def test_summarize():
df = pd.DataFrame(
{
"Brand": ["Honda Civic", "Toyota Corolla", "Ford Focus", "Audi A4"],
"Price": [22000, 25000, 27000, 35000],
},
columns=["Brand", "Price"],
)
summary = summarize(df, {"Brand": String, "Price": Integer}, CompleteSummary())
assert summary["types"] == {"Brand": String, "Price": Integer}
def test_summarize_frame():
df = pd.DataFrame(
{
"Brand": ["Honda Civic", "Toyota Corolla", "Ford Focus", "Audi A4"],
"Price": [22000, 25000, 27000, 35000],
},
columns=["Brand", "Price"],
)
summary = summarize_frame(
df, {"Brand": String, "Price": Integer}, CompleteSummary()
)
summary.pop("type_counts")
assert summary == {
"n_observations": 4,
"n_variables": 2,
"memory_size": 430,
"na_count": 0,
"n_vars_missing": 0,
}
def test_summarize_series():
brand_series = pd.Series(["Honda Civic", "Toyota Corolla", "Ford Focus", "Audi A4"])
summary = summarize_series(brand_series, String, CompleteSummary())
assert summary == {
"n_unique": 4,
"length": {7: 1, 14: 1, 11: 1, 10: 1},
"category_short_values": {
"H": "Lu",
"o": "Ll",
"n": "Ll",
"d": "Ll",
"a": "Ll",
" ": "Zs",
"C": "Lu",
"i": "Ll",
"v": "Ll",
"c": "Ll",
"T": "Lu",
"y": "Ll",
"t": "Ll",
"r": "Ll",
"l": "Ll",
"F": "Lu",
"u": "Ll",
"s": "Ll",
"A": "Lu",
"4": "Nd",
},
"category_alias_values": {
"H": "Uppercase_Letter",
"o": "Lowercase_Letter",
"n": "Lowercase_Letter",
"d": "Lowercase_Letter",
"a": "Lowercase_Letter",
" ": "Space_Separator",
"C": "Uppercase_Letter",
"i": "Lowercase_Letter",
"v": "Lowercase_Letter",
"c": "Lowercase_Letter",
"T": "Uppercase_Letter",
"y": "Lowercase_Letter",
"t": "Lowercase_Letter",
"r": "Lowercase_Letter",
"l": "Lowercase_Letter",
"F": "Uppercase_Letter",
"u": "Lowercase_Letter",
"s": "Lowercase_Letter",
"A": "Uppercase_Letter",
"4": "Decimal_Number",
},
"script_values": {
"H": "Latin",
"o": "Latin",
"n": "Latin",
"d": "Latin",
"a": "Latin",
" ": "Common",
"C": "Latin",
"i": "Latin",
"v": "Latin",
"c": "Latin",
"T": "Latin",
"y": "Latin",
"t": "Latin",
"r": "Latin",
"l": "Latin",
"F": "Latin",
"u": "Latin",
"s": "Latin",
"A": "Latin",
"4": "Common",
},
"block_values": {
"H": "Basic Latin",
"o": "Basic Latin",
"n": "Basic Latin",
"d": "Basic Latin",
"a": "Basic Latin",
" ": "Basic Latin",
"C": "Basic Latin",
"i": "Basic Latin",
"v": "Basic Latin",
"c": "Basic Latin",
"T": "Basic Latin",
"y": "Basic Latin",
"t": "Basic Latin",
"r": "Basic Latin",
"l": "Basic Latin",
"F": "Basic Latin",
"u": "Basic Latin",
"s": "Basic Latin",
"A": "Basic Latin",
"4": "Basic Latin",
},
"block_alias_values": {
"H": "ASCII",
"o": "ASCII",
"n": "ASCII",
"d": "ASCII",
"a": "ASCII",
" ": "ASCII",
"C": "ASCII",
"i": "ASCII",
"v": "ASCII",
"c": "ASCII",
"T": "ASCII",
"y": "ASCII",
"t": "ASCII",
"r": "ASCII",
"l": "ASCII",
"F": "ASCII",
"u": "ASCII",
"s": "ASCII",
"A": "ASCII",
"4": "ASCII",
},
"frequencies": {
"Audi A4": 1,
"Honda Civic": 1,
"Ford Focus": 1,
"Toyota Corolla": 1,
},
"n_records": 4,
"memory_size": 398,
"dtype": np.object_,
"types": {"str": 4},
"na_count": 0,
}
price_series = pd.Series([22000, 25000, 27000, 35000])
summary = summarize_series(price_series, Integer, CompleteSummary())
assert summary == {
"inf_count": 0,
"mean": 27250.0,
"std": 5560.275772537426,
"var": 30916666.666666668,
"max": 35000.0,
"min": 22000.0,
"median": 26000.0,
"kurt": 1.8192544372679649,
"skew": 1.19978923754086,
"sum": 109000.0,
"mad": 3875.0,
"quantile_5": 22450.0,
"quantile_25": 24250.0,
"quantile_50": 26000.0,
"quantile_75": 29000.0,
"quantile_95": 33800.0,
"iqr": 4750.0,
"range": 13000.0,
"cv": 0.20404681734082297,
"n_zeros": 0,
"n_unique": 4,
"frequencies": {27000: 1, 35000: 1, 25000: 1, 22000: 1},
"n_records": 4,
"memory_size": 160,
"dtype": np.int64,
"types": {"int": 4},
"na_count": 0,
"monotonic_decrease": False,
"monotonic_increase": True,
}
"digits": ["01234", "121223", "123123"],
"specials": ["$", "%^&*(", "!!!~``"],
"whitespace": ["\t", "\n", " "],
"jiddisch": ["רעכט צו לינקס", "שאָסיי 61", "פּיצאַ איז אָנגענעם"],
"arabic": ["بوب ديلان", "باتي فالنتين", "السيد الدف الرجل"],
"playing_cards": ["🂶", "🃁", "🂻"],
})
# Initialize the typeset
typeset = CompleteSet()
# Infer the column type
types = detect_type(df, typeset)
# Generate a summary
summarizer = CompleteSummary()
summary = summarizer.summarize(df, types)
print("| {h1: <15}| {h2: <17}| {h3: <84}| {h4: <25}|".format(h1="Column",
h2="Scripts",
h3="Categories",
h4="Blocks"))
print("{e:-<17}+{e:-<18}+{e:-<85}+{e:-<26}+".format(e=""))
for column, variable_summary in summary["series"].items():
scripts = ", ".join(set(variable_summary["script_values"].values()))
categories = ", ".join(
set(variable_summary["category_alias_values"].values()))
blocks = ", ".join(set(variable_summary["block_values"].values()))
print("| {column: <15}| {scripts: <17}| {categories: <84}| {blocks: <25}|".
format(column=column,
from pprint import pprint
import numpy as np
import pandas as pd
import visions as v
from visions.application.summaries import CompleteSummary
datetime_series = pd.Series([
pd.datetime(2010, 1, 1),
pd.datetime(2010, 8, 2),
pd.datetime(2011, 2, 1),
np.datetime64("NaT"),
])
# Generate a summary
summarizer = CompleteSummary()
summary = summarizer.summarize_series(datetime_series, v.DateTime)
pprint(summary)
def summary():
return CompleteSummary()
import numpy as np
import pandas as pd
import visions.types as vt
from visions.application.summaries import CompleteSummary
integer_series = pd.Series([1, 2, 3, 4, 5, -100000, np.nan], dtype="Int64")
summarizer = CompleteSummary()
summary = summarizer.summarize_series(integer_series, vt.Integer)
print(summary)
# Output:
# {
# "inf_count": 0,
# "mean": -16664.166666666668,
# "std": 40826.05381575185,
# "var": 1666766670.1666665,
# "max": 5.0,
# "min": -100000.0,
# "median": 2.5,
# "kurt": 5.999999974801513,
# "skew": -2.449489736169953,
# "sum": -99985.0,
# "mad": 27778.611111111113,
# "quantile_5": -74999.75,
# "quantile_25": 1.25,
# "quantile_50": 2.5,
# "quantile_75": 3.75,
# "quantile_95": 4.75,
# "iqr": 2.5,
def test_summarize_series():
