前一百成绩分析

一、实施目的

基于考情，针对目标生制定学习成果“一生一案”方案，帮助目标生消灭短板学科，达到各科均衡发展。

二、实施方法

1、对年级总分科目总分排名前80的学生，制定“一生一案”
2、对标总分名次，设置单科合理区间，超出单科合理区间视为“薄弱学科”，并按名次划分不同档位
3、找出薄弱学科的责任老师
4、由各班班主任在班科联席会上，落实到人，安排到位
5、下次统考，进行成果考核

三、单科区间设置标准

总分前30名，单科合理区间为【总分名次，总分名次+20】
总分31至80名，单科合理区间为【总分名次，总分名次+30】
各单科合理区间往后A、B、C、D档区间长度分别设置为10、20、30、50，超出D档为E档

四、考核标准

下次统考目标生单科名次前进1挡，视为达标
前进2挡及以上，定为优秀

最后成果：

实现方式：

通过python代码实现：

1.下载vscode

通过腾讯应用里面可以下载

vscode下载地址
安装就ok了

2.下载安装python解释器

python 官网找到python 3.12.0版本下载安装(各个版本之间语法有些区别)

版本下载地址:https://www.python.org/ftp/python/3.12.0/python-3.12.0-amd64.exe

然后安装的时候勾选path

点击立即安装就好了，然后勾选Add python.exe to PATH

3.配置环境和库

同时按win+r

然后输入cmd

然后输入一下指令

pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple some-package

pip install numpy -i https://pypi.tuna.tsinghua.edu.cn/simple some-package

pip install pandas -i https://pypi.tuna.tsinghua.edu.cn/simple some-package

pip install openpyxl -i https://pypi.tuna.tsinghua.edu.cn/simple some-package

pip install jupyter -i https://pypi.tuna.tsinghua.edu.cn/simple some-package

4.新建一个成绩分析文件夹

将他拖到vscode里面

5.在这个文件夹下新建一个前一百分析.ipynb文件

然后贴入代码:

import numpy as np 
import pandas as pd 
import os
import glob
from openpyxl import load_workbook
from openpyxl.styles import PatternFill

f_name = r"C:\Users\xxxxxx\Desktop\成绩\考试.xlsx" #复制文件地址就好，
                                                                      #不需要改斜杠，出现黄色框框也没事

df = pd.read_excel(f_name)
subjects = ["语文","数学","英语","物理","历史","道法","化学","体育","生物","地理","英语听说","历史与道法"]
columns_list = df.columns.tolist() #获取源文件的所有列

#1.计算总分
df['总分']=0
for i in columns_list: #添加总分这一列
    if i in subjects and i != "历史与道法":
        df["总分"]=df['总分']+df[i]  

df = df.sort_values(by='总分',ascending=False)

#提取生成新的dataframe
data = df[['班级','姓名','总分']][:100]
data['总分校名'] = data['总分'].rank(ascending=False,method='min').astype(int)

#年级前三十单科下线位+20,剩下的单科下线为+30
data['单科下线'] = np.where(data["总分校名"]<=30,data['总分校名']+20,data['总分校名']+30)
data['单科合理区间'] = data.apply(lambda row:f"[{row['总分校名']}~{row['单科下线']}]",axis=1)
data['A档下线'] = data['单科下线']+10   #A
data['单科A档区间'] = data.apply(lambda row:f"[{row['单科下线']+1}~{row['A档下线']}]",axis=1)
data['B档下线'] = data['A档下线']+20    #B
data['单科B档区间'] = data.apply(lambda row:f"[{row['A档下线']+1}~{row['B档下线']}]",axis=1)
data['C档下线'] = data['B档下线']+30    #C
data['单科C档区间'] = data.apply(lambda row:f"[{row['B档下线']+1}~{row['C档下线']}]",axis=1)
data['D档下线'] = data['C档下线']+50    #D
data['单科D档区间'] = data.apply(lambda row:f"[{row['C档下线']+1}~{row['D档下线']}]",axis=1)
#E
data['单科E档区间'] = data.apply(lambda row:f"[{row['D档下线']+1}~+∞]",axis=1)
#
###单科档位比较获得
def compare_grade(row,subject):
    subject_grade = row[subject+"校名"]
    if subject_grade<=row["单科下线"]:
        return ""
    elif subject_grade>row["单科下线"] and subject_grade<=row["A档下线"]:
        return "A"
    elif subject_grade>row["A档下线"] and subject_grade<=row["B档下线"]:
        return "B"
    elif subject_grade>row["B档下线"] and subject_grade<=row["C档下线"]:
        return "C"
    elif subject_grade>row["C档下线"] and subject_grade<=row["D档下线"]:
        return "D"
    elif subject_grade>row['D档下线']:
        return "E"
    else:
        return ""
#
def single_subject_analysis(subject):
    if subject in subjects:
        data[subject] = df[subject]#获得语文成绩
        data[subject+'校名'] = data[subject].rank(ascending=False,method='min')#获得语文排名
        data[subject+"档位"] = data.apply(lambda row:compare_grade(row,subject),axis=1)
        data[subject+"责任教师"] = np.where(data[subject+"档位"]!="",data.apply(lambda row:f"{row["班级"]}班{subject}",axis=1),None)
        
