first commit

200312/categorization_of_files copy/categorization.py

@@ -0,0 +1,57 @@
+import collections
+
+# this script was adapted from:
+# https://towardsdatascience.com/very-simple-python-script-for-extracting-most-common-words-from-a-story-1e3570d0b9d0
+# https://git.xpub.nl/rita/categorization_of_files/src/branch/master/categorization.py
+
+
+# open and read file
+file = open(input("\nwhich platform's Terms of Service do you want to look at: \n"), encoding="utf8")
+a = file.read()
+
+# my stopwords are common words I don't want to count, like "a", "an", "the".
+stopwords = set(line.strip() for line in open('stopwords.txt'))
+
+# dictionary
+wordcount = {}
+
+# spliting words from punctuation so "book" and "book!" counts as the same word
+for word in a.lower().split():
+    word = word.replace(".","")
+    word = word.replace(",","")
+    word = word.replace(":","")
+    word = word.replace("\"","")
+    word = word.replace("!","")
+    word = word.replace("“","")
+    word = word.replace("‘","")
+    word = word.replace("*","")
+
+# counting
+    if word not in stopwords:
+        if word not in wordcount:
+            wordcount[word] = 1
+        else:
+            wordcount[word] += 1
+
+# print x most common words
+# n_print = int(input("How many most common words to print: "))
+n_print = int(5)
+print("\nMost used colonial words are:")
+word_counter = collections.Counter(wordcount)
+for word, count in word_counter.most_common(n_print):
+    print(word,"—", count)
+
+# categories
+
+# words that are inside the category Library Studies
+library_studies = set(line.strip() for line in open('library_studies.txt'))
+
+for word, count in word_counter.most_common(n_print):
+    if word in library_studies:
+        print("\nWe suggest the following categorization for this file:\nLibrary Studies\n")
+        break
+else:
+    print("\nWe don't have any suggestion of categorization for this file.\n")
+
+# Close the file
+file.close()

200312/categorization_of_files copy/colonialwords.py

@@ -0,0 +1,82 @@
+import collections
+# from termcolor import colored
+# this script was adapted from:
+# https://towardsdatascience.com/very-simple-python-script-for-extracting-most-common-words-from-a-story-1e3570d0b9d0
+# https://git.xpub.nl/rita/categorization_of_files/src/branch/master/categorization.py
+
+
+# open and read file
+file = open(input("\nwhich platform's Terms of Service do you want to look at: \n"), encoding="utf8")
+a = file.read()
+
+# f = open("tiktok.txt", "r")
+# print(f.read())
+
+# my stopwords are common words I don't want to count, like "a", "an", "the".
+stopwords = set(line.strip() for line in open('stopwords.txt'))
+
+# dictionary
+wordcount = {}
+
+# spliting words from punctuation so "book" and "book!" counts as the same word
+for word in a.lower().split():
+    word = word.replace(".","")
+    word = word.replace(",","")
+    word = word.replace(":","")
+    word = word.replace("\"","")
+    word = word.replace("!","")
+    word = word.replace("“","")
+    word = word.replace("‘","")
+    word = word.replace("*","")
+    word = word.replace("(","")
+    word = word.replace(")","")
+
+# counting
+    if word not in stopwords:
+        if word not in wordcount:
+            wordcount[word] = 1
+        else:
+            wordcount[word] += 1
+
+# print x most common words
+n_print = int(100)
+print("\nMost used colonial words are:")
+
+word_counter = collections.Counter(wordcount)
+for word, count in word_counter.most_common(n_print):
+    print(word,"—", count)
+
+
+# word_counter = collections.Counter(wordcount)
+# for word, count in word_counter.most_common(n_print):
+#     print(word,"—", count)
+
+
+# colonial texts in bold 
+# for word in n_print:
+#     if word in n_print:
+#         wordcount.append(colored(word, 'white', 'on_red'))
+#     else:
+#         wordcount.append(t)
+
+
+# print(" ".join(colored(word, 'white', 'on_red'))
+
+
+
+
+
+# categories
+
+# words that are inside the category Library Studies
+library_studies = set(line.strip() for line in open('library_studies.txt'))
+
+for word, count in word_counter.most_common(n_print):
+    if word in library_studies:
+        print("\nWe suggest the following categorization for this platform:\nLibrary Studies\n")
+        break
+else:
+    print("\nThese are the TikTok's colonial words.\n")
+
+# Close the file
+file.close()

200312/categorization_of_files copy/faceapp.txt

@@ -0,0 +1,3 @@
+Any questions, comments, suggestions, ideas, original or creative materials or other information you submit about FaceApp or our products or Services (collectively, “Feedback”), is non-confidential and we have no obligations (including without limitation obligations of confidentiality) with respect to such Feedback. You hereby grant to FaceApp a fully paid, royalty-free, perpetual, irrevocable, worldwide, non-exclusive, and fully sublicensable right and license to use, reproduce, perform, display, distribute, adapt, modify, re-format, create derivative works of, and otherwise commercially or non-commercially exploit in any manner, any and all Feedback, and to sublicense the foregoing rights, in connection with the operation and maintenance of the Services and/or FaceApp’s business.
+
+- If you choose to login to the Services via a third-party platform or social media network, you will need to use your credentials (e.g., username and password) from a third-party online platform. You must maintain the security of your third party account and promptly notify us if you discover or suspect that someone has accessed your account without your permission. If you permit others to use your account credentials, you are responsible for the activities of such users that occur in connection with your account.

