Created
October 3, 2017 16:34
-
-
Save ccd97/768f7fd030b3cab8a71f3712679a5c4f to your computer and use it in GitHub Desktop.
Get glossary from text
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import requests | |
| # pip install numpy | |
| import numpy as np | |
| # pip install pandas | |
| import pandas as pd | |
| # pip install scikit-learn | |
| from sklearn.feature_extraction.text import TfidfVectorizer | |
| # ################# Edit this parameters ################### | |
| # Add you Oxford API id and key here | |
| app_id = 'ffffffff' | |
| app_key = 'ffffffffffffffffffffffffffffffff' | |
| input_file_name = 'report.txt' | |
| output_file_name = 'glossary.txt' | |
| max_word = 20 | |
| ############################################################ | |
| in_file = open(input_file_name, 'r') | |
| out_file = open(output_file_name, 'w') | |
| data = in_file.read() | |
| vectorize = TfidfVectorizer() | |
| tvec_weights = vectorize.fit_transform([data]) | |
| weights = np.asarray(tvec_weights.mean(axis=0)).ravel().tolist() | |
| weights_df = pd.DataFrame({'term': vectorize.get_feature_names(), 'weight': weights}) | |
| weights_df = weights_df.sort_values(by='weight', ascending=True) | |
| def get_defination(word): | |
| url = 'https://od-api.oxforddictionaries.com:443/api/v1/entries/en/' + word.lower() | |
| r = requests.get(url, headers={'app_id': app_id, 'app_key': app_key}) | |
| try: | |
| r_dict = r.json() | |
| return r_dict['results'][0]['lexicalEntries'][0]['entries'][0]['senses'][0]['definitions'][0] | |
| except: | |
| return None | |
| i = 0 | |
| for w in weights_df['term']: | |
| print("Getting defination for " + w) | |
| defination = get_defination(w) | |
| if defination is not None: | |
| i += 1 | |
| print("Defination of " + w + " -> " + defination) | |
| out_file.write("%s - %s\n" % (w, defination)) | |
| if i >= max_word: | |
| break | |
| else: | |
| print("Cannot find defination of " + w) | |
| in_file.close() | |
| out_file.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment