add files

.gitignore

@@ -0,0 +1,175 @@
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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 maintained 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/
+
+# gitignore template for Jupyter Notebooks
+# website: http://jupyter.org/
+
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Remove previous ipynb_checkpoints
+#   git rm -r .ipynb_checkpoints/

.jupyter/lab/workspaces/default-37a8.jupyterlab-workspace

@@ -0,0 +1 @@
+{"data":{"layout-restorer:data":{"main":{"dock":{"type":"tab-area","currentIndex":2,"widgets":["notebook:analisis.ipynb","csvviewer:data/articles.csv"]},"current":"csvviewer:data/articles.csv"},"down":{"size":0,"widgets":[]},"left":{"collapsed":false,"visible":true,"current":"filebrowser","widgets":["filebrowser","running-sessions","git-sessions","@jupyterlab/toc:plugin","extensionmanager.main-view"],"widgetStates":{"jp-running-sessions":{"sizes":[0.16666666666666666,0.16666666666666666,0.16666666666666666,0.16666666666666666,0.16666666666666666,0.16666666666666666],"expansionStates":[false,false,false,false,false,false]},"extensionmanager.main-view":{"sizes":[0.5,0.5],"expansionStates":[false,false]}}},"right":{"collapsed":true,"visible":true,"widgets":["jp-property-inspector","debugger-sidebar"],"widgetStates":{"jp-debugger-sidebar":{"sizes":[0.2,0.2,0.2,0.2,0.2],"expansionStates":[false,false,false,false,false]}}},"relativeSizes":[0.1663353214049039,0.8336646785950961,0],"top":{"simpleVisibility":true}},"docmanager:recents":{"opened":[{"path":"data","contentType":"directory","root":"/home/jovyan"},{"path":"data/articles.csv","contentType":"file","factory":"CSVTable","root":"/home/jovyan"},{"path":"","contentType":"directory","root":"/home/jovyan"},{"path":"analisis.ipynb","contentType":"notebook","factory":"Notebook","root":"/home/jovyan"}],"closed":[]},"file-browser-filebrowser:cwd":{"path":"data"},"csvviewer:data/articles.csv":{"data":{"path":"data/articles.csv","factory":"CSVTable"}},"notebook:analisis.ipynb":{"data":{"path":"analisis.ipynb","factory":"Notebook"}}},"metadata":{"id":"default"}}

Dockerfile

@@ -0,0 +1,12 @@
+FROM quay.io/jupyter/scipy-notebook
+
+# Install in the default python3 environment
+RUN pip install --no-cache-dir 'flake8' && \
+  fix-permissions "${CONDA_DIR}" && \
+  fix-permissions "/home/${NB_USER}"
+
+# Install from the requirements.txt file
+COPY --chown=${NB_UID}:${NB_GID} requirements.txt /tmp/
+RUN pip install --no-cache-dir --requirement /tmp/requirements.txt && \
+  fix-permissions "${CONDA_DIR}" && \
+  fix-permissions "/home/${NB_USER}"

README.md

@@ -1,2 +1,94 @@
-# how-gen-ai-affects-researchers
+import pandas as pd
+import seaborn as sns
+from wordcloud import WordCloud
+import matplotlib.pyplot as plt
+from IPython.display import display, Markdown
+from collections import Counter
+from itertools import islice
 
+articles = pd.read_csv('data/articles.csv')# how-gen-ai-affects-researchers
+
+## Most common tags
+
+man_tags = articles['Manual Tags'].dropna().str.lower()
+auto_tags = articles['Automatic Tags'].dropna().str.lower()
+tags = man_tags.str.split(';').explode().str.strip().to_list() + auto_tags.str.split(';').explode().str.strip().to_list()
+c = Counter(tags)
+
+text = '## Top 50 common tags:\n\n'
+for val, key in c.most_common(50):
+    text += f"1. {val} ({key})\n"
+display(Markdown(text))
+
+wc = WordCloud(scale=8, background_color="white").generate_from_frequencies(c)
+plt.figure(figsize=(10,10))
+plt.imshow(wc)
+plt.axis("off")
+plt.show()
+
+## Title
+
+titles = articles['Title'].dropna().str.lower()
+
+tc = WordCloud(scale=8, background_color="white").generate(" ".join(titles))
+plt.figure(figsize=(10,10))
+plt.imshow(tc)
+plt.axis("off")
+plt.show()
+
+---
+
+top_title = "### Top 50 phrase in title\n\n"
+
+tc_words = dict(islice(dict(sorted(WordCloud(scale=8, background_color="white").process_text(" ".join(titles)).items(), key=lambda item: item[1], reverse=True)).items(), 50))
+
+for word, freq in tc_words.items():
+    top_title += f"1. {word} ({freq})\n"
+
+display(Markdown(top_title))
+
+---
+
+## Abstract
+
+abstracts = articles['Abstract Note'].dropna().str.lower()
+
+ac = WordCloud(scale=8, background_color="white").generate(" ".join(abstracts))
+plt.figure(figsize=(10,10))
+plt.imshow(ac)
+plt.axis("off")
+plt.show()
+
+---
+
+top_abstract = "### Top 50 phrase in abstract\n\n"
+
+ac_words = dict(islice(dict(sorted(WordCloud(scale=8, background_color="white").process_text(" ".join(abstracts)).items(), key=lambda item: item[1], reverse=True)).items(), 50))
+
+for word, freq in ac_words.items():
+    top_abstract += f"1. {word} ({freq})\n"
+
+display(Markdown(top_abstract))
+
+---
+
+## Journal
+
+pub = articles['Publication Title'].dropna().str.lower()
+
+pc = WordCloud(scale=8, background_color="white").generate(" ".join(pub))
+plt.figure(figsize=(10,10))
+plt.imshow(pc)
+plt.axis("off")
+plt.show()
+
+---
+
+top_pub = "### Top 50 phrase in publication title\n\n"
+
+pc_words = dict(islice(dict(sorted(WordCloud(scale=8, background_color="white").process_text(" ".join(pub)).items(), key=lambda item: item[1], reverse=True)).items(), 50))
+
+for word, freq in pc_words.items():
+    top_pub += f"1. {word} ({freq})\n"
+
+display(Markdown(top_pub))

requirements.txt

@@ -0,0 +1,2 @@
+nltk==3.9.1
+wordcloud==1.9.4