Question

我的代码给了我这个错误，如下所示：

KeyError: 9763

我尝试搜索此错误，但我不知道如何解决。下面是我正在使用的代码

from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.decomposition import NMF, LatentDirichletAllocation
import numpy as np

def display_topics(H, W, feature_names, documents, no_top_words, no_top_documents):
for topic_idx, topic in enumerate(H):
    print ("Topic %d:" % (topic_idx))
    print (" ".join([feature_names[i]
                    for i in topic.argsort()[:-no_top_words - 1:-1]]))
    top_doc_indices = np.argsort( W[:,topic_idx] )[::-1][0:no_top_documents]
    for doc_index in top_doc_indices:
        print (documents[doc_index])

import pandas as pd
from pandas import DataFrame

ReadCsv = pd.read_csv (r'C:\Users\yelp_review10K.csv')

documents = DataFrame(ReadCsv,columns=['business_id','date','review_id','stars','text','type','user_id'])            


no_features = 1000

# NMF is able to use tf-idf
tfidf_vectorizer = TfidfVectorizer(max_df=0.95, min_df=2, max_features=no_features, stop_words='english')
tfidf = tfidf_vectorizer.fit_transform(documents['text'])
tfidf_feature_names = tfidf_vectorizer.get_feature_names()

# LDA can only use raw term counts for LDA because it is a probabilistic graphical model
tf_vectorizer = CountVectorizer(max_df=0.95, min_df=2, max_features=no_features, stop_words='english')
tf = tf_vectorizer.fit_transform(documents['text'])
tf_feature_names = tf_vectorizer.get_feature_names()

no_topics = 5

# Run NMF
nmf_model = NMF(n_components=no_topics, random_state=1, alpha=.1, l1_ratio=.5, init='nndsvd').fit(tfidf)
nmf_W = nmf_model.transform(tfidf)
nmf_H = nmf_model.components_

# Run LDA
lda_model = LatentDirichletAllocation(n_topics=no_topics, max_iter=5, learning_method='online', learning_offset=50.,random_state=0).fit(tf)
lda_W = lda_model.transform(tf)
lda_H = lda_model.components_

no_top_words = 5
no_top_documents = 2
display_topics(nmf_H, nmf_W, tfidf_feature_names, documents, no_top_words, no_top_documents)
display_topics(lda_H, lda_W, tf_feature_names, documents, no_top_words, no_top_documents)

我正在使用here中的数据集。在此方面的任何帮助，我将不胜感激

无法理解SciKit Learn中的错误

0 个答案: