我在csv文件中有nmea句子。
示例：
$GPGSA,A,3,03,22,06,19,11,14,32,01,28,18,,,1.8,0.8,1.6*3F
我如何用逗号和*？
分隔with f as csvfile:
readCSV = csv.reader(csvfile,delimiter=',')
我可以用*替换,吗？
我试图使用readCSV = str.replace("*", ',')但没有成功。
每个完整代码的请求：
import os
import csv
from csv import *
import matplotlib
from numpy import *
from matplotlib import *
import matplotlib.pyplot as plt
from matplotlib.pylab import *
import numpy as np
#import nmea_defs
#from nmea_defs import *
#to export to excel
import xlsxwriter
from xlsxwriter.workbook import Workbook
#to get the csv converter functions
import os
import subprocess
import glob
#to get the datetime functions
import datetime
from datetime import datetime
from pytz import timezone
import time
import calendar
#creates the path needed for incoming and outgoing files
path_in = 'C:/Python34/gps_txts/'
path_out = 'C:/Python34/output_files/'
#prints all the data in the file if you want
q_show_content = input('Print list of files type y:')
if q_show_content == 'y':
for root, dirs, files in os.walk(path_in):
print(root, dirs, files)
else:
print('ok')
data = [] #empty because we will store data into it
#Reads a CSV file and return it as a list of rows
def read_csv_file(filename):
"""Reads a CSV file and return it as a list of rows."""
for row in csv.reader(open(filename)):
data.append(row)
return data
#request of what file to look at
print ("- - - - - - - - - - - - -")
data_file = input('Which file do you want to look at?')
f = open(path_in + data_file)
read_it = read_csv_file(path_in + data_file)
with f as csvfile:
for line in csvfile:
row = re.split('[,*]', line)
# readCSV = csv.reader(csvfile,delimiter=',')
#print number of rows
print ("- - - - - - - - - - - - -")
rows = len(read_it)
print (data_file, " has "+ str(rows) + " rows of data")
#Counts the number of times a GPS command is observed
def list_gps_commands(data):
"""Counts the number of times a GPS command is observed.
Returns a dictionary object."""
gps_cmds = dict()
for row in data:
try:
gps_cmds[row[0]] += 1
except KeyError:
gps_cmds[row[0]] = 1
return gps_cmds
class GPS:
def process_gprmc_data(self, data):
"""Processes GPS data, NMEA 0183 format.
Returns a tuple of arrays: latitude, longitude, velocity [km/h],
time [sec] and number of satellites.
See also: http://www.gpsinformation.org/dale/nmea.htm.
"""
global NMI
NMI = 1852.0
self.latitude = []
self.longitude = []
self.velocity = []
self.timestamp = []
self.speed = []
self.course = []
print ("- - - - - - - - - - - - -")
print('processing gprmc data')
print ("- - - - - - - - - - - - -")
for row in data:
if row[0] == '$GPRMC': # Valid position/time sentence
y = (float(row[3][0:2]) + float(row[3][2:])/60.0)
if row[4] == "S":
y = -y
self.latitude.append(y)
x = (float(row[5][0:3]) + float(row[5][3:])/60.0)
if row[6] == "W":
x = -x
self.longitude.append(x)
self.velocity.append(float(row[7])*NMI/1000.0)
gpstime = row[1][0:6] # hhmmss
gdate = row[9] # ddmmyy
gpsdate = gdate[4:6]+gdate[2:4]+gdate[0:2] # yymmdd
real_time =gpsdate + gpstime
add_date_time = datetime.strptime(real_time, "%y%m%d%H%M%S")
self.timestamp.append(add_date_time)
knots2mph = (float(row[7])*1.15078)
self.speed.append(knots2mph)
self.course.append(float(row[8]))
return (array(self.latitude), array(self.longitude), array(self.velocity), array(self.timestamp), array(self.speed), array(self.course))
def process_gpgga_data(self, data):
"""Processes GPS data, NMEA 0183 format.
