import pandas as pd
import numpy as np
from collections import Counter
from matplotlib import pyplot as plt
import os
import cv2
%matplotlib inline

%%javascript
IPython.OutputArea.auto_scroll_threshold = 9999;

def load_filepaths():
    imdir_ideology = 'ideology_image_dataset/'
    ideology_files=os.listdir('ideology_image_dataset/')
    ideology_files_path=[os.path.join(imdir_ideology,file) for file in ideology_files ]
    
    return ideology_files_path

ideology_files_path=load_filepaths()
len(ideology_files_path)

2942

def showClustering(predicted_labels,label):
    label_indexs= np.where(predicted_labels==label)[0]
    print("CLUSTER--> ",label,"TOTAL IMAGES--> ",len(label_indexs))
    if(len(label_indexs)>=2000):
        print("Cannot be visualize")
    
    else:
        if(len(label_indexs)>=500):
            fig=plt.figure(figsize=(10, 400))


        elif(len(label_indexs)>100 and len(label_indexs)<500):
            fig=plt.figure(figsize=(10, 70))
        elif(len(label_indexs)>=50 and len(label_indexs)<100):
            fig=plt.figure(figsize=(10, 30))

        elif(len(label_indexs)>=20 and len(label_indexs)<50):
            fig=plt.figure(figsize=(10, 20))

        elif(len(label_indexs)>=0 and len(label_indexs)<20):
            fig=plt.figure(figsize=(10, 8))

        for i,index in enumerate(label_indexs):


            image = cv2.imread(ideology_files_path[index])
            image= cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

            columns = 4
            rows = np.ceil(len(label_indexs)/float(columns))

            fig.add_subplot(rows,columns, i+1)
            plt.imshow(image)


        plt.show()

    

VGG-16

Here we can visualize the results of optics, mean shift and agglomerative clustering . Also we will not visualize the cluster that will more than 2000 images

results_df=pd.read_csv('image-results2/ideology_model_vgg_16.npy.csv')
results_df

	Unnamed: 0	n_clusters	silhouette	calinski	davies
0	Agglomerative clustering	2	0.052873	242.662997	2.846778
1	DBSCAN	0	-1.000000	-1.000000	-1.000000
2	Mean-shift	51	0.099957	4.555625	0.917647
3	Optics	51	-0.195670	6.969148	1.454804
4	Agglomerative clustering-scipy	30	0.109012	6.717517	0.991022
5	HDBSCAN	2	0.117461	67.867594	3.463518

predicted_Labels=np.load('image-results2/ideology_model_vgg_16.npy_mean_shift_labels.npy')
unique_labels=set(predicted_Labels)
for label in unique_labels:
    if(label!=-1):
        showClustering(predicted_Labels,label)

CLUSTER-->  0 TOTAL IMAGES-->  2849
Cannot be visualize
CLUSTER-->  1 TOTAL IMAGES-->  2

