python分析多个特征的相关性并绘制热力图
首先先得到分析的数据
- 引入分析数据的3大库
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
- 这里已经提前获取好分析数据了，存于
df中
#打印数据 df
print(df)
# x10 x11 x12 x13 x14 x15 x16 x17 x18 x19
# 0 49.895756 17.775994 5.270920 0.771761 0.018632 0.006864 0.003923 0.003923 0.486903 0.100025
# 1 57.709936 23.799994 3.325423 0.234185 0.003903 0.003903 0.003903 0.003903 0.520908 0.144414
# 2 55.831441 27.993933 12.687485 4.852282 1.393889 0.373252 0.041817 0.007744 0.530904 0.128548
# 3 40.467228 18.445954 9.118901 3.079428 0.840261 0.272434 0.007653 0.001531 0.483284 0.114790
# 4 18.026254 8.570709 0.410381 0.000000 0.000000 0.000000 0.000000 0.000000 0.475935 0.123572
# ... ... ... ... ... ... ... ... ... ... ...
# 1146 6.071765 0.937472 0.031145 0.003115 0.000000 0.000000 0.000000 0.000000 0.537470 0.116795
# 1147 63.197145 27.377668 8.067688 0.979548 0.001552 0.000000 0.000000 0.000000 0.516733 0.124190
# 1148 30.461898 13.966980 1.763305 0.137858 0.011221 0.000000 0.000000 0.000000 0.560632 0.129843
# 1149 40.525739 12.604947 4.740919 1.077570 0.563518 0.326860 0.239568 0.174584 0.485972 0.106690
# 1150 69.423565 7.031843 1.750548 0.046597 0.021180 0.008472 0.000000 0.000000 0.556192 0.088957分析各个特征的之间的相关性
- 这里直接使用
df.corr()
#对df进行相关性分析
new_df = df.corr()
print(new_df)#打印值
# x10 x11 x12 x13 x14 x15 x16 x17
# x10 1.000000 0.767091 0.763409 0.486606 0.163915 0.132227 0.114722 0.084682
# x11 0.767091 1.000000 0.919589 0.624537 0.257159 0.216127 0.181431 0.139196
# x12 0.763409 0.919589 1.000000 0.780891 0.383977 0.328839 0.273616 0.214250
# x13 0.486606 0.624537 0.780891 1.000000 0.825772 0.758195 0.636787 0.518501
# x14 0.163915 0.257159 0.383977 0.825772 1.000000 0.931661 0.772151 0.625245
# x15 0.132227 0.216127 0.328839 0.758195 0.931661 1.000000 0.906374 0.782185
# x16 0.114722 0.181431 0.273616 0.636787 0.772151 0.906374 1.000000 0.943460
# x17 0.084682 0.139196 0.214250 0.518501 0.625245 0.782185 0.943460 1.000000
# x18 -0.086155 -0.128990 -0.128006 -0.167954 -0.149553 -0.150996 -0.122688 -0.097073
# x19 -0.086474 -0.090721 -0.098866 -0.090738 -0.058645 -0.060441 -0.039783 -0.019091
# x18 x19
# x10 -0.086155 -0.086474
# x11 -0.128990 -0.090721
# x12 -0.128006 -0.098866
# x13 -0.167954 -0.090738
# x14 -0.149553 -0.058645
# x15 -0.150996 -0.060441
# x16 -0.122688 -0.039783
# x17 -0.097073 -0.019091
# x18 1.000000 -0.131497
# x19 -0.131497 1.000000绘制其热力图
- 这里使用了
