as np np.random.seed(20) a=np.random.randn(10,10) # a=np.mat('2,3,4;2,3,4') print(a) # 转为pandas 的 DataFrame df=pd.DataFrame(a) df.to_excel('packages/写入的XLSX.xlsx')

3 pandas 读写 csv

# 写入 a=np.mat('2,3,4;2,3,4') df=pd.DataFrame(a) df.to_csv('packages/csv_0.csv') # 读取 df=pd.read_csv('packages/csv_0.csv') print(df) # 读取保存csv 添加列名 group_0_1 = pd.read_csv('DATA/Fly_0_1.csv',header=None) group_0_1.columns = ['Fly','Game','Table'] print(group_0_1) group_0_1.to_csv('DATA/Fly_0_2.csv',index=None,usecols = (0,1,2))

4 HDF (注：没有运行成功！)

import tables import numpy as np from os.path import getsize from tempfile import NamedTemporaryFile np.random.seed(42) a=np.random.randn(365,4) tmpf = NamedTemporaryFile() h5file = tables.openFile(tmpf.name,mode='w',title='NumpPy Array') root = h5file.root h5file.createArray(root,'array',a) h5file.close() h5file = tables.openFile(tmpf.name,'r') print(getsize(tmpf.name)) for node in h5file.iterNodes(h5file.root): b = node.read() print(type(b),b.shape) h5file.close()

5 HDF5仓库 HDFStore(注：没有运行成功！)

import numpy as np import pandas as pd from tempfile import NamedTemporaryFile np.random.seed(42) a = np.random.randn(365, 4) tmpf = NamedTemporaryFile() store = pd.io.pytables.HDFStore(tmpf.name) print( store) df = pd.DataFrame(a) store['df'] = df print( store) print( "Get", store.get('df').shape) print( "Lookup", store['df'].shape) print( "Dotted", store.df.shape) del store['df'] print( "After del\n", store) print( "Before close", store.is_open) store.close() print( "After close", store.is_open) df.to_hdf(tmpf.name, 'data', format='table') print( pd.read_hdf(tmpf.name, 'data', where=['index>363']))

6 pandas Json 读写

import pandas as pd json_str = '{"country":"Netherlands","dma_code":"0","timezone":"Europe\/Amsterdam","area_code":"0","ip":"46.19.37.108","asn":"AS196752","continent_code":"EU","isp":"Tilaa V.O.F.","longitude":5.75,"latitude":52.5,"country_code":"NL","country_code3":"NLD"}' # 读取Json data = pd.read_json(json_str, typ='series') print ("Series\n", data) # 写入 data["country"] = "Brazil" print ("New Series\n", data.to_json()) # 解析Json import json import requests ip = '50.78.253.58' html=requests.get('http://freegeoip.net/json/'+ip) respondjson=json.loads(html.text) print(respondjson.get('country_code'))

7 cv2 图片 读写

import cv2 import numpy as np # 读取 img = cv2.imread('packages/000.jpg') # 编辑 img[50:150,50:150]=255 img[:,:,2]=255 img[300:600,300:600]=(200,200,0) #BGR # 显示图片 cv2.imshow('2',img) cv2.waitKey() cv2.destroyAllWindows() # 写入图片 cv2.imwrite('packages/Output.jpg',img)

