inspectpd 0.2.0__py3-none-any.whl

inspectpd/__init__.py

@@ -0,0 +1,71 @@
+"""inspectpd: inspection, comparison and visualisation of pandas data frames.
+
+Importing this package monkey-patches a family of ``inspect_*`` methods onto
+pandas objects. Two small example datasets (``starwars`` and ``tdf``) are
+exposed as lazily loaded module attributes.
+"""
+
+from functools import cache
+from importlib.resources import files
+
+from pandas import read_csv
+from pandas.core.base import PandasObject
+
+from .inspect.inspect_cat import inspect_cat
+from .inspect.inspect_cor import inspect_cor
+from .inspect.inspect_imb import inspect_imb
+from .inspect.inspect_mem import inspect_mem
+from .inspect.inspect_na import inspect_na
+from .inspect.inspect_num import inspect_num
+from .inspect.inspect_types import inspect_types
+
+__all__ = [
+    "inspect_cat",
+    "inspect_cor",
+    "inspect_imb",
+    "inspect_mem",
+    "inspect_na",
+    "inspect_num",
+    "inspect_types",
+    "load_dataset",
+    "starwars",
+    "tdf",
+]
+
+# monkey-patch the inspect_* functions as methods on pandas objects
+PandasObject.inspect_imb = inspect_imb
+PandasObject.inspect_na = inspect_na
+PandasObject.inspect_types = inspect_types
+PandasObject.inspect_mem = inspect_mem
+PandasObject.inspect_cat = inspect_cat
+PandasObject.inspect_cor = inspect_cor
+PandasObject.inspect_num = inspect_num
+
+
+# read_csv kwargs for each bundled example dataset
+_DATASETS = {
+    "starwars": {"index_col": 0},
+    "tdf": {},
+}
+
+
+@cache
+def load_dataset(name):
+    """Load a bundled example dataset by name (``"starwars"`` or ``"tdf"``)."""
+    if name not in _DATASETS:
+        valid = ", ".join(sorted(_DATASETS))
+        raise ValueError(f"unknown dataset {name!r}; choose from: {valid}")
+    resource = files("inspectpd").joinpath("data", f"{name}.csv")
+    with resource.open("rb") as handle:
+        return read_csv(handle, **_DATASETS[name])
+
+
+def __getattr__(name):
+    """Lazily expose example datasets as module attributes (PEP 562)."""
+    if name in _DATASETS:
+        return load_dataset(name)
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+
+def __dir__():
+    return sorted(set(globals()) | set(_DATASETS))