Returns a tuple of arrays: latitude, longitude, velocity [km/h],
time [sec] and number of satellites.
See also: http://www.gpsinformation.org/dale/nmea.htm.
"""
self.latitude = []
self.longitude = []
self.altitude = []
self.timestamp = []
self.num_sats = []
print ("- - - - - - - - - - - - -")
print('processing gpgga data')
print ("- - - - - - - - - - - - -")
for row in data:
if row[0] == '$GPGGA': # Valid position/time sentence
y = (float(row[2][0:2]) + float(row[2][2:])/60.0)
if row[3] == "S":
y = -y
self.latitude.append(y)
x = (float(row[4][0:3]) + float(row[4][3:])/60.0)
if row[5] == "W":
x = -x
self.longitude.append(x)
gpstime = row[1][0:6] # hhmmss
add_time = datetime.strptime(gpstime, "%H%M%S")
self.timestamp.append(add_time)
self.altitude.append(float(row[9]))
self.num_sats.append(float(row[7]))
return (array(self.latitude), array(self.longitude), array(self.altitude), array(self.timestamp), array(self.num_sats))
def process_gpgll_data(self, data):
"""Processes GPS data, NMEA 0183 format.
Returns a tuple of arrays: latitude, longitude, velocity [km/h],
time [sec] and number of satellites.
See also: http://www.gpsinformation.org/dale/nmea.htm.
"""
self.latitude = []
self.longitude = []
self.timestamp = []
print ("- - - - - - - - - - - - -")
print('processing gpgll data')
print ("- - - - - - - - - - - - -")
for row in data:
if row[0] == '$GPGLL': # Valid position/time sentence
y = (float(row[1][0:2]) + float(row[1][2:])/60.0)
if row[2] == "S":
y = -y
self.latitude.append(y)
x = (float(row[3][0:3]) + float(row[3][3:])/60.0)
if row[4] == "W":
x = -x
self.longitude.append(x)
gpstime = row[5][0:6] # hhmmss
add_time = datetime.strptime(gpstime, "%H%M%S")
self.timestamp.append(add_time)
return (array(self.latitude), array(self.longitude), array(self.timestamp))
def process_gpgsa_data(self,data):
"""Processes GSA data, NMEA 0183 format.
Returns a tuple of arrays: latitude, longitude, velocity [km/h],
time [sec] and number of satellites.
See also: http://www.gpsinformation.org/dale/nmea.htm.
"""
self.fix = []
self.sats = []
self.pdop = []
self.hdop = []
self.vdop = []
print ("- - - - - - - - - - - - -")
print('processing gpgsa data')
print ("- - - - - - - - - - - - -")
for row in data:
if row[0] == '$GPGSA': # Valid position/time sentence
self.fix.append(float(row[2]))
self.sats.append(str(row[3:15]))
self.pdop.append(float(row[15]))
self.hdop.append(float(row[16]))
self.vdop.append(float(row[17]))
return (array(self.fix), array(self.sats), array(self.pdop), array(self.hdop), array(self.vdop))
class CreateWorkbook:
def openworkbook(self, data):
global output_filename
output_filename = input('output filename:')
global workbook
workbook = xlsxwriter.Workbook(path_out + output_filename + '_' + command_type +'.xlsx')
self.worksheet = workbook.add_worksheet()
#formatting definitions
global bold
bold = workbook.add_format({'bold': True})
global date_format
date_format = workbook.add_format({'num_format': "m/d/yyyy hh:mm:ss"})
global time_format
time_format = workbook.add_format({'num_format': "hh:mm:ss"})
def closeworkbook_gprmc(self, data):
print('closeworkbook')
#pull data from process_gprmc_data
gps = GPS()
(lati, long, v, t_stamp, mph, crse) = gps.process_gprmc_data(data)
#sets up the header row
self.worksheet.write('A1','TimeStamp',bold)
self.worksheet.write('B1', 'Latitude',bold)
self.worksheet.write('C1', 'Longitude',bold)
self.worksheet.write('D1', 'Velocity',bold)
self.worksheet.write('E1', 'Speed-MPH',bold)
self.worksheet.write('F1', 'Course',bold)
self.worksheet.autofilter('A1:F1') #dropdown menu created for filtering
# Create a For loop to iterate through each row in the XLS file, starting at row 2 to skip the headers
for r, row in enumerate(data, start=1): #where you want to start printing results inside workbook
for c, col in enumerate(data):
self.worksheet.write_column(r,0, t_stamp, date_format)
self.worksheet.write_column(r,1, lati)
