Python数据标准化

Catalog

零一标准化

import pandas as pd
import matplotlib.pyplot as mp
d = {'name': list('ABCD'), 'value': [1002, 1000, 1010, 1001]}
df = pd.DataFrame(d)
# 0-1标准化
value_01 = (
    (df['value'] - df['value'].min())
    /
    (df['value'].max() - df['value'].min())
)
df['0-1'] = value_01
print(df)

# 可视化
mp.figure(num='Title', facecolor='lightgray', figsize=(6, 3))
# 左图：处理前
mp.subplot(1, 2, 1)
mp.title('origin', fontsize=12)
mp.bar(df['name'], df['value'], 0.2, color='dodgerblue', label='value')
mp.legend()
# 右图：【零一标准化】处理后
mp.subplot(1, 2, 2)
mp.title('0-1 standardization', fontsize=12)
mp.bar(df['name'], df['0-1'], 0.2, color='orangered', label='0-1')
mp.legend()
# 展示
mp.tight_layout()  # 紧凑布局，防止叠压
mp.show()

以中位数为0的可视化

import pandas as pd
import matplotlib.pyplot as mp
d = {'name': list('ABCD'), 'value': [101, 95, 115, 100]}
df = pd.DataFrame(d)
# 中位数变0
median0 = (
    (df['value'] - df['value'].median())
)
df['median-->0'] = median0
print(df)

# 可视化
mp.figure(num='Title', facecolor='lightgray', figsize=(6, 3))
# 左图：处理前
mp.subplot(1, 2, 1)
mp.title('origin')
mp.bar(df['name'], df['value'], 0.2, color='dodgerblue', label='origin')
mp.legend()
# 右图：【中位数变0】处理后
mp.subplot(1, 2, 2)
mp.title('median-->0')
ax = mp.gca()  # 获取当前坐标轴对象
ax.spines['bottom'].set_position(('data', 0))  # 将底边框置于数据坐标原点
mp.bar(df['name'], df['median-->0'], 0.2, color='orangered', label='median-->0')
mp.legend()
# 展示
mp.tight_layout()  # 紧凑布局，防止叠压
mp.show()