U Y{j@stdZdddZdddZddZd d Zd d Zd dZddZdddZdddZ dddZ d ddZ ddZ dS)!zE Built-in datasets for demonstration, educational and test purposes. FNc Cstd}|r||d|k}|r<|dtdd|d<|sR|jddgdd}|r~|jtd d d d d dddddd ddd|S)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']`. If `datetimes` is True, the 'year' column will be a datetime column If `centroids` is True, two new columns are added: ['centroid_lat', 'centroid_lon'] If `year` is an integer, the dataset will be filtered for that year gapminderyearz-01-01datetime64[ns] centroid_lat centroid_lon)axisZCountryZ ContinentZYearzLife ExpectancyzGDP per CapitaZ PopulationzISO Alpha Country CodezISO Numeric Country CodezCentroid LatitudezCentroid Longitude) ZcountryZ continentrZlifeExpZ gdpPercappopZ iso_alphaZiso_numrrcolumnsTZmapperrZinplace) _get_datasetastypestrZdroprenamedict) datetimesZ centroidsr pretty_namesdfrS/var/www/html/bwave/python/venv/lib/python3.8/site-packages/plotly/data/__init__.pyrs2 rc Cs2td}|r.|jtdddddddd d d d |S) 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']`.tipsz Total BillZTipz Payer GenderzSmokers at Tablez Day of WeekZMealz Party Size)Z total_billZtipZsexZsmokerdaytimesizer Tr )r rr)rrrrrr/s   rcCstdS)a 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']`.irisr rrrrrKs 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']`.windrrrrrrWsrcCstdS)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']`.electionrrrrrrasrc Csjddl}ddl}ddl}|j|j|jtddd}||d}|| d}W5QRX|S)a0 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!r"r#r$fresultrrrelection_geojsonlsr.cCstdS)a! Each row represents the availability of car-sharing services near the centroid of a zone in Montreal over a month-long period. Returns: A `pandas.DataFrame` with 249 rows and the following columns: `['centroid_lat', 'centroid_lon', 'car_hours', 'peak_hour']`.carsharerrrrrr/sr/cCs8td}|r|dd|d<|r4|d}d|j_|S)a Each row in this wide dataset represents closing prices from 6 tech stocks in 2018/2019. Returns: A `pandas.DataFrame` with 100 rows and the following columns: `['date', 'GOOG', 'AAPL', 'AMZN', 'FB', 'NFLX', 'MSFT']`. If `indexed` is True, the 'date' column is used as the index and the column index If `datetimes` is True, the 'date' column will be a datetime column is named 'company'stocksdaterZcompany)r r set_indexr name)indexedrrrrrr0s  r0cCstd}|rd|j_|S)a Each row in this wide dataset represents the results of 100 simulated participants on three hypothetical experiments, along with their gender and control/treatment group. Returns: A `pandas.DataFrame` with 100 rows and the following columns: `['experiment_1', 'experiment_2', 'experiment_3', 'gender', 'group']`. If `indexed` is True, the data frame index is named "participant" experimentZ participant)r indexr3r4rrrrr5s r5cCs"td}|r|d}d|j_|S)au This dataset represents the medal table for Olympic Short Track Speed Skating for the top three nations as of 2020. Returns: A `pandas.DataFrame` with 3 rows and the following columns: `['nation', 'gold', 'silver', 'bronze']`. If `indexed` is True, the 'nation' column is used as the index and the column index is named 'medal'medalsnationmedal)r r2r r3r7rrr medals_wides  r;cCs(tdjdgddd}|r$|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.r8r9countr:)Zid_varsZ value_namevar_name)r Zmeltr2r7rrr medals_longs  r>c Cs<ddl}ddl}||j|j|jtdd|dS)Nrrrz.csv.gz)pandasr#Zread_csvr$r%r&r')dr?r#rrrr sr )FFNF)F)FF)F)F)F) __doc__rrrrrr.r/r0r5r;r>r rrrrs )