没有合适的资源?快使用搜索试试~ 我知道了~
Project_Twitter_NLP:为Twitter构建事件提取和趋势框架
共102个文件
ipynb:74个
pyc:12个
py:9个
需积分: 12 0 下载量 52 浏览量
2021-02-06
08:19:06
上传
评论
收藏 36MB ZIP 举报
温馨提示
为Twitter构建事件提取和趋势框架 这是我在大会上沉浸于数据科学领域的顶峰项目。 在这个项目中,我的目标是: 设置实时数据收集流程和数据基础架构 检查收集的推文上的不同自然语言处理工具 根据相似度比较创建A | B测试模型 使用时间序列建模来捕捉趋势 调整超参数以改进模型 要测试我的框架: 我通过使用TwitterStream API收集并清理了超过150万条推文 /lib/get_tweets.py 创建计划的和按需的LSA处理以进行文本替换 /ipynb/01_Fit_pipeline_TfiDf_SVD.ipynb 使用余弦相似度和ARIMA建模进行事件和趋势检测
资源推荐
资源详情
资源评论
收起资源包目录
Project_Twitter_NLP:为Twitter构建事件提取和趋势框架 (102个子文件)
Dockerfile 291B
.gitignore 91B
02_Tweets_Modeling_CategoryPrediction_NN_CM-checkpoint.ipynb 3.19MB
02_Tweets_Modeling_CategoryPrediction_NN-checkpoint.ipynb 3.19MB
02_Tweets_Modeling_CategoryPrediction_NN.ipynb 3.19MB
02_Tweets_Modeling_CategoryPrediction_NN_CM.ipynb 3.19MB
05_Hashtags_Modeling_WhatsTrending-checkpoint.ipynb 2.23MB
05_Hashtags_Modeling_WhatsTrending.ipynb 2.23MB
bkup_05_Hashtags_Modeling_WhatsTrending.ipynb 1.94MB
bkup_05_Hashtags_Modeling_WhatsTrending-checkpoint.ipynb 1.94MB
bkup_05_Hashtags_Modeling_WhatsTrending-checkpoint.ipynb 1.94MB
ARIMA-codealong.ipynb 1.21MB
ARIMA-codealong-checkpoint.ipynb 1.21MB
ARIMA-codealong-checkpoint.ipynb 1.21MB
05_Hashtags_Modeling_TrendingAnalysis.ipynb 1.14MB
05_Hashtags_Modeling_TrendingAnalysis-checkpoint.ipynb 1.14MB
03_Tweets_Modeling_CosineSim_AB_Test_SVD.ipynb 806KB
03_Tweets_Modeling_CosineSim_AB_Test_SVD-checkpoint.ipynb 805KB
04_Tweets_Modeling_Kmean_AB_Test.ipynb 697KB
04_Tweets_Modeling_Kmean_AB_Test-checkpoint.ipynb 423KB
Playground_Hashtags_WhatsTrendin.ipynb 390KB
Playground_Hashtags_WhatsTrendin-checkpoint.ipynb 390KB
Playground_Hashtags_WhatsTrendin-checkpoint.ipynb 390KB
Hashtags_Modeling_TrendingAnalysis_Geo-checkpoint.ipynb 311KB
Hashtags_Modeling_TrendingAnalysis_Geo-checkpoint.ipynb 311KB
Tweets_Modeling_CosineSim_AB_Test_Word2Vec.ipynb 201KB
Tweets_Modeling_CosineSim_AB_Test_Word2Vec-checkpoint.ipynb 201KB
Tweets_Modeling_CosineSim_AB_Test_Word2Vec-checkpoint.ipynb 201KB
Tweets_EDA_PCA.ipynb 191KB
00_Data_EDA_GetHashtag-checkpoint.ipynb 187KB
00_Data_EDA_GetHashtag.ipynb 187KB
00_Data_EDA_GetHashtag-checkpoint.ipynb 187KB
Tweets_EDA_PCA-checkpoint.ipynb 185KB
Tweets_EDA_PCA-checkpoint.ipynb 185KB
Hashtags_Modeling_TrendingAnalysis_Geo.ipynb 160KB
temp_modeling_demo-checkpoint.ipynb 104KB
temp_modeling_demo-checkpoint.ipynb 104KB
