简单的学生数据处理
对学生数据预处理
data_frame=pd.read_excel(r'D:\17uml成绩.xls',header=5, nrows=1).values[0]
df=pd.read_excel(r'D:\17uml成绩.xls',header=5, skiprows=1)
df.columns=data_frame
简单对数据分区间并画图
age_bins = [0,60,70,80,90,100]
d5= pd.concat([d4,d2],ignore_index=True)
a_bins=[0,60,70,80,90,100]
d5["区间"]= pd.cut(d5["总评成绩"],bins=a_bins)
counts=pd.value_counts(d5["区间"],sort=False)
完整代码
import pandas as pd
import xlrd
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
d1=pd.read_excel(r'D:\17uml成绩.xls',header=5,usecols=[6,7,8,9,10,11],nrows=1).values[0]
d2=pd.read_excel(r'D:\17uml成绩.xls',header=5, usecols=[6,7,8,9,10,11],skiprows=1)
d3=pd.read_excel(r'D:\17uml成绩.xls',header=5,usecols=[0,1,2,3,4,5],nrows=1).values[0]
d4=pd.read_excel(r'D:\17uml成绩.xls',header=5, usecols=[0,1,2,3,4,5],skiprows=1)
d4.columns=d3
d2.columns=d1
age_bins = [0,60,70,80,90,100]
d5= pd.concat([d4,d2],ignore_index=True)
a_bins=[0,60,70,80,90,100]
d5["区间"]= pd.cut(d5["总评成绩"],bins=a_bins)
counts=pd.value_counts(d5["区间"],sort=False)
print(d5.agg({"平时成绩":['mean','max','min'],"考试成绩":['mean','max','min'],"总评成绩":['mean','max','min']}))