火烧云数据-B站数据分析平台-B站营销增长 (hsydata.com)

没时间，未完成，需修改
以下代码跑不了
只是关键点参考

import pandas as pd
from collections import Counter
import ast
import matplotlib.pyplot as plt
from wordcloud import WordCloud

df = pd.read_csv('小约翰可汗.csv')
df=df.dropna()
# 做词云
def word_cloud():
    all_tags = []
    for item_list in df['标签'].dropna():  # 使用 dropna() 确保忽略空值
        tags_list = ast.literal_eval(item_list)
        for tag in tags_list:
            all_tags.append(tag)
    tags_counts = Counter(all_tags)
    print(tags_counts)
    wordcloud = WordCloud(
        font_path='C:\\Windows\\Fonts\\HGWT_CNKI.TTF',
        width=1200,
        height=800,
        background_color='white'
    )
    wordcloud.generate_from_frequencies(tags_counts)
    plt.figure(figsize=(12, 8))
    plt.imshow(wordcloud, interpolation='bilinear')
    plt.axis('off')  # 去除坐标轴
    plt.show()

def dd():

    # 做播放点赞比
    df_no_na=df.dropna()
    df_no_na['播放点赞比']=df_no_na['点赞数']/df_no_na['播放数']
    # print(df_no_na['播放点赞比'])
    df_no_na['播放投币比']=df_no_na['投币数']/df_no_na['播放数']
    # print(df_no_na['播放投币比'])

    # 对播放点赞比进行降序排序
    df_sorted = df_no_na.sort_values(by='播放点赞比', ascending=False)

    plt.rcParams['font.sans-serif'] = ['SimHei']  # 指定默认字体
    plt.rcParams['axes.unicode_minus'] = False  # 解决负号显示问题

    plt.figure(figsize=(10, 5))  # 可以调整图形大小
    df_top = df_sorted.head(10) 
    plt.plot(df_top['名称'], df_top['播放点赞比'], marker='o')  # 使用圆点标记每个数据点
    plt.plot(df_top['名称'], df_top['播放投币比'], marker='o')  # 使用圆点标记每个数据点
    # 添加标题和标签
    plt.title('Sorted Like-to-Play Ratio')
    plt.xlabel('Video Titles')
    plt.ylabel('Like-to-Play Ratio')

    # 旋转x轴标签，以免重叠
    plt.xticks(rotation=45, ha='right',size=8)

    # 展示图形
    plt.show()

def sjbx():
    # 计算总和
    total_plays = df['播放数'].sum()
    total_likes = df['点赞数'].sum()
    total_coins = df['投币数'].sum()

    # 计算平均值
    average_plays = total_plays / len(df)
    average_likes = total_likes / len(df)
    average_coins = total_coins / len(df)

    # 计算平均点赞与播放的比例
    like_to_play_ratio = average_likes / average_plays

    # 计算平均投币与播放的比例
    coin_to_play_ratio = average_coins / average_plays

    # 输出结果
    print(f"总播放数: {total_plays / 10000:.2f}万")
    print(f"总点赞数: {total_likes / 10000:.2f}万")
    print(f"总投资币数: {total_coins / 10000:.2f}万")
    print(f"平均播放数: {average_plays / 10000:.2f}万")
    print(f"平均点赞数: {average_likes / 10000:.2f}万")
    print(f"平均投币数: {average_coins / 10000:.2f}万")
    print(f"平均点赞与播放的比例: {like_to_play_ratio * 100 :.2f}%")
    print(f"平均投币与播放的比例: {coin_to_play_ratio * 100 :.2f}%")  


for index, row in df.iterrows():
    play = row['播放数']
    like = row['点赞数']
    coin = row['投币数']
    tag_list = ast.literal_eval(row['标签'])


def tag_statistics():
    p_tag_dict = {}
    l_tag_dict = {}
    c_tag_dict = {}
    for index, row in df.iterrows():
        play = row['播放数']
        like = row['点赞数']
        coin = row['投币数']
        tag_list = ast.literal_eval(row['标签'])
        for tag in tag_list:
            # 如果标签已存在于字典中，则累加播放数
            if tag in p_tag_dict:
                p_tag_dict[tag] += play
                l_tag_dict[tag] += play
                c_tag_dict[tag] += play            
            # 如果标签不存在于字典中，则添加到字典并设置其播放数
            else:
                p_tag_dict[tag] = play
                l_tag_dict[tag] = play
                c_tag_dict[tag] = play     
          


    p_tag_df = pd.DataFrame(list(p_tag_dict.items()), columns=['标签', '播放数'])
    l_tag_df = pd.DataFrame(list(l_tag_dict.items()), columns=['标签', '点赞'])
    c_tag_df = pd.DataFrame(list(c_tag_dict.items()), columns=['标签', '投币'])
    tag_play_df_top = tag_play_df.sort_values(by='播放数', ascending=False).head(20)
    excluded_tags = ['历史', '人文', '人物']
    tag_play_df_top = tag_play_df_top[~tag_play_df_top['标签'].isin(excluded_tags)]
    # print(tag_play_df)
    plt.rcParams['font.family'] = 'SimHei'
    plt.rcParams['font.sans-serif'] = ['SimHei']



    plt.figure(figsize=(10, 8))  # 设置图形的大小
    plt.bar(tag_play_df_top['标签'], tag_play_df_top['播放数'], color='skyblue')  # 创建条形图

    # 添加标题和标签
    plt.title('标签播放数统计')
    plt.xlabel('Tag')
    plt.ylabel('播放数')

    # 显示图形
    plt.show()