temp_modeling_demo.ipynb 102KB
Playground_HashingVec.ipynb 98KB
03_Tweets_Modeling_CosineSim_AB_Test_Spacy.ipynb 96KB
03_Tweets_Modeling_CosineSim_AB_Test_Spacy-checkpoint.ipynb 96KB
temp-checkpoint.ipynb 92KB
Playground_HashingVec-checkpoint.ipynb 91KB
Playground_HashingVec-checkpoint.ipynb 91KB
01_Hashtags_FeatureEngineering_ModelFit_Tfidf.ipynb 63KB
SVD_Variance.ipynb 41KB
SVD_Variance-checkpoint.ipynb 40KB
SVD_Variance-checkpoint.ipynb 40KB
Playground_GetTweets-checkpoint.ipynb 37KB
Playground_GetTweets-checkpoint.ipynb 37KB
topic+modeling.ipynb 31KB
topic+modeling-checkpoint.ipynb 31KB
topic+modeling-checkpoint.ipynb 31KB
00_Data_Collection.ipynb 30KB
00_Data_Collection-checkpoint.ipynb 25KB
00_Data_Collection-checkpoint.ipynb 25KB
01_Tweets_FeatureEngineering_ModelFit_Tfidf_SVD.ipynb 17KB
Playground_TimeSeries.ipynb 16KB
Playground_TimeSeries-checkpoint.ipynb 16KB
Playground_TimeSeries-checkpoint.ipynb 16KB
Playground_pipe.ipynb 16KB
Playground_GetTweets.ipynb 13KB
Playground_NLPVectorizing.ipynb 10KB
Playground_NLPVectorizing-checkpoint.ipynb 9KB
Playground_NLPVectorizing-checkpoint.ipynb 9KB
01_Tweets_FeatureEngineering_ModelFit_Tfidf_SVD-checkpoint.ipynb 9KB
Playground_KeyWord_Extraction-checkpoint.ipynb 8KB
Playground_KeyWord_Extraction.ipynb 8KB
Playground_KeyWord_Extraction-checkpoint.ipynb 8KB
Untitled-checkpoint.ipynb 7KB
01_Hashtags_FeatureEngineering_ModelFit_Tfidf-checkpoint.ipynb 6KB
01_Fit_pipeline_TfiDf_SVD.ipynb 4KB
01_Fit_pipeline_TfiDf_SVD-checkpoint.ipynb 4KB
00_Capstone_Intro-checkpoint.ipynb 4KB
00_Capstone_Intro.ipynb 4KB
Untitled1-checkpoint.ipynb 72B
README.md 1KB
Twitter_capstone_GA_Profile.pdf 1.43MB
Twitter_capstone.pptx 10.42MB
Twitter_capstone_GA_Profile.pptx 5.02MB
get_tweets.py 9KB
conn_postgres.py 2KB
tweet_vectorizor.py 1KB
__init__.py 1KB
pipeline_tweet_tfd.py 1020B
twitter_key.py 264B
helper_system.py 158B
postgres_conn.py 77B
Google_API_Key.py 62B
get_tweets.cpython-35.pyc 5KB
get_tweets_new.cpython-35.pyc 4KB
get_tweets.cpython-35.pyc 3KB
conn_postgres.cpython-35.pyc 2KB
tweet_vectorizor.cpython-35.pyc 2KB
__init__.cpython-35.pyc 1KB
pipeline_tweet_tfd.cpython-35.pyc 1KB
twitter_keys.cpython-35.pyc 393B
twitter_key.cpython-35.pyc 391B
helper_system.cpython-35.pyc 325B
DataConnection.cpython-35.pyc 260B
共 102 条
- 1
- 2
资源评论
空气安全讲堂
- 粉丝: 41
- 资源: 4795
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功