Piter De Vries,David Dastmalchian,2021
Baron Vladimir Harkonnen,Stellan Skarsgård,2021
Reverend Mother Gaius Helen Mohiam,Charlotte Rampling,2021
Thufir Hawat,Stephen McKinley Henderson,2021
Dr. Yueh,Chen Chang,2021
Dr. Liet-Kynes,Sharon Duncan-Brewster,2021
Jamis,Babs Olusanmokun,2021
Harah,Gloria Obianyo,2021
Padishah Emperor Shaddam IV,...,2021
Shadout Mapes,...,2021
Princess Irulan,...,2021
Reverend Mother Ramallo,...,2021
Feyd-Rautha Harkonnen,...,2021
Alia Atreides,...,2021
Otheym,...,2021
"""
dune_casts = lt.Table("dune_1984").csv_import(dune_casts_csv).create_index(
"character")
dune_1984 = dune_casts.where(year="1984").add_field("actor (1984)",
attrgetter("actor"))
dune_2000 = dune_casts.where(year="2000").add_field("actor (2000)",
attrgetter("actor"))
dune_2021 = dune_casts.where(year="2021").add_field("actor (2021)",
attrgetter("actor"))
join = dune_1984.join_on("character") + dune_2000 + dune_2021
dune_combined = join()("Dune Casts (combined)")
dune_combined.present(
fields=["character", "actor (1984)", "actor (2000)", "actor (2021)"])
# that normalize back to ASCII characters that can be used in Python
# identifiers (A-Z, a-z, 0-9, _, and ·)
_· = "_·"
ident_chars = ("ABCDEFGHIJKLMNOPQRSTUVWXYZ"
"abcdefghijklmnopqrstuvwxyz"
"0123456789" + _·)
accum = {ch: [] for ch in ident_chars}
# build up accumulator by walking Unicode range
unicode_upper_limit = sys.maxunicode+1 if ALL_UNICODE_CHARS else 65536
for i in range(32, unicode_upper_limit):
ch = chr(i)
norm = unicodedata.normalize("NFKC", ch)
if norm in accum:
accum[norm].append(ch)
# convert accumulator to a littletable Table for presentation
normalizations = lt.Table()
for asc_char, normalizing_chars in accum.items():
normalizations.insert_many(
{"ASCII": asc_char,
"ord": ord(asc_char),
"Unicode": norm_char,
"code_point": ord(norm_char),
"name": unicodedata.name(norm_char),
}
for norm_char in normalizing_chars
)
normalizations.sort("ASCII")
normalizations.present(groupby="ASCII ord")
title,ingredients
Tuna casserole,tuna noodles cream of mushroom soup
Hawaiian pizza,pizza dough pineapple ham tomato sauce
Margherita pizza,pizza dough cheese pesto artichoke hearts
Pepperoni pizza,pizza dough cheese tomato sauce pepperoni
Grilled cheese sandwich,bread cheese butter
Tuna melt,tuna mayonnaise tomato bread cheese
Chili dog,hot dog chili onion bun
French toast,egg milk vanilla bread maple syrup
BLT,bread bacon lettuce tomato mayonnaise
Reuben sandwich,rye bread sauerkraut corned beef swiss cheese russian dressing thousand island
Hamburger,ground beef bun lettuce ketchup mustard pickle
Cheeseburger,ground beef bun lettuce ketchup mustard pickle cheese
Bacon cheeseburger,ground beef bun lettuce ketchup mustard pickle cheese bacon
""")
recipes = lt.Table().csv_import(recipe_data)
# define search index on "ingredients" attribute
search_attr = "ingredients"
recipes.create_search_index(search_attr)
# run sample queries
queries = """\
tuna
tuna +cheese
pineapple +bacon lettuce beef -sauerkraut tomato
pizza dough -pineapple
pizza dough --pineapple
bread bacon
bread ++bacon""".splitlines()
tbl = lt.Table("Academy Awards 1960-1969").csv_import("""\
year,award,movie,recipient
1960,Best Picture,Ben-Hur,
1960,Best Actor,Ben-Hur,Charlton Heston
1960,Best Actress,The Heiress,Simone Signoret
1960,Best Director,Ben-Hur,William Wyler
1961,Best Picture,The Apartment,
1961,Best Actor,Elmer Gantry,Burt Lancaster
1961,Best Actress,Butterfield 8,Elizabeth Taylor
1961,Best Director,The Apartment,Billy Wilder
1962,Best Picture,West Side Story,
1962,Best Actor,Judgment at Nuremberg,Maximilian Schell
1962,Best Actress,Two Women,Sophia Loren
1962,Best Director,West Side Story,Willian Wise/Jerome Robbins
1963,Best Picture,Lawrence of Arabia,
