def test_type_inference_frame():
# Create a DataFrame with various string columns
df = pd.DataFrame(
{
"latin": ["orange", "apple", "pear"],
"cyrillic": ["Кириллица", "гласность", "демократија"],
"mixed": ["Кириллица", "soep", "демократија"],
"burmese": ["ရေကြီးခြင်း", "စက်သင်ယူမှု", "ဉာဏ်ရည်တု"],
"digits": ["1234", "121223", "12312"],
"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 = infer_type(df, typeset)
assert types == {
"latin": String,
"cyrillic": String,
"mixed": String,
"burmese": String,
"digits": Integer,
"specials": String,
"whitespace": String,
"jiddisch": String,
"arabic": String,
"playing_cards": String,
}
def test_type_inference_series():
string_series = pd.Series(["(12.0+10.0j)", "(-4.0+6.2j)", "(8.0+2.0j)"])
typeset = StandardSet()
detected_type = infer_type(string_series, typeset)
assert detected_type == Complex
def df_get_data_types_task(df: pd.DataFrame) -> dict:
typeset = CompleteSet()
dtypes = infer_type(df, typeset)
dtypes_dict = {k: str(v) for k, v in dtypes.items()}
return dtypes_dict
"url": [
"http://www.cwi.nl:80/%7Eguido/Python.html",
"https://numpy.org/",
"https://github.com/pandas-profiling/pandas-profiling",
],
"uuid": [
"0b8a22ca-80ad-4df5-85ac-fa49c44b7ede",
"aaa381d6-8442-4f63-88c8-7c900e9a23c6",
"00000000-0000-0000-0000-000000000000",
],
})
# Choose the complete typeset, which includes URLs
typeset = CompleteSet()
# Detect the type (without casting)
print(detect_type(df, typeset))
# {'numbers_with_nan': Float, 'url': String, 'uuid': String}
# Cast the dataframe to inferred types
cast_df = cast_to_inferred(df, typeset)
print(cast_df.to_string())
# numbers_with_nan url uuid
# 0 3 (http, www.cwi.nl:80, /%7Eguido/Python.html, ,... 0b8a22ca-80ad-4df5-85ac-fa49c44b7ede
# 1 7 (https, numpy.org, /, , , ) aaa381d6-8442-4f63-88c8-7c900e9a23c6
# 2 NaN (https, github.com, /pandas-profiling/pandas-p... 00000000-0000-0000-0000-000000000000
# Print the inferred types
print(infer_type(df, typeset))
# {'numbers_with_nan': Integer, 'url': URL, 'uuid': UUID}