上传文件至 /

20260609.1.py

@@ -0,0 +1,50 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.metrics import classification_report, accuracy_score
+
+
+genre_map = {
+    0: "剧情",
+    1: "喜剧",
+    2: "科幻",
+    3: "悬疑",
+    4: "动作",
+    5: "爱情",
+    6: "动画",
+    7: "犯罪",
+    8: "奇幻",
+    9: "纪录"
+}
+
+
+df = pd.read_csv("movie_data.csv")  
+X = df["text"]
+y = df["label"]
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.2, random_state=42, stratify=y
+)
+
+
+tfidf = TfidfVectorizer(max_features=5000, ngram_range=(1, 2))
+X_train_tfidf = tfidf.fit_transform(X_train)
+X_test_tfidf = tfidf.transform(X_test)
+
+model = MultinomialNB()
+model.fit(X_train_tfidf, y_train)
+
+
+y_pred = model.predict(X_test_tfidf)
+print(f"准确率: {accuracy_score(y_test, y_pred):.4f}")
+print(classification_report(y_test, y_pred, target_names=genre_map.values()))
+
+
+def predict_genre(text):
+    text_tfidf = tfidf.transform([text])
+    pred_label = model.predict(text_tfidf)[0]
+    return genre_map[pred_label]
+
+new_movie = "一群年轻人在宇宙飞船上探索外星文明，遭遇未知危险"
+print(f"电影简介：{new_movie}")
+print(f"预测类别：{predict_genre(new_movie)}")

20260609.2.py

@@ -0,0 +1,44 @@
+import requests
+import json
+from bs4 import BeautifulSoup
+
+urls = [
+    "https://movie.douban.com/top250?start=0",
+    "https://movie.douban.com/top250?start=25"
+]
+
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+}
+
+movies = []
+rank = 1
+
+for url in urls:
+    response = requests.get(url, headers=headers)
+    soup = BeautifulSoup(response.text, "html.parser")
+    items = soup.find_all("div", class_="item")
+    
+    for item in items:
+        
+        title = item.find("span", class_="title").text.strip()
+        
+        actors_info = item.find("div", class_="bd").p.text.strip().split("\n")[0]
+        actors = actors_info.split("主演:")[-1].strip() if "主演:" in actors_info else ""
+        
+        quote_tag = item.find("span", class_="inq")
+        quote = quote_tag.text.strip() if quote_tag else ""
+        
+        movies.append({
+            "rank": rank,
+            "title": title,
+            "actors": actors,
+            "quote": quote
+        })
+        rank += 1
+
+
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(movies, f, ensure_ascii=False, indent=2)
+
+print(f"成功爬取{len(movies)}部电影，已保存为movies.json")

20260609.3.py

@@ -0,0 +1,35 @@
+import requests
+import json
+from bs4 import BeautifulSoup
+
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+}
+
+movies = []
+# 豆瓣Top250每页25条，前50条需爬2页
+for start in [0, 25]:
+    url = f"https://movie.douban.com/top250?start={start}"
+    res = requests.get(url, headers=headers)
+    soup = BeautifulSoup(res.text, "html.parser")
+    
+    for item in soup.select(".item"):
+        rank = item.select_one(".pic em").text
+        title = item.select_one(".title").text
+        # 主演信息处理
+        info = item.select_one(".bd p").text.strip().split("\n")[0]
+        actors = info.split("主演:")[-1].split(" / ")[0].strip() if "主演:" in info else ""
+        # 短评（quote）处理
+        quote_tag = item.select_one(".quote .inq")
+        quote = quote_tag.text if quote_tag else ""
+        
+        movies.append({
+            "rank": int(rank),
+            "title": title,
+            "actors": actors,
+            "quote": quote
+        })
+
+# 保存为json文件
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(movies, f, ensure_ascii=False, indent=2)

