g\dZddZddZdZdZdZdZdZdd Zdd Z dd Z dd Z d Z y)zE Built-in datasets for demonstration, educational and test purposes. Nctd}|r ||d|k(}|r-|djtdzjd|d<|s|jddgd}|r'|j t d d d d d ddddd dd|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)axisCountry ContinentYearzLife ExpectancyzGDP per Capita PopulationzISO Alpha Country CodezISO Numeric Country CodezCentroid LatitudezCentroid Longitude) country continentrlifeExp gdpPercappop iso_alphaiso_numrrcolumnsTmapperr inplace) _get_datasetastypestrdroprenamedict) datetimes centroidsr pretty_namesdfs Q/var/www/dash_apps/app1/venv/lib/python3.12/site-packages/plotly/data/__init__.pyrrs k "B 6 d" #j'',x7??@PQ6  WWnn5AW > !%)* 2201   Ic htd}|r$|jtddddddd d d |S) a Each row represents a restaurant bill. https://vincentarelbundock.github.io/Rdatasets/doc/reshape2/tips.html Returns: A `pandas.DataFrame` with 244 rows and the following columns: `['total_bill', 'tip', 'sex', 'smoker', 'day', 'time', 'size']`.tipsz Total BillTipz Payer GenderzSmokers at Tablez Day of WeekMealz Party Size) total_billtipsexsmokerdaytimesizerTr)rrr)r!r"s r#r&r&/sN f B '")!!   Ir$ctdS)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']`.irisrr$r#r1r1Ks  r$ctdS)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']`.windr2r3r$r#r5r5Ws  r$ctdS)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']`.electionr2r3r$r#r7r7a  ##r$crddl}ddl}ddl}|jj |jj |jj t ddd}|j|d5}|j|jjd}ddd|S#1swYSxYw)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@rAfresults r#election_geojsonrKls 77<< 12  D tS !6QAFFHOOG456 M6 Ms 3/B,,B6ctdS)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']`.carsharer2r3r$r#rMrMr8r$ctd}|r|djd|d<|r"|jd}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'stocksdatercompany)rr set_indexrname)indexedrr"s r#rOrOsK h BZ&&'786  \\& !#  Ir$cBtd}|rd|j_|S)a Each row in this wide dataset represents the results of 100 simulated participants on three hypothetical experiments, along with their gender and control/treatment group. Returns: A `pandas.DataFrame` with 100 rows and the following columns: `['experiment_1', 'experiment_2', 'experiment_3', 'gender', 'group']`. If `indexed` is True, the data frame index is named "participant" experiment participant)rindexrSrTr"s r#rVrVs! l #B% Ir$cdtd}|r"|jd}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)rrRrrSrYs r# medals_wider^s/ h B \\( #!  Ir$chtdjdgdd}|r|jd}|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])id_vars value_namevar_name)rmeltrRrYs r# medals_longres? h  $ $ w % B \\( # Ir$c ddl}ddl}|j|jj |jj |jj t dd|dzS)Nr:r;r<z.csv.gz)pandasr@read_csvrArBrCrD)drgr@s r#rrsS ??  GGOOBGGOOH5 6   M   r$)FFNF)F)FF) __doc__rr&r1r5r7rKrMrOrVr^rerr3r$r#rksG &R8   $.$&  "" r$