現在的情況：我有一個函數將二進制類目標變量分為“1”和“0”，然后讀取每個變量的所有自變量。該函數還根據類別“1”和“0”確定每個自變量的 KDE，然后計算相交面積：import numpy as npimport pandas as pdimport matplotlib.pyplot as pltfrom scipy.stats import gaussian_kdedef intersection_area(data, bandwidth, margin,target_variable_name): #target_variable_name is the column name of the response variable data = data.dropna() X = data.drop(columns = [str(target_variable_name)], axis = 1) names = list(X.columns) new_columns = [] for column_name in names[:-1]: x0= data.loc[data[str(target_variable_name)] == 0,str(column_name)] x1= data.loc[data[str(target_variable_name)] == 1,str(column_name)] kde0 = gaussian_kde(x0, bw_method=bandwidth) kde1 = gaussian_kde(x1, bw_method=bandwidth) x_min = min(x0.min(), x1.min()) #find the lowest value between two minimum points x_max = min(x0.max(), x1.max()) #finds the lowest value between two maximum points dx = margin * (x_max - x_min) # add a margin since the kde is wider than the data x_min -= dx x_max += dx x = np.linspace(x_min, x_max, 500) kde0_x = kde0(x) kde1_x = kde1(x) inters_x = np.minimum(kde0_x, kde1_x) area_inters_x = np.trapz(inters_x, x) #intersection of two kde print(area_inters_x)問題： 如果我有 n_class = 4 該函數將如下所示：
1 回答
撒科打諢
TA貢獻1934條經驗 獲得超2個贊
考慮使用每個目標級別的多個類的列表理解來構建 x 和 kde 的列表。并且不是在每次迭代中打印結果，而是將結果綁定到數據框中：
def intersection_area_new(data, bandwidth, margin, target_variable_name):
# Collect the names of the independent variables
data = data.dropna()
# determine the number of unique classes from a multi-class target variable and save them as a list.
classes = data['target'].unique()
kde_dicts = []
for column_name in data.columns[:-1]:
# BUILD LIST OF x's AND kde's
x_s = [data.loc[(data[target_variable_name] == i), str(column_name)] for i in classes]
kde_s = [gaussian_kde(x, bw_method=bandwidth) for x in x_s]
x_min = min([x.min() for x in x_s]) # find the lowest value between two minimum points
x_max = min([x.max() for x in x_s]) # find the lowest value between two maximum points
dx = margin * (x_max - x_min) # add a margin since the kde is wider than the data
x_min -= dx
x_max += dx
x_array = np.linspace(x_min, x_max, 500)
kde_x_s = [kde(x_array) for kde in kde_s]
inters_x = np.array(kde_x_s).min(axis=0)
area_inters_x = np.trapz(inters_x, x_array) # intersection of kdes
kde_dicts.append({'target': target_variable_name,
'column': column_name,
'intersection': area_inters_x})
return pd.DataFrame(kde_dicts)
輸出
output = intersection_area_new(sample_dataset, None, 0.5, "target")
print(output.head(10))
# target column intersection
# 0 target var1 0.842256
# 1 target var2 0.757190
# 2 target var3 0.676021
# 3 target var4 0.873074
# 4 target var5 0.763626
# 5 target var6 0.868560
添加回答
舉報
0/150
提交
取消