KL-Py 0.3.9__tar.gz → 0.4.0__tar.gz

{kl_py-0.3.9 → kl_py-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: KL_Py
-Version: 0.3.9
+Version: 0.4.0
 Summary: A Python simplification module
 Author-email: Abbaskhurram255 <abbaskhurram255@gmail.com>
 Classifier: Programming Language :: Python :: 3

{kl_py-0.3.9 → kl_py-0.4.0}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "KL_Py"
-version = "0.3.9"
+version = "0.4.0"
 authors = [
     { name = "Abbaskhurram255", email = "abbaskhurram255@gmail.com" }
 ]

{kl_py-0.3.9 → kl_py-0.4.0}/src/KL_Py/KL_Py.py

@@ -30,6 +30,15 @@ from inspect import *
 from KL_Py import requests
 from .hindGui import *
 from .when import *
+home_path_obj: Path = Path.home()
+USER_HOME =\
+		USER_HOME_DIR =\
+			str(home_path_obj)
+DESKTOP_DIR =\
+	USER_DESKTOP_DIR =\
+	USER_DESKTOP =\
+	DESKTOP =\
+		str(home_path_obj / "Desktop")
 TypeDict = typedict = typeddict = TypedDict
 copy = deepcopy
 # for ease of access
@@ -56,7 +65,7 @@ ALPHA_RE = ALPHA_REGEX = r"[A-Za-z]+"
 LETTERS_WITH_SYMBOLS_RE = LETTERS_WITH_SYMBOLS_REGEX = r"[a-zA-Z (\(\)\{\}\[\]\&\:\;\-\'\"\?\!\,\.)]+"
 TRAILING_SPACE_RE = TRAILING_SPACE_REGEX = r"(^\s+|\s+$)"
 NUM_RE = NUM_REGEX = r"(\-?\d*\.?\d+)"
-NON_NUM_RE: str = r"[^\-\.\d]+"
+NON_NUM_RE: str = r"[^Ee\+\-\.\d]|(?<=[A-Za-z_])[Ee]|[Ee\.](?![\d\+\-])|(?<![^\de\+\-\.])[\.\+\-](?=[^\de\+\-\.])"
 INT_RE = INTEGEGER_RE = INT_REGEX = INTEGEGER_REGEX = r"\-?\d+"
 WORD_RE = WORD_REGEX = r"[A-Za-z_\'][\w\']*(?:\-[A-Za-z_\']\w*(?: [A-Za-z_\'][\w\']*){0})*"
 NON_WORD_RE = NON_WORD_REGEX = r"[^A-Za-z_\-]|\-(?![A-Za-z_])"
@@ -993,6 +1002,37 @@ class Date:
 						}
 					)
 			return self
+	def __call__(
+		self,
+		item=None,
+		default = 0
+	) ->\
+		Union[
+			Any,
+			datetime.datetime
+		]:
+				if isinstance(
+					item,
+					str
+				):
+						try:
+							retrieved = self[
+								item
+							]
+							if not bool(
+								retrieved
+							):
+									return default
+							return retrieved
+						except (
+							KeyError,
+							AttributeError,
+							NotImplemented
+						):
+								return default
+				return self\
+					.to_datetime()
+	get = __call__
 	def set_(
 		self,
 		h: int = 0,
@@ -1661,7 +1701,15 @@ class Date:
 	def to_datetime(self) -> datetime.datetime:
 		return self\
 			.date_object
-	get_object = to_datetime
+	get_object =\
+		todt =\
+		to_dt =\
+		todatetime =\
+		to_datetime
+	@property
+	def dt(self) -> datetime.datetime:
+		return self\
+			.to_datetime()
 	def format(
 		self,
 		short: bool = False,
@@ -1691,7 +1739,7 @@ class Date:
 			return formatted_date\
 				.lstrip("0")\
 				.replace(" 0", " ")
-	get = get_long = long_get = get_full =\
+	get_long = long_get = get_full =\
 		full_get = read = parh =\
 		parho = full_read =\
 		read_full = long_read =\
@@ -1903,12 +1951,14 @@ class Date:
 				.date_object\
 				.day
 	d_nr =\
+		d_n =\
 		d_num =\
 		d_number =\
 		d_only =\
 		day_nr = day_num =\
 		din_nr = din_num =\
 		din_number =\
+		din_n =\
 		day_of_month =\
 		dom = day_number
 	get_d_nr =\
@@ -2558,6 +2608,13 @@ class Date:
 		increment_hour =\
 		dalo_h =\
 		daalo_h =\
+		dalo_ghanta =\
+		dalo_ghante =\
+		daalo_ghanta =\
+		daalo_ghante =\
+		dalo_hr = daalo_hr =\
+		dalo_hour = daalo_hour =\
+		dalo_hours = daalo_hours =\
 		add_h =\
 		add_hour
 	def remove_hour(
@@ -2579,6 +2636,10 @@ class Date:
 		decrement_hours = decrement_hour =\
 		subtract_hours = subtract_hour =\
 		nikalo_h = nikaalo_h =\
+		nikalo_ghanta =\
+		nikalo_ghante =\
+		nikaalo_ghanta =\
+		nikaalo_ghante =\
 		nikalo_hr = nikaalo_hr =\
 		nikalo_hour = nikaalo_hour =\
 		nikalo_hours = nikaalo_hours =\
@@ -2992,13 +3053,13 @@ class Date:
 		set_sec =\
 		set_second =\
 		set_seconds
-Tarikh = Tareekh = Date
+Tarikh = Tareekh = Dt = Date
 class Char(str):
 	def __new__(cls, value: Any):
 		if value is None:
 			return ""
 		character: str = ""
-		if isinstance(value, int|float):
+		if isinstance(value, (int, float)):
 			character = chr(
 				int(
 					value
@@ -3018,8 +3079,8 @@ char = Char
 Str = lafz = jumla = lambda x: str(x).strip() # trim the string after parsing
 # no one needs additional whitespace
 nr = num = Num = Nr = Number
-INFINITY = Infinity = infinity = Inf = inf
-INT_INFINITY = INTEGER_INFINITY = INTINFINITY = INTEGERINFINITY = IntInfinity = Int_Infinity = int_infinity = intinfinity = int_inf = IntInf = intinf = sys.maxsize
+INFINITY = Infinity = infinity = Inf = FLOAT_INFINITY = float_infinity = FLOAT_INF = float_inf = FLT_INF = flt_inf = inf
+INT_INFINITY = INTEGER_INFINITY = INTINFINITY = INTEGERINFINITY = IntInfinity = Int_Infinity = int_infinity = intinfinity = int_inf = IntInf = INT_INF = INTINF = intinf = sys.maxsize
 goto = open_link = link_kholo = kholo_link = webbrowser.open
 link = webbrowser
 _dir = os.getcwd()
@@ -3058,7 +3119,7 @@ class AbstractBaseClassMeta(ABCMeta):
 				if base_method_type == subclass_method_type:
 					continue
 				raise TypeError(
-					f"Concrete class '{name}' ke method '{method_name}' ka kism BASE CLASS '{base.__name__}' ke sath match nahi karta"
+					f"Concrete class '{name}' ke method '{method_name}' ka kism BASE CLASS '{base.__name__}' ke sath match karna chahie"
 				)
 		return cls
 # preserve the sequence
@@ -3132,11 +3193,27 @@ def ltype(o: object, max_depth: int = 6, _current_depth: int = 0) -> str:
 		return "..."
 	parsed_type = __ltype_helper_fn__(o)
 	if (not isinstance(o, Iterable) or 
-		isinstance(o, (str, bytes, bytearray, memoryview, Generator, Iterator, zip, map, builtins.filter, enumerate))):
+		isinstance(
+			o,
+			(
+				str,
+				bytes,
+				bytearray,
+				memoryview,
+				Generator,
+				Iterator,
+				zip,
+				map,
+				builtins.filter,
+				enumerate
+			)
+		)
+	):
 		return parsed_type
 	try:
-		if callable(getattr(o, "__len__", None)) and not len(o):
-			return parsed_type
+		if callable(getattr(o, "__len__", None))\
+			and not len(o):
+				return parsed_type
 	except Exception:
 		pass
 	if isinstance(o, Mapping):
@@ -3148,7 +3225,13 @@ def ltype(o: object, max_depth: int = 6, _current_depth: int = 0) -> str:
 			return parsed_type
 		filtered_items = [
 			(k, v) for k, v in items_snapshot 
-			if not (isinstance(k, str) and re.search(r"^\b(?:k[aeio]|mese)\b$", k))
+				if not (
+					isinstance(k, str)\
+						and re.search(
+							r"^\b(?:k[aeio]|mese)\b$",
+							k
+						)
+				)
 		]
 		if not filtered_items:
 			return parsed_type
@@ -4038,7 +4121,7 @@ def Int(
 				.strip()
 			x = replace(
 				x,
-				r"[^Ee\+\-\.\d]|(?<=[A-Za-z_])[Ee]|[Ee](?=[A-Za-z_])|(?<!\d)[\.\+\-](?!\d)",
+				r"[^Ee\+\-\.\d]|(?<=[A-Za-z_])[Ee]|[Ee\.](?![\d\+\-])|(?<![^\de\+\-\.])[\.\+\-](?=[^\de\+\-\.])",
 				""
 			)
 			if "e" in x:
@@ -4063,7 +4146,7 @@ def Int(
 		except (
 			ValueError,
 			TypeError
-		):
+		) as e:
 				return 0
 def Flt(
 	x: Union[
@@ -4087,7 +4170,7 @@ def Flt(
 			if isinstance(x, str):
 				x = replacei(
 					x.strip(),
-					r"[^Ee\+\-\.\d]|(?<=[A-Za-z_])[Ee]|[Ee](?=[A-Za-z_])|(?<!\d)[\.\+\-](?!\d)",
+					r"[^Ee\+\-\.\d]|(?<=[A-Za-z_])[Ee]|[Ee\.](?![\d\+\-])|(?<![^\de\+\-\.])[\.\+\-](?=[^\de\+\-\.])",
 					""
 				)
 			return float(
@@ -4096,7 +4179,7 @@ def Flt(
 		except (
 			ValueError,
 			TypeError
-		):
+		) as e:
 				return 0.0
 def is_pos(n: int|float) -> bool:
 	"""agar number ek positive number he to kehta he `Han`,
@@ -4368,7 +4451,10 @@ def numbered(x: str|list|tuple|dict, *args, **kwargs) -> list[list[Any], list[in
 	# allowing the following syntax:
 	#	for item, i in numbered(arr):
 	#		print("{i}. {item}")
-enumer = numbered
+enumer = with_index =\
+	sath_index = with_numbers =\
+	sath_numbers =\
+	numbered
 __old_list__ = builtins.list
 class Arr(__old_list__):
 	current_type = Any
@@ -5862,24 +5948,33 @@ def split_into_words(s: str) -> list[str]:
 	if not isinstance(s, str) or not s.strip(): return ""