brand_series = pd.Series(
["Honda Civic", "Toyota Corolla", "Ford Focus", "Audi A4"])
summary = summarize_series(brand_series, String, CompleteSummary())
assert summary["n_unique"] == 4
assert summary["length"].to_dict() == {0: 11, 1: 14, 2: 10, 3: 7}
assert summary["max_length"] == 14
assert summary["min_length"] == 7
assert summary["mean_length"] == 10.5
assert summary["median_length"] == 10.5
assert summary["n_characters"] == 20
assert summary["category_alias_values"] == {
"H": "Uppercase_Letter",
"o": "Lowercase_Letter",
"n": "Lowercase_Letter",
"d": "Lowercase_Letter",
"a": "Lowercase_Letter",
" ": "Space_Separator",
"C": "Uppercase_Letter",
"i": "Lowercase_Letter",
"v": "Lowercase_Letter",
"c": "Lowercase_Letter",
"T": "Uppercase_Letter",
"y": "Lowercase_Letter",
"t": "Lowercase_Letter",
"r": "Lowercase_Letter",
"l": "Lowercase_Letter",
"F": "Uppercase_Letter",
"u": "Lowercase_Letter",
"s": "Lowercase_Letter",
"A": "Uppercase_Letter",
"4": "Decimal_Number",
}
assert summary["frequencies"] == {
"Audi A4": 1,
"Honda Civic": 1,
"Ford Focus": 1,
"Toyota Corolla": 1,
}
price_series = pd.Series([22000, 25000, 27000, 35000])
summary = summarize_series(price_series, Integer, CompleteSummary())
assert summary == {
"n_infinite": 0,
"mean": 27250.0,
"std": 5560.275772537426,
"variance": 30916666.666666668,
"max": 35000.0,
"min": 22000.0,
"median": 26000.0,
"kurt": 1.8192544372679649,
"skew": 1.19978923754086,
"sum": 109000.0,
"mad": 2500.0,
"quantile_5": 22450.0,
"quantile_25": 24250.0,
"quantile_50": 26000.0,
"quantile_75": 29000.0,
"quantile_95": 33800.0,
"iqr": 4750.0,
"range": 13000.0,
"cv": 0.20404681734082297,
"n_zeros": 0,
"is_unique": True,
"n_unique": 4,
"frequencies": {
27000: 1,
35000: 1,
25000: 1,
22000: 1
},
"n_records": 4,
"memory_size": 160,
"dtype": np.int64,
"types": {
"int": 4
},
"na_count": 0,
"monotonic_decrease": False,
"monotonic_decrease_strict": False,
"monotonic_increase": True,
"monotonic_increase_strict": True,
}
from pprint import pprint
import numpy as np
import pandas as pd
import visions as v
from visions.application.summaries import CompleteSummary
category_series = pd.Series(
pd.Categorical(
[True, False, np.nan, "test"], categories=[True, False, "test", "missing"]
)
)
# Generate a summary
summarizer = CompleteSummary()
summary = summarizer.summarize_series(category_series, v.Categorical)
pprint(summary)
import pandas as pd
import visions as v
from visions.application.summaries import CompleteSummary
string_series = pd.Series(["orange", "apple", "pear", "🂶", "🃁", "🂻"])
summarizer = CompleteSummary()
summary = summarizer.summarize_series(string_series, v.String)
print(summary)
# Output:
# {
# "n_unique": 6,
# "length": {1: 3, 6: 1, 5: 1, 4: 1},
# "category_short_values": {
# "o": "Ll",
# "r": "Ll",
# "a": "Ll",
# "n": "Ll",
# "g": "Ll",
# "e": "Ll",
# "p": "Ll",
# "l": "Ll",
# "🂶": "So",
# "🃁": "So",
# "🂻": "So",
# },
# "category_alias_values": {
# "o": "Lowercase_Letter",
# "r": "Lowercase_Letter",
