Add standard Python .gitignore and add link to write-up in my portfolio

.gitignore

@@ -1,6 +1,168 @@
+# 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/#use-with-ide
+.pdm.toml
+
+# 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/
+
+# Custom
 .ipynb_checkpoints
 *.pyc
 *.log
 *.json
 code_test.ipynb
-.env
+.env

README.md

@@ -1,7 +1,5 @@
 # canadians-in-college-baseball
-Python web scraper for the Canadian Baseball Network
-
-[Full project write-up](https://peteb206.github.io/projects/canadians-in-college-baseball/)
+Python web scraper for the Canadian Baseball Network... [view full project description](https://peteb206.github.io/projects/canadians-in-college-baseball/)
 
 ## [Canadians in College Baseball](https://www.canadianbaseballnetwork.com/canadian-baseball-network-canadians-in-college)
 [![scrape-schools](https://github.com/peteb206/canadians-in-college-baseball/actions/workflows/scrape-schools.yml/badge.svg)](https://github.com/peteb206/canadians-in-college-baseball/actions/workflows/scrape-schools.yml)

google_sheets.py

@@ -244,7 +244,7 @@ def update_stats_sheet():
                 df_filtered = df_filtered[df_filtered[stat] > 0] # Eliminate 0's
 
             if len(df_filtered.index) > 0:
-                df_filtered.sort_values(by = stat, ascending = (stat == 'ERA'), ignore_index = True, inplace = True)
+                df_filtered.sort_values(by = [stat, 'last_name', 'first_name'], ascending = [stat == 'ERA', True, True], ignore_index = True, inplace = True)
 
                 cutoff = df_filtered[stat].iloc[9] if len(df_filtered.index) >= 10 else df_filtered[stat].iloc[-1]
                 df_filtered = df_filtered[df_filtered[stat] <= cutoff] if stat == 'ERA' else df_filtered[df_filtered[stat] >= cutoff]

model.py

@@ -525,17 +525,18 @@ def get_ncaa_id(x):
                                                         how = 'outer', on = ['id', 'NAME'])
                     else:
                         combined_df = df.copy()
-            combined_df.NAME.replace(self.__corrections__, inplace = True)
-            combined_df['last_name'] = combined_df.NAME.apply(lambda x: RosterPage.format_player_name(x)[1])
-            combined_df['first_name'] = combined_df.NAME.apply(lambda x: RosterPage.format_player_name(x)[0])
-            combined_df['OPS'] = combined_df.OBP.astype(float) + combined_df.SLG.astype(float)
-            if 'W' not in combined_df.columns: # TODO: remove this whenever NAIA/CCCAA stats pages start tracking W, L, SV, BB again
-                combined_df['W'] = 0
-                combined_df['L'] = 0
-                combined_df['SV'] = 0
-                combined_df['BB'] = 0
-            stat_cols = [col for stat_type in cbn_utils.stats_labels.keys() for col in cbn_utils.stats_labels[stat_type].keys()]
-            self.__df__ = combined_df.fillna(0).loc[:, ['id', 'last_name', 'first_name'] + stat_cols]
+            if type(combined_df) == pd.DataFrame:
+                combined_df.NAME.replace(self.__corrections__, inplace = True)
+                combined_df['last_name'] = combined_df.NAME.apply(lambda x: RosterPage.format_player_name(x)[1])
+                combined_df['first_name'] = combined_df.NAME.apply(lambda x: RosterPage.format_player_name(x)[0])
+                combined_df['OPS'] = combined_df.OBP.astype(float) + combined_df.SLG.astype(float)
+                if 'W' not in combined_df.columns: # TODO: remove this whenever NAIA/CCCAA stats pages start tracking W, L, SV, BB again
+                    combined_df['W'] = 0
+                    combined_df['L'] = 0
+                    combined_df['SV'] = 0
+                    combined_df['BB'] = 0
+                stat_cols = [col for stat_type in cbn_utils.stats_labels.keys() for col in cbn_utils.stats_labels[stat_type].keys()]
+                self.__df__ = combined_df.fillna(0).loc[:, ['id', 'last_name', 'first_name'] + stat_cols]
         return self.__df__
 
 class SchedulePage(WebPage):