 	return re.findall(WORD_RE, s)
 find_words = findwords = to_words = towords = to_word_list = towordlist = pakro_words = pakrowords = pakro_alfaaz = pakroalfaaz = split_into_words
-def json_load(filename: str) -> dict | list:
-	if not isinstance(filename, str) or not filename.strip():
-		return {}
-	filename = os.path.normpath(filename)
+def json_load(filename: str) -> Obj | list:
+	if not isinstance(filename, str)\
+		or not filename.strip():
+			return Obj()
+	filename = os.path.normpath(
+		filename
+	)
 	if "." not in filename:
 		filename += ".json"
 	if not os.path.exists(filename):
-		return {}
-	contents: Any = {}
+		return Obj()
+	contents: Any = Obj()
 	try:
-		with open(filename, mode="r") as file:
-			contents = json.load(file)
+		with open(
+			filename,
+			mode="r"
+		) as file:
+				contents = json.load(
+					file
+				)
 	except Exception as e:
 		print(e)
 	# the loaded contents can be a list, too
 	# not always a dictionary
-	if isinstance(contents, dict) and "Obj" in globals():
-		contents = Obj(contents)
+	if isinstance(contents, dict)\
+		and "Obj" in globals():
+			contents = Obj(contents)
 	return contents
 load_json = loadjson = jsonload = json_load
 def replace(src: str, to_replace: str|dict|None = None, replacement: str|Callable = "", ignore_case: bool = False, case_insensitive: bool = False, count: int = IntInfinity) -> str:
@@ -6506,7 +6601,7 @@ def asset(to_filename: str) -> str:
 	path: str = ""
 	try:
 		if either(hasattr(sys, '_MEIPASS'), getattr(sys, 'frozen', False)) and both("_filepaths" in globals(), "PROGRAMS_DIR" in dir(globals().get("_filepaths", {}))):
-			from _filepaths import PROGRAMS_DIR
+			from ._filepaths import PROGRAMS_DIR
 			path = os.path.join(PROGRAMS_DIR, to_filename)
 		else:
 			path = to_path(f"../{to_filename}")
@@ -6763,7 +6858,7 @@ if __name__ == "__main__":
 	print(belongs_to(IOError | OSError, Exception))
 	print(chuno(rng(1, 10), koi=2))
 	my_dict: dict[str, dict[str, str] | int] = {"name": {"first": "Mike", "last": "Dawson"}, "age": 22000}
-	from _klang_builtins import cust_print
+	from ._klang_builtins import cust_print
 	cust_print(my_dict)
 	print(deep_get(my_dict, "first"))
 	dt: Date = Date("2.44 am, Jan 24, 2002")
@@ -6792,7 +6887,7 @@ if __name__ == "__main__":
 	print(is_pin("1535"))
 	print(is_pin("153"))
 	print(ishex("#68fafe"))
-	countries: dict = load_json(r"json/countries.json")
+	countries: dict = load_json(r"json/country_namES")
 	print(countries)
 	arr = (1, 3.8, 7)
 	arr = _map(arr, str, lambda x: type(x) != float)
@@ -6855,4 +6950,23 @@ if __name__ == "__main__":
 	print("11.52 aM, jan 24 n!!2002")
 	print(encodeurl(decode(encode("hello world"))))
 	print(Date("3pm, Jan 24, 2002").view())
-	print(Date().set_time("  7 :.. 11 .:. 9 pm  ").set_mn(mn=2).set_d(d=14).set_yr(y=2003).change(month=6, year=2010)._str(s=True))
+	print(Date().time("  7 :.. 11 .:. 9 pm  ").set_m(66).set_mn(mn=13).set_d(d=14).set_yr(y=2003).change(year=2010).y(2028).mn(3).d(21).mn("SEptember ").remove_h(12).remove_min(60).h(11).m(13).s(12).p("pm").t(8, "am").nikalo_mn(1).nikalo_min(1).nikalo_s(2).rakho_time("5.11 am").ghante(3).zamana("pm").mahina(6).d(11).set_y(2023).din(21).parho())
+	print(Date("Jan 24, 2032") >= Date())
+	print(Date().set_time("11 pm").add_h(1))
+	print(Date().tomorrow())
+	print(Date().after_tomorrow())
+	print(Date.yesterday().yesterday())
+	print(Date().add_h(48, "pm"))
+	print(Date().remove_day().set_time("3pm"))
+	print(Date().time("  7 :.. 11 .:. 9 pm  ").dalo_ghante(50).remove_h(1).dalo_din(3).am().pm().am().pm().he_am(not False).add_m(3).add_wk(2)._str())
+	print(Date() + Date("1.30 pm, Jan 24 2002"))
+	dt = Date("Jan 4, 2026") & {"mn": 2} & {"y": 2020} & 3.50
+	dt &= (12, 11, 13, "pm")
+	dt["mn_num"] -= 1
+	print(dt["mn_num"])
+	print(dt)
+	print(Date(13)())
+	print(Flt(True))
+	print(Flt("hello worl200.4e-2d"))
+	print(Flt("       4.3e5 t hee e                      "))
+	print(countries)