CLUSTER-->  2 TOTAL IMAGES-->  2

CLUSTER-->  3 TOTAL IMAGES-->  2

CLUSTER-->  4 TOTAL IMAGES-->  3

CLUSTER-->  5 TOTAL IMAGES-->  5

CLUSTER-->  6 TOTAL IMAGES-->  2

CLUSTER-->  7 TOTAL IMAGES-->  2

CLUSTER-->  8 TOTAL IMAGES-->  1

CLUSTER-->  9 TOTAL IMAGES-->  1

CLUSTER-->  10 TOTAL IMAGES-->  2

CLUSTER-->  11 TOTAL IMAGES-->  1

CLUSTER-->  12 TOTAL IMAGES-->  3

CLUSTER-->  13 TOTAL IMAGES-->  2

CLUSTER-->  14 TOTAL IMAGES-->  1

CLUSTER-->  15 TOTAL IMAGES-->  1

CLUSTER-->  16 TOTAL IMAGES-->  1

CLUSTER-->  17 TOTAL IMAGES-->  2

CLUSTER-->  18 TOTAL IMAGES-->  1

CLUSTER-->  19 TOTAL IMAGES-->  1

CLUSTER-->  20 TOTAL IMAGES-->  1

CLUSTER-->  21 TOTAL IMAGES-->  1

CLUSTER-->  22 TOTAL IMAGES-->  1

CLUSTER-->  23 TOTAL IMAGES-->  1

CLUSTER-->  24 TOTAL IMAGES-->  9

CLUSTER-->  25 TOTAL IMAGES-->  2

CLUSTER-->  26 TOTAL IMAGES-->  2

CLUSTER-->  27 TOTAL IMAGES-->  6

CLUSTER-->  28 TOTAL IMAGES-->  1

CLUSTER-->  29 TOTAL IMAGES-->  1

CLUSTER-->  30 TOTAL IMAGES-->  1

CLUSTER-->  31 TOTAL IMAGES-->  1

CLUSTER-->  32 TOTAL IMAGES-->  1

CLUSTER-->  33 TOTAL IMAGES-->  2

CLUSTER-->  34 TOTAL IMAGES-->  1

CLUSTER-->  35 TOTAL IMAGES-->  2

CLUSTER-->  36 TOTAL IMAGES-->  2

CLUSTER-->  37 TOTAL IMAGES-->  1

CLUSTER-->  38 TOTAL IMAGES-->  1

CLUSTER-->  39 TOTAL IMAGES-->  1

CLUSTER-->  40 TOTAL IMAGES-->  1

CLUSTER-->  41 TOTAL IMAGES-->  3

CLUSTER-->  42 TOTAL IMAGES-->  1

CLUSTER-->  43 TOTAL IMAGES-->  1

CLUSTER-->  44 TOTAL IMAGES-->  1

CLUSTER-->  45 TOTAL IMAGES-->  4

CLUSTER-->  46 TOTAL IMAGES-->  1

CLUSTER-->  47 TOTAL IMAGES-->  1

CLUSTER-->  48 TOTAL IMAGES-->  3

CLUSTER-->  49 TOTAL IMAGES-->  1

CLUSTER-->  50 TOTAL IMAGES-->  3

predicted_Labels=np.load('image-results2/ideology_model_vgg_16.npy_optics_labels.npy')
unique_labels=set(predicted_Labels)
for label in unique_labels:
    if(label!=-1):
        showClustering(predicted_Labels,label)

