The antm from hamedr96

Questions about running the ANTM model example

Sorry to bother you, I encountered the following problem when running the ANTM model example. How can I solve it? Thank you very much.

Aligned Dimension Reduction is initialized...
Traceback (most recent call last):
File "D:\TopicModel\ANTM-main\ExampleDemo\123.py", line 17, in
topics_per_period=model.fit(save=True)
^^^^^^^^^^^^^^^^^^^^
File "D:\TopicModel\ANTM-main\antm\main.py", line 85, in fit
self.umap_embeddings_clustering, self.umap_embeddings_visulization = aligned_umap(
^^^^^^^^^^^^^
File "D:\TopicModel\ANTM-main\antm\aligned_clustering_layer.py", line 11, in aligned_umap
model_umap_clustering = umap.aligned_umap.AlignedUMAP(
^^^^^^^^^^^^^^^^^
AttributeError: module 'umap' has no attribute 'aligned_umap'

Process finished with exit code 1

I can not run the example code in Colab

I try to run code in colab but I got some issue like this:

contextual document embedding is initiated...
Pandas Apply: 100%
2000/2000 [23:34<00:00, 1.27it/s]
Token indices sequence length is longer than the specified maximum sequence length for this model (549 > 512). Running this sequence through the model will result in indexing errors
Summarizing a document with BART due to its Large length for Embedding...
Summarizing a document with BART due to its Large length for Embedding...
Summarizing a document with BART due to its Large length for Embedding...
Summarizing a document with BART due to its Large length for Embedding...
Sliding Window Segmentation is initialized...
Aligned Dimension Reduction is initialized...
Sequential Document-cluster association is initialized...
Cluster Alignment Procedure is initialized...
---------------------------------------------------------------------------
LookupError                               Traceback (most recent call last)
[<ipython-input-5-675c8f899d3c>](https://localhost:8080/#) in <cell line: 2>()
      1 #learn the model and save it
----> 2 topics_per_period=model.fit(save=True)
      3 #output is a list of timeframes including all the topics associated with that period

8 frames
[/usr/local/lib/python3.10/dist-packages/nltk/data.py](https://localhost:8080/#) in find(resource_name, paths)
    581     sep = "*" * 70
    582     resource_not_found = f"\n{sep}\n{msg}\n{sep}\n"
--> 583     raise LookupError(resource_not_found)
    584 
    585 

LookupError: 
**********************************************************************
  Resource punkt not found.
  Please use the NLTK Downloader to obtain the resource:

  >>> import nltk
  >>> nltk.download('punkt')
  
  For more information see: https://www.nltk.org/data.html

  Attempted to load tokenizers/punkt/PY3/english.pickle

  Searched in:
    - '/root/nltk_data'
    - '/usr/nltk_data'
    - '/usr/share/nltk_data'
    - '/usr/lib/nltk_data'
    - '/usr/share/nltk_data'
    - '/usr/local/share/nltk_data'
    - '/usr/lib/nltk_data'
    - '/usr/local/lib/nltk_data'
    - ''
**********************************************************************

I run code in readme which is:

from antm import ANTM
import pandas as pd

# load data
df=pd.read_parquet("./data/dblpFullSchema_2000_2020_extract_big_data_2K.parquet")
df=df[["abstract","year"]].rename(columns={"abstract":"content","year":"time"})
df=df.dropna().sort_values("time").reset_index(drop=True).reset_index()

# choosing the windows size and overlapping length for time frames
window_size = 6
overlap = 2

#initialize model
model=ANTM(df,overlap,window_size,umap_n_neighbors=10, partioned_clusttering_size=5,mode="data2vec",num_words=10,path="./saved_data")

#learn the model and save it
topics_per_period=model.fit(save=True)    # <------- ERROR when save model.
#output is a list of timeframes including all the topics associated with that period

hamedr96 / antm Goto Github PK

antm's People

Contributors

Stargazers

Watchers

Forkers

antm's Issues

Questions about running the ANTM model example

I can not run the example code in Colab

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent