Add prepare_dataset.py script for private dataset extraction

.gitignore

@@ -0,0 +1,254 @@
+
+# Created by https://www.toptal.com/developers/gitignore/api/python,pycharm+all
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,pycharm+all
+
+### PyCharm+all ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### PyCharm+all Patch ###
+# Ignores the whole .idea folder and all .iml files
+# See https://github.com/joeblau/gitignore.io/issues/186 and https://github.com/joeblau/gitignore.io/issues/360
+
+.idea/*
+
+# Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-249601023
+
+*.iml
+modules.xml
+.idea/misc.xml
+*.ipr
+
+# Sonarlint plugin
+.idea/sonarlint
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# End of https://www.toptal.com/developers/gitignore/api/python,pycharm+all

.run/prepare_dataset (ulpressa).run.xml

@@ -0,0 +1,25 @@
+<component name="ProjectRunConfigurationManager">
+    <configuration default="false" name="prepare_dataset (ulpressa)" type="PythonConfigurationType"
+                   factoryName="Python">
+        <module name="social-clusters"/>
+        <option name="INTERPRETER_OPTIONS" value=""/>
+        <option name="PARENT_ENVS" value="true"/>
+        <envs>
+            <env name="PYTHONUNBUFFERED" value="1"/>
+        </envs>
+        <option name="SDK_HOME" value="C:\Users\user\Projects\python\social-clusters\venv\Scripts\python.exe"/>
+        <option name="SDK_NAME" value="Python 3.10 (social-clusters)"/>
+        <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$"/>
+        <option name="IS_MODULE_SDK" value="false"/>
+        <option name="ADD_CONTENT_ROOTS" value="true"/>
+        <option name="ADD_SOURCE_ROOTS" value="true"/>
+        <option name="SCRIPT_NAME" value="$PROJECT_DIR$/prepare_dataset.py"/>
+        <option name="PARAMETERS" value="raw_dataset/ulpressa.json"/>
+        <option name="SHOW_COMMAND_LINE" value="false"/>
+        <option name="EMULATE_TERMINAL" value="false"/>
+        <option name="MODULE_MODE" value="false"/>
+        <option name="REDIRECT_INPUT" value="false"/>
+        <option name="INPUT_FILE" value=""/>
+        <method v="2"/>
+    </configuration>
+</component>

.run/prepare_dataset (ultra).run.xml

@@ -0,0 +1,24 @@
+<component name="ProjectRunConfigurationManager">
+    <configuration default="false" name="prepare_dataset (ultra)" type="PythonConfigurationType" factoryName="Python">
+        <module name="social-clusters"/>
+        <option name="INTERPRETER_OPTIONS" value=""/>
+        <option name="PARENT_ENVS" value="true"/>
+        <envs>
+            <env name="PYTHONUNBUFFERED" value="1"/>
+        </envs>
+        <option name="SDK_HOME" value="C:\Users\user\Projects\python\social-clusters\venv\Scripts\python.exe"/>
+        <option name="SDK_NAME" value="Python 3.10 (social-clusters)"/>
+        <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$"/>
+        <option name="IS_MODULE_SDK" value="false"/>
+        <option name="ADD_CONTENT_ROOTS" value="true"/>
+        <option name="ADD_SOURCE_ROOTS" value="true"/>
+        <option name="SCRIPT_NAME" value="$PROJECT_DIR$/prepare_dataset.py"/>
+        <option name="PARAMETERS" value="raw_dataset/ultra.json"/>
+        <option name="SHOW_COMMAND_LINE" value="false"/>
+        <option name="EMULATE_TERMINAL" value="false"/>
+        <option name="MODULE_MODE" value="false"/>
+        <option name="REDIRECT_INPUT" value="false"/>
+        <option name="INPUT_FILE" value=""/>
+        <method v="2"/>
+    </configuration>
+</component>

prepare_dataset.py

@@ -0,0 +1,47 @@
+#!/usr/bin/env python3
+
+import json
+import os
+import sys
+
+import pandas as pd
+
+from src.person import Person
+
+
+def __main(json_file_name):
+    json_file = open(json_file_name, encoding='utf-8')
+    data = json.load(json_file)
+
+    persons = []
+    for item in data:
+        person = Person(item)
+        if person.is_closed:
+            continue
+        if person.deactivated:
+            continue
+        persons.append(person.__dict__)
+
+    if len(persons) == 0:
+        raise Exception("No data")
+
+    df = pd.DataFrame()
+    for key in persons[0].keys():
+        current_col = []
+        for person in persons:
+            current_col.append(person[key])
+        df[key] = pd.Series(current_col)
+
+    pathname, extension = os.path.splitext(json_file_name)
+    filename = pathname.split('/')[-1]
+
+    df.to_json(f'{filename}.private.json')
+
+
+if __name__ == '__main__':
+    if len(sys.argv) != 2:
+        print('You must specify the VK data in json')
+        exit(1)
+    if not os.path.isfile(sys.argv[1]):
+        print(f'File {sys.argv[1]} is not exists')
+    __main(sys.argv[1])

readme.md

@@ -0,0 +1,7 @@
+Скрипт prepare_dataset используется для получения обезличенного датасета из данных, которые были загружены из ВК.
+
+"Сырые" датасеты находятся в каталоге raw_dataset.
+
+Была загружена информамция из пабликов "Улпресса" и "Ultra".
+
+Обезличенные датасеты находятся в корневом каталоге проекта.