inspectpd/data/starwars.csv

@@ -0,0 +1,88 @@
+"","name","height","mass","hair_color","skin_color","eye_color","birth_year","gender","homeworld","species"
+"1","Luke Skywalker",172,77,"blond","fair","blue",19,"male","Tatooine","Human"
+"2","C-3PO",167,75,NA,"gold","yellow",112,NA,"Tatooine","Droid"
+"3","R2-D2",96,32,NA,"white, blue","red",33,NA,"Naboo","Droid"
+"4","Darth Vader",202,136,"none","white","yellow",41.9,"male","Tatooine","Human"
+"5","Leia Organa",150,49,"brown","light","brown",19,"female","Alderaan","Human"
+"6","Owen Lars",178,120,"brown, grey","light","blue",52,"male","Tatooine","Human"
+"7","Beru Whitesun lars",165,75,"brown","light","blue",47,"female","Tatooine","Human"
+"8","R5-D4",97,32,NA,"white, red","red",NA,NA,"Tatooine","Droid"
+"9","Biggs Darklighter",183,84,"black","light","brown",24,"male","Tatooine","Human"
+"10","Obi-Wan Kenobi",182,77,"auburn, white","fair","blue-gray",57,"male","Stewjon","Human"
+"11","Anakin Skywalker",188,84,"blond","fair","blue",41.9,"male","Tatooine","Human"
+"12","Wilhuff Tarkin",180,NA,"auburn, grey","fair","blue",64,"male","Eriadu","Human"
+"13","Chewbacca",228,112,"brown","unknown","blue",200,"male","Kashyyyk","Wookiee"
+"14","Han Solo",180,80,"brown","fair","brown",29,"male","Corellia","Human"
+"15","Greedo",173,74,NA,"green","black",44,"male","Rodia","Rodian"
+"16","Jabba Desilijic Tiure",175,1358,NA,"green-tan, brown","orange",600,"hermaphrodite","Nal Hutta","Hutt"
+"17","Wedge Antilles",170,77,"brown","fair","hazel",21,"male","Corellia","Human"
+"18","Jek Tono Porkins",180,110,"brown","fair","blue",NA,"male","Bestine IV","Human"
+"19","Yoda",66,17,"white","green","brown",896,"male",NA,"Yoda's species"
+"20","Palpatine",170,75,"grey","pale","yellow",82,"male","Naboo","Human"
+"21","Boba Fett",183,78.2,"black","fair","brown",31.5,"male","Kamino","Human"
+"22","IG-88",200,140,"none","metal","red",15,"none",NA,"Droid"
+"23","Bossk",190,113,"none","green","red",53,"male","Trandosha","Trandoshan"
+"24","Lando Calrissian",177,79,"black","dark","brown",31,"male","Socorro","Human"
+"25","Lobot",175,79,"none","light","blue",37,"male","Bespin","Human"
+"26","Ackbar",180,83,"none","brown mottle","orange",41,"male","Mon Cala","Mon Calamari"
+"27","Mon Mothma",150,NA,"auburn","fair","blue",48,"female","Chandrila","Human"
+"28","Arvel Crynyd",NA,NA,"brown","fair","brown",NA,"male",NA,"Human"
+"29","Wicket Systri Warrick",88,20,"brown","brown","brown",8,"male","Endor","Ewok"
+"30","Nien Nunb",160,68,"none","grey","black",NA,"male","Sullust","Sullustan"
+"31","Qui-Gon Jinn",193,89,"brown","fair","blue",92,"male",NA,"Human"
+"32","Nute Gunray",191,90,"none","mottled green","red",NA,"male","Cato Neimoidia","Neimodian"
+"33","Finis Valorum",170,NA,"blond","fair","blue",91,"male","Coruscant","Human"
+"34","Jar Jar Binks",196,66,"none","orange","orange",52,"male","Naboo","Gungan"
+"35","Roos Tarpals",224,82,"none","grey","orange",NA,"male","Naboo","Gungan"
+"36","Rugor Nass",206,NA,"none","green","orange",NA,"male","Naboo","Gungan"
+"37","Ric Olié",183,NA,"brown","fair","blue",NA,"male","Naboo",NA
+"38","Watto",137,NA,"black","blue, grey","yellow",NA,"male","Toydaria","Toydarian"
+"39","Sebulba",112,40,"none","grey, red","orange",NA,"male","Malastare","Dug"
+"40","Quarsh Panaka",183,NA,"black","dark","brown",62,"male","Naboo",NA
+"41","Shmi Skywalker",163,NA,"black","fair","brown",72,"female","Tatooine","Human"
+"42","Darth Maul",175,80,"none","red","yellow",54,"male","Dathomir","Zabrak"
+"43","Bib Fortuna",180,NA,"none","pale","pink",NA,"male","Ryloth","Twi'lek"
+"44","Ayla Secura",178,55,"none","blue","hazel",48,"female","Ryloth","Twi'lek"
+"45","Dud Bolt",94,45,"none","blue, grey","yellow",NA,"male","Vulpter","Vulptereen"
+"46","Gasgano",122,NA,"none","white, blue","black",NA,"male","Troiken","Xexto"
+"47","Ben Quadinaros",163,65,"none","grey, green, yellow","orange",NA,"male","Tund","Toong"
+"48","Mace Windu",188,84,"none","dark","brown",72,"male","Haruun Kal","Human"
+"49","Ki-Adi-Mundi",198,82,"white","pale","yellow",92,"male","Cerea","Cerean"
+"50","Kit Fisto",196,87,"none","green","black",NA,"male","Glee Anselm","Nautolan"
+"51","Eeth Koth",171,NA,"black","brown","brown",NA,"male","Iridonia","Zabrak"
+"52","Adi Gallia",184,50,"none","dark","blue",NA,"female","Coruscant","Tholothian"
+"53","Saesee Tiin",188,NA,"none","pale","orange",NA,"male","Iktotch","Iktotchi"
+"54","Yarael Poof",264,NA,"none","white","yellow",NA,"male","Quermia","Quermian"
+"55","Plo Koon",188,80,"none","orange","black",22,"male","Dorin","Kel Dor"
+"56","Mas Amedda",196,NA,"none","blue","blue",NA,"male","Champala","Chagrian"
+"57","Gregar Typho",185,85,"black","dark","brown",NA,"male","Naboo","Human"
+"58","Cordé",157,NA,"brown","light","brown",NA,"female","Naboo","Human"
+"59","Cliegg Lars",183,NA,"brown","fair","blue",82,"male","Tatooine","Human"
+"60","Poggle the Lesser",183,80,"none","green","yellow",NA,"male","Geonosis","Geonosian"
+"61","Luminara Unduli",170,56.2,"black","yellow","blue",58,"female","Mirial","Mirialan"
+"62","Barriss Offee",166,50,"black","yellow","blue",40,"female","Mirial","Mirialan"
+"63","Dormé",165,NA,"brown","light","brown",NA,"female","Naboo","Human"
+"64","Dooku",193,80,"white","fair","brown",102,"male","Serenno","Human"
+"65","Bail Prestor Organa",191,NA,"black","tan","brown",67,"male","Alderaan","Human"
+"66","Jango Fett",183,79,"black","tan","brown",66,"male","Concord Dawn","Human"
+"67","Zam Wesell",168,55,"blonde","fair, green, yellow","yellow",NA,"female","Zolan","Clawdite"
+"68","Dexter Jettster",198,102,"none","brown","yellow",NA,"male","Ojom","Besalisk"
+"69","Lama Su",229,88,"none","grey","black",NA,"male","Kamino","Kaminoan"
+"70","Taun We",213,NA,"none","grey","black",NA,"female","Kamino","Kaminoan"
+"71","Jocasta Nu",167,NA,"white","fair","blue",NA,"female","Coruscant","Human"
+"72","Ratts Tyerell",79,15,"none","grey, blue","unknown",NA,"male","Aleen Minor","Aleena"
+"73","R4-P17",96,NA,"none","silver, red","red, blue",NA,"female",NA,NA
+"74","Wat Tambor",193,48,"none","green, grey","unknown",NA,"male","Skako","Skakoan"
+"75","San Hill",191,NA,"none","grey","gold",NA,"male","Muunilinst","Muun"
+"76","Shaak Ti",178,57,"none","red, blue, white","black",NA,"female","Shili","Togruta"
+"77","Grievous",216,159,"none","brown, white","green, yellow",NA,"male","Kalee","Kaleesh"
+"78","Tarfful",234,136,"brown","brown","blue",NA,"male","Kashyyyk","Wookiee"
+"79","Raymus Antilles",188,79,"brown","light","brown",NA,"male","Alderaan","Human"
+"80","Sly Moore",178,48,"none","pale","white",NA,"female","Umbara",NA
+"81","Tion Medon",206,80,"none","grey","black",NA,"male","Utapau","Pau'an"
+"82","Finn",NA,NA,"black","dark","dark",NA,"male",NA,"Human"
+"83","Rey",NA,NA,"brown","light","hazel",NA,"female",NA,"Human"
+"84","Poe Dameron",NA,NA,"brown","light","brown",NA,"male",NA,"Human"
+"85","BB8",NA,NA,"none","none","black",NA,"none",NA,"Droid"
+"86","Captain Phasma",NA,NA,"unknown","unknown","unknown",NA,"female",NA,NA
+"87","Padmé Amidala",165,45,"brown","light","brown",46,"female","Naboo","Human"