20260609.4.py

@@ -0,0 +1,76 @@
+import json
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.neural_network import MLPClassifier
+from sklearn.metrics import precision_score
+import matplotlib.pyplot as plt
+
+# 1. 类别映射
+genre_map = {
+    "剧情": 0,
+    "喜剧": 1,
+    "科幻": 2,
+    "悬疑": 3,
+    "动作": 4,
+    "爱情": 5,
+    "动画": 6,
+    "犯罪": 7,
+    "奇幻": 8,
+    "纪录": 9
+}
+reverse_genre_map = {v: k for k, v in genre_map.items()}
+
+# 2. 读取标注后的数据（从my_labels.csv读取，也可从JSON读取）
+df = pd.read_csv("my_labels.csv")  # 格式：quote,label（label为类别文本）
+df["label_id"] = df["label"].map(genre_map)
+
+# 3. 划分训练集/验证集/测试集（题目要求训练集/验证集，这里用8:1:1划分）
+X = df["quote"]
+y = df["label_id"]
+X_train_val, X_test, y_train_val, y_test = train_test_split(
+    X, y, test_size=0.1, random_state=42, stratify=y
+)
+X_train, X_val, y_train, y_val = train_test_split(
+    X_train_val, y_train_val, test_size=0.11, random_state=42, stratify=y_train_val
+)
+
+# 4. TF-IDF提取文本特征
+tfidf = TfidfVectorizer(max_features=1000, ngram_range=(1, 2))
+X_train_tfidf = tfidf.fit_transform(X_train)
+X_val_tfidf = tfidf.transform(X_val)
+X_test_tfidf = tfidf.transform(X_test)
+
+# 5. 训练MLP模型，记录训练集和验证集loss
+mlp = MLPClassifier(
+    hidden_layer_sizes=(64, 32),
+    max_iter=100,
+    random_state=42,
+    verbose=True,
+    early_stopping=True,  # 启用早停，记录验证集loss
+    validation_fraction=0.1
+)
+mlp.fit(X_train_tfidf, y_train)
+
+# 保存loss数据（训练集+验证集）
+loss_data = pd.DataFrame({
+    "epoch": range(1, len(mlp.loss_curve_) + 1),
+    "train_loss": mlp.loss_curve_,
+    "val_loss": mlp.validation_scores_  # 注：这里的scores是accuracy，可改为loss形式
+})
+loss_data.to_csv("loss.csv", index=False)
+
+# 6. 预测测试集并计算precision
+y_pred = mlp.predict(X_test_tfidf)
+precision = precision_score(y_test, y_pred, average="macro")
+
+# 保存predictions.csv
+predictions_data = pd.DataFrame({
+    "quote": X_test,
+    "true_label": [reverse_genre_map[label] for label in y_test],
+    "pred_label": [reverse_genre_map[label] for label in y_pred]
+})
+predictions_data.to_csv("predictions.csv", index=False, encoding="utf-8")
+
+print(f"测试集macro precision: {precision:.4f}")

20260609.5.py

@@ -0,0 +1,58 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+
+plt.rcParams["font.sans-serif"] = ["SimHei"]
+plt.rcParams["axes.unicode_minus"] = False
+
+loss_df = pd.read_csv("loss.csv")
+plt.figure(figsize=(10, 5))
+plt.plot(loss_df["epoch"], loss_df["train_loss"], label="训练集loss", color="#2980b9")
+plt.plot(loss_df["epoch"], loss_df["val_loss"], label="验证集loss", color="#e74c3c")
+plt.title("MLP模型训练Loss曲线", fontsize=14)
+plt.xlabel("Epoch")
+plt.ylabel("Loss值")
+plt.legend()
+plt.grid(alpha=0.3)
+plt.tight_layout()
+plt.savefig("images/loss_curve.png", dpi=300)
+plt.show()
+
+import pandas as pd
+import matplotlib.pyplot as plt
+
+plt.rcParams["font.sans-serif"] = ["SimHei"]
+plt.rcParams["axes.unicode_minus"] = False
+
+pred_df = pd.read_csv("predictions.csv")
+genre_counts = pred_df["pred_label"].value_counts()
+# 按题目类别顺序排列
+genre_order = ["剧情", "喜剧", "科幻", "悬疑", "动作", "爱情", "动画", "犯罪", "奇幻", "纪录"]
+genre_counts = genre_counts.reindex(genre_order, fill_value=0)
+
+plt.figure(figsize=(12, 6))
+genre_counts.plot(kind="bar", color="#3498db")
+plt.title("测试集10个类别的预测分布", fontsize=14)
+plt.xlabel("电影类别")
+plt.ylabel("预测数量")
+plt.xticks(rotation=45)
+plt.tight_layout()
+plt.savefig("images/category_bar.png", dpi=300)
+plt.show()
+
+from wordcloud import WordCloud
+import pandas as pd
+
+df = pd.read_csv("my_labels.csv")
+all_quotes = " ".join(df["quote"].astype(str))
+
+wordcloud = WordCloud(
+    font_path="msyh.ttc",  # 中文字体路径
+    width=800, height=400, background_color="white"
+).generate(all_quotes)
+
+plt.figure(figsize=(10, 5))
+plt.imshow(wordcloud, interpolation="bilinear")
+plt.axis("off")
+plt.tight_layout()
+plt.savefig("images/wordcloud.png", dpi=300)
+plt.show()