import matplotlib.pyplot as plt
# Linux show Chinese characters *** important
plt.rcParams['font.family'] = 'WenQuanYi Micro Hei' 

import warnings
warnings.filterwarnings("ignore")

import pandas as pd

# read by default 1st sheet of an excel file
path = '/home/shiyu/Desktop/path_acdemic/ant/数模/历年题目/2022/附件.xlsx'
d1 = pd.read_excel(path, sheet_name='表单1')
d2 = pd.read_excel(path, sheet_name='表单2')
d3 = pd.read_excel(path, sheet_name='表单3')

print(d1.shape)
print(d2.shape)
print(d3.shape)

(58, 5)
(69, 15)
(8, 16)

问题 1

1.1 对这些玻璃文物的表面风化与其玻璃类型、纹饰和颜色的关系进行分析

数据探索 – 单个分类变量的绘图

树形图

https://www.geeksforgeeks.org/treemaps-in-python-using-squarify/

import seaborn as sb 
import matplotlib.pyplot as plt
import squarify
    
data = list(d1['颜色'].value_counts())
labels = list(d1['颜色'].value_counts().index)

plt.rcParams['figure.dpi'] = 300
plt.rcParams['savefig.dpi'] = 300

plt.figure(figsize=(15,8))
squarify.plot(sizes=data, label=labels, text_kwargs={
   'fontsize': 20},
              color=sb.color_palette("Spectral",len(data))) 

plt.axis("off") 

(0.0, 100.0, 0.0, 100.0)

条形图

df = pd.DataFrame(d1['颜色'].value_counts())
df['颜色'] = df.index
df

	count	颜色
颜色
浅蓝	20	浅蓝
蓝绿	15	蓝绿
深绿	7	深绿
紫	4	紫
浅绿	3	浅绿
深蓝	2	深蓝
黑	2	黑
绿	1	绿

import matplotlib.pyplot as plt
import plotly.express as px
import numpy as np

# Linux show Chinese characters *** important
plt.rcParams['font.family'] = 'WenQuanYi Micro Hei' 

fig = px.bar(df, x="颜色", y="count", 
             title="颜色类别计数")
# center title
fig.update_layout(title_x=0.5)
# remove background color
fig.update_layout({
   
'plot_bgcolor': 'rgba(0, 0, 0, 0)',
'paper_bgcolor': 'rgba(0, 0, 0, 0)',
})

fig.show()

扇形图

print(d1['纹饰'].value_counts())

纹饰
C    30
A    22
B     6
Name: count, dtype: int64

import plotly.express as px
fig = px.pie(d1, names='纹饰', title="玻璃纹饰类别的比例分布")
# center title
fig.update_layout(title_x=0.5)
fig.show()

print(d1['类型'].value_counts())
fig = px.pie(d1, names='类型', title="玻璃类型的比例分布")
# center title
fig.update_layout(title_x=0.5)
fig.show()

类型
铅钡    40
高钾    18
Name: count, dtype: int64

print(d1['颜色'].value_counts