B &[_V@spdZddZddZddZddZd d Zd d Zd dZdddZdddZ dddZ dddZ ddZ dS)zE Built-in datasets for demonstration, educational and test purposes. cCstdS)a Each row represents a country on a given year. https://www.gapminder.org/data/ Returns: A `pandas.DataFrame` with 1704 rows and the following columns: `['country', 'continent', 'year', 'lifeExp', 'pop', 'gdpPercap', 'iso_alpha', 'iso_num']`. gapminder) _get_datasetrr8/tmp/pip-install-l29rncou/plotly/plotly/data/__init__.pyrs rcCstdS)a Each row represents a restaurant bill. https://vincentarelbundock.github.io/Rdatasets/doc/reshape2/tips.html Returns: A `pandas.DataFrame` with 244 rows and the following columns: `['total_bill', 'tip', 'sex', 'smoker', 'day', 'time', 'size']`. tips)rrrrrrs rcCstdS)z Each row represents a flower. https://en.wikipedia.org/wiki/Iris_flower_data_set Returns: A `pandas.DataFrame` with 150 rows and the following columns: `['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species', 'species_id']`. iris)rrrrrr!s rcCstdS)z Each row represents a level of wind intensity in a cardinal direction, and its frequency. Returns: A `pandas.DataFrame` with 128 rows and the following columns: `['direction', 'strength', 'frequency']`. wind)rrrrrr.srcCstdS)a Each row represents voting results for an electoral district in the 2013 Montreal mayoral election. Returns: A `pandas.DataFrame` with 58 rows and the following columns: `['district', 'Coderre', 'Bergeron', 'Joly', 'total', 'winner', 'result', 'district_id']`. election)rrrrrr9s rc Csjddl}ddl}ddl}|j|j|jtddd}||d}|| d}WdQRX|S)a Each feature represents an electoral district in the 2013 Montreal mayoral election. Returns: A GeoJSON-formatted `dict` with 58 polygon or multi-polygon features whose `id` is an electoral district numerical ID and whose `district` property is the ID and district name. N package_datadatasetszelection.geojson.gzrzutf-8) gzipjsonospathjoindirname__file__GzipFileloadsreaddecode)r rrrfresultrrrelection_geojsonEs rcCstdS)a Each row represents the availability of car-sharing services near the centroid of a zone in Montreal over a month-long period. Returns: A `pandas.DataFrame` with 249 rows and the following columns: `['centroid_lat', 'centroid_lon', 'car_hours', 'peak_hour']`. carshare)rrrrrr]s rFcCs"td}|r|d}d|j_|S)aQ Each row in this wide dataset represents closing prices from 6 tech stocks in 2018/2019. Returns: A `pandas.DataFrame` with 100 rows and the following columns: `['date', 'GOOG', 'AAPL', 'AMZN', 'FB', 'NFLX', 'MSFT']`. If `indexed` is True, the 'date' column is used as the index and the column index is named 'company' stocksdateZcompany)r set_indexcolumnsname)indexeddfrrrris  rcCstd}|rd|j_|S)a Each row in this wide dataset represents the results of 100 simulated participants on three hypothetical experiments, along with their gender and control/treatment group. Returns: A `pandas.DataFrame` with 100 rows and the following columns: `['experiment_1', 'experiment_2', 'experiment_3', 'gender', 'group']`. If `indexed` is True, the data frame index is named "participant" experimentZ participant)rindexr )r!r"rrrr#zs r#cCs"td}|r|d}d|j_|S)aZ This dataset represents the medal table for Olympic Short Track Speed Skating for the top three nations as of 2020. Returns: A `pandas.DataFrame` with 3 rows and the following columns: `['nation', 'gold', 'silver', 'bronze']`. If `indexed` is True, the 'nation' column is used as the index and the column index is named 'medal' medalsnationmedal)rrrr )r!r"rrr medals_wides  r(cCs(tdjdgddd}|r$|d}|S)a' This dataset represents the medal table for Olympic Short Track Speed Skating for the top three nations as of 2020. Returns: A `pandas.DataFrame` with 9 rows and the following columns: `['nation', 'medal', 'count']`. If `indexed` is True, the 'nation' column is used as the index. r%r&countr')Zid_varsZ value_namevar_name)rZmeltr)r!r"rrr medals_longs  r+c Cs<ddl}ddl}||j|j|jtdd|dS)Nr r r z.csv.gz)pandasrZread_csvrrrr)dr,rrrrrsrN)F)F)F)F) __doc__rrrrrrrrr#r(r+rrrrrs