CLUSTER-->  0 TOTAL IMAGES-->  5

CLUSTER-->  1 TOTAL IMAGES-->  6

CLUSTER-->  2 TOTAL IMAGES-->  8

CLUSTER-->  3 TOTAL IMAGES-->  8

CLUSTER-->  4 TOTAL IMAGES-->  7

CLUSTER-->  5 TOTAL IMAGES-->  5

CLUSTER-->  6 TOTAL IMAGES-->  7

CLUSTER-->  7 TOTAL IMAGES-->  5

CLUSTER-->  8 TOTAL IMAGES-->  7

CLUSTER-->  9 TOTAL IMAGES-->  11

CLUSTER-->  10 TOTAL IMAGES-->  5

CLUSTER-->  11 TOTAL IMAGES-->  15

CLUSTER-->  12 TOTAL IMAGES-->  15

CLUSTER-->  13 TOTAL IMAGES-->  6

CLUSTER-->  14 TOTAL IMAGES-->  6

CLUSTER-->  15 TOTAL IMAGES-->  5

CLUSTER-->  16 TOTAL IMAGES-->  8

CLUSTER-->  17 TOTAL IMAGES-->  6

CLUSTER-->  18 TOTAL IMAGES-->  5

CLUSTER-->  19 TOTAL IMAGES-->  5

CLUSTER-->  20 TOTAL IMAGES-->  6

CLUSTER-->  21 TOTAL IMAGES-->  8

CLUSTER-->  22 TOTAL IMAGES-->  5

CLUSTER-->  23 TOTAL IMAGES-->  5

CLUSTER-->  24 TOTAL IMAGES-->  12

CLUSTER-->  25 TOTAL IMAGES-->  5

CLUSTER-->  26 TOTAL IMAGES-->  5

CLUSTER-->  27 TOTAL IMAGES-->  12

CLUSTER-->  28 TOTAL IMAGES-->  11

CLUSTER-->  29 TOTAL IMAGES-->  9

CLUSTER-->  30 TOTAL IMAGES-->  5

CLUSTER-->  31 TOTAL IMAGES-->  5

CLUSTER-->  32 TOTAL IMAGES-->  6

CLUSTER-->  33 TOTAL IMAGES-->  7

CLUSTER-->  34 TOTAL IMAGES-->  8

CLUSTER-->  35 TOTAL IMAGES-->  12

CLUSTER-->  36 TOTAL IMAGES-->  6

CLUSTER-->  37 TOTAL IMAGES-->  15

CLUSTER-->  38 TOTAL IMAGES-->  6

CLUSTER-->  39 TOTAL IMAGES-->  6

CLUSTER-->  40 TOTAL IMAGES-->  6

CLUSTER-->  41 TOTAL IMAGES-->  6

CLUSTER-->  42 TOTAL IMAGES-->  5

CLUSTER-->  43 TOTAL IMAGES-->  6

CLUSTER-->  44 TOTAL IMAGES-->  5

CLUSTER-->  45 TOTAL IMAGES-->  11

CLUSTER-->  46 TOTAL IMAGES-->  5

CLUSTER-->  47 TOTAL IMAGES-->  5

CLUSTER-->  48 TOTAL IMAGES-->  8

CLUSTER-->  49 TOTAL IMAGES-->  6

CLUSTER-->  50 TOTAL IMAGES-->  5

predicted_Labels=np.load('image-results2/ideology_model_vgg_16.npy_agg-scipy_labels.npy')
unique_labels=set(predicted_Labels)
for label in unique_labels:
    if(label!=-1):
        showClustering(predicted_Labels,label)

CLUSTER-->  1 TOTAL IMAGES-->  1

CLUSTER-->  2 TOTAL IMAGES-->  1

CLUSTER-->  3 TOTAL IMAGES-->  1

CLUSTER-->  4 TOTAL IMAGES-->  3

CLUSTER-->  5 TOTAL IMAGES-->  1

CLUSTER-->  6 TOTAL IMAGES-->  1

CLUSTER-->  7 TOTAL IMAGES-->  2

CLUSTER-->  8 TOTAL IMAGES-->  2

CLUSTER-->  9 TOTAL IMAGES-->  1

CLUSTER-->  10 TOTAL IMAGES-->  1

CLUSTER-->  11 TOTAL IMAGES-->  1

CLUSTER-->  12 TOTAL IMAGES-->  13

CLUSTER-->  13 TOTAL IMAGES-->  2

CLUSTER-->  14 TOTAL IMAGES-->  2

CLUSTER-->  15 TOTAL IMAGES-->  3

CLUSTER-->  16 TOTAL IMAGES-->  18

CLUSTER-->  17 TOTAL IMAGES-->  1

CLUSTER-->  18 TOTAL IMAGES-->  1

CLUSTER-->  19 TOTAL IMAGES-->  11

CLUSTER-->  20 TOTAL IMAGES-->  26

CLUSTER-->  21 TOTAL IMAGES-->  7

CLUSTER-->  22 TOTAL IMAGES-->  2835
Cannot be visualize
CLUSTER-->  23 TOTAL IMAGES-->  1

CLUSTER-->  24 TOTAL IMAGES-->  1

CLUSTER-->  25 TOTAL IMAGES-->  1

CLUSTER-->  26 TOTAL IMAGES-->  1

CLUSTER-->  27 TOTAL IMAGES-->  1

CLUSTER-->  28 TOTAL IMAGES-->  1

CLUSTER-->  29 TOTAL IMAGES-->  1

CLUSTER-->  30 TOTAL IMAGES-->  1

VGG-19

We can viualize the mean shift and the optics here

results_df=pd.read_csv('image-results2/ideology_model_vgg_19.npy.csv')
results_df

	Unnamed: 0	n_clusters	silhouette	calinski	davies
0	Agglomerative clustering	2	0.103830	400.562021	2.244039
1	DBSCAN	0	-1.000000	-1.000000	-1.000000
2	Mean-shift	38	0.111716	4.551748	0.901795
3	Optics	56	-0.213514	6.926977	1.470868
4	Agglomerative clustering-scipy	17	0.173857	5.670576	0.762570
5	HDBSCAN	3	-0.054606	75.892894	3.302271

predicted_Labels=np.load('image-results2/ideology_model_vgg_19.npy_mean_shift_labels.npy')
unique_labels=set(predicted_Labels)
for label in unique_labels:
    if(label!=-1):
        showClustering(predicted_Labels,label)

