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)}")