inspectpd/data/tdf.csv

@@ -0,0 +1,111 @@
+edition,start_date,winner_name,winner_team,distance,time_overall,time_margin,stage_wins,stages_led,height,weight,age,born,died,full_name,nickname,birth_town,birth_country,nationality
+1,1903-07-01,Maurice Garin,La Française,2428,94.55388888888889,2.9891666666666667,3,6,1.62,60,32,1871-03-03,1957-02-19,NA,The Little Chimney-sweep,Arvier,Italy, France
+2,1904-07-02,Henri Cornet,Conte,2428,96.09861111111111,2.2705555555555557,1,3,NA,NA,19,1884-08-04,1941-03-18,NA,Le rigolo (The joker),Desvres,France, France
+3,1905-07-09,Louis Trousselier,Peugeot–Wolber,2994,NA,NA,5,10,NA,NA,24,1881-06-29,1939-04-24,NA,Levaloy / Trou-trou,Paris,France, France
+4,1906-07-04,René Pottier,Peugeot–Wolber,4637,NA,NA,5,12,NA,NA,27,1879-06-05,1907-01-25,NA,NA,Moret-sur-Loing,France, France
+5,1907-07-08,Lucien Petit-Breton,Peugeot–Wolber,4488,NA,NA,2,5,NA,NA,24,1882-10-18,1917-12-20,Lucien Georges Mazan,Lucien Petit-Breton,Plessé,France, France
+6,1908-07-13,Lucien Petit-Breton,Peugeot–Wolber,4497,NA,NA,5,13,NA,NA,25,1882-10-18,1917-12-20,Lucien Georges Mazan,Lucien Petit-Breton,Plessé,France, France
+7,1909-07-05,François Faber,Alcyon–Dunlop,4498,NA,NA,6,13,1.78,88,22,1887-01-26,1915-05-09,NA,The giant of colombes,Aulnay-sur-Iton,France, Luxembourg
+8,1910-07-01,Octave Lapize,Alcyon–Dunlop,4734,NA,NA,4,3,NA,NA,22,1887-10-24,1917-07-14,NA,NA,Paris,France, France
+9,1911-07-02,Gustave Garrigou,Alcyon–Dunlop,5343,NA,NA,2,13,NA,NA,26,1884-09-24,1963-01-28,Cyprien Gustave Garrigou,NA,Vabres,France, France
+10,1912-06-30,Odile Defraye,Alcyon–Dunlop,5289,NA,NA,3,13,NA,NA,23,1888-07-14,1965-08-21,NA,NA,Rumbeke,Belgium, Belgium
+11,1913-06-29,Philippe Thys,Peugeot–Wolber,5287,197.9,0.13555555555555554,1,8,NA,NA,23,1889-10-08,1971-01-16,NA,Le basset (The Basset Hound),Anderlecht,Belgium, Belgium
+12,1914-06-28,Philippe Thys,Peugeot–Wolber,5380,200.48,0.016944444444444443,1,15,NA,NA,24,1889-10-08,1971-01-16,NA,Le basset (The Basset Hound),Anderlecht,Belgium, Belgium
+13,1919-06-29,Firmin Lambot,La Sportive,5560,231.12083333333334,1.7149999999999999,1,2,NA,NA,33,1886-03-14,1964-01-19,NA,NA,Florennes,Belgium, Belgium
+14,1920-06-27,Philippe Thys,La Sportive,5503,228.6036111111111,0.9658333333333333,4,14,NA,NA,30,1889-10-08,1971-01-16,NA,Le basset (The Basset Hound),Anderlecht,Belgium, Belgium
+15,1921-06-26,Léon Scieur,La Sportive,5485,221.84055555555557,0.305,2,14,NA,NA,33,1888-03-18,1969-10-07,NA,NA,Florennes,Belgium, Belgium
+16,1922-06-25,Firmin Lambot,Peugeot–Wolber,5375,222.135,0.6947222222222222,0,3,NA,NA,36,1886-03-14,1964-01-19,NA,NA,Florennes,Belgium, Belgium
+17,1923-06-24,Henri Pélissier,Automoto–Hutchinson,5386,222.25833333333333,0.5083333333333333,3,6,NA,NA,34,1889-01-22,1935-05-01,NA,NA,Paris,France, France
+18,1924-06-22,Ottavio Bottecchia,Automoto,5425,226.30583333333334,0.5930555555555556,4,15,NA,NA,29,1894-08-01,1927-06-15,NA,NA,San Martino di Colle Umberto,Italy, Italy
+19,1925-06-21,Ottavio Bottecchia,Automoto–Hutchinson,5440,219.17166666666665,0.915,4,13,NA,NA,30,1894-08-01,1927-06-15,NA,NA,San Martino di Colle Umberto,Italy, Italy
+20,1926-06-20,Lucien Buysse,Automoto–Hutchinson,5745,238.74027777777778,1.3736111111111111,2,8,NA,NA,33,1892-09-11,1980-01-03,NA,NA,Wontergem,Belgium, Belgium
+21,1927-06-19,Nicolas Frantz,Alcyon–Dunlop,5398,198.27833333333334,1.811388888888889,3,14,NA,NA,27,1899-11-04,1985-11-08,NA,NA,Mamer,Luxembourg, Luxembourg
+22,1928-06-17,Nicolas Frantz,Alcyon–Dunlop,5476,192.81611111111113,0.8472222222222222,5,22,NA,NA,28,1899-11-04,1985-11-08,NA,NA,Mamer,Luxembourg, Luxembourg
+23,1929-06-30,Maurice De Waele,Alcyon–Dunlop,5286,186.65416666666667,0.7455555555555555,1,16,NA,NA,32,1896-12-27,1952-02-14,NA,NA,Lovendegem,Belgium, Belgium
+24,1930-07-02,André Leducq,Alcyon–Dunlop,4822,172.20444444444442,0.23722222222222222,2,13,NA,NA,26,1904-02-27,1980-06-18,NA,NA,Saint-Ouen,France, France
+25,1931-06-30,Antonin Magne,France,5091,177.1675,0.20333333333333334,1,16,NA,NA,27,1904-01-15,1983-09-08,NA,NA,Ytrac,France, France
+26,1932-07-06,André Leducq,France,4479,154.19694444444445,0.4066666666666667,6,19,NA,NA,28,1904-02-27,1980-06-18,NA,NA,Saint-Ouen,France, France
+27,1933-06-27,Georges Speicher,France,4395,147.86027777777778,0.06777777777777777,3,12,NA,NA,26,1907-06-08,1978-01-24,NA,NA,Paris,France, France
+28,1934-07-03,Antonin Magne,France,4470,147.23277777777778,0.4575,3,22,NA,NA,30,1904-01-15,1983-09-08,NA,NA,Ytrac,France, France
+29,1935-07-04,Romain Maes,Belgium,4338,141.38333333333333,0.28805555555555556,3,21,NA,NA,22,1912-08-10,1983-02-22,NA,NA,Zerkegem,Belgium, Belgium
+30,1936-07-07,Sylvère Maes,Belgium,4442,142.79222222222222,0.4405555555555556,4,14,NA,NA,26,1909-08-27,1966-12-05,NA,NA,Zevekote,Belgium, Belgium
+31,1937-06-30,Roger Lapébie,France,4415,138.9752777777778,0.11861111111111111,3,4,NA,NA,26,1911-01-16,1996-10-12,NA,NA,Bayonne,France, France
+32,1938-07-05,Gino Bartali,Italy,4694,148.48666666666665,0.305,2,8,1.72,66,23,1914-07-18,2000-05-05,NA,"Gino the Pious, Ginettaccio, L'uomo di ferro, L'intramontabile",Ponte e Ema,Italy, Italy
+33,1939-07-10,Sylvère Maes,Belgium,4224,132.05472222222224,0.5083333333333333,2,8,NA,NA,29,1909-08-27,1966-12-05,NA,NA,Zevekote,Belgium, Belgium
+34,1947-06-25,Jean Robic,France,4642,148.1902777777778,0.050833333333333335,3,1,1.61,60,26,1921-06-10,1980-10-06,NA,"Biquet (Kid goat), Tête de cuir (Leather-head), Le farfadet de la lande Bretonne,
+Gueule cassée",Vouziers,France, France
+35,1948-06-30,Gino Bartali,Italy,4922,147.17666666666665,0.4405555555555556,7,9,1.72,66,33,1914-07-18,2000-05-05,NA,"Gino the Pious, Ginettaccio, L'uomo di ferro, L'intramontabile",Ponte e Ema,Italy, Italy
+36,1949-06-30,Fausto Coppi,Italy,4808,149.68027777777777,0.16944444444444443,3,5,1.77,68,29,1919-09-15,1960-01-02,Angelo Fausto Coppi,"The Heron,Il Campionissimo
+(Champion of Champions)",Castellania,Italy, Italy
+37,1950-07-13,Ferdinand Kübler,Switzerland,4773,145.61555555555555,0.1525,3,11,NA,NA,30,1919-07-24,2016-12-29,NA,"Ferdi, The Cowboy, The Eagle of Adliswil, Mr 100,000 Volts[",Marthalen,Switzerland,  Switzerland
+38,1951-07-04,Hugo Koblet,Switzerland,4690,142.33722222222224,0.37277777777777776,5,11,NA,NA,26,1925-03-21,1964-11-06,NA,"Beautiful Hugo, Le pédaleur de charme",Zürich,Switzerland,  Switzerland
+39,1950-06-25,Fausto Coppi,Italy,4898,151.95555555555555,0.47444444444444445,5,14,1.77,68,30,1919-09-15,1960-01-02,Angelo Fausto Coppi,"The Heron,Il Campionissimo
+(Champion of Champions)",Castellania,Italy, Italy
+40,1951-07-03,Louison Bobet,France,4476,129.39027777777778,0.23722222222222222,2,5,1.79,75,26,1925-03-12,1983-03-13,NA,"Louison, Zonzon",Saint-Méen-le-Grand,France, France
+41,1954-07-08,Louison Bobet,France,4656,140.1013888888889,0.25416666666666665,3,14,1.79,75,29,1925-03-12,1983-03-13,NA,"Louison, Zonzon",Saint-Méen-le-Grand,France, France
+42,1955-07-07,Louison Bobet,France,4495,130.49055555555555,0.06777777777777777,2,6,1.79,75,30,1925-03-12,1983-03-13,NA,"Louison, Zonzon",Saint-Méen-le-Grand,France, France
+43,1956-07-05,Roger Walkowiak,France,4498,124.02111111111111,0.016944444444444443,0,8,NA,NA,29,1927-03-02,2017-02-06,NA,Walko,Montluçon,France, France
+44,1957-06-27,Jacques Anquetil,France,4669,135.74499999999998,0.23722222222222222,4,15,1.76,70,23,1934-01-08,1987-11-18,NA,"Monsieur Chrono, Maître Jacques",Mont-Saint-Aignan,France, France
+45,1958-06-26,Charly Gaul,Luxembourg,4319,116.98472222222222,0.050833333333333335,4,2,1.73,64,25,1932-12-08,2005-12-06,NA,Angel of the Mountains,Pfaffenthal,Luxembourg, Luxembourg
+46,1959-06-25,Federico Bahamontes,Spain,4358,123.77916666666667,0.06777777777777777,1,6,NA,NA,30,1928-07-09,NA,Alejandro Martín Bahamontes,The Eagle of Toledo,Santo Domingo-Caudilla,Spain, Spain
+47,1960-06-26,Gastone Nencini,Italy,4173,112.14500000000001,0.08472222222222221,0,14,NA,NA,30,1930-03-01,1980-02-01,NA,"Il Leone del Mugello, Faccia di fatica (Fatigue-face)",Barberino di Mugello,Italy, Italy
+48,1961-06-25,Jacques Anquetil,France,4397,122.02583333333334,0.20333333333333334,2,21,1.76,70,27,1934-01-08,1987-11-18,NA,"Monsieur Chrono, Maître Jacques",Mont-Saint-Aignan,France, France
+49,1962-06-24,Jacques Anquetil,Saint-Raphaël–Helyett–Hutchinson,4274,114.53166666666667,0.06777777777777777,2,3,1.76,70,28,1934-01-08,1987-11-18,NA,"Monsieur Chrono, Maître Jacques",Mont-Saint-Aignan,France, France
+50,1963-06-23,Jacques Anquetil,Saint-Raphaël–Gitane–R. Geminiani,4138,113.50138888888888,0.050833333333333335,4,5,1.76,70,29,1934-01-08,1987-11-18,NA,"Monsieur Chrono, Maître Jacques",Mont-Saint-Aignan,France, France
+51,1964-06-22,Jacques Anquetil,Saint-Raphaël–Gitane–Dunlop,4504,127.16222222222223,0.015277777777777777,4,6,1.76,70,30,1934-01-08,1987-11-18,NA,"Monsieur Chrono, Maître Jacques",Mont-Saint-Aignan,France, France
+52,1965-06-22,Felice Gimondi,Salvarani,4188,116.70166666666667,0.033888888888888885,3,18,1.81,71,22,1942-09-29,2019-08-16,NA,The Phoenix,Sedrina,Italy, Italy
+53,1966-06-21,Lucien Aimar,Ford France–Hutchinson,4329,117.57249999999999,0.016944444444444443,0,6,NA,NA,25,1941-04-28,NA,NA,NA,Hyères,France, France
+54,1967-06-29,Roger Pingeon,Peugeot–BP–Michelin,4779,136.8972222222222,0.050833333333333335,1,17,1.82,72,26,1940-08-28,2017-03-19,NA,"Le grand échassier, Le plombier-zingueur",Hauteville-Lompnes,France, France
+55,1968-06-27,Jan Janssen,Pelforth–Sauvage–Lejeune,4492,133.82833333333332,0.010555555555555556,2,1,NA,NA,28,1940-05-19,NA,Johannes Adrianus Janssen,NA,Nootdorp,Netherlands, Netherlands
+56,1969-06-28,Eddy Merckx,Faema,4117,116.26722222222222,0.28805555555555556,6,18,1.82,74,24,1945-06-17,NA,Édouard Louis Joseph Merckx,The Cannibal,Meensel-Kiezegem,Belgium, Belgium
+57,1970-06-27,Eddy Merckx,Faemino–Faema,4254,119.53027777777778,0.20333333333333334,8,20,1.82,74,25,1945-06-17,NA,Édouard Louis Joseph Merckx,The Cannibal,Meensel-Kiezegem,Belgium, Belgium
+58,1971-06-26,Eddy Merckx,Molteni,3608,96.7538888888889,0.1525,4,17,1.82,74,26,1945-06-17,NA,Édouard Louis Joseph Merckx,The Cannibal,Meensel-Kiezegem,Belgium, Belgium
+59,1972-07-01,Eddy Merckx,Molteni,3846,108.28833333333333,0.16944444444444443,6,15,1.82,74,27,1945-06-17,NA,Édouard Louis Joseph Merckx,The Cannibal,Meensel-Kiezegem,Belgium, Belgium
+60,1973-06-30,Luis Ocaña,Bic,4090,122.42611111111111,0.25416666666666665,6,14,1.65,52,28,1945-06-09,1994-06-19,Jesús Luis Ocaña Pernía,NA,Priego,Spain, Spain
+61,1974-06-27,Eddy Merckx,Molteni,4098,116.28277777777778,0.13555555555555554,8,18,1.82,74,29,1945-06-17,NA,Édouard Louis Joseph Merckx,The Cannibal,Meensel-Kiezegem,Belgium, Belgium
+62,1975-06-26,Bernard Thévenet,Peugeot–BP–Michelin,4000,114.59194444444444,0.033888888888888885,2,8,NA,NA,27,1948-01-10,NA,NA,Nanard,Saint-Julien-de-Civry,France, France
+63,1976-06-24,Lucien Van Impe,Gitane–Campagnolo,4017,116.37305555555555,0.06777777777777777,1,12,NA,58,29,1946-10-20,NA,NA,de kleine van Mere,Mere,Belgium, Belgium
+64,1977-06-30,Bernard Thévenet,Peugeot–Esso–Michelin,4096,115.64166666666668,0.013333333333333334,1,8,NA,NA,29,1948-01-10,NA,NA,Nanard,Saint-Julien-de-Civry,France, France
+65,1978-06-29,Bernard Hinault,Renault–Gitane–Campagnolo,3908,108.3,0.050833333333333335,3,3,1.74,62,23,1954-11-14,NA,NA,"Le Blaireau (The Badger), Le Patron (The Boss)",Yffiniac,France, France
+66,1979-06-27,Bernard Hinault,Renault–Gitane,3765,103.11388888888888,0.2202777777777778,7,17,1.74,62,24,1954-11-14,NA,NA,"Le Blaireau (The Badger), Le Patron (The Boss)",Yffiniac,France, France
+67,1980-06-26,Joop Zoetemelk,TI–Raleigh–Creda,3842,109.32055555555556,0.10166666666666667,2,10,1.73,68,33,1946-12-03,NA,Hendrik Gerardus Joseph Zoetemelk,Joop,The Hague,Netherlands, Netherlands
+68,1981-06-25,Bernard Hinault,Renault–Elf–Gitane,3753,96.32722222222222,0.23722222222222222,5,18,1.74,62,26,1954-11-14,NA,NA,"Le Blaireau (The Badger), Le Patron (The Boss)",Yffiniac,France, France
+69,1982-07-02,Bernard Hinault,Renault–Elf–Gitane,3507,92.14611111111111,0.10166666666666667,4,12,1.74,62,27,1954-11-14,NA,NA,"Le Blaireau (The Badger), Le Patron (The Boss)",Yffiniac,France, France
+70,1983-07-01,Laurent Fignon,Renault–Elf,3809,105.13111111111111,0.06777777777777777,1,6,1.74,67,22,1960-08-12,2010-08-31,Laurent Patrick Fignon,Le Professeur (The Professor),Paris,France, France
+71,1984-06-29,Laurent Fignon,Renault–Elf,4021,112.0611111111111,0.16944444444444443,5,7,1.74,67,23,1960-08-12,2010-08-31,Laurent Patrick Fignon,Le Professeur (The Professor),Paris,France, France
+72,1985-06-28,Bernard Hinault,La Vie Claire,4109,113.4063888888889,0.016944444444444443,2,16,1.74,62,30,1954-11-14,NA,NA,"Le Blaireau (The Badger), Le Patron (The Boss)",Yffiniac,France, France
+73,1986-07-04,Greg LeMond,La Vie Claire,4094,110.5886111111111,0.050833333333333335,1,7,1.78,67,25,1961-06-26,NA,Gregory James LeMond,"L’Americain, LeMonster",Lakewood,USA, United States
+74,1987-07-01,Stephen Roche,Carrera Jeans–Vagabond,4231,115.46166666666667,0.011111111111111112,1,3,1.75,74,27,1959-11-28,NA,NA,NA,Dundrum,Ireland, Ireland
+75,1988-07-02,Pedro Delgado,Reynolds,3286,84.46472222222222,0.11861111111111111,1,11,1.71,64,28,1960-04-15,NA,Pedro Delgado Robledo,Perico,Segovia,Spain, Spain
+76,1989-07-01,Greg LeMond,AD Renting–W-Cup–Bottecchia,3285,87.64305555555556,0.0022222222222222222,3,8,1.78,67,28,1961-06-26,NA,Gregory James LeMond,"L’Americain, LeMonster",Lakewood,USA, United States
+77,1990-06-30,Greg LeMond,Z–Tomasso,3504,90.72222222222223,0.033888888888888885,0,2,1.78,67,29,1961-06-26,NA,Gregory James LeMond,"L’Americain, LeMonster",Lakewood,USA, United States
+78,1991-07-06,Miguel Induráin,Banesto,3914,101.02222222222223,0.050833333333333335,2,10,1.86,80,26,1964-07-16,NA,Miguel Induráin Larraya,"Miguelón, Big Mig (English)",Villava,Spain, Spain
+79,1992-07-04,Miguel Induráin,Banesto,3983,100.825,0.06777777777777777,3,10,1.86,80,27,1964-07-16,NA,Miguel Induráin Larraya,"Miguelón, Big Mig (English)",Villava,Spain, Spain
+80,1993-07-03,Miguel Induráin,Banesto,3714,95.9525,0.06777777777777777,2,14,1.86,80,28,1964-07-16,NA,Miguel Induráin Larraya,"Miguelón, Big Mig (English)",Villava,Spain, Spain
