Register
Login
Resources
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Product
Data Engine LLMs Platform Enterprise
Pricing Explore
Connect to our Discord channel
Resources  
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Explore Pricing
Product  
Data Engine LLMs Platform Enterprise
Connect to Dagshub Discord channel
Register
Login

snambi
/
dib-covid-dataset
forked from breno-madruga/dib-covid-dataset

Watch 1
Discussions 0

preprocess_scopus.py 5.6 KB
Permalink History Raw

You have to be logged in to leave a comment. Sign In
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91 
  1. ##############################################################################################
    2. 

  2. ############ Cleaning and Preprocessing the Scopus publications related to COVID-19 ##########
    3. 

  3. ##############################################################################################
    4. 

  4. 

  5. # For collecting the Scopus publications related to COVID-19, we used the "pybliometrics"
    6. 

  6. # library. It is avaliable on https://pypi.org/project/pybliometrics/.
    7. 

  7. 

  8. ########################################################################
    9. 

  9. # Importing the required libraries.
    10. 

  10. import re, pandas as pd, numpy as np
    11. 

  11. from preprocess import Preprocess
    12. 

  12. ########################################################################
    13. 

  13. 

  14. class ProcessScopus(Preprocess):
    15. 

  15.     # Cleaning and preprocessing the dataframe.
    16. 

  16.     def _preprocess(self):
    17. 

  17.         # Removing the invalid articles.
    18. 

  18.         self._dataframe = self._dataframe.loc[
    19. 

  19.             self._dataframe.id.notnull() & self._dataframe.eid.notnull()]
    20. 

  20. 

  21.         # Defining the "None" value for the "NaN" values.
    22. 

  22.         self._dataframe.replace({np.nan: None}, inplace=True)
    23. 

  23. 

  24.         # Defining the "zero" value for the articles without numbers of citation and references.
    25. 

  25.         self._dataframe.citation_num.loc[self._dataframe.citation_num.isnull()] = 0
    26. 

  26.         self._dataframe.ref_count.loc[self._dataframe.ref_count.isnull()] = 0
    27. 

  27. 

  28.         # Normalizing the feature "abstract".
    29. 

  29.         self._dataframe.abstract.loc[
    30. 

  30.             self._dataframe.abstract.isnull() & self._dataframe.description.notnull()
    31. 

  31.         ] = self._dataframe.description.loc[
    32. 

  32.             self._dataframe.abstract.isnull() & self._dataframe.description.notnull()]
    33. 

  33. 

  34.         # Normalizing the feature "vehicle_name".
    35. 

  35.         self._dataframe.vehicle_name.loc[
    36. 

  36.             self._dataframe.conference_name.notnull() & self._dataframe.vehicle_name.notnull()
    37. 

  37.         ] = self._dataframe.conference_name.loc[
    38. 

  38.             self._dataframe.conference_name.notnull() & self._dataframe.vehicle_name.notnull()]
    39. 

  39. 

  40.         # Removing unnecessary columns.
    41. 

  41.         columns_drop = ["eid", "pii", "description", "isbn", "conf_location", "conference_name",
    42. 

  42.             "vehicle_address", "title_edition"]
    43. 

  43.         self._dataframe.drop(axis=1, columns=columns_drop, inplace=True)
    44. 

  44. 

  45.         # Changing the type of features.
    46. 

  46.         self._dataframe.loc[:, ["citation_num", "ref_count"]] = self._dataframe.loc[:,
    47. 

  47.             ["citation_num", "ref_count"]].astype("int")
    48. 

  48.         self._dataframe.auth_keywords.loc[self._dataframe.auth_keywords.notnull()] = \
    49. 

  49.             self._dataframe.auth_keywords.loc[self._dataframe.auth_keywords.notnull()].apply(eval)
    50. 

  50.         self._dataframe.index_terms.loc[self._dataframe.index_terms.notnull()] = \
    51. 

  51.             self._dataframe.index_terms.loc[self._dataframe.index_terms.notnull()].apply(eval)
    52. 

  52.         self._dataframe.affiliations.loc[self._dataframe.affiliations.notnull()] = \
    53. 

  53.             self._dataframe.affiliations.loc[self._dataframe.affiliations.notnull()].apply(eval)
    54. 

  54.         self._dataframe.subject_areas.loc[self._dataframe.subject_areas.notnull()] = \
    55. 

  55.             self._dataframe.subject_areas.loc[self._dataframe.subject_areas.notnull()].apply(eval)
    56. 