self.worksheet.write_column(r,2, long)
self.worksheet.write_column(r,3, v)
self.worksheet.write_column(r,4, mph)
self.worksheet.write_column(r,5, crse)
workbook.close()
csvfile.close()
print('XLSX file named ' + output_filename + '_' + command_type +' was created')
def closeworkbook_gpgga(self, data):
print('closeworkbook')
#pull data from process_gpgga_data
gps = GPS()
(lati, long, alt, t_stamp,numsats) = gps.process_gpgga_data(data)
#sets up the header row
self.worksheet.write('A1','TimeStamp',bold)
self.worksheet.write('B1', 'Latitude',bold)
self.worksheet.write('C1', 'Longitude',bold)
self.worksheet.write('D1', 'Altitude',bold)
self.worksheet.write('E1', 'Num_sats',bold)
self.worksheet.autofilter('A1:E1') #dropdown menu created for filtering
# Create a For loop to iterate through each row in the XLS file, starting at row 2 to skip the headers
for r, row in enumerate(data, start=1): #where you want to start printing results inside workbook
for c, col in enumerate(data):
self.worksheet.write_column(r,0, t_stamp, time_format)
self.worksheet.write_column(r,1, lati)
self.worksheet.write_column(r,2, long)
self.worksheet.write_column(r,3, alt)
self.worksheet.write_column(r,4, numsats)
workbook.close()
f.close()
print('XLSX file named ' + output_filename + '_' + command_type + ' was created')
def closeworkbook_gpgll(self, data):
print('closeworkbook')
#pull data from process_gpgga_data
gps = GPS()
(lati, long, t_stamp) = gps.process_gpgll_data(data)
#sets up the header row
self.worksheet.write('A1','TimeStamp',bold)
self.worksheet.write('B1', 'Latitude',bold)
self.worksheet.write('C1', 'Longitude',bold)
self.worksheet.autofilter('A1:C1') #dropdown menu created for filtering
# Create a For loop to iterate through each row in the XLS file, starting at row 2 to skip the headers
for r, row in enumerate(data, start=1): #where you want to start printing results inside workbook
for c, col in enumerate(data):
self.worksheet.write_column(r,0, t_stamp, time_format)
self.worksheet.write_column(r,1, lati)
self.worksheet.write_column(r,2, long)
workbook.close()
f.close()
print('XLSX file named ' + output_filename + '_' + command_type + ' was created')
def closeworkbook_gpgsa(self, data):
print('closeworkbook')
#pull data from process_gprmc_data
gps = GPS()
(fix, sats, pdop, hdop, vdop) = gps.process_gpgsa_data(data)
#sets up the header row
self.worksheet.write('A1','Fix',bold)
self.worksheet.write('B1', 'Satellites',bold)
self.worksheet.write('C1', 'Position DOP',bold)
self.worksheet.write('D1', 'Horizon DOP',bold)
self.worksheet.write('E1', 'Vertical DOP',bold)
self.worksheet.autofilter('A1:E1') #dropdown menu created for filtering
# Create a For loop to iterate through each row in the XLS file, starting at row 2 to skip the headers
for r, row in enumerate(data, start=1): #where you want to start printing results inside workbook
for c, col in enumerate(data):
self.worksheet.write_column(r,0, fix)
self.worksheet.write_column(r,1, sats)
self.worksheet.write_column(r,2, pdop)
self.worksheet.write_column(r,3, hdop)
self.worksheet.write_column(r,4, vdop)
workbook.close()
csvfile.close()
print('XLSX file named ' + output_filename + '_' + command_type +' was created')
class ConvertFile:
def convert2csv(self, data):
# set path to folder containing xlsx files
os.chdir(path_out)
# find the file with extension .xlsx
xlsx = glob.glob(output_filename + '_' + command_type + '.xlsx')
# create output filenames with extension .csv
csvs = [x.replace('.xlsx','.csv') for x in xlsx]
# zip into a list of tuples
in_out = zip(xlsx,csvs)
# loop through each file, calling the in2csv utility from subprocess
for xl,csv in in_out:
out = open(csv,'w')
command = 'c:/python34/scripts/in2csv %s\\%s' % (path_out,xl)
proc = subprocess.Popen(command,stdout=out)
proc.wait()
out.close()
print('CSV file named ' + output_filename + '_' + command_type + ' was created')
def convert2kml(self, data):
#Input the file name.
