Python：A Rubbish Diversity Criteria

'''
author:Daniel
date:2020-12-11
organization: CQUPT
Reference: D. Wu, C. Lin, J. Huang. Active learning for regression using greeding sampling. Information Sciences, 2019, 474: 90-105.
'''
import xlwt
import numpy as np
import pandas as pd
from copy import deepcopy
from sklearn.metrics import accuracy_score, mean_absolute_error
from collections import OrderedDict
from mord import LogisticAT
from sklearn.model_selection import StratifiedKFold
from pathlib import Path
from sklearn import datasets
import matplotlib.pyplot as plt
from scipy.spatial.distance import pdist,squareform


class Max():
    def __init__(self,X_pool,y_pool,labeled,budget,X_test,y_test):
        self.X_pool = X_pool
        self.y_pool = y_pool
        self.X_test = X_test
        self.y_test = y_test
        self.nSample = self.X_pool.shape[0]
        self.labeled = list(deepcopy(labeled))
        self.unlabeled = self.initialization()
        self.budgetLeft = deepcopy(budget)
        self.budget = deepcopy(budget)
        self.pdist = pdist(self.X_pool,metric="euclidean")
        self.matrix = squareform(self.pdist)
        self.meanDist = np.mean(self.pdist)
        self.rho = self.cal_rho()
        self.model = LogisticAT()


    def cal_rho(self):
        print("meanDist",self.meanDist)
        rho = np.zeros(self.nSample)
        for idx in range(self.nSample):
            rho[idx] = 0
            for jdx in range(self.nSample):
                if idx != jdx:
                    rho[idx] += np.exp(-(self.matrix[idx,jdx]/1)**2)
        return rho

    def initialization(self):
        unlabeled = [i for i in range(self.nSample)]
        for j in self.labeled:
            unlabeled.remove(j)
        return unlabeled

    def select(self):
        while self.budgetLeft > 0:
            criteria = OrderedDict()
            for idx in self.unlabeled:
                criteria[idx] = 0
                for jdx in self.labeled:
                    criteria[idx] += self.matrix[idx,jdx]
            tar_idx = max(criteria,key=criteria.get)
            plt.scatter(self.X_pool[:,0],self.X_pool[:,1],c=y)
            plt.scatter(self.X_pool[self.labeled][:,0],self.X_pool[self.labeled][:,1],c=self.y_pool[self.labeled],edgecolors='r',linewidths=1)
            # plt.scatter(self.X_pool[self.unavaiable][:,0],self.X_pool[self.unavaiable][:,1],c=self.y_pool[self.unavaiable],edgecolors='b',linewidths=1.5)
            plt.scatter(self.X_pool[tar_idx][0],self.X_pool[tar_idx][1],marker="*",c="r",s=120)

            self.labeled.append(tar_idx)
            self.unlabeled.remove(tar_idx)
            self.budgetLeft -= 1
        plt.show()


if __name__ == '__main__':

    '''generate the dataset contain four categories data'''
    add = [0, 6, 12, 19]
    data = None
    for i in range(4):
        X, yy = datasets.make_blobs(n_samples=200, n_features=2, center_box=(0, 0), cluster_std=3, random_state=45)
        X += add[i]
        if i == 0:
            data = X
        else:
            data = np.vstack((data, X))
    y = np.ones(800)
    y[:200] = 0
    y[200:400] = 1
    y[400:600] = 2
    y[600:800] = 3
    X = data
    labeled = [6, 206, 406, 606]
    budget = 40
    '''Execute the algorithm'''
    model = Max(X_pool=X,y_pool=y,labeled=labeled,budget=budget,X_test=X,y_test=y)
    model.select()