eview面板数据之混合回归模型_数据统计的理解和应用（十三）预测模型篇之logistic回归...

报错ValueError: np.nan is an invalid document, expected byte or unicode string. 怎么修改import pandas as pd from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer from sklearn.model_selection import train_test_split from sklearn.linear_model import LogisticRegression from sklearn.metrics import accuracy_score # 读取电影评论数据集 data = pd.read_csv(r'D:\shujukexue\review_data.csv', encoding='gbk') x = v.fit_transform(df['eview'].apply(lambda x: np.str_(x))) # 分割数据集为训练集和测试集 X_train, X_test, y_train, y_test = train_test_split(data['review'], data['sentiment'], test_size=0.2, random_state=42) # 创建CountVectorizer对象进行词频统计和向量化 count_vectorizer = CountVectorizer() X_train_count = count_vectorizer.fit_transform(X_train) X_test_count = count_vectorizer.transform(X_test) # 创建TfidfVectorizer对象进行TF-IDF计算和向量化 tfidf_vectorizer = TfidfVectorizer() X_train_tfidf = tfidf_vectorizer.fit_transform(X_train) X_test_tfidf = tfidf_vectorizer.transform(X_test) # 创建逻辑回归分类器并在CountVectorizer上进行训练和预测 classifier_count = LogisticRegression() classifier_count.fit(X_train_count, y_train) y_pred_count = classifier_count.predict(X_test_count) accuracy_count = accuracy_score(y_test, y_pred_count) print("Accuracy using CountVectorizer:", accuracy_count) # 创建逻辑回归分类器并在TfidfVectorizer上进行训练和预测 classifier_tfidf = LogisticRegression() classifier_tfidf.fit(X_train_tfidf, y_train) y_pred_tfidf = classifier_tfidf.predict(X_test_tfidf) accuracy_tfidf = accuracy_score(y_test, y_pred_tfidf) print("Accuracy using TfidfVectorizer:", accuracy_tfidf)