h = open(path_out + output_filename + '_' + command_type + '.csv')
with h as csvfile2:
data2 = csv.reader(csvfile2,delimiter=',')
next(data2)
#Open the file to be written.
g = open(output_filename + '_' + command_type +'.kml','w')
g.write("<?xml version='1.0' encoding='UTF-8'?>\n")
g.write("<kml xmlns='http://earth.google.com/kml/2.1'>\n")
g.write("<Document>\n")
g.write(" <name>" + output_filename + '_' + command_type + '.kml' +"</name>\n")
for row in data2:
g.write(" <Placemark>\n")
g.write(" <TimeStamp><when>" + str(row[0]) + "</when></TimeStamp>\n")
g.write(" <Point>\n")
g.write(" <coordinates>" + str(row[2]) + "," + str(row[1]) + "</coordinates>\n")
g.write(" </Point>\n")
g.write(" </Placemark>\n")
g.write("</Document>\n")
g.write("</kml>\n")
g.close()
h.close()
print('and ' + output_filename + '_' + command_type +'.kml was created,too!')
print ("- - - - - - - - - - - - -")
class PrintGPS(GPS):
def process_gprmc_data(self, data):
print('PrintGPS')
# how to call process_gprmc_data()
(lati, long, v, t_stamp, mph, crse) = gps.process_gprmc_data(data)
print('got definitions in')
print ("- - - - - - - - - - - - -")
print('lat:',lati)
print ("- - - - - - - - - - - - -")
print('long:',long)
print ("- - - - - - - - - - - - -")
print('v:',v)
print ("- - - - - - - - - - - - -")
print('date:', t_stamp)
print ("- - - - - - - - - - - - -")
if rows > 200:
print('Big file please wait...thinking')
def process_gpgga_data(self, data):
# how to call process_gpgga_data()
(lati, long, alt, t_stamp,numsats) = gps.process_gpgga_data(data)
print('got definitions in')
print ("- - - - - - - - - - - - -")
print('lat:',lati)
print ("- - - - - - - - - - - - -")
print('long:',long)
print ("- - - - - - - - - - - - -")
print('alt:',alt)
print ("- - - - - - - - - - - - -")
print('date:', t_stamp)
print ("- - - - - - - - - - - - -")
print('numsats:', numsats)
print ("- - - - - - - - - - - - -")
if rows > 200:
print('Big file please wait...thinking')
def process_gpgll_data(self, data):
# how to call process_gpgll_data()
(lati, long, t_stamp) = gps.process_gpgga_data(data)
print('got definitions in')
print ("- - - - - - - - - - - - -")
print('lat:',lati)
print ("- - - - - - - - - - - - -")
print('long:',long)
print ("- - - - - - - - - - - - -")
print('time:', t_stamp)
print ("- - - - - - - - - - - - -")
if rows > 200:
print('Big file please wait...thinking')
def process_gpgsa_data(self, data):
print('PrintGPS')
# how to call process_gprmc_data()
(fix, sats, pdop, hdop, vdop) = gps.process_gpgsa_data(data)
print('got definitions in')
print ("- - - - - - - - - - - - -")
print('fix:',fix)
print ("- - - - - - - - - - - - -")
print('sats:',sats)
print ("- - - - - - - - - - - - -")
print('pdop:',pdop)
print ("- - - - - - - - - - - - -")
print('hdop:', hdop)
print ("- - - - - - - - - - - - -")
print('vdop:', vdop)
print ("- - - - - - - - - - - - -")
if rows > 200:
print('Big file please wait...thinking')
#processing piece
keep_asking = True
while keep_asking:
print ("- - - - - - - - - - - - -")
print(list_gps_commands(read_it))
print ("- - - - - - - - - - - - -")
command_type = input("What message type do you want to look at?")