for i in columns_list:
    if i in subjects:
        single_subject_analysis(i)

#-----------------------
result_folder = "数据处理文件夹"
os.makedirs(result_folder,exist_ok=True)
file_path = os.path.join(result_folder,"前一百全科.xlsx")
data.to_excel(file_path,index=False)
file_name = [file_path]
for i in columns_list:
    if i in subjects:
        single_df = data[["班级","姓名","总分","总分校名","单科合理区间","单科A档区间","单科B档区间","单科C档区间","单科D档区间","单科E档区间",i,i+"校名",i+"档位",i+"责任教师"]] 
        filename = i+"单科分析.xlsx"
        file_path = os.path.join(result_folder,filename)
        single_df.to_excel(file_path,index=False)
        file_name.append(file_path)
#至此所有文件已经生成

#对文件进行润色--------------
#----------------------------------------------------------------对列进行染色
def color_specific_column(file_path, color, column_name):
    workbook = load_workbook(filename=file_path)
    sheet = workbook.active
    
    header_row = next(sheet.iter_rows(min_row=1, max_row=1))
    column_index = None
    for cell in header_row:
        if cell.value == column_name:
            column_index = cell.column
            break
    
    if column_index is not None:
        for row in sheet.iter_rows(min_row=2):  # 从第二行开始染色
            cell = row[column_index - 1]  # 注意列索引从0开始，而列号从1开始
            cell.fill = PatternFill(start_color=color, end_color=color, fill_type="solid")
    
    workbook.save(filename=file_path)

def process_excel_files_with_columns(folder_path, color, column_names):
    file_paths = glob.glob(os.path.join(folder_path, "*.xlsx"))
    
    for file_path in file_paths:
        for i in range(len(column_names)):
            color_specific_column(file_path, color, column_names[i])

# 示例用法
folder_path = r"C:\Users\xxxxxx\Desktop\成绩\数据处理文件夹"  # 文件夹路径
column_names = ["单科合理区间", "单科A档区间", "单科B档区间", "单科C档区间", "单科D档区间", "单科E档区间"]
colors = ["00FFCC99","00FF99CC","00FFFF99","0099CCFF","00CCFFFF","00FFFFCC"]
for i in range(6):
    process_excel_files_with_columns(folder_path, colors[i], [column_names[i]])

#--------------------------------------------------------------------------对字母进行染色
def color_specific_columns(file_path, colors):
    workbook = load_workbook(filename=file_path)
    sheet = workbook.active
    
    target_values = ["A", "B", "C", "D", "E"]
    for row in sheet.iter_rows():
        for cell in row:
            if cell.value in target_values:
                fill_color = colors[target_values.index(cell.value) % len(colors)]
                cell.fill = PatternFill(start_color=fill_color, end_color=fill_color, fill_type="solid")
    
    workbook.save(filename=file_path)

def process_excel_files_with_columns(folder_path, colors):
    file_paths = glob.glob(os.path.join(folder_path, "*.xlsx"))
    
    for file_path in file_paths:
        color_specific_columns(file_path, colors)

# 示例用法
folder_path = r"C:\Users\lxxxxxx\Desktop\成绩\数据处理文件夹"  # 文件夹路径
colors = ["00FF99CC","00FFFF99","0099CCFF","00CCFFFF","00FFFFCC"]
process_excel_files_with_columns(folder_path, colors)