问题描述
当前情况:
我有一个将二进制目标变量分为“ 1”和“ 0”的函数,然后读取每个变量的所有自变量。该函数还根据类别“ 1”和“ 0”确定每个自变量的KDE,然后计算相交面积:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from scipy.stats import gaussian_kde
def 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)
def intersection_area(data,str(column_name)]
x2= data.loc[data[str(target_variable_name)] == 2,str(column_name)]
x3= data.loc[data[str(target_variable_name)] == 3,bw_method=bandwidth)
kde2 = gaussian_kde(x2,bw_method=bandwidth)
kde3 = gaussian_kde(x3,x1.min(),x2.min(),x3.min())
x_max = min(x0.max(),x1.max(),x3.min())
dx = margin * (x_max - x_min)
x_min -= dx
x_max += dx
x = np.linspace(x_min,500)
kde0_x = kde0(x)
kde1_x = kde1(x)
kde2_x = kde1(x)
kde3_x = kde1(x)
inters_x = np.minimum(kde0_x,kde1_x,kde2_x,kde3_x)
area_inters_x = np.trapz(inters_x,x)
print(area_inters_x)
现在,如果我有n个类的未知数据集怎么办?我正在尝试改进旧代码,以使其对多类数据集变得更健壮,确定给定类的独立变量的KDE并计算区域的交集。但是我被困在x = data.loc[data[str(target_name)] == i,str(column_name)]
部分:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from scipy.stats import gaussian_kde
def intersection_area(data,target_variable_name):
# Collect the names of the independent variables
data = data.dropna()
X = data.drop(columns = [str(target_variable_name)],axis = 1)
names = list(X.columns)
# determine the number of unique classes from a multi-class and save them as a list.
classes = []
for unique_class in data.target_variable_name.unique():
classes.append(unique_class)
new_columns = []
# for each unique class,run through the different independent variables
for i in classes:
for column_name in names[:-1]:
print(i) #to show the class (target variable: 0,1,...,n)
print(column_name) #to show the variable name to be analyzed
'''This is the part where I got stuck'''
x = data.loc[data[str(target_name)] == i,str(column_name)]
有兴趣复制问题的人的模拟数据集:
from sklearn.datasets import make_classification
#note: to create a binary class target change n_class = 2
X,y = make_classification(n_samples=50000,n_features=6,n_informative=6,n_redundant=0,n_repeated=0,n_classes=4,n_clusters_per_class=3,class_sep=0.95,flip_y=0.2,weights=[0.7,0.2,0.1],shuffle=True,random_state=93)
dataset_x = pd.DataFrame({'var1': X[:,0],'var2': X[:,1],'var3': X[:,2],'var4': X[:,3],'var5': X[:,4],'var6': X[:,5]})
dataset_y = pd.DataFrame({'target': y})
sample_dataset = pd.concat([dataset_x,dataset_y],axis=1)
print(sample_dataset)
解决方法
考虑使用列表理解为每个目标级别的多个类构建x和kde的列表。而不是在每次迭代中打印出结果,而是将结果绑定到数据框中:
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)
输出
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