CLUSTER-->  0 TOTAL IMAGES-->  2873
Cannot be visualize
CLUSTER-->  1 TOTAL IMAGES-->  2

CLUSTER-->  2 TOTAL IMAGES-->  2

CLUSTER-->  3 TOTAL IMAGES-->  2

CLUSTER-->  4 TOTAL IMAGES-->  2

CLUSTER-->  5 TOTAL IMAGES-->  2

CLUSTER-->  6 TOTAL IMAGES-->  1

CLUSTER-->  7 TOTAL IMAGES-->  1

CLUSTER-->  8 TOTAL IMAGES-->  2

CLUSTER-->  9 TOTAL IMAGES-->  1

CLUSTER-->  10 TOTAL IMAGES-->  3

CLUSTER-->  11 TOTAL IMAGES-->  3

CLUSTER-->  12 TOTAL IMAGES-->  1

CLUSTER-->  13 TOTAL IMAGES-->  1

CLUSTER-->  14 TOTAL IMAGES-->  2

CLUSTER-->  15 TOTAL IMAGES-->  1

CLUSTER-->  16 TOTAL IMAGES-->  7

CLUSTER-->  17 TOTAL IMAGES-->  1

CLUSTER-->  18 TOTAL IMAGES-->  1

CLUSTER-->  19 TOTAL IMAGES-->  1

CLUSTER-->  20 TOTAL IMAGES-->  1

CLUSTER-->  21 TOTAL IMAGES-->  3

CLUSTER-->  22 TOTAL IMAGES-->  1

CLUSTER-->  23 TOTAL IMAGES-->  1

CLUSTER-->  24 TOTAL IMAGES-->  1

CLUSTER-->  25 TOTAL IMAGES-->  3

CLUSTER-->  26 TOTAL IMAGES-->  1

CLUSTER-->  27 TOTAL IMAGES-->  1

CLUSTER-->  28 TOTAL IMAGES-->  1

CLUSTER-->  29 TOTAL IMAGES-->  4

CLUSTER-->  30 TOTAL IMAGES-->  1

CLUSTER-->  31 TOTAL IMAGES-->  1

CLUSTER-->  32 TOTAL IMAGES-->  1

CLUSTER-->  33 TOTAL IMAGES-->  3

CLUSTER-->  34 TOTAL IMAGES-->  2

CLUSTER-->  35 TOTAL IMAGES-->  6

CLUSTER-->  36 TOTAL IMAGES-->  1

CLUSTER-->  37 TOTAL IMAGES-->  1

predicted_Labels=np.load('image-results2/ideology_model_vgg_19.npy_optics_labels.npy')
unique_labels=set(predicted_Labels)
for label in unique_labels:
    if(label!=-1):
        showClustering(predicted_Labels,label)

