Hi @ggqshr No problem. If you want to be able to reproduce the same result each time then you can set the random_state to an interger value. See the parameters on the gensim page: https://radimrehurek.com/gensim/models/ldamodel.html
Hope this helps :)
fakeDataset = downloader.load('fake-news')I could try to distribute the dataset manually, but are there any other suggestions?
Good day. I'm going through the tutorials and I'm getting an error. On the run_corpora_and_vector_spaces.ipynb notebook, in the cell with the following code
for vector in corpus_memory_friendly: # load one vector into memory at a time print(vector)
I get this error
HTTPError: 404 Client Error: Not Found for url: https://radimrehurek.com/gensim/mycorpus.txt
The code does not look like it should be calling/visiting a URL, but it seems to be trying and failing to. What's going on here? How may I run the tutorial?
Operating System: Manjaro Linux
Processors: 4 × Intel® Core™ i5-3320M CPU @ 2.60GHz
Memory: 15.5 GiB of RAM
Notebook is running in Jupyter Lab in Firefox 77.0.1 (64-bit)
I'm trying to get some code for older gensim working on V4.
This is part of the code:
# Get the doc2vec labels from indices for elem in bestdoc2vec: ind = d_indices[elem] temp = model1.dv.index_to_doctag(ind) resultdoc2vec.append((temp, float(avgdoc2vec[elem])))
This results in the error:
AttributeError: 'KeyedVectors' object has no attribute 'index_to_doctag'.
Any ideas how to rewrite this code for V4?