2023 Higher Education Society Cup National College Student Mathematical Modeling Competition Code Analysis for Question C

Due to some force majeure, only part of the code (the part of the first question) is shown below. The rest of the code can be found at the end of the article.

First import the required packages:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import os
import warnings
warnings.filterwarnings('ignore')
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
import matplotlib.font_manager as fm

Read data:

 Read the data
'''
# data_1: 6 个蔬菜品类的商品信息
# data_2: 销售流水明细数据
# data_3: 蔬菜类商品的批发价格
# data_4: 蔬菜类商品的近期损耗率
附件 1 中，部分单品名称包含的数字编号表示不同的供应来源。
附件 4 中的损耗率反映了近期商品的损耗情况，通过近期盘点周期的数据计算得到。

'''
data_1 = pd.read_excel('../data/附件1.xlsx')
data_2 = pd.read_excel('../data/附件2.xlsx')
data_3 = pd.read_excel('../data/附件3.xlsx')
data_4 = pd.read_excel('../data/附件4.xlsx')

I’m skipping some data processing parts in the middle and let’s take a look at the visual results:

# 以季度为周期，可视化不同蔬菜品类销售量的变化趋势
# 将销售数据按照季度进行重采样
quarterly_sales = merged_data.resample('Q', on='销售日期')['销量(千克)'].sum()
# 将销售数据按照分类名称和季度进行分组，计算每个品类在每个季度的销售量
# sales_by_category = merged_data[merged_data['销售类型'] == '销售'].groupby(['分类名称', pd.Grouper(key='销售日期', freq='Q')])['销量(千克)'].sum() - merged_data[merged_data['销售类型'] == '退货'].groupby(['分类名称', pd.Grouper(key='销售日期', freq='Q')])['销量(千克)'].sum()
sales_by_category = merged_data[merged_data['销售类型'] == '销售'].groupby(['分类名称', pd.Grouper(key='销售日期', freq='Q')])['销量(千克)'].sum()
# 可视化销售量变化趋势
fig, ax = plt.subplots(figsize=(10, 6))
for category in sales_by_category.index.levels[0]:
    ax.plot(sales_by_category.loc[category].index, sales_by_category.loc[category].values, label=category)
ax.legend()
ax.set_xlabel('季度')
ax.set_ylabel('销售量（千克）')
ax.set_title('蔬菜各品类销售量变化趋势')
plt.savefig('../results/sales_num_trend.png', dpi=300, bbox_inches='tight')

Part of the code for the heat map:

# 计算各品类销售量之间的相关系数
corr_matrix = sales_by_quarter.corr()

# 可视化相关系数矩阵
sns.set(style='white')
fig, ax = plt.subplots(figsize=(10, 8))
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', ax=ax)
ax.set_title('蔬菜各品类销售量相关系数矩阵', fontproperties=font)
for tick in ax.get_xticklabels():
    tick.set_rotation(45)
    tick.set_fontproperties(font)
for tick in ax.get_yticklabels():
    tick.set_rotation(0)
    tick.set_fontproperties(font)
plt.xlabel('分类名称', fontproperties=font)
plt.ylabel('分类名称', fontproperties=font)
plt.savefig('../results/corr_matrix.png', dpi=300, bbox_inches='tight')
plt.show()

# 可视化相关系数矩阵
sns.set(style='white')
fig, ax = plt.subplots(figsize=(16, 16))
sns.heatmap(corr_matrix_top_veggies, annot=True, cmap='coolwarm', ax=ax)
ax.set_title('销量前15的蔬菜单品销售量相关系数矩阵', fontproperties=font)
for tick in ax.get_xticklabels():
    tick.set_rotation(45)
    tick.set_fontproperties(font)
for tick in ax.get_yticklabels():
    tick.set_rotation(0)
    tick.set_fontproperties(font)
plt.xlabel('分类名称', fontproperties=font)
plt.ylabel('分类名称', fontproperties=font)
plt.savefig('../results/corr_matrix_top_veggies.png', dpi=300, bbox_inches='tight')
plt.show()

For ideas, related codes, explanation videos, references and other related content, you can click on the group business card below!

2023 Higher Education Society Cup National College Student Mathematical Modeling Competition Code Analysis for Question C

Guess you like