8 全部代码：

print('----------1 TXT读写-----------\n') # 写入 txt_0=open('packages/txt_0.txt','w') # w 只写 r 只读 txt_0.write('写入数据到TXT') txt_0.close() # 读取 txt_1=open('packages/txt_0.txt','r') print(txt_1.read()) group = pd.read_table('bayes.txt',header=None,usecols = (0,1,3)) print('\n\n----------------2 Excel 读写-----------------------') # 1 xlsxwriter 读取写入 import xlsxwriter # 写入 workbook = xlsxwriter.Workbook('packages/写入的XLSX.xlsx') worksheet = workbook.add_worksheet() N=0 for i in range(101): # print(i) worksheet.write(N,0,i) N=N+1 workbook.close() print('写入成功') print('\n\n pandas读取写入 转为DataFrame用pd写入') # 读取 import pandas as pd excel_0=pd.read_excel('packages/写入的XLSX.xlsx') # print(excel_0) # 写入 import numpy as np np.random.seed(20) a=np.random.randn(10,10) # a=np.mat('2,3,4;2,3,4') print(a) # 转为pandas 的 DataFrame df=pd.DataFrame(a) df.to_excel('packages/写入的XLSX.xlsx') print('\n\n----------3 pandas 读写 csv----------------') # 写入 a=np.mat('2,3,4;2,3,4') df=pd.DataFrame(a) df.to_csv('packages/csv_0.csv') # 读取 df=pd.read_csv('packages/csv_0.csv') print(df) # 读取保存csv 添加列名 group_0_1 = pd.read_csv('DATA/Fly_0_1.csv',header=None) group_0_1.columns = ['Fly','Game','Table'] print(group_0_1) group_0_1.to_csv('DATA/Fly_0_2.csv',index=None,usecols = (0,1,2)) print('\n\n----------------4 HDF-运行失败----------------') import tables import numpy as np from os.path import getsize from tempfile import NamedTemporaryFile np.random.seed(42) a=np.random.randn(365,4) tmpf = NamedTemporaryFile() h5file = tables.openFile(tmpf.name,mode='w',title='NumpPy Array') root = h5file.root h5file.createArray(root,'array',a) h5file.close() h5file = tables.openFile(tmpf.name,'r') print(getsize(tmpf.name)) for node in h5file.iterNodes(h5file.root): b = node.read() print(type(b),b.shape) h5file.close() print('\n\n------------------5 HDF5仓库 HDFStore-运行失败---------------------') import numpy as np import pandas as pd from tempfile import NamedTemporaryFile np.random.seed(42) a = np.random.randn(365, 4) tmpf = NamedTemporaryFile() store = pd.io.pytables.HDFStore(tmpf.name) print( store) df = pd.DataFrame(a) store['df'] = df print( store) print( "Get", store.get('df').shape) print( "Lookup", store['df'].shape) print( "Dotted", store.df.shape) del store['df'] print( "After del\n", store) print( "Before close", store.is_open) store.close() print( "After close", store.is_open) df.to_hdf(tmpf.name, 'data', format='table') print( pd.read_hdf(tmpf.name, 'data', where=['index>363'])) print('\n\n------------pandas Json---------------------') import pandas as pd json_str = '{"country":"Netherlands","dma_code":"0","timezone":"Europe\/Amsterdam","area_code":"0","ip":"46.19.37.108","asn":"AS196752","continent_code":"EU","isp":"Tilaa V.O.F.","longitude":5.75,"latitude":52.5,"country_code":"NL","country_code3":"NLD"}' # 读取Json data = pd.read_json(json_str, typ='series') print ("Series\n", data) # 写入 data["country"] = "Brazil" print ("New Series\n", data.to_json()) # 解析Json import json import requests ip = '50.78.253.58' html=requests.get('http://freegeoip.net/json/'+ip) respondjson=json.loads(html.text) print(respondjson.get('country_code')) print('\n\n----------------------cv2 图片--------------------------') import cv2 import numpy as np # 读取 img = cv2.imread('packages/000.jpg') # 编辑 img[50:150,50:150]=255 img[:,:,2]=255 img[300:600,300:600]=(200,200,0) #BGR # 显示图片 cv2.imshow('2',img) cv2.waitKey() cv2.destroyAllWindows() # 写入图片 cv2.imwrite('packages/Output.jpg',img)

9 参数：

参数 Parameters: path_or_buf : string or file handle, default None File path or object, if None is provided the result is returned as a string. sep : character, default ‘,’ Field delimiter for the output file. na_rep : string, default ‘’ Missing data representation float_format : string, default None Format string for floating point numbers columns : sequence, optional Columns to write header : boolean or list of string, default True Write out column names. If a list of string is given it is assumed to be aliases for the column names index : boolean, default True Write row names (index) index_label : string or sequence, or False, default None Column label for index column(s) if desired. If None is given, and header and index are True, then the index names are used. A sequence should be given if the DataFrame uses MultiIndex. If False do not print fields for index names. Use index_label=False for easier importing in R mode : str Python write mode, default ‘w’ encoding : string, optional A string representing the encoding to use in the output file, defaults to ‘ascii’ on Python 2 and ‘utf-8’ on Python 3. compression : string, optional a string representing the compression to use in the output file, allowed values are ‘gzip’, ‘bz2’, ‘xz’, only used when the first argument is a filename line_terminator : string, default '\n' The newline character or character sequence to use in the output file quoting : optional constant from csv module defaults to csv.QUOTE_MINIMAL. If you have set a float_format then floats are comverted to strings and thus csv.QUOTE_NONNUMERIC will treat them as non-numeric quotechar : string (length 1), default ‘”’ character used to quote fields doublequote : boolean, default True Control quoting of quotechar inside a field escapechar : string (length 1), default None character used to escape sep and quotechar when appropriate chunksize : int or None rows to write at a time tupleize_cols : boolean, default False write multi_index columns as a list of tuples (if True) or new (expanded format) if False date_format : string, default None Format string for datetime objects decimal: string, default ‘.’ Character recognized as decimal separator. E.g. use ‘,’ for European data New in version 0.16.0.