2024华为杯研赛D题原创python代码+结果表｜全部可运行｜精美可视化

终于要写完了论文，太不容易了。

import pandas as pd

import os
import pandas as pd

# 定义数据文件夹路径
data_folder = r'C:\Users\Administrator\Documents\工作类\数模-研赛-9.20\T1'

# 初始化一个字典来存储每年的统计结果 
annual_stats = {}

# 遍历数据文件夹中的所有文件
for filename in os.listdir(data_folder):
    if filename.startswith('baoyu_') and filename.endswith('.xls'):
        # 解析文件名中的年份和月份
        year = filename.split('_')[1]
        month = filename.split('_')[2].split('.')[0]

        # 读取CSV文件
        file_path = os.path.join(data_folder, filename)
        df = pd.read_excel(file_path)

        # 提取省份、暴雨次数和降雨总量
        provinces = df['PR'].unique()
        for province in provinces:
            province_data = df[df['PR'] == province]
            baoyu_cishu = province_data['baoyu_cishu'].sum()
            jiangyu_sum = province_data['jiangyu_sum'].sum()

            # 存储每年的统计结果
            if year not in annual_stats:
                annual_stats[year] = {}
            if province not in annual_stats[year]:
                annual_stats[year][province] = {'baoyu_cishu': 0, 'jiangyu_sum': 0}

            annual_stats[year][province]['baoyu_cishu'] += baoyu_cishu
            annual_stats[year][province]['jiangyu_sum'] += jiangyu_sum

# 创建汇总表
summary_df = pd.DataFrame(columns=['统计指标'] + list(annual_stats.keys()))

# 添加全国降雨总量
national_jiangyu_sums = [sum(province_stats['jiangyu_sum'] for province_stats in provinces.values()) for provinces in
                         annual_stats.values()]
summary_df.loc[0] = ['全国降雨总量'] + national_jiangyu_sums

# 添加全国暴雨次数
national_baoyu_cishus = [sum(province_stats['baoyu_cishu'] for province_stats in provinces.values()) for provinces in
                         annual_stats.values()]
summary_df.loc[1] = ['全国暴雨次数'] + national_baoyu_cishus

# 保存汇总表
summary_df.to_csv('sta_summary.csv', index=False)

# 保存各省市的统计结果
for year, provinces in annual_stats.items():
    # 读取原始数据文件以获取原始结构
    original_file_path = os.path.join(data_folder, f'sheng.xls')  # 假设1月文件存在
    original_df = pd.read_excel(original_file_path)

    # 更新所有省份的暴雨次数和降雨总量
    for province, stats in provinces.items():
        province_data = original_df[original_df['PR'] == province]
        original_df.loc[original_df['PR'] == province, 'baoyu_cishu'] = stats['baoyu_cishu']
        original_df.loc[original_df['PR'] == province, 'jiangyu_sum'] = stats['jiangyu_sum']

    # 保存结果
    original_df.to_csv(f'sta_{year}.csv', index=False)

print("统计完成！")

以上仅为部分。其中更详细的思路、各题目思路、代码、讲解视频、成品论文及其他相关内容，可以看下面的群名片！