200312/categorization_of_files copy/stopwords.txt

@@ -0,0 +1,67 @@
+-
+a
+about
+all
+an
+and
+are
+as
+at
+be
+but
+by
+can
+do
+for
+from
+get
+had
+has
+have
+he
+I
+i
+if
+in
+into
+is
+it
+its
+me
+more
+my
+not
+of
+on
+one
+or
+other
+out
+so
+some
+such
+than
+that
+the
+their
+them
+then
+there
+these
+they
+this
+those
+to
+up
+was
+were
+what
+when
+which
+who
+whom
+will
+with
+would
+|
+—

200312/categorization_of_files copy/tiktok.txt

@@ -0,0 +1,3 @@
+Any questions, comments, suggestions, ideas, original or creative materials or other information you submit about FaceApp or our products or Services (collectively, “Feedback”), is non-confidential and we have no obligations (including without limitation obligations of confidentiality) with respect to such Feedback. You hereby grant to FaceApp a fully paid, royalty-free, perpetual, irrevocable, worldwide, non-exclusive, and fully sublicensable right and license to use, reproduce, perform, display, distribute, adapt, modify, re-format, create derivative works of, and otherwise commercially or non-commercially exploit in any manner, any and all Feedback, and to sublicense the foregoing rights, in connection with the operation and maintenance of the Services and/or FaceApp’s business.
+
+- If you choose to login to the Services via a third-party platform or social media network, you will need to use your credentials (e.g., username and password) from a third-party online platform. You must maintain the security of your third party account and promptly notify us if you discover or suspect that someone has accessed your account without your permission. If you permit others to use your account credentials, you are responsible for the activities of such users that occur in connection with your account.

200312/categorization_of_files/categorization.py

@@ -0,0 +1,57 @@
+import collections
+
+# this script was adapted from:
+# https://towardsdatascience.com/very-simple-python-script-for-extracting-most-common-words-from-a-story-1e3570d0b9d0
+# https://git.xpub.nl/rita/categorization_of_files/src/branch/master/categorization.py
+
+
+# open and read file
+file = open(input("\nwhich platform's Terms of Service do you want to look at: \n"), encoding="utf8")
+a = file.read()
+
+# my stopwords are common words I don't want to count, like "a", "an", "the".
+stopwords = set(line.strip() for line in open('stopwords.txt'))
+
+# dictionary
+wordcount = {}
+
+# spliting words from punctuation so "book" and "book!" counts as the same word
+for word in a.lower().split():
+    word = word.replace(".","")
+    word = word.replace(",","")
+    word = word.replace(":","")
+    word = word.replace("\"","")
+    word = word.replace("!","")
+    word = word.replace("“","")
+    word = word.replace("‘","")
+    word = word.replace("*","")
+
+# counting
+    if word not in stopwords:
+        if word not in wordcount:
+            wordcount[word] = 1
+        else:
+            wordcount[word] += 1
+
+# print x most common words
+# n_print = int(input("How many most common words to print: "))
+n_print = int(5)
+print("\nMost used colonial words are:")
+word_counter = collections.Counter(wordcount)
+for word, count in word_counter.most_common(n_print):
+    print(word,"—", count)
+
+# categories
+
+# words that are inside the category Library Studies
+library_studies = set(line.strip() for line in open('library_studies.txt'))
+
+for word, count in word_counter.most_common(n_print):
+    if word in library_studies:
+        print("\nWe suggest the following categorization for this file:\nLibrary Studies\n")
+        break
+else:
+    print("\nWe don't have any suggestion of categorization for this file.\n")
+
+# Close the file
+file.close()