  56.         self._dataframe.authors.loc[self._dataframe.authors.notnull()] = \
    57. 

  57.             self._dataframe.authors.loc[self._dataframe.authors.notnull()].apply(eval)
    58. 

  58.         self._dataframe.author_affil.loc[self._dataframe.author_affil.notnull()] = \
    59. 

  59.             self._dataframe.author_affil.loc[self._dataframe.author_affil.notnull()].apply(eval)
    60. 

  60.         self._dataframe.references.loc[self._dataframe.references.notnull()] = \
    61. 

  61.             self._dataframe.references.loc[self._dataframe.references.notnull()].apply(eval)
    62. 

  62.         self._dataframe.publication_date = pd.to_datetime(self._dataframe.publication_date)
    63. 

  63. 

  64.         # Normalizing the feature "abstract".
    65. 

  65.         self._dataframe.abstract.loc[self._dataframe.abstract.notnull()] = \
    66. 

  66.             self._dataframe.abstract.loc[self._dataframe.abstract.notnull()].apply(
    67. 

  67.                 lambda x: x.replace("\\u0019", "").replace("\\%", "%").replace("\\s", "s").strip())
    68. 

  68. 

  69.         # Normalizing the itens contained in the features "auth_keywords" and "index_terms".
    70. 

  70.         self._dataframe.auth_keywords.loc[self._dataframe.auth_keywords.notnull()] = \
    71. 

  71.             self._dataframe.auth_keywords.loc[self._dataframe.auth_keywords.notnull()].apply(
    72. 

  72.                 lambda x: tuple([item.replace("\ufeff", "").strip() for item in x]))
    73. 

  73.         self._dataframe.index_terms.loc[self._dataframe.index_terms.notnull()] = \
    74. 

  74.             self._dataframe.index_terms.loc[self._dataframe.index_terms.notnull()].apply(
    75. 

  75.                 lambda x: tuple([item.replace("\ufeff", "").strip() for item in x]))
    76. 

  76. 

  77.         # Normalizing the affiliations contained in the features "affiliations" and "author_affil".
    78. 

  78.         self._dataframe.affiliations.loc[self._dataframe.affiliations.notnull()] = \
    79. 

  79.             self._dataframe.affiliations.loc[self._dataframe.affiliations.notnull()].apply(
    80. 

  80.                 lambda x: tuple([{"id": affil["id"],
    81. 

  81.                     "affiliation": affil["affiliation"].replace("\u200b", "").replace(
    82. 

  82.                         "\u202f", "").strip(),
    83. 

  83.                     "country": affil["country"]}
    84. 

  84.                 for affil in x]))
    85. 

  85.         self._dataframe.author_affil.loc[self._dataframe.author_affil.notnull()] = \
    86. 

  86.             self._dataframe.author_affil.loc[self._dataframe.author_affil.notnull()].apply(
    87. 

  87.                 lambda x: tuple([{"id": item["id"], "name": item["name"],
    88. 

  88.                     "affil_id": item["affil_id"], "affiliation": item["affiliation"].replace(
    89. 

  89.                         "\u200b", "").replace("\u202f", "").strip() if item["affiliation"] else None,
    90. 

  90.                     "country": item["country"]}
    91. 

  91.                 for item in x]))
    92.
Prev
Next
Tip!

Press p or to see the previous file or, n or to see the next file

Comments

Write Preview
Loading...
Integrate Google Cloud Storage
Use Google Storage
Select bucket
Upload key
Finish

Use Google Cloud Storage!

Browsing data directories saved to Google Cloud Storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your Google Storage bucket

Service Account Key

Congratulations!

dib-covid-dataset is now integrated with Google Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate AWS S3
Use S3 remote
Select bucket
Access key
Finish

Use AWS S3 as storage!

Browsing data directories saved to S3 is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your S3 bucket

Access key (If needed)

Congratulations!

dib-covid-dataset is now integrated with AWS S3!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate S3 compatible storage
Use S3 like remote
Select bucket
Access key
Finish

Use any S3 compatible storage!

Browsing data directories saved to S3 compatible storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your S3 bucket

Access key (If needed)

Congratulations!

dib-covid-dataset is now integrated with your S3 compatible storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate Azure Cloud Storage
Use Azure Storage
Select bucket
Set key
Finish

Use Azure Cloud Storage!

Browsing data directories saved to Azure Cloud Storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your Azure Storage bucket

Access key (If needed)

Congratulations!

dib-covid-dataset is now integrated with Azure Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes