blog_hahow_crawler_3.py

with open('hahow_courses.json', 'r', encoding='utf-8') as f:
    courses = json.load(f)
	
# 取出程式類課程的募資價/上線價/學生數，並顯示統計資料
pre_order_prices = list()
prices = list()
tickets = list()
lengths = list()
for c in courses:
    if '55de81ac9d1fa51000f94770' in c['categories']:
        pre_order_prices.append(c['preOrderedPrice'])
        prices.append(c['price'])
        tickets.append(c['numSoldTickets'])
        lengths.append(c['totalVideoLengthInSeconds'])
		
print('程式類課程共有 %d 堂' % len(prices))  # 23
print('平均募資價:', np.mean(pre_order_prices))  # 719.09
print('平均上線價:', np.mean(prices))  # 1322.57
print('平均學生數:', np.mean(tickets))  # 483.22
print('平均課程分鐘:', np.mean(lengths)/60)  # 515.12

corrcoef = np.corrcoef([tickets, pre_order_prices, prices, lengths])
print('募資價與學生數之相關係數: ', corrcoef[0, 1])  # 0.18
print('上線價與學生數之相關係數: ', corrcoef[0, 2])  # 0.36
print('課程長度與學生數之相關係數: ', corrcoef[0, 3])  # 0.65