1963,Best Actor,Gregory Peck,To Kill A Mockingbird
1963,Best Actress,Anne Bancroft,The Miracle Worker
1963,Best Director,David Lean,Lawrence of Arabia
1964,Best Picture,Tom Jones,
1964,Best Actor,Sidney Poitier,Lilies of the Field
1964,Best Actress,Patricia Neal,Hud
1964,Best Director,Tony Richardson,Tom Jones
1965,Best Picture,My Fair Lady,
1965,Best Actor,Rex Harrison,My Fair Lady
1965,Best Actress,Julie Andrews,Mary Poppins
1965,Best Director,George Kukor,My Fair Lady
1966,Best Picture,The Sound of Music,
1966,Best Actor,Lee Marvin,Cat Ballou
1966,Best Actress,Julie Christie,Darling
1966,Best Director,Robert Wise,The Sound of Music
1967,Best Picture,A Man for All Season,
1967,Best Actor,Paul Scofield,A Man for All Seasons
1967,Best Actress,Elizabeth Taylor,Who's Afraid of Virginia Woolf
1967,Best Director,Fred Zinnemann,A Man for All Seasons
1968,Best Picture,In The Heat of The Night,
1968,Best Actor,Rod Steiger,In The Heat of The Night
1968,Best Actress,Katherine Hepburn,Guess Who's Coming to Dinner
1968,Best Director,Mike Nichols,The Graduate
1969,Best Picture,Oliver!,
1969,Best Actor,Cliff Robertson,Charly
1969,Best Actress,Barbra Streisand,Funny Girl
1969,Best Director,Carol Reed,Oliver!
""")
columns = [
(
"id_no",
0,
),
(
"name",
4,
),
(
"address",
21,
),
(
"city",
42,
),
(
"state",
56,
58,
),
("tech_skill_score", 59, None, float),
]
characters_table = lt.Table().insert_many(
lt.DataObject(**rec) for rec in lt.FixedWidthReader(columns, data))
print(len(characters_table))
print(characters_table[0])
#
# excel_data_types.py
#
# Demonstrate data type conversions done automatically when importing from Excel
#
import littletable as lt
xl = lt.Table().excel_import("../test/data_types.xlsx")
xl.present()
for row in xl:
print(row.name, repr(row.value), type(row.value), row.type)
lasts = pathlib.Path('last_names.txt').read_text().splitlines()
NUM_NURSES = 12
NUM_DOCTORS = 8
names = set()
reset_id()
while len(names) < NUM_NURSES:
names.add(
StaffMember(next_id(), random.choice(lasts), random.choice(firsts),
"nurse"))
while len(names) < NUM_NURSES + NUM_DOCTORS:
names.add(
StaffMember(next_id(), random.choice(lasts), random.choice(firsts),
"doctor"))
staff = lt.Table()
staff.insert_many(sorted(names))
staff.create_index("staff_id", unique=True)
print(len(staff))
print(staff.info())
print(staff[0])
staff.csv_export("staff.csv")
departments = lt.Table()
reset_id()
departments.insert(lt.DataObject(id=next_id(), name="ER"))
departments.insert(lt.DataObject(id=next_id(), name="ICU"))
departments.insert(lt.DataObject(id=next_id(), name="OR"))
print(departments.info())
departments.create_index("id", unique=True)
departments.csv_export("departments.csv")
"digit_value",
"numeric_value",
"mirrored",
"unicode_1_name",
"iso10646_comment",
"uppercase_hex",
"lowercase_hex",
"titlecase_hex",
]
unicode_url = "https://www.unicode.org/Public/3.2-Update/UnicodeData-3.2.0.txt"
unicode_file = "unicode_320.txt.zip"
unicode = lt.Table().csv_import(
unicode_file,
delimiter=";",
transforms={
"decimal_digit_value": int,
"digit_value": int,
"numeric_value": int,
},
fieldnames=fieldnames,
)
unicode.add_field("code_value", lambda r: int(r.code_value_hex, 16))
unicode.add_field("uppercase", lambda r: int(r.uppercase_hex, 16))
unicode.add_field("lowercase", lambda r: int(r.lowercase_hex, 16))
unicode.add_field("titlecase", lambda r: int(r.titlecase_hex, 16))
unicode.add_field("character", lambda r: chr(r.code_value))
unicode.add_field("upper_char", lambda r: chr(r.uppercase))
unicode.add_field("lower_char", lambda r: chr(r.lowercase))
unicode.add_field("title_char", lambda r: chr(r.titlecase))
unicode.add_field("is_identifier", lambda r: r.character.isidentifier())
unicode.create_index("code_value_hex", unique=True)