+81,1994-07-02,Miguel Induráin,Banesto,3978,103.6438888888889,0.08472222222222221,1,13,1.86,80,29,1964-07-16,NA,Miguel Induráin Larraya,"Miguelón, Big Mig (English)",Villava,Spain, Spain
+82,1995-07-01,Miguel Induráin,Banesto,3635,92.74972222222222,0.06777777777777777,2,13,1.86,80,30,1964-07-16,NA,Miguel Induráin Larraya,"Miguelón, Big Mig (English)",Villava,Spain, Spain
+83,1996-06-29,Bjarne Riis,Team Telekom,3765,95.95444444444445,0.016944444444444443,2,13,1.84,71,32,1964-04-03,NA,Bjarne Lykkegård Riis,"Ørnen fra Herning
+(The Eagle from Herning)",Herning,Denmark, Denmark
+84,1997-07-05,Jan Ullrich,Team Telekom,3950,100.50972222222222,0.1525,2,12,1.83,73,23,1973-12-02,NA,NA,"Der Kaiser, Der Jan, Der Junge, The Yoyo",Rostock,Germany, Germany
+85,1998-07-11,Marco Pantani,Mercatone Uno–Bianchi,3875,92.82944444444443,0.050833333333333335,2,7,1.72,57,28,1970-01-13,2004-02-14,NA,"Il Pirata (The pirate), Elefantino (The little elephant)",Cesena,Italy, Italy
+86,1999-07-03,Lance Armstrong,U.S. Postal Service,3687,91.53777777777778,0.11861111111111111,4,15,1.77,75,27,1971-09-18,NA,Lance Edward Armstrong,"Le Boss, Big Tex",Plano,USA, United States
+87,2000-07-01,Lance Armstrong,U.S. Postal Service,3662,92.55222222222221,0.10166666666666667,1,12,1.77,75,28,1971-09-18,NA,Lance Edward Armstrong,"Le Boss, Big Tex",Plano,USA, United States
+88,2001-07-07,Lance Armstrong,U.S. Postal Service,3458,86.2911111111111,0.10166666666666667,4,8,1.77,75,29,1971-09-18,NA,Lance Edward Armstrong,"Le Boss, Big Tex",Plano,USA, United States
+89,2002-07-06,Lance Armstrong,U.S. Postal Service,3272,82.08666666666666,0.11861111111111111,4,11,1.77,75,30,1971-09-18,NA,Lance Edward Armstrong,"Le Boss, Big Tex",Plano,USA, United States
+90,2003-07-05,Lance Armstrong,U.S. Postal Service,3427,83.68666666666667,0.016944444444444443,1,13,1.77,75,31,1971-09-18,NA,Lance Edward Armstrong,"Le Boss, Big Tex",Plano,USA, United States
+91,2004-07-03,Lance Armstrong,U.S. Postal Service,3391,83.60055555555554,0.10166666666666667,5,7,1.77,75,32,1971-09-18,NA,Lance Edward Armstrong,"Le Boss, Big Tex",Plano,USA, United States
+92,2005-07-02,Lance Armstrong,Discovery Channel,3593,86.25055555555555,0.06777777777777777,1,17,1.77,75,33,1971-09-18,NA,Lance Edward Armstrong,"Le Boss, Big Tex",Plano,USA, United States
+93,2006-07-01,Óscar Pereiro,Caisse d'Epargne–Illes Balears,3657,89.67416666666666,0.008888888888888889,0,8,1.77,68,28,1977-08-03,NA,Óscar Pereiro Sío,NA,Mos,Spain, Spain
+94,2007-07-07,Alberto Contador,Discovery Channel,3570,91.00722222222223,0.006388888888888889,1,4,1.76,62,24,1982-12-06,NA,Alberto Contador Velasco,El Pistolero,Pinto,Spain, Spain
+95,2008-07-05,Carlos Sastre,Team CSC,3559,87.88111111111111,0.01611111111111111,1,5,1.73,60,33,1975-04-22,NA,Carlos Sastre Candil,NA,Leganés,Spain, Spain
+96,2009-07-04,Alberto Contador,Astana,3459,85.80972222222222,0.06777777777777777,2,7,1.76,62,26,1982-12-06,NA,Alberto Contador Velasco,El Pistolero,Pinto,Spain, Spain
+97,2010-07-03,Andy Schleck,Team Saxo Bank,3642,91.99083333333333,0.016944444444444443,2,12,1.86,68,25,1985-06-10,NA,Andy Raymond Schleck,NA,Luxembourg City,Luxembourg, Luxembourg
+98,2011-07-02,Cadel Evans,BMC Racing Team,3430,86.20611111111111,0.016944444444444443,1,2,1.74,64,34,1977-02-14,NA,Cadel Lee Evans,NA,Katherine,Australia, Australia
+99,2012-06-20,Bradley Wiggins,Team Sky,3496,87.57972222222222,0.050833333333333335,2,14,1.9,69,32,1980-04-28,NA,Bradley Marc Wiggins,Wiggo,Ghent,Belgium, Great Britain
+100,2013-06-29,Chris Froome,Team Sky,3404,83.9388888888889,0.06777777777777777,3,14,1.86,69,28,1985-05-20,NA,Christopher Clive Froome,Froomey,Nairobi,Kenya, Great Britain
+101,2014-07-05,Vincenzo Nibali,Astana,3660.5,89.985,0.11861111111111111,4,19,1.8,65,29,1984-11-14,NA,NA,"Lo Squalo (The Shark), 'il Roditore' (The Nibbler)",Messina,Italy, Italy
+102,2015-07-04,Chris Froome,Team Sky,3360.3,84.77055555555556,0.016944444444444443,1,16,1.86,69,30,1985-05-20,NA,Christopher Clive Froome,Froomey,Nairobi,Kenya, Great Britain
+103,2016-07-02,Chris Froome,Team Sky,3529,89.08,0.06777777777777777,2,14,1.86,69,31,1985-05-20,NA,Christopher Clive Froome,Froomey,Nairobi,Kenya, Great Britain
+104,2017-07-01,Chris Froome,Team Sky,3540,86.34861111111111,0.015,0,15,1.86,69,32,1985-05-20,NA,Christopher Clive Froome,Froomey,Nairobi,Kenya, Great Britain
+105,2018-07-07,Geraint Thomas,Team Sky,3349,83.28694444444444,0.016944444444444443,2,11,1.83,71,32,1986-05-25,NA,Geraint Howell Thomas,G,Cardiff,Wales, Great Britain
+106,2019-07-06,Egan Bernal,Team Ineos,3349,82.95,0.016944444444444443,0,2,1.75,60,22,1997-01-13,NA,Egan Arley Bernal Gómez,NA,Bogotá,Columbia, Colombia

