File size: 2,877 Bytes
1da285f | 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 | import matplotlib.pyplot as plt
import pandas as pd
import os
import argparse
import json
split = os.getenv('split', '')
suf_split = f'-{split}' if split else ''
RESULT_DIR = f'./results{suf_split}'
cat_apps_file = f'./cat_apps{suf_split}.json'
def plot_box(random_data, guided_data, datatype, min_apps = 0):
DATATYPE_MAP = {
'effective_interacts_cnt': 'Effective Interacts Count',
'effective_interacts_rate': 'Effective Interacts Rate',
'coverage_rate': 'IGE Coverage Rate'
}
# categories = guided_data.columns[1:] # 获取所有category
with open(cat_apps_file, 'r') as f:
category_apps_map = json.load(f)
categories = [cat for cat, apps in category_apps_map.items() if len(apps) >= min_apps and cat != 'All']
categories = ['All'] + categories
num_categories = len(categories)
num_cols = 6
num_rows = (num_categories + num_cols - 1) // num_cols # 计算行数
fig, axes = plt.subplots(num_rows, num_cols, figsize=(15.5, num_rows * 2.5))
axes = axes.flatten()
for i, category in enumerate(categories):
data = [random_data[category], guided_data[category]]
box = axes[i].boxplot(data, labels=['Base', 'Ori.'], patch_artist=True, widths=0.6)
colors = ['purple', 'green']
for patch, color in zip(box['boxes'], colors):
patch.set_facecolor(color)
for median in box['medians']:
median.set_color('blue')
median.set_linewidth(2)
axes[i].set_title(category, fontsize=20)
axes[i].tick_params(axis='both', which='major', labelsize=20)
axes[i].grid(True)
for i in range(num_categories, len(axes)):
fig.delaxes(axes[i]) # 删除多余的子图
fig.text(0.5, 0.01, 'App Category', ha='center', fontsize=20)
fig.text(0.01, 0.5, DATATYPE_MAP[datatype], va='center', rotation='vertical', fontsize=20)
plt.tight_layout(rect=[0.02, 0.02, 1, 1])
plt.savefig(f'{RESULT_DIR}/category_eval_{datatype}.png', format='png')
plt.savefig(f'{RESULT_DIR}/category_eval_{datatype}.pdf', format='pdf')
def main(args):
random_data = pd.read_csv(f'{args.random}/{args.type}.csv')
guided_data = pd.read_csv(f'{args.guided}/{args.type}.csv')
plot_box(random_data, guided_data, args.type, min_apps=args.min_apps)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Plot the category evaluation results')
parser.add_argument('-r', '--random', type=str, help='The random interact evaluation result')
parser.add_argument('-g', '--guided', type=str, help='The our interact evaluation result')
parser.add_argument('-t', '--type', type=str, help='The type of the evaluation result')
parser.add_argument('-m', '--min_apps', type=int, default=1, help='Minimum number of apps per category')
args = parser.parse_args()
main(args)
|