2024/03/07/22:24

analysis/others/shap_model.py

@@ -2,8 +2,12 @@ import matplotlib.pyplot as plt
 import numpy as np
 import shap
 
+from classes.static_custom_class import StaticValue
+
 
 def draw_shap_beeswarm(model, x, feature_names, type, paint_object):
+    plt.clf()
+    x = shap.sample(x, min(123, len(x)), random_state=StaticValue.RANDOM_STATE)
     explainer = shap.KernelExplainer(model.predict, x)
     shap_values = explainer(x)
 
@@ -16,6 +20,8 @@ def draw_shap_beeswarm(model, x, feature_names, type, paint_object):
 
 
 def draw_waterfall(model, x, feature_names, number, paint_object):
+    plt.clf()
+    x = shap.sample(x, min(123, len(x)), random_state=StaticValue.RANDOM_STATE)
     explainer = shap.KernelExplainer(model.predict, x, feature_names=feature_names)
     shap_values = explainer(x)
 
@@ -28,6 +34,7 @@ def draw_waterfall(model, x, feature_names, number, paint_object):
 
 
 def draw_force(model, x, feature_names, number, paint_object):
+    plt.clf()
     explainer = shap.KernelExplainer(model.predict, x, feature_names=feature_names)
     shap_values = explainer(x[number])
 
@@ -40,6 +47,8 @@ def draw_force(model, x, feature_names, number, paint_object):
 
 
 def draw_dependence(model, x, feature_names, col, paint_object):
+    plt.clf()
+    x = shap.sample(x, min(123, len(x)), random_state=StaticValue.RANDOM_STATE)
     explainer = shap.KernelExplainer(model.predict, x, feature_names=feature_names)
     shap_values = explainer(x)
 

app.py

@@ -1180,10 +1180,10 @@ class Dataset:
         data_copy = cls.data
 
         if cls.assign == MN.classification:
-            gr.Info("分类任务请确保目标变量列(第一列)数值为字符型[有限个标签]")
+            # gr.Info("分类任务请确保目标变量列(第一列)数值为字符型[有限个标签]")
             data_copy.iloc[:, 0] = data_copy.iloc[:, 0].astype(str)
         else:
-            gr.Info("回归任务请确保目标变量列(第一列)数值为数值型")
+            # gr.Info("回归任务请确保目标变量列(第一列)数值为数值型")
             data_copy.iloc[:, 0] = data_copy.iloc[:, 0].astype(float)
 
         cls.data = data_copy

data/notes.md

@@ -147,24 +147,28 @@
 ·需要选择已训练的模型名称
 ·需要选择图像类型
 ·特征对模型整体能力的表征程度
+·若样本量大于123,则随机抽样123个作为输入
 ```
 ##### *vii.特征瀑布图*
 ```angular2html
 ·需要选择已训练的模型名称
 ·需要选择相关特征的变量索引
 ·特征对模型整体能力的表征程度
+·若样本量大于123,则随机抽样123个作为输入
 ```
 ##### *viii.特征力图*
 ```angular2html
 ·需要选择已训练的模型名称
 ·需要选择相关特征的变量索引
 ·特征对模型整体能力的表征程度
+·若样本量大于123,则随机抽样123个作为输入
 ```
 ##### *viiii.特征依赖图*
 ```angular2html
 ·需要选择已训练的模型名称
 ·需要选择对应的列
 ·特征对模型整体能力的表征程度
+·若样本量大于123,则随机抽样123个作为输入
 ```
 ##### *图例*
 ```angular2html

visualization/draw_boxplot.py

@@ -2,6 +2,7 @@ import matplotlib.pyplot as plt
 
 
 def draw_boxplot(x_data, paint_object, will_rotate=False):
+    plt.clf()
     plt.figure(figsize=(10, 8), dpi=300)
 
     plt.grid(True)

visualization/draw_data_fit_total.py

@@ -3,6 +3,7 @@ from matplotlib import pyplot as plt
 
 
 def draw_data_fit_total(input_dict, paint_object):
+    plt.clf()
     plt.figure(figsize=(10, 6), dpi=300)
 
     for i, input_dict_items in enumerate(input_dict.items()):

visualization/draw_heat_map.py

@@ -4,6 +4,7 @@ import pandas as pd
 
 
 def draw_heat_map(x_data, col_list, paint_object, will_rotate=False):
+    plt.clf()
     plt.rcParams.update({'figure.autolayout': True})
 
     plt.figure(figsize=(10, 8), dpi=300)

visualization/draw_histogram.py

@@ -3,6 +3,7 @@ import numpy as np
 
 
 def draw_histogram(nums, labels, paint_object, will_rotate=False, will_show_text=True):
+    plt.clf()
     plt.figure(figsize=(10, 8), dpi=300)
 
     bars = plt.bar(

visualization/draw_learning_curve_total.py

@@ -2,6 +2,7 @@ from matplotlib import pyplot as plt
 
 
 def draw_learning_curve_total(input_dict, paint_object):
+    plt.clf()
     plt.figure(figsize=(10, 8), dpi=300)
 
     for i, values in enumerate(input_dict.values()):