From 1cff9723fe3c8ead46c33df286504b4e6c293301 Mon Sep 17 00:00:00 2001
From: pvcfg6a7k <3378341862@qq.com>
Date: Sun, 13 Apr 2025 21:04:28 +0800
Subject: [PATCH] Update README.md

---
 README.md | 61 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 60 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 04f5e9e..64b023c 100644
--- a/README.md
+++ b/README.md
@@ -53,4 +53,63 @@ special
 所以事情还是很紧急的
 PPT汇报具体要求什么的4.11课上问问，同时也可以尝试能不能延期
 现在急需将其完善，可以在功能上进一步简化，而图形界面能看即可，确保能交差
-如果可以延期就再美化，不能就能交差即可
\ No newline at end of file
+如果可以延期就再美化，不能就能交差即可
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+plt.rcParams['font.sans-serif'] = ['SimHei']
+plt.rcParams['axes.unicode_minus'] = False
+
+movies_df_new = pd.read_csv("/data/bigfiles/movie_metadata_new.csv")
+################begin########################
+#票房与预算关系
+# 筛选2014年及之后的数据
+df_2014_2016 = movies_df_new[movies_df_new['title_year'] >= 2014]
+
+# 按预算升序排序
+df_sorted = df_2014_2016.sort_values('budget')
+
+# 绘制散点图
+plt.figure(figsize=(10, 10))
+plt.scatter(df_sorted['movie_title'], df_sorted['budget'], color='red', s=20, label='budget')
+plt.scatter(df_sorted['movie_title'], df_sorted['gross'], color='green', s=20, label='gross')
+plt.xticks([])
+# 设置图表属性
+plt.title('电影票房与预算的关系', fontsize=20)
+plt.xlabel('movie_title')
+plt.ylabel('budget/gross')
+
+ # 旋转x轴标签
+
+plt.legend()
+#################end#########################
+plt.savefig("step5/result/pic1.png")
+plt.close()
+
+################begin########################
+#数据归一化处理
+# 筛选2015-2016年数据（不包含2014）
+df_2015_2016 = movies_df_new[(movies_df_new['title_year'] > 2014) & (movies_df_new['title_year'] <= 2016)]
+
+# 归一化处理
+df_2015_2016['cast_total_likes_norm'] = df_2015_2016['cast_total_likes'] / df_2015_2016['cast_total_likes'].max()
+df_2015_2016['gross_norm'] = df_2015_2016['gross'] / df_2015_2016['gross'].max()
+
+# 演员的获赞总数与票房的关系
+plt.figure(figsize=(10, 10))
+plt.scatter(df_2015_2016['movie_title'], df_2015_2016['cast_total_likes_norm'], color='red', s=20, label='cast_total_likes')
+plt.scatter(df_2015_2016['movie_title'], df_2015_2016['gross_norm'], color='green', s=20, label='gross')
+plt.xticks([])
+# 设置图表属性
+plt.title('演员的获赞总数与票房的关系', fontsize=10)
+plt.xlabel('movie_title')
+plt.ylabel('cast_total_likes/gross')
+plt.legend()
+ # 旋转x轴标签
+
+
+#################end#########################
+plt.savefig("step5/result/pic2.png")
+plt.close()
\ No newline at end of file