checkpoint 11.06

.gitignore

@@ -0,0 +1,160 @@
+# 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/

app.py

@@ -1,5 +1,80 @@
 import streamlit as st
 import pandas as pd
-import numpy as np
+import plotly.express as px
+from gapminder import gapminder
 
-st.title('Uber pickups in NYC')
+#######
+# Data loading
+#######
+
+df = gapminder
+year_values = (int(df["year"].min()), int(df["year"].max()))
+metrics = ["lifeExp", "pop", "gdpPercap"]
+dimension = ["country", "continent", "year"]
+
+#######
+# Helper functions
+#######
+def get_filtered_data(
+    continents="All", 
+    countries="All",
+    min_year=year_values[0],
+    max_year=year_values[1],
+):
+    if isinstance(continents, str) and continents != "All":
+        mask_continent = df["continent"] == continents
+    else:
+        mask_continent = df["continent"].isin(continents)
+    if isinstance(countries, str) and countries != "All":
+        mask_country = df["country"] == countries
+    else:
+        mask_country = df["country"].isin(countries)
+    mask_year = ((df["year"] >= min_year) & (df["year"] <= max_year))
+    return df[mask_continent & mask_country & mask_year]
+        
+def box_plot(df, x, y):
+    fig = px.box(
+        df, x=x, y=y, hover_data=df[dimension + [x]],
+        points="all", color=x)
+    return fig
+
+def scatter_plot(df, x, y, hue):
+    fig = px.scatter(
+        df, x=x, y=y, 
+        color=hue, symbol=hue)
+    return fig
+
+
+#######
+# Streamlit app code
+#######
+
+st.title('[Gapminder] Exploratory Data Analysis')
+
+st.markdown("## Gapminder Table")
+selected_continents = st.multiselect("Select Continents:", df["continent"].unique(), key="table_continent")
+selected_countries = st.multiselect("Select Countries:", df.loc[df["continent"].isin(selected_continents), "country"].unique(), key="table_country")
+min_year, max_year = st.slider("Select Year:", year_values[0], year_values[1], year_values, key="table_year")
+st.dataframe(get_filtered_data(selected_continents, selected_countries, min_year, max_year))
+
+st.markdown("## Gapminder Boxplot")
+col1, col2 = st.columns(2)
+with col1:
+    x = st.selectbox("Select x Axis", dimension, key="boxplot_x")
+with col2:
+    y = st.selectbox("Select y Axis", metrics, key="boxplot_y")
+st.plotly_chart(box_plot(df, x, y))
+
+## TODO add lineplot
+# st.markdown('## Gapminder Lineplot')
+
+
+st.markdown('## Gapminder Scatterplot')
+col1, col2, col3 = st.columns(3)
+with col1:
+    x = st.selectbox("Select x Axis", metrics, key="scatterplot_x")
+with col2:
+    y = st.selectbox("Select y Axis", metrics, key="scatterplot_y")
+with col3:
+    hue = st.selectbox("Select hue", ["country", "continent"], key="scatterplot_hue")
+st.plotly_chart(scatter_plot(df, x, y, hue))