项目：电影口碑与海报图像的相关性分析

深碍√TFBOYSˉ_ 2021-10-29 18:03 227阅读 0赞

# 1.涉及内容 #

# 2.代码 #

mian.py

# -*- coding: utf-8 -*-
    
    
    import pandas as pd
    from tools import get_n_face, get_color_mean #自己写的
    import matplotlib.pyplot as plt
    
    # 数据集路径
    dataset_path = './dataset/movie_metadata.csv'
    
    # 是否第一次运行
    is_first_run = False
    
    
    def run_main():
        """
            主函数
        """
        if is_first_run:
            # 第一次运行程序
            data_df = pd.read_csv(dataset_path, nrows=100)
    
            # 记录海报中人脸个数
            print('海报人脸检测：')
            data_df['n_face'] = data_df['movie_imdb_link'].apply(get_n_face)
    
            # 保存结果
            data_df.to_csv('./imdb_face.csv', index=False, encoding='utf-8')
    
            # 记录海报的平均像素值（这里代表图像的主要颜色，可通过颜色的表达方式替代）
            print('海报像素均值计算：')
            data_df['color_mean'] = data_df['movie_imdb_link'].apply(get_color_mean)
    
            # 保存结果
            data_df.to_csv('./imdb_face_color.csv', index=False, encoding='utf-8')
    
        data_df = pd.read_csv('./imdb_face_color.csv')
        # 分析结果
        # 人脸个数和评分的关系
        # 去除无效人脸
        data_df = data_df[data_df['n_face'] != -1]
        face_score = data_df['imdb_score'].groupby(data_df['n_face']).mean()
        face_score.name = 'Score'
        face_score.index.name = 'Number of Face'
        face_score.plot(kind='bar')
        plt.show()
    
        # 像素均值和评分的关系
        color_score = data_df['imdb_score'].groupby(data_df['color_mean']).mean()
        color_score.name = 'Score'
        color_score.index.name = 'Mean of color'
        color_score.plot(kind='bar')
        plt.show()
    
    
    if __name__ == '__main__':
        run_main()

tools.py

# -*- coding: utf-8 -*-
    
    
    from bs4 import BeautifulSoup
    import urllib.request
    import cognitive_face as CF
    from skimage import io
    import numpy as np
    
    
    def get_img_link(movie_link):
        """
            通过电影的链接爬取海报的链接
        """
        movie_html = urllib.request.urlopen(movie_link)
        movie_html_obj = BeautifulSoup(movie_html, 'html.parser', from_encoding='utf-8')
        # 获取海报小图的链接
        small_poster_img_link = movie_html_obj.find('div', class_='poster').find('img')['src']
    
        # 获取海报大图的链接
        big_poster_img_link = small_poster_img_link[:small_poster_img_link.find('._V1_') + 4] + '.jpg'
    
        return big_poster_img_link
    
    
    def get_n_face(movie_link):
        """
            通过图像链接获取包含的人脸个数
        """
        print('正在处理链接：', movie_link)
        img_link = get_img_link(movie_link)
        Key = 'xxxxxxxxxx '  # 这里请替换成自己申请的key
        CF.Key.set(Key)
        n_face = -1
        try:
            face_list = CF.face.detect(img_link)
            n_face = len(face_list)
            print('人脸个数：', n_face)
        except CF.util.CognitiveFaceException:
            print('无效图片')
        return n_face
    
    
    def round_to_int(x, base=10):
        """
            将数字转换到最近的整数
        """
        return int(base * round(float(x)/base))
    
    
    def get_color_mean(movie_link):
        """
            通过图像链接获取其平均像素值
        """
        print('正在处理链接：', movie_link)
        img_link = get_img_link(movie_link)
        image = io.imread(img_link)
        int_mean_color = round_to_int(np.mean(image))
        print('像素均值：', int_mean_color)
        return int_mean_color