今天博士师兄让我帮忙实现一个画图的代码，虽然研究背景比较专业，但是需求就是在某两个大表中找到相同的数据并画柱状图，下面就直接贴代码了，主要用的就是numpy包，注释也比较详细：
代码语言：javascript复制#!/usr/bin/env python
import numpy as np
import xlsxwriter
# Step 1: Read data from flux plane raw particle files
def caculate():
# Change the file names to match your project settings
f1 = 'FLUX_upstream_raw_particle'
f2 = 'FLUX_downstream_raw_particle'
# Check column numbers, because they might be different for your project
# Fluxplane
#
# @ 1 "Time" "s"
# @ 2 "Unique particle ID" ""
tCol = 1
pidCol = 2
t1, pid1 = np.genfromtxt(f1, usecols=(tCol - 1, pidCol - 1), unpack=True)
t2, pid2 = np.genfromtxt(f2, usecols=(tCol - 1, pidCol - 1), unpack=True)
# Step 2: Calculate travel time between the two flux planes
# 用numpy包创建一个array数组
travelTimeArray = np.array([])
# 将第一个文件里的第一列和第二列的每两个元素组装成一个元组 比如第一个文件的第一行是1,3；第二行是2,9
# 现在的zip(t1, pid1)就变成了[(1,3),(2,9)]
for myTime, myPID in zip(t1, pid1):
# 判断第一个表格的Id是否在第二个文件的id列里出现
if np.isin(myPID, pid2):
# 遍历出第二个文件里面的第二列的id和第一个文件里的id相等的一个array数组，每一个
# arrayIndex就是第二个文件里相应的pid的行数
for arrayIndex in np.where(pid2 == myPID)[0]:
# if t2[arrayIndex] > myTime:
# 把得到的数据保存到之前创建的travelTimeArray数组中
travelTimeArray = np.append(travelTimeArray, t2[arrayIndex] - myTime)
# 跳出内层循环
break
# --------------------------保存到excel------------------------------------------
#先定义一个workbook就是excel表格，参数填写想要的名称，每次执行前一定要保证没有此文件
workbook = xlsxwriter.Workbook('hello.xlsx') # 建立文件
# 添加sheet的名字
worksheet = workbook.add_worksheet(
"time")
# 遍历刚才保存的数组，遍历上限是数组的长度，也就是结果的个数
for i in range(len(travelTimeArray)):
# 向excel中写入数据，i 1的原因是excel里的第一行是1开始，但是range函数是从0开始
worksheet.write('A' str(i 1), travelTimeArray[i]) # 向A1写入
# 执行完后关闭表格IO操作
workbook.close()
# Step 3: Print some general information about the calculated travel times
print("========= General information about calculated travel times =========")
print("Length of travelTimeArray =", len(travelTimeArray))
print("Average travel time =", "{0:.4f}".format(np.mean(travelTimeArray)), "s")
print("Standard dev. of travel time =", "{0:.4f}".format(np.std(travelTimeArray)), "s")
print("Minimum travel time =", "{0:.4f}".format(np.amin(travelTimeArray)), "s")
print("Maximum travel time =", "{0:.4f}".format(np.amax(travelTimeArray)), "s")
# Step 4: Calculate a histogram of the travel times, to summarize the data
hist, bin_edges = np.histogram(travelTimeArray)
print()
print("========= Histogram of calculated travel times =========")
print("bin edges:", bin_edges)
print("histogram:", hist)
if __name__ == '__main__':
caculate()