CLUSTER-->  0 TOTAL IMAGES-->  7

CLUSTER-->  1 TOTAL IMAGES-->  7

CLUSTER-->  2 TOTAL IMAGES-->  7

CLUSTER-->  3 TOTAL IMAGES-->  8

CLUSTER-->  4 TOTAL IMAGES-->  6

CLUSTER-->  5 TOTAL IMAGES-->  7

CLUSTER-->  6 TOTAL IMAGES-->  6

CLUSTER-->  7 TOTAL IMAGES-->  8

CLUSTER-->  8 TOTAL IMAGES-->  10

CLUSTER-->  9 TOTAL IMAGES-->  19

CLUSTER-->  10 TOTAL IMAGES-->  5

CLUSTER-->  11 TOTAL IMAGES-->  12

CLUSTER-->  12 TOTAL IMAGES-->  8

CLUSTER-->  13 TOTAL IMAGES-->  6

CLUSTER-->  14 TOTAL IMAGES-->  5

CLUSTER-->  15 TOTAL IMAGES-->  6

CLUSTER-->  16 TOTAL IMAGES-->  8

CLUSTER-->  17 TOTAL IMAGES-->  5

CLUSTER-->  18 TOTAL IMAGES-->  8

CLUSTER-->  19 TOTAL IMAGES-->  5

CLUSTER-->  20 TOTAL IMAGES-->  7

CLUSTER-->  21 TOTAL IMAGES-->  5

CLUSTER-->  22 TOTAL IMAGES-->  6

CLUSTER-->  23 TOTAL IMAGES-->  5

CLUSTER-->  24 TOTAL IMAGES-->  5

CLUSTER-->  25 TOTAL IMAGES-->  5

CLUSTER-->  26 TOTAL IMAGES-->  5

CLUSTER-->  27 TOTAL IMAGES-->  8

CLUSTER-->  28 TOTAL IMAGES-->  6

CLUSTER-->  29 TOTAL IMAGES-->  12

CLUSTER-->  30 TOTAL IMAGES-->  7

CLUSTER-->  31 TOTAL IMAGES-->  8

CLUSTER-->  32 TOTAL IMAGES-->  5

CLUSTER-->  33 TOTAL IMAGES-->  7

CLUSTER-->  34 TOTAL IMAGES-->  5

CLUSTER-->  35 TOTAL IMAGES-->  8

CLUSTER-->  36 TOTAL IMAGES-->  6

CLUSTER-->  37 TOTAL IMAGES-->  5

CLUSTER-->  38 TOTAL IMAGES-->  7

CLUSTER-->  39 TOTAL IMAGES-->  5

CLUSTER-->  40 TOTAL IMAGES-->  6

CLUSTER-->  41 TOTAL IMAGES-->  5

CLUSTER-->  42 TOTAL IMAGES-->  6

CLUSTER-->  43 TOTAL IMAGES-->  15

CLUSTER-->  44 TOTAL IMAGES-->  7

CLUSTER-->  45 TOTAL IMAGES-->  12

CLUSTER-->  46 TOTAL IMAGES-->  5

CLUSTER-->  47 TOTAL IMAGES-->  9

CLUSTER-->  48 TOTAL IMAGES-->  5

CLUSTER-->  49 TOTAL IMAGES-->  7

CLUSTER-->  50 TOTAL IMAGES-->  5

CLUSTER-->  51 TOTAL IMAGES-->  6

CLUSTER-->  52 TOTAL IMAGES-->  5

CLUSTER-->  53 TOTAL IMAGES-->  11

CLUSTER-->  54 TOTAL IMAGES-->  6

CLUSTER-->  55 TOTAL IMAGES-->  5

RESNET50

results_df=pd.read_csv('image-results2/ideology_model_resnet50.npy.csv')
results_df

	Unnamed: 0	n_clusters	silhouette	calinski	davies
0	Agglomerative clustering	2	0.050838	192.773120	3.319562
1	DBSCAN	0	-1.000000	-1.000000	-1.000000
2	Mean-shift	42	0.114504	3.044071	0.784067
3	Optics	53	-0.143944	8.001208	1.526539
4	Agglomerative clustering-scipy	211	0.025470	5.737732	1.150174
5	HDBSCAN	12	-0.128384	18.965519	2.631275

predicted_Labels=np.load('image-results2/ideology_model_resnet50.npy_mean_shift_labels.npy')
unique_labels=set(predicted_Labels)
for label in unique_labels:
    if(label!=-1):
        showClustering(predicted_Labels,label)

CLUSTER-->  0 TOTAL IMAGES-->  2886
Cannot be visualize
CLUSTER-->  1 TOTAL IMAGES-->  4

