3

q4/q4_1/q4_1.py

@@ -0,0 +1,24 @@
+import json
+import matplotlib.pyplot as plt
+
+# 设置中文字体（防止中文乱码）
+plt.rcParams['font.sans-serif'] = ['SimHei'] 
+plt.rcParams['axes.unicode_minus'] = False
+
+with open('simulated-examination/q2_1_crawler/movies.json', 'r', encoding='utf-8') as f:
+    movies = json.load(f)
+
+genre_count = {}
+for m in movies:
+    genre_count[m['genre']] = genre_count.get(m['genre'], 0) + 1
+
+genres = list(genre_count.keys())
+counts = list(genre_count.values())
+
+plt.figure()
+plt.bar(genres, counts)
+plt.title("类型电影数量分布")
+plt.xlabel("类型名称")
+plt.ylabel("电影数量")
+plt.savefig('q4_1_bar.png', dpi=150)
+# plt.show() # 如果是在IDE里不想显示弹窗可以注释掉

q4/q4_2/q4_2.py

@@ -0,0 +1,18 @@
+import json
+import matplotlib.pyplot as plt
+
+plt.rcParams['font.sans-serif'] = ['SimHei']
+plt.rcParams['axes.unicode_minus'] = False
+
+with open('simulated-examination/q2_1_crawler/movies.json', 'r', encoding='utf-8') as f:
+    movies = json.load(f)
+
+durations = [m['duration'] for m in movies]
+ratings = [m['rating'] for m in movies]
+
+plt.figure()
+plt.scatter(durations, ratings, c='red', alpha=0.6)
+plt.title("时长与评分关系散点图")
+plt.xlabel("时长（分钟）")
+plt.ylabel("评分")
+plt.savefig('q4_2_scatter.png', dpi=150)

q4/q4_3a/q4_3a.py

@@ -0,0 +1,16 @@
+import json
+import matplotlib.pyplot as plt
+
+plt.rcParams['font.sans-serif'] = ['SimHei']
+plt.rcParams['axes.unicode_minus'] = False
+
+with open('simulated-examination/q2_1_crawler/movies.json', 'r', encoding='utf-8') as f:
+    movies = json.load(f)
+
+ratings = [m['rating'] for m in movies]
+
+plt.figure()
+plt.hist(ratings, bins=5, color='blue')
+plt.title("评分分布")
+plt.xlabel("评分")
+plt.savefig('q4_3a_hist.png', dpi=150)

q4/q4_3b/q4_3b.py

@@ -0,0 +1,16 @@
+import json
+import matplotlib.pyplot as plt
+
+plt.rcParams['font.sans-serif'] = ['SimHei']
+plt.rcParams['axes.unicode_minus'] = False
+
+with open('simulated-examination/q2_1_crawler/movies.json', 'r', encoding='utf-8') as f:
+    movies = json.load(f)
+
+durations = [m['duration'] for m in movies]
+
+plt.figure()
+plt.hist(durations, bins=5, color='green')
+plt.title("时长分布")
+plt.xlabel("时长（分钟）")
+plt.savefig('q4_3b_hist.png', dpi=150)