This repository provides access to patent information from Espacenet and enables text analysis of the extracted data.
-
Install the required packages listed in
requirements.txt. -
Define a
.envfile with the following format to set yourCLIENT_KEYandCLIENT_SECRETfrom Espacenet:CLIENT_KEY=YOUR_CLIENT_KEY CLIENT_SECRET=YOUR_CLIENT_SECRET
-
Navigate to the
extractionfolder. -
Run the
search_patents.pyscript to extract patent information. -
Monitor the amount of data extracted by your API key by executing
usage.py. -
Convert the extracted files and standardize the format to text files by running
conversion.py.
-
Execute
citation_analysis.pyto perform a citation network analysis on the extracted patents. -
Run
descriptive_analysis.pyfor descriptive analysis and generate ranking graphs. -
Execute
lda_analysis.pyto conduct Latent Dirichlet Allocation (LDA) analysis. -
Run
semantic_analysis.pyfor a semantic analysis of the patents.