CLUSTER-->  2 TOTAL IMAGES-->  2

CLUSTER-->  3 TOTAL IMAGES-->  2

CLUSTER-->  4 TOTAL IMAGES-->  2

CLUSTER-->  5 TOTAL IMAGES-->  1

CLUSTER-->  6 TOTAL IMAGES-->  1

CLUSTER-->  7 TOTAL IMAGES-->  4

CLUSTER-->  8 TOTAL IMAGES-->  1

CLUSTER-->  9 TOTAL IMAGES-->  3

CLUSTER-->  10 TOTAL IMAGES-->  1

CLUSTER-->  11 TOTAL IMAGES-->  1

CLUSTER-->  12 TOTAL IMAGES-->  1

CLUSTER-->  13 TOTAL IMAGES-->  1

CLUSTER-->  14 TOTAL IMAGES-->  1

CLUSTER-->  15 TOTAL IMAGES-->  1

CLUSTER-->  16 TOTAL IMAGES-->  2

CLUSTER-->  17 TOTAL IMAGES-->  1

CLUSTER-->  18 TOTAL IMAGES-->  1

CLUSTER-->  19 TOTAL IMAGES-->  2

CLUSTER-->  20 TOTAL IMAGES-->  1

CLUSTER-->  21 TOTAL IMAGES-->  2

CLUSTER-->  22 TOTAL IMAGES-->  1

CLUSTER-->  23 TOTAL IMAGES-->  1

CLUSTER-->  24 TOTAL IMAGES-->  1

CLUSTER-->  25 TOTAL IMAGES-->  1

CLUSTER-->  26 TOTAL IMAGES-->  1

CLUSTER-->  27 TOTAL IMAGES-->  1

CLUSTER-->  28 TOTAL IMAGES-->  2

CLUSTER-->  29 TOTAL IMAGES-->  1

CLUSTER-->  30 TOTAL IMAGES-->  1

CLUSTER-->  31 TOTAL IMAGES-->  1

CLUSTER-->  32 TOTAL IMAGES-->  1

CLUSTER-->  33 TOTAL IMAGES-->  1

CLUSTER-->  34 TOTAL IMAGES-->  1

CLUSTER-->  35 TOTAL IMAGES-->  1

CLUSTER-->  36 TOTAL IMAGES-->  1

CLUSTER-->  37 TOTAL IMAGES-->  1

CLUSTER-->  38 TOTAL IMAGES-->  1

CLUSTER-->  39 TOTAL IMAGES-->  1

CLUSTER-->  40 TOTAL IMAGES-->  1

CLUSTER-->  41 TOTAL IMAGES-->  1

predicted_Labels=np.load('image-results2/ideology_model_resnet50.npy_mean_shift_labels.npy')
unique_labels=set(predicted_Labels)
for label in unique_labels:
    if(label!=-1):
        showClustering(predicted_Labels,label)

CLUSTER-->  0 TOTAL IMAGES-->  2886
Cannot be visualize
CLUSTER-->  1 TOTAL IMAGES-->  4

CLUSTER-->  2 TOTAL IMAGES-->  2

CLUSTER-->  3 TOTAL IMAGES-->  2

CLUSTER-->  4 TOTAL IMAGES-->  2

CLUSTER-->  5 TOTAL IMAGES-->  1

CLUSTER-->  6 TOTAL IMAGES-->  1

CLUSTER-->  7 TOTAL IMAGES-->  4

CLUSTER-->  8 TOTAL IMAGES-->  1

CLUSTER-->  9 TOTAL IMAGES-->  3

CLUSTER-->  10 TOTAL IMAGES-->  1

CLUSTER-->  11 TOTAL IMAGES-->  1

CLUSTER-->  12 TOTAL IMAGES-->  1

CLUSTER-->  13 TOTAL IMAGES-->  1

CLUSTER-->  14 TOTAL IMAGES-->  1

CLUSTER-->  15 TOTAL IMAGES-->  1

CLUSTER-->  16 TOTAL IMAGES-->  2

CLUSTER-->  17 TOTAL IMAGES-->  1

CLUSTER-->  18 TOTAL IMAGES-->  1

CLUSTER-->  19 TOTAL IMAGES-->  2

CLUSTER-->  20 TOTAL IMAGES-->  1

CLUSTER-->  21 TOTAL IMAGES-->  2

CLUSTER-->  22 TOTAL IMAGES-->  1

CLUSTER-->  23 TOTAL IMAGES-->  1

CLUSTER-->  24 TOTAL IMAGES-->  1

CLUSTER-->  25 TOTAL IMAGES-->  1

CLUSTER-->  26 TOTAL IMAGES-->  1

CLUSTER-->  27 TOTAL IMAGES-->  1

CLUSTER-->  28 TOTAL IMAGES-->  2

CLUSTER-->  29 TOTAL IMAGES-->  1

CLUSTER-->  30 TOTAL IMAGES-->  1

CLUSTER-->  31 TOTAL IMAGES-->  1

CLUSTER-->  32 TOTAL IMAGES-->  1

CLUSTER-->  33 TOTAL IMAGES-->  1

CLUSTER-->  34 TOTAL IMAGES-->  1

CLUSTER-->  35 TOTAL IMAGES-->  1

CLUSTER-->  36 TOTAL IMAGES-->  1

CLUSTER-->  37 TOTAL IMAGES-->  1

CLUSTER-->  38 TOTAL IMAGES-->  1

CLUSTER-->  39 TOTAL IMAGES-->  1

CLUSTER-->  40 TOTAL IMAGES-->  1

CLUSTER-->  41 TOTAL IMAGES-->  1

Inceptionv3

results_df=pd.read_csv('image-results2/ideology_model_inceptionv3.npy.csv')
results_df

	Unnamed: 0	n_clusters	silhouette	calinski	davies
0	Agglomerative clustering	2	0.383595	1902.910288	1.186455
1	DBSCAN	0	-1.000000	-1.000000	-1.000000
2	Mean-shift	49	0.263252	76.792516	2.044841
3	Optics	28	-0.393399	11.928438	1.333732
4	Agglomerative clustering-scipy	2	0.522594	749.840801	0.830656
5	HDBSCAN	3	0.356685	649.991763	1.457040

predicted_Labels=np.load('image-results2/ideology_model_inceptionv3.npy_mean_shift_labels.npy')
unique_labels=set(predicted_Labels)
for label in unique_labels:
    if(label!=-1):
        showClustering(predicted_Labels,label)

CLUSTER-->  0 TOTAL IMAGES-->  2199
Cannot be visualize
CLUSTER-->  1 TOTAL IMAGES-->  78

CLUSTER-->  2 TOTAL IMAGES-->  8

CLUSTER-->  3 TOTAL IMAGES-->  18

CLUSTER-->  4 TOTAL IMAGES-->  14

CLUSTER-->  5 TOTAL IMAGES-->  3

CLUSTER-->  6 TOTAL IMAGES-->  2

CLUSTER-->  7 TOTAL IMAGES-->  2

CLUSTER-->  8 TOTAL IMAGES-->  2

CLUSTER-->  9 TOTAL IMAGES-->  18

CLUSTER-->  10 TOTAL IMAGES-->  1

CLUSTER-->  11 TOTAL IMAGES-->  1

CLUSTER-->  12 TOTAL IMAGES-->  10

CLUSTER-->  13 TOTAL IMAGES-->  1

CLUSTER-->  14 TOTAL IMAGES-->  2

CLUSTER-->  15 TOTAL IMAGES-->  3

CLUSTER-->  16 TOTAL IMAGES-->  5

CLUSTER-->  17 TOTAL IMAGES-->  14

CLUSTER-->  18 TOTAL IMAGES-->  8

CLUSTER-->  19 TOTAL IMAGES-->  21

CLUSTER-->  20 TOTAL IMAGES-->  1

CLUSTER-->  21 TOTAL IMAGES-->  17

CLUSTER-->  22 TOTAL IMAGES-->  9

CLUSTER-->  23 TOTAL IMAGES-->  1

CLUSTER-->  24 TOTAL IMAGES-->  28

CLUSTER-->  25 TOTAL IMAGES-->  5

CLUSTER-->  26 TOTAL IMAGES-->  94

CLUSTER-->  27 TOTAL IMAGES-->  5

CLUSTER-->  28 TOTAL IMAGES-->  9

CLUSTER-->  29 TOTAL IMAGES-->  1

CLUSTER-->  30 TOTAL IMAGES-->  4

CLUSTER-->  31 TOTAL IMAGES-->  43

CLUSTER-->  32 TOTAL IMAGES-->  9

CLUSTER-->  33 TOTAL IMAGES-->  10

CLUSTER-->  34 TOTAL IMAGES-->  1

CLUSTER-->  35 TOTAL IMAGES-->  11

CLUSTER-->  36 TOTAL IMAGES-->  74

CLUSTER-->  37 TOTAL IMAGES-->  45

CLUSTER-->  38 TOTAL IMAGES-->  1

CLUSTER-->  39 TOTAL IMAGES-->  35

predicted_Labels=np.load('image-results2/ideology_model_inceptionv3.npy_mean_shift_labels.npy')
unique_labels=set(predicted_Labels)
for label in unique_labels:
    if(label!=-1):
        showClustering(predicted_Labels,label)