The Diversity of Multi-label in Real Data

In [ ]:

    

%matplotlib inline
import os, sys
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns


    

In [ ]:

    

sys.path.append('src/')


    

In [ ]:

    

from shared import TrajData, evaluate


    

In [ ]:

    

dat_ix = 0
data_dir = 'data/data-new'


    

In [ ]:

    

dat_obj = TrajData(dat_ix, data_dir=data_dir)


    

In [ ]:

    

def calc_diversity_mat(dat_obj, query):
    assert(query in dat_obj.TRAJ_GROUP_DICT)
    if len(dat_obj.TRAJ_GROUP_DICT[query]) == 1:
        print('only one label for query:', query)
    tid_list = sorted(dat_obj.TRAJ_GROUP_DICT[query])
    nLabels = len(tid_list)
    assert(nLabels > 1)
    mat = np.zeros((nLabels, nLabels), dtype=np.float)
    for i in range(nLabels):
        ti = dat_obj.traj_dict[tid_list[i]]
        for j in range(i+1, nLabels):
            tj = dat_obj.traj_dict[tid_list[j]]
            assert(len(ti) == len(tj))
            mat[i, j] = np.sum(np.asarray(ti) != np.asarray(tj)) / len(ti)
    return mat


    

In [ ]:

    

queries = sorted(dat_obj.TRAJ_GROUP_DICT.keys())
print(len(queries))


    

In [ ]:

    

q_ix = 0
query = queries[q_ix]


    

In [ ]:

    

[dat_obj.traj_dict[x] for x in dat_obj.TRAJ_GROUP_DICT[query]]


    

In [ ]:

    

mat = calc_diversity_mat(dat_obj, query)


    

In [ ]:

    

sns.heatmap(mat, cmap='BuGn', vmin=0, vmax=1)