File size: 6,549 Bytes
6d35aff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
import json
import pandas as pd
from collections import defaultdict
from matplotlib import pyplot as plt
import numpy as np

SPLIT_GENRE = {
        "TRAIN": [
            "Casual",
            "Adventure",
            "Action",
            "Indie"
        ],
        "VAL": [
            "Strategy",
            "Education",
            "RPG",
            "Massively Multiplayer",
            "Design & Illustration",
            "Animation & Modeling"
        ],
        "TEST": [
            "Simulation",
            "Sports"
        ]
    }


def parse_img_id(img_id):
    img_id = str(img_id)
    return int(img_id[:-3]), int(img_id[-3:])


def plot(data, img_name, is_genre=False):
    plt.rcParams.update({'font.size': 18})
    colors = []
    for cat in data.keys():
        if cat in SPLIT_GENRE['TRAIN']:
            colors.append('tab:blue')
        elif cat in SPLIT_GENRE['VAL']:
            colors.append('tab:orange')
        elif cat in SPLIT_GENRE['TEST']:
            colors.append('tab:green')
        else:
            colors.append('gray')
    
    
    if is_genre:
        plt.figure(figsize=(10, 6))
        plt.grid(True, axis='y', zorder=0)
        plt.bar(data.keys(), data.values(), color=colors, zorder=3)
        plt.xticks(rotation=30, ha='right')
        plt.legend(handles=[
            plt.Line2D([0], [0], color='tab:blue', lw=10, label='Train'),
            plt.Line2D([0], [0], color='tab:orange', lw=10, label='Val'),
            plt.Line2D([0], [0], color='tab:green', lw=10, label='Test'),
        ])
    else:
        plt.figure(figsize=(15, 6))
        plt.grid(True, axis='y', zorder=0)
        plt.bar(data.keys(), data.values(), zorder=3)
        plt.xticks(rotation=45, ha='right')
    plt.gca().yaxis.set_major_locator(plt.MaxNLocator(integer=True))
    for i, v in enumerate(data.values()):
        plt.text(i, v, str(v), ha='center', va='bottom')
    y_max = max(data.values())
    plt.ylim(0, 1.1 * y_max)
    
    plt.tight_layout()
    plt.savefig(img_name + '.png')
    plt.savefig(img_name + '.pdf')


def plot_genre():

    df = pd.read_csv('app_genre.csv')
    with open('../data/coco_merged/annotations/semantics.json', 'r') as f:
        dataset = json.load(f)

    app_img_map = {}

    for img in dataset['images']:
        img_id = img['id']
        app_id, _ = parse_img_id(img['id'])
        if app_id not in app_img_map:
            app_img_map[app_id] = []
        app_img_map[app_id].append(img_id)

    gnr_app_map = defaultdict(list)

    for i in range(len(df)):
        app_id = df['id'][i]
        tags = df['genre'][i].split(';')
        for tag in tags:
            gnr_app_map[tag].append(int(app_id))


    gnr_app_count = {cat: len(apps) for cat, apps in gnr_app_map.items()}
    gnr_img_count = {cat: sum([len(app_img_map[app]) for app in apps]) for cat, apps in gnr_app_map.items()}
    gnr_anno_count = {cat: sum([len([anno for anno in dataset['annotations'] if anno['image_id'] in app_img_map[app]]) for app in apps]) for cat, apps in gnr_app_map.items()}

    split_genre_order = {genre: i for i, genre in enumerate(SPLIT_GENRE['TRAIN'] + SPLIT_GENRE['VAL'] + SPLIT_GENRE['TEST'])}
    gnr_app_count = {cat: gnr_app_count[cat] for cat in sorted(gnr_app_count, key=lambda x: split_genre_order.get(x, float('inf')))}
    gnr_img_count = {cat: gnr_img_count[cat] for cat in sorted(gnr_img_count, key=lambda x: split_genre_order.get(x, float('inf')))}
    gnr_anno_count = {cat: gnr_anno_count[cat] for cat in sorted(gnr_anno_count, key=lambda x: split_genre_order.get(x, float('inf')))}
    
    
    plot(gnr_app_count, 'genre_app_count', is_genre=True)
    plot(gnr_img_count, 'genre_img_count', is_genre=True)
    plot(gnr_anno_count, 'genre_anno_count', is_genre=True)
    

def plot_cat():

    df = pd.read_csv('app_tag.csv')
    with open('../data/coco_merged/annotations/semantics.json', 'r') as f:
        dataset = json.load(f)

    app_img_map = {}

    for img in dataset['images']:
        img_id = img['id']
        app_id, _ = parse_img_id(img['id'])
        if app_id not in app_img_map:
            app_img_map[app_id] = []
        app_img_map[app_id].append(img_id)

    cat_app_map = defaultdict(list)

    for i in range(len(df)):
        app_id = df['id'][i]
        tags = df['tag'][i].split(';')
        for tag in tags:
            cat_app_map[tag].append(int(app_id))

    cat_app_map.pop('VR')

    cat_app_count = {cat: len(apps) for cat, apps in cat_app_map.items()}
    cat_img_count = {cat: sum([len(app_img_map[app]) for app in apps]) for cat, apps in cat_app_map.items()}
    cat_anno_count = {cat: sum([len([anno for anno in dataset['annotations'] if anno['image_id'] in app_img_map[app]]) for app in apps]) for cat, apps in cat_app_map.items()}

    cat_app_count = {cat: count for cat, count in list(cat_app_count.items())[:30]}
    cat_img_count = {cat: count for cat, count in list(cat_img_count.items())[:30]}
    cat_anno_count = {cat: count for cat, count in list(cat_anno_count.items())[:30]}

    cat_app_count = {cat: count for cat, count in sorted(cat_app_count.items(), key=lambda item: item[1], reverse=True)}
    cat_img_count = {cat: count for cat, count in sorted(cat_img_count.items(), key=lambda item: item[1], reverse=True)}
    cat_anno_count = {cat: count for cat, count in sorted(cat_anno_count.items(), key=lambda item: item[1], reverse=True)}

    plot(cat_app_count, 'tag_app_count')
    plot(cat_img_count, 'tag_img_count')
    plot(cat_anno_count, 'tag_anno_count')


def plot_cat_anno():
    with open('../data/coco_merged/annotations/semantics.json', 'r') as f:
        dataset = json.load(f)
    
    cat_catname_map = {}
    for cat in dataset['categories']:
        cat_catname_map[cat['id']] = cat['name']
        
    cat_anno_map = defaultdict(list)
    for anno in dataset['annotations']:
        cat_anno_map[cat_catname_map[anno['category_id']]].append(anno)
    
    print(len(cat_anno_map['button']))
    cat_anno_map.pop('button')
    
    cat_anno_count = {cat: len(annos) for cat, annos in cat_anno_map.items()}
    cat_anno_count = {cat: count for cat, count in sorted(cat_anno_count.items(), key=lambda item: item[1], reverse=True)}
    cat_anno_count = {cat: count for cat, count in list(cat_anno_count.items())[:30]}
    plot(cat_anno_count, 'ige_cat_anno_count')
    


plot_genre()
plot_cat()
plot_cat_anno()