全新Gensim4.0代码实战(01)-安装与快速上手

!pip install  gensim==4.0.0b0 -i https://pypi.tuna.tsinghua.edu.cn/simple

Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting gensim==4.0.0b0
  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/d0/86/2d03cb418e9fae6dbc17bafd7524d407be0691a703829cecca23e2bc31a9/gensim-4.0.0b0-cp38-cp38-manylinux1_x86_64.whl (24.0 MB)
     |████████████████████████████████| 24.0 MB 8.7 MB/s eta 0:00:01
Requirement already satisfied: numpy>=1.11.3 in /opt/conda/lib/python3.8/site-packages (from gensim==4.0.0b0) (1.19.1)
Requirement already satisfied: smart-open>=1.8.1 in /opt/conda/lib/python3.8/site-packages (from gensim==4.0.0b0) (4.1.2)
Requirement already satisfied: scipy>=0.18.1 in /opt/conda/lib/python3.8/site-packages (from gensim==4.0.0b0) (1.5.2)
Installing collected packages: gensim
  Attempting uninstall: gensim
    Found existing installation: gensim 3.8.3
    Uninstalling gensim-3.8.3:
      Successfully uninstalled gensim-3.8.3
Successfully installed gensim-4.0.0b0

import pprint

document = "Human machine interface for lab abc computer applications"

text_corpus = [
    "Human machine interface for lab abc computer applications",
    "A survey of user opinion of computer system response time",
    "The EPS user interface management system",
    "System and human system engineering testing of EPS",
    "Relation of user perceived response time to error measurement",
    "The generation of random binary unordered trees",
    "The intersection graph of paths in trees",
    "Graph minors IV Widths of trees and well quasi ordering",
    "Graph minors A survey",
]

# Create a set of frequent words
stoplist = set('for a of the and to in'.split(' '))
# Lowercase each document, split it by white space and filter out stopwords
texts = [[word for word in document.lower().split() if word not in stoplist]
         for document in text_corpus]
# Count word frequencies
from collections import defaultdict
frequency = defaultdict(int)
for text in texts:
    for token in text:
        frequency[token] += 1
# Only keep words that appear more than once
processed_corpus = [[token for token in text if frequency[token] > 1] for text in texts]
pprint.pprint(processed_corpus)

from gensim import corpora
dictionary = corpora.Dictionary(processed_corpus)
print(dictionary)

pprint.pprint(dictionary.token2id)

{'computer': 0,
 'eps': 8,
 'graph': 10,
 'human': 1,
 'interface': 2,
 'minors': 11,
 'response': 3,
 'survey': 4,
 'system': 5,
 'time': 6,
 'trees': 9,
 'user': 7}

new_doc = "Human computer interaction"
new_vec = dictionary.doc2bow(new_doc.lower().split())
print(new_vec)

[(0, 1), (1, 1)]

bow_corpus = [dictionary.doc2bow(text) for text in processed_corpus]
pprint.pprint(bow_corpus)

[[(0, 1), (1, 1), (2, 1)],
 [(0, 1), (3, 1), (4, 1), (5, 1), (6, 1), (7, 1)],
 [(2, 1), (5, 1), (7, 1), (8, 1)],
 [(1, 1), (5, 2), (8, 1)],
 [(3, 1), (6, 1), (7, 1)],
 [(9, 1)],
 [(9, 1), (10, 1)],
 [(9, 1), (10, 1), (11, 1)],
 [(4, 1), (10, 1), (11, 1)]]

from gensim import models
# train the model
tfidf = models.TfidfModel(bow_corpus)
# transform the "system minors" string
words = "system minors".lower().split()
print(tfidf[dictionary.doc2bow(words)])

[(5, 0.5898341626740045), (11, 0.8075244024440723)]

from gensim import similarities
index = similarities.SparseMatrixSimilarity(tfidf[bow_corpus], num_features=12)

query_document = 'system engineering'.split()
query_bow = dictionary.doc2bow(query_document)
sims = index[tfidf[query_bow]]
print(list(enumerate(sims)))

[(0, 0.0), (1, 0.32448703), (2, 0.41707572), (3, 0.7184812), (4, 0.0), (5, 0.0), (6, 0.0), (7, 0.0), (8, 0.0)]

for document_number, score in sorted(enumerate(sims), key=lambda x: x[1], reverse=True):
    print(document_number, score)

3 0.7184812
2 0.41707572
1 0.32448703
0 0.0
4 0.0
5 0.0
6 0.0
7 0.0
8 0.0