if command_type in ('$GPGGA', 'GPGGA', 'GGA','$gpgga', 'gpgga', 'gga'):
#define the classes
gps = GPS()
createworkbook = CreateWorkbook()
convertfile = ConvertFile()
print_gps = PrintGPS()
#do the deeds
createworkbook.openworkbook(data)
print_gps.process_gpgga_data(data)
createworkbook.closeworkbook_gpgga(data)
convertfile.convert2csv(data)
convertfile.convert2kml(data)
elif command_type in ('$GPRMC', 'GPRMC', 'RMC', '$gprmc', 'gprmc', 'rmc'):
#define the classes
gps = GPS()
createworkbook = CreateWorkbook()
convertfile = ConvertFile()
print_gps = PrintGPS()
#do the deeds
createworkbook.openworkbook(data)
print_gps.process_gprmc_data(data)
createworkbook.closeworkbook_gprmc(data)
convertfile.convert2csv(data)
convertfile.convert2kml(data)
elif command_type in ('$GPGLL', 'GPGLL', 'GLL', '$gpgll', 'gpgll', 'gll'):
#define the classes
gps = GPS()
createworkbook = CreateWorkbook()
convertfile = ConvertFile()
print_gps = PrintGPS()
#do the deeds
createworkbook.openworkbook(data)
print_gps.process_gpgll_data(data)
createworkbook.closeworkbook_gpgll(data)
convertfile.convert2csv(data)
convertfile.convert2kml(data)
elif command_type in ('$GPGSA', 'GPGSA', 'GSA', '$gpgsa', 'gpgsa', 'gsa'):
#define the classes
gps = GPS()
createworkbook = CreateWorkbook()
convertfile = ConvertFile()
print_gps = PrintGPS()
#do the deeds
createworkbook.openworkbook(data)
print_gps.process_gpgsa_data(data)
createworkbook.closeworkbook_gpgsa(data)
convertfile.convert2csv(data)
elif command_type in ('$GPVTG', 'GPVTG', 'VTG', '$gpvtg', 'gpvtg', 'vtg'):
print('Better check $GPRMC')
list_gps_commands(data)
wannalook = input('Want to look at another message or no?')
if not wannalook.startswith('y'):
keep_asking = False
print('********************')
print('**mischief managed**')
print('********************')
答案 0 :(得分：1)
csv不支持多个分隔符（从技术上讲，这也不是CSV文件）。看一下您的文件格式，我说您可以使用re.split()解析它而不会出现问题：
with open(...) as csvfile:
for line in csvfile:
fields = re.split('[,*]', line)
仅当您的文件包含带引号的字符串时，才会遇到问题。
答案 1 :(得分：1)
考虑到您正在进行大量的数值计算，您可能会发现pandas很有用，使用两个分隔符读取csv文件非常简单：
import pandas as pd
df = pd.read_csv(infile,sep=",|\*")