变量分析图

1、类别柱状图

用于展示类别特征在当前维度下的种类和占比

def barPlot(df,feature,figsize=(14, 6),save=False, filename=None):
    feature_name = feature#.capitalize()
    df_temp = df.copy()
    df_temp[feature] = df_temp[feature].fillna('null')

    #plt.figure(figsize=figsize)
    #plt.suptitle(f'{feature_name} Distributions', fontsize=22)
    
    # 柱形图：该特征下各类型占比
    plt.subplot(111)
    g = sns.countplot(x=feature, data=df_temp.sort_values(by=feature))
    plt.xticks(rotation=60)
    g.set_title(f"{feature_name}", fontsize=19)
    g.set_xlabel(feature_name, ,fontsize=17)
    g.set_ylabel("Count", fontsize=17)
    for p in g.patches:
        height = p.get_height()
        g.text(p.get_x()+p.get_width()/2.,
                height + 3,
                '{:1.2f}%'.format(height/df.shape[0]*100),
                ha="center", fontsize=14) 
    plt.xticks(rotation=60)
    if save: # 保存图片
        if filename:
            plt.savefig(f'../pics/{filename}.png', bbox_inches='tight', dpi=300)
        else:
            plt.savefig(f'../pics/{feature_name}.png', bbox_inches='tight', dpi=300)
    plt.show()

 2、柱状&折现图

用于展示类别特征的数量分布，和各类别下命中target占比趋势。

import matplotlib.pyplot as plt
import matplotlib as mlp

plt.rcParams['font.family'] = ['sans-serif']
plt.rcParams['font.sans-serif'] = [&