seaborn库，如果没有直接在在终端pip install seaborn下载
注：本人使用的是
vscode
import seaborn as sns
#引入seaborn库
plt.figure(1)
sns.heatmap(new_df,annot=True, vmax=1, square=True)#绘制new_df的矩阵热力图
plt.show()#显示图片- 效果图：
- 如果觉得颜色不喜欢，可以加入
cmap属性，可选值入下：
‘Accent’, ‘Accent_r’, ‘Blues’, ‘Blues_r’, ‘BrBG’, ‘BrBG_r’, ‘BuGn’, ‘BuGn_r’, ‘BuPu’, ‘BuPu_r’, ‘CMRmap’,
‘CMRmap_r’, ‘Dark2’, ‘Dark2_r’, ‘GnBu’, ‘GnBu_r’, ‘Greens’, ‘Greens_r’, ‘Greys’, ‘Greys_r’, ‘OrRd’, ‘OrRd_r’, ‘Oranges’, ‘Oranges_r’, ‘PRGn’, ‘PRGn_r’, ‘Paired’, ‘Paired_r’, ‘Pastel1’, ‘Pastel1_r’, ‘Pastel2’, ‘Pastel2_r’, ‘PiYG’, ‘PiYG_r’, ‘PuBu’, ‘PuBuGn’, ‘PuBuGn_r’, ‘PuBu_r’, ‘PuOr’, ‘PuOr_r’, ‘PuRd’, ‘PuRd_r’, ‘Purples’, ‘Purples_r’, ‘RdBu’, ‘RdBu_r’, ‘RdGy’, ‘RdGy_r’, ‘RdPu’, ‘RdPu_r’, ‘RdYlBu’, ‘RdYlBu_r’, ‘RdYlGn’, ‘RdYlGn_r’, ‘Reds’, ‘Reds_r’, ‘Set1’, ‘Set1_r’, ‘Set2’, ‘Set2_r’, ‘Set3’, ‘Set3_r’, ‘Spectral’, ‘Spectral_r’, ‘Wistia’, ‘Wistia_r’, ‘YlGn’, ‘YlGnBu’, ‘YlGnBu_r’, ‘YlGn_r’, ‘YlOrBr’, ‘YlOrBr_r’, ‘YlOrRd’, ‘YlOrRd_r’, ‘afmhot’, ‘afmhot_r’, ‘autumn’, ‘autumn_r’, ‘binary’, ‘binary_r’,
‘bone’, ‘bone_r’, ‘brg’, ‘brg_r’, ‘bwr’, ‘bwr_r’, ‘cividis’, ‘cividis_r’, ‘cool’, ‘cool_r’, ‘coolwarm’, ‘coolwarm_r’, ‘copper’, ‘copper_r’, ‘crest’, ‘crest_r’, ‘cubehelix’, ‘cubehelix_r’, ‘flag’, ‘flag_r’, ‘flare’, ‘flare_r’, ‘gist_earth’, ‘gist_earth_r’, ‘gist_gray’, ‘gist_gray_r’, ‘gist_heat’, ‘gist_heat_r’, ‘gist_ncar’, ‘gist_ncar_r’, ‘gist_rainbow’, ‘gist_rainbow_r’, ‘gist_stern’, ‘gist_stern_r’, ‘gist_yarg’, ‘gist_yarg_r’, ‘gnuplot’, ‘gnuplot2’, ‘gnuplot2_r’, ‘gnuplot_r’, ‘gray’, ‘gray_r’, ‘hot’, ‘hot_r’, ‘hsv’, ‘hsv_r’,‘plasma’, ‘plasma_r’, ‘prism’, ‘prism_r’, ‘rainbow’, ‘rainbow_r’, ‘rocket’, ‘rocket_r’, ‘seismic’, ‘seismic_r’, ‘spring’, ‘spring_r’, ‘summer’, ‘summer_r’, ‘tab10’, ‘tab10_r’, ‘tab20’, ‘tab20_r’, ‘tab20b’, ‘tab20b_r’, ‘tab20c’, ‘tab20c_r’, ‘terrain’, ‘terrain_r’, ‘turbo’, ‘turbo_r’, ‘twilight’, ‘twilight_r’, ‘twilight_shifted’, ‘twilight_shifted_r’, ‘viridis’, ‘viridis_r’, ‘vlag’, ‘vlag_r’, ‘winter’, ‘winter_r’
- 下面举例加入
cmap=‘Accent’属性：
import seaborn as sns
#引入seaborn库
plt.figure(1)
sns.heatmap(new_df,annot=True, vmax=1, square=True，cmap='Accent')#绘制new_df的矩阵热力图
plt.show()#显示图片