200312/categorization_of_files/colonialwords.py

@@ -0,0 +1,82 @@
+import collections
+# from termcolor import colored
+# this script was adapted from:
+# https://towardsdatascience.com/very-simple-python-script-for-extracting-most-common-words-from-a-story-1e3570d0b9d0
+# https://git.xpub.nl/rita/categorization_of_files/src/branch/master/categorization.py
+
+
+# open and read file
+file = open(input("\nwhich platform's Terms of Service do you want to look at: \n"), encoding="utf8")
+a = file.read()
+
+# f = open("tiktok.txt", "r")
+# print(f.read())
+
+# my stopwords are common words I don't want to count, like "a", "an", "the".
+stopwords = set(line.strip() for line in open('stopwords.txt'))
+
+# dictionary
+wordcount = {}
+
+# spliting words from punctuation so "book" and "book!" counts as the same word
+for word in a.lower().split():
+    word = word.replace(".","")
+    word = word.replace(",","")
+    word = word.replace(":","")
+    word = word.replace("\"","")
+    word = word.replace("!","")
+    word = word.replace("“","")
+    word = word.replace("‘","")
+    word = word.replace("*","")
+    word = word.replace("(","")
+    word = word.replace(")","")
+
+# counting
+    if word not in stopwords:
+        if word not in wordcount:
+            wordcount[word] = 1
+        else:
+            wordcount[word] += 1
+
+# print x most common words
+n_print = int(100)
+print("\nMost used colonial words are:")
+
+word_counter = collections.Counter(wordcount)
+for word, count in word_counter.most_common(n_print):
+    print(word,"—", count)
+
+
+# word_counter = collections.Counter(wordcount)
+# for word, count in word_counter.most_common(n_print):
+#     print(word,"—", count)
+
+
+# colonial texts in bold 
+# for word in n_print:
+#     if word in n_print:
+#         wordcount.append(colored(word, 'white', 'on_red'))
+#     else:
+#         wordcount.append(t)
+
+
+# print(" ".join(colored(word, 'white', 'on_red'))
+
+
+
+
+
+# categories
+
+# words that are inside the category Library Studies
+library_studies = set(line.strip() for line in open('library_studies.txt'))
+
+for word, count in word_counter.most_common(n_print):
+    if word in library_studies:
+        print("\nWe suggest the following categorization for this platform:\nLibrary Studies\n")
+        break
+else:
+    print("\nThese are the TikTok's colonial words.\n")
+
+# Close the file
+file.close()

200312/categorization_of_files/faceapp.txt

@@ -0,0 +1,3 @@
+Any questions, comments, suggestions, ideas, original or creative materials or other information you submit about FaceApp or our products or Services (collectively, “Feedback”), is non-confidential and we have no obligations (including without limitation obligations of confidentiality) with respect to such Feedback. You hereby grant to FaceApp a fully paid, royalty-free, perpetual, irrevocable, worldwide, non-exclusive, and fully sublicensable right and license to use, reproduce, perform, display, distribute, adapt, modify, re-format, create derivative works of, and otherwise commercially or non-commercially exploit in any manner, any and all Feedback, and to sublicense the foregoing rights, in connection with the operation and maintenance of the Services and/or FaceApp’s business.
+
+- If you choose to login to the Services via a third-party platform or social media network, you will need to use your credentials (e.g., username and password) from a third-party online platform. You must maintain the security of your third party account and promptly notify us if you discover or suspect that someone has accessed your account without your permission. If you permit others to use your account credentials, you are responsible for the activities of such users that occur in connection with your account.

200312/categorization_of_files/library_studies.txt

@@ -0,0 +1,19 @@
+archives
+author
+bibliographic
+bibliotheca
+book
+bookcase
+books
+bookshelf
+bookstore
+catalogue
+e-book
+librarian
+librarianship
+library
+literature
+manuscripts
+papyrus
+read
+reading

200312/categorization_of_files/stopwords.txt

@@ -0,0 +1,67 @@
+-
+a
+about
+all
+an
+and
+are
+as
+at
+be
+but
+by
+can
+do
+for
+from
+get
+had
+has
+have
+he
+I
+i
+if
+in
+into
+is
+it
+its
+me
+more
+my
+not
+of
+on
+one
+or
+other
+out
+so
+some
+such
+than
+that
+the
+their
+them
+then
+there
+these
+they
+this
+those
+to
+up
+was
+were
+what
+when
+which
+who
+whom
+will
+with
+would
+|
+—

200312/categorization_of_files/tiktok.txt

@@ -0,0 +1,3 @@
+Any questions, comments, suggestions, ideas, original or creative materials or other information you submit about FaceApp or our products or Services (collectively, “Feedback”), is non-confidential and we have no obligations (including without limitation obligations of confidentiality) with respect to such Feedback. You hereby grant to FaceApp a fully paid, royalty-free, perpetual, irrevocable, worldwide, non-exclusive, and fully sublicensable right and license to use, reproduce, perform, display, distribute, adapt, modify, re-format, create derivative works of, and otherwise commercially or non-commercially exploit in any manner, any and all Feedback, and to sublicense the foregoing rights, in connection with the operation and maintenance of the Services and/or FaceApp’s business.
+
+- If you choose to login to the Services via a third-party platform or social media network, you will need to use your credentials (e.g., username and password) from a third-party online platform. You must maintain the security of your third party account and promptly notify us if you discover or suspect that someone has accessed your account without your permission. If you permit others to use your account credentials, you are responsible for the activities of such users that occur in connection with your account.