inspectpd/inspect/inspect_cat.py

@@ -0,0 +1,56 @@
+import numpy as np
+import pandas as pd
+
+from inspectpd.inspect_object.inspect_object import inspect_object
+
+
+# inspect_cat
+def inspect_cat(df):
+    """
+    Summary and comparison of the levels in categorical columns
+
+    Parameters
+    ----------
+
+    df: A pandas dataframe.
+
+    Returns
+    ----------
+
+    A pandas dataframe with columns:
+      + col_name: object
+        column of strings containing column names of df
+      + cnt: int64
+        integer column containing count of unique levels
+        found in each column of df.
+      + common: object
+        column of strings containing the name of the most common level
+      + common_pcnt: float64
+        the percentage of each column occupied by the most common level
+        shown in common.
+      + levels: object
+        a list containing relative frequency dataframes for each column in df.
+    """
+
+    # get the string / categorical columns
+    df_cat = df.select_dtypes(["category", "object"])
+    # new df with columns names as first col
+    out = pd.DataFrame(df_cat.columns, columns=["col_name"])
+    # tabulate values in each column
+    levels_list = []
+    for col in df_cat.columns:
+        col_vals = df_cat[col].value_counts(dropna=False).reset_index(drop=False)
+        col_vals.columns = ["value", "cnt"]
+        col_vals["pcnt"] = 100 * col_vals.cnt / np.sum(col_vals.cnt)
+        col_vals = col_vals.sort_values(["pcnt"], ascending=False)
+        col_vals = col_vals[["value", "pcnt", "cnt"]]
+        levels_list.append(col_vals)
+    # number of unique values per column
+    out["cnt"] = [x.shape[0] for x in levels_list]
+    out["common"] = [x.value[0] for x in levels_list]
+    out["common_pcnt"] = [x.pcnt[0] for x in levels_list]
+    out["levels"] = levels_list
+    out = out.sort_values("col_name").reset_index(drop=True)
+    # subclass output, adds plot methods
+    out = inspect_object(out, my_attr="inspect_cat")
+    return out

inspectpd/inspect/inspect_cor.py

@@ -0,0 +1,99 @@
+import numpy as np
+import scipy.stats as st
+
+from inspectpd.inspect_object.inspect_object import inspect_object
+
+
+def inspect_cor(df, method="pearson", alpha=0.05, with_col=None):
+    """
+    Tidy correlation coefficients for numeric dataframe columns.
+
+    Parameters
+    ----------
+
+    df: A pandas dataframe.
+
+    method: str, default 'pearson'
+      a character string indicating which type of correlation
+      coefficient to use, one of "pearson", "kendall", or "spearman".
+
+    alpha: float, default 0.05.
+      Alpha level for correlation confidence intervals. Defaults to 0.05.
+
+    with_col: str, default None
+      Column name to filter correlations by.  Uses pandas .withcorr() under
+      the hood instead of .corr(), which can save time for large data sets.
+
+    Returns
+    ----------
+
+    A pandas dataframe with columns
+      + col_1, co1_2: object
+        character columns containing names of numeric columns in df1.
+      + corr: float64
+        columns of correlation coefficients
+      + p_value: float64
+        p-value associated with a test where the null hypothesis is
+        that the numeric pair have 0 correlation.
+      + lower, upper: float64
+        lower and upper values of the confidence interval for the correlations.
+      + pcnt_na:
+        the number of pairs of observations that were non missing for each
+        pair of columns. The correlation calculation used by .inspect_cor()
+        uses only pairwise complete observations.
+    """
+    df_num = df.select_dtypes("number").copy()
+    if with_col is None:
+        out = df_num.corr(method=method)
+        # get the number of variables
+        nvarb = out.shape[0]
+        # unpivot the correlation matrix
+        out = out.unstack().reset_index(drop=False)
+        # rename columns
+        out.columns = ["col_1", "col_2", "corr"]
+        # row index of off diagonal elements
+        inds = [(np.arange(i + 1) + i * nvarb).tolist() for i in range(nvarb)]
+        inds = [j for i in inds for j in i]
+        # drop off diagonals
+        out = out[~out.index.isin(inds)].reset_index(drop=True)
+    else:
+        out = df_num.corrwith(df_num[with_col]).reset_index(drop=False)
+        out["col_2"] = with_col
+        # rename columns and reorder
+        out.columns = ["col_1", "corr", "col_2"]
+        out = out[["col_1", "col_2", "corr"]]
+
+    # remove self-correlations
+    out = out.query("col_1 != col_2").reset_index(drop=True)
+    # get pairwise non-na
+    df_null = 1 - df_num.isnull().astype("int")
+    nna_mat = df_null.transpose().dot(df_null)
+    nna_df = nna_mat.unstack().reset_index(drop=False)
+    nna_df.columns = ["col_1", "col_2", "nna"]
+    # add standard errors
+    nna_df = nna_df.assign(se=(1 / np.sqrt(nna_df.nna - 3)))
+    nna_df = nna_df.assign(pcnt_na=100 * nna_df.nna / df.shape[0]).drop("nna", axis=1)
+    # join pairwise nna to the output df
+    out = out.merge(nna_df, how="left", on=["col_1", "col_2"])
+    out["p_value"] = 2 * st.norm.cdf(-np.abs(out["corr"].values / out.se))
+    # swicth off divide by zero error pinged by numpy with arctans
+    np.seterr(all="ignore")
+    out["lower"] = np.tanh(
+        np.arctanh(out["corr"].values) - st.norm.ppf(1 - alpha / 2) * out.se
+    )
+    out["upper"] = np.tanh(
+        np.arctanh(out["corr"].values) + st.norm.ppf(1 - alpha / 2) * out.se
+    )
+    np.seterr(all="warn")
+    # sort by absolute value of corr
+    out = (
+        out.assign(abs_cor=np.abs(out["corr"].values))
+        .sort_values("abs_cor", ascending=False)
+        .drop(["abs_cor", "se"], axis=1)
+        .reset_index(drop=True)
+    )
+    # change order of output columns
+    out = out[["col_1", "col_2", "corr", "p_value", "lower", "upper", "pcnt_na"]]
+    # add type attribute to output
+    out = inspect_object(out, my_attr="inspect_cor")
+    return out