requirements.txt

@@ -0,0 +1 @@
+pandas==2.0.1

src/career.py

@@ -0,0 +1,14 @@
+from src.raw_data import RawData
+
+
+class Career:
+    def __init__(self, raw_career):
+        data = RawData(raw_career)
+        self.id = data.id
+        self.group_id = data.group_id
+        self.company = data.company
+        self.country_id = data.country_id
+        self.city_id = data.city_id
+        self.year_from = raw_career['from']
+        self.until = data.until
+        self.position = data.position

src/military.py

@@ -0,0 +1,12 @@
+from src.raw_data import RawData
+
+
+class Military:
+    def __init__(self, raw_military):
+        data = RawData(raw_military)
+        self.id = data.id
+        self.unit_id = data.unit_id
+        self.unit = data.unit
+        self.country_id = data.country_id
+        self.year_from = raw_military['from']
+        self.until = data.until

src/person.py

@@ -0,0 +1,63 @@
+from src.career import Career
+from src.military import Military
+from src.raw_data import RawData
+from src.school import School
+from src.university import University
+
+
+class Person:
+    def __init__(self, raw_person):
+        data = RawData(raw_person)
+        self.id = hash(str(data.id))
+        self.is_closed = data.is_closed
+        self.deactivated = data.deactivated is not None
+        self.has_photo = data.has_photo == 1
+        self.followers_count = data.followers_count
+        self.sex = data.sex
+        self.bdate = data.get_date(data.bdate)
+        self.relation = data.relation
+        self.country_id = data.get_int(data.country, 'id')
+        self.country = data.get_int(data.country, 'title')
+        self.city_id = data.get_int(data.city, 'id')
+        self.city = data.get_int(data.city, 'title')
+        self.home_town = data.home_town
+        self.status = data.status
+        self.site = data.site is not None
+        self.facebook = data.facebook is not None
+        self.twitter = data.twitter is not None
+        self.instagram = data.instagram is not None
+        self.mobile_phone = data.mobile_phone is not None
+        self.activities = data.activities
+        self.interests = data.interests
+        self.books = data.books
+        self.movies = data.movies
+        self.music = data.music
+        self.tv = data.tv
+        self.games = data.games
+        self.quotes = data.quotes
+        self.about = data.about
+        personal = None
+        if data.personal is not None:
+            if len(data.personal) == 1:
+                personal = data.personal[0]
+            if len(data.personal) > 1:
+                raise Exception(f'PERSONAL {data.id}')
+        self.political = data.get_int(personal, 'political')
+        self.religion = data.get_str(personal, 'religion')
+        self.inspired_by = data.get_str(personal, 'inspired_by')
+        self.people_main = data.get_int(personal, 'people_main')
+        self.life_main = data.get_int(personal, 'life_main')
+        self.smoking = data.get_int(personal, 'smoking')
+        self.alcohol = data.get_int(personal, 'alcohol')
+        self.relatives = Person.__collection(data.relatives, lambda item: item['type'])
+        self.occupation_type = data.get_str(data.occupation, 'type')
+        self.occupation_place_id = data.get_int(data.occupation, 'id')
+        self.occupation_place_name = data.get_str(data.occupation, 'name')
+        self.universities = Person.__collection(data.universities, lambda item: University(item).__dict__)
+        self.schools = Person.__collection(data.schools, lambda item: School(item).__dict__)
+        self.career = Person.__collection(data.career, lambda item: Career(item).__dict__)
+        self.military = Person.__collection(data.military, lambda item: Military(item).__dict__)
+
+    @staticmethod
+    def __collection(collection, function):
+        return list(map(lambda item: function(item), [] if collection is None else collection))

src/raw_data.py

@@ -0,0 +1,31 @@
+from datetime import datetime
+
+
+class RawData:
+    def __init__(self, data):
+        self.__dict__.update(data)
+
+    @staticmethod
+    def get_str(value, attr):
+        if value is None:
+            return ''
+        return '' if value is None else value[attr]
+
+    @staticmethod
+    def get_int(value, attr):
+        if value is None:
+            return -1
+        return -1 if value is None else value[attr]
+
+    @staticmethod
+    def get_date(value):
+        if value is None:
+            return None
+        try:
+            return datetime.strptime(value, '%d.%m.%Y').date()
+        except ValueError:
+            try:
+                return datetime.strptime(value, '%d.%m.%y').date()
+            except ValueError:
+                print(f'Invalid date {value}')
+                return None

src/school.py

@@ -0,0 +1,18 @@
+from src.raw_data import RawData
+
+
+class School:
+    def __init__(self, raw_school):
+        data = RawData(raw_school)
+        self.id = data.id
+        self.name = data.name
+        self.country_id = data.get_int(data.country, 'id')
+        self.city_id = data.get_int(data.city, 'id')
+        self.year_from = data.year_from
+        self.year_to = data.year_to
+        self.year_graduated = data.year_graduated
+        self.speciality = data.speciality
+        self.type_id = data.type
+        self.type = data.type_str
+        self.litera = raw_school['class']
+        self.litera_id = data.class_id

src/university.py

@@ -0,0 +1,19 @@
+from src.raw_data import RawData
+
+
+class University:
+    def __init__(self, raw_university):
+        data = RawData(raw_university)
+        self.id = data.id
+        self.name = data.name
+        self.country_id = data.get_int(data.country, 'id')
+        self.city_id = data.get_int(data.city, 'id')
+        self.faculty_id = data.faculty
+        self.faculty = data.faculty_name
+        self.chair_id = data.chair
+        self.chair = data.chair_name
+        self.graduation = data.graduation
+        self.form_id = data.education_form_id
+        self.form = data.education_form
+        self.status_id = data.education_status_id
+        self.status = data.education_status