230702417 王鹏 (1).zip

``` import numpy as np import pandas as pd import matplotlib.pyplot as plt data = {'index': np.arange(1, 10001), 'count': np.random.randint(0, 10001, size=10000), 'class': np.random.choice([1, 2, 3, 4, 5], size=10000), 'normal_distribution': np.random.normal(0, 10000, 10000), '0-1': np.random.rand(10000)} df = pd.DataFrame(data) df.to_csv(r"D:\230702417 王鹏\2_data.csv", index=False) plt.figure(figsize=(10, 5))#图的宽度和长度 plt.hist(df['normal_distribution'], bins=100) plt.xlabel('x') plt.ylabel('y') plt.title('normal_distribution') plt.show() class_counts = df['class'].value_counts()#计算class出现的次数 plt.figure(figsize=(5, 5)) plt.pie(class_counts, labels='class', autopct='%1.1f%%', startangle=60) plt.title('class_distribution') plt.show() class_count_sum = df.groupby('class')['count'].sum()#groupby可以允许你按照某列的值对数据进行分组 plt.figure(figsize=(10, 5)) plt.bar(class_count_sum.index, class_count_sum, color='orange')#索引作x轴，另外一个作y轴 plt.xlabel('Class') plt.ylabel('Count sum') plt.title('count sum of the class') for i, v in enumerate(class_count_sum):#循环添加标签，从1开始，水平居中，垂直方式对齐 plt.text(i+1, v+50, str(v), ha='center', va='bottom') plt.show() plt.figure(figsize=(10, 5)) plt.hist(df['count'], bins=10)#bins：组距 plt.xlabel('count') plt.ylabel('y') plt.show() support_rates = df.groupby('class')['0-1'].mean() plt.figure(figsize=(10, 5)) plt.bar(support_rates.index, support_rates, color=('red', 'blue', 'red', 'blue', 'red')) plt.xlabel('Class') plt.ylabel('Support rate') plt.title('Support rates') for i, v in enumerate(support_rates): plt.text(i+1, v+0.01, f'{v:.2f}', ha='center', va='bottom')#为每个条形添加值 plt.show() ```