inspectpd/inspect/inspect_imb.py

@@ -0,0 +1,52 @@
+import numpy as np
+import pandas as pd
+
+from inspectpd.inspect_object.inspect_object import inspect_object
+
+
+def inspect_imb(df):
+    """
+    Summary of the most common levels in categorical columns
+
+    Parameters
+    ----------
+
+    df: A pandas dataframe.
+
+    Returns
+    ----------
+
+    A pandas dataframe with columns:
+      + col_name: object
+        column of strings containing column names of df.
+      + value: object
+        column of strings containing the most common categorical level
+        in each column of df.
+      + cnt: int64
+        the number of occurrences of the most common categorical level
+        in each column of df1.
+      + pcnt: float64
+        the relative frequency of each column's most common categorical
+        level expressed as a percentage.
+    """
+
+    df_cat = df.select_dtypes(["category", "object"])
+    # new df with columns names as first col
+    out = pd.DataFrame(df_cat.columns, columns=["col_name"])
+    # tabulate values in each column
+    levels_list = []
+    for col in df_cat.columns:
+        col_vals = df_cat[col].value_counts().reset_index(drop=False)
+        col_vals.columns = ["value", "cnt"]
+        col_vals["pcnt"] = 100 * col_vals.cnt / np.sum(col_vals.cnt)
+        col_vals = col_vals.sort_values(["pcnt"], ascending=False)
+        col_vals = col_vals[["value", "pcnt", "cnt"]]
+        levels_list.append(col_vals)
+    # number of unique values per column
+    out["value"] = [x.value[0] for x in levels_list]
+    out["cnt"] = [x.cnt[0] for x in levels_list]
+    out["pcnt"] = [x.pcnt[0] for x in levels_list]
+    out = out.sort_values("pcnt", ascending=False).reset_index(drop=True)
+    # subclass output, adds plot methods
+    out = inspect_object(out, my_attr="inspect_imb")
+    return out

inspectpd/inspect/inspect_mem.py

@@ -0,0 +1,54 @@
+from inspectpd.inspect_object.inspect_object import inspect_object
+
+
+# inspect_mem
+def inspect_mem(df):
+    """
+    Summary of memory usage of dataframe columns
+
+    Parameters
+    ----------
+
+    df: A pandas dataframe.
+
+    Returns
+    ----------
+
+    A pandas dataframe with columns:
+
+      + col_name: object
+        column of strings containing column names of df
+      + bytes: int64
+        integer column containing the number of bytes in each column of df
+      + size: object
+        column of strings containing display-friendly memory usage in SI units
+        of each column.
+      + pcnt: float64
+        the percentage of the dataframe's total memory footprint used by each
+        column.
+    """
+
+    out = (
+        df.memory_usage(index=False, deep=True)
+        .sort_values(ascending=False)
+        .reset_index(drop=False)
+    )
+    out.columns = ["col_name", "bytes"]
+    # add printable size strings
+    out = out.assign(size=out["bytes"].apply(format_size))
+    # add percentage of total
+    out = out.assign(pcnt=100 * out["bytes"] / out["bytes"].sum())
+    # add type attribute to output
+    out = inspect_object(out, my_attr="inspect_mem")
+    return out
+
+
+# function for making nice printable object sizes
+def format_size(num):
+    for unit in ["", "K", "M", "G", "T", "P", "E", "Z", "Y"]:
+        if num < 1024.0:
+            if unit == "":
+                return f"{num:3.0f} {unit}B"
+            else:
+                return f"{num:3.2f} {unit}B"
+        num /= 1024.0

inspectpd/inspect/inspect_na.py

@@ -0,0 +1,46 @@
+from inspectpd.inspect_object.inspect_object import inspect_object
+
+
+# inspect_na
+def inspect_na(df):
+    """
+    Summary of the rate of missingness across dataframe columns
+
+    Parameters
+    ----------
+
+    df: A pandas dataframe.
+
+    Returns
+    ----------
+
+    A pandas dataframe with columns:
+      + col_name: object
+        column of strings containing column names of df
+      + cnt: int64
+        integer column containing the number of missing values by column.
+      + pcnt: float64
+        the percentage of records in each column that is missing.
+    """
+
+    df_null = df.isnull()
+    # number of nulls
+    df_nnl = (
+        df_null.sum()
+        .reset_index(drop=False)
+        .rename(columns={"index": "col_name", 0: "cnt"})
+    )
+    # proportion of nulls
+    df_mnl = (
+        df_null.mean()
+        .reset_index(drop=False)
+        .rename(columns={"index": "col_name", 0: "pcnt"})
+    )
+    # convert proportion to percentage
+    df_mnl = df_mnl.assign(pcnt=df_mnl.pcnt * 100)
+    # combine null summary into single df
+    out = df_nnl.merge(df_mnl, on="col_name", how="left")
+    out = out.sort_values("pcnt", ascending=False).reset_index(drop=True)
+    # subclass output, adds plot methods
+    out = inspect_object(out, my_attr="inspect_na")
+    return out