{kl_py-0.3.9 → kl_py-0.4.0}/src/KL_Py/_custom_pandas.py

@@ -4,6 +4,126 @@ from ._translate import translate_for_jupyter
 from inspect import ismodule
 from collections import Counter
 
+def deep_cleaned(
+	data_input,
+	missing_threshold=0.9,
+	rows: bool = True,
+	index: bool = True,
+):
+		if data_input is None:
+			raise ValueError("Input data cannot be None.")
+		chaos_nulls = {
+			'', 'na', 'n/a', 'naa', 'null', 'nul', 'nll', 'nl', 'nil', 'none', 'non', 
+			'?', '-', 'nan', 'nat', 'undefined', 'inf', '-inf', 'tbd', 'tbh', 'tba',
+			'unknown', 'unkown', 'missing', 'msng', 'n.a.', 'n / a', 'none.',
+			'na/na', 'nullvalue', 'blank', 'empty', 'nil.', 'null value',
+			'no value', '<empty>', '<blank>'
+		}
+		try:
+			if isinstance(data_input, (str, os.PathLike)) or hasattr(data_input, 'read'):
+				df = pd.read_csv(
+					data_input, 
+					encoding='utf-8', 
+					encoding_errors='ignore',
+					low_memory=False
+				)
+			else:
+				df = data_input.copy()
+		except Exception as e:
+			raise RuntimeError(
+				f"Failed to ingest dataset: {e}"
+			)
+		if df.empty:
+			return df
+		if df.columns.duplicated().any():
+			cols = pd.Series(df.columns)
+			for dup in cols[cols.duplicated()].unique():
+				cols[cols[cols == dup].index.values.tolist()] = [f"{dup}_{i}" if i != 0 else dup for i in range(sum(cols == dup))]
+			df.columns = cols
+		for col in df.select_dtypes(include=['str']).columns:
+			try:
+				df[col] = (
+					df[col].astype(str)
+					.str.replace(r'(\d+)\.(\.+)(\d+)', r'\1.\3', regex=True)
+					.str.replace(r'[\x00-\x1F\x7F-\x9F]', '', regex=True)
+				)
+			except Exception:
+				continue
+		df.columns = (
+			df.columns.astype(str)
+			.str.strip()
+			.str.lower()
+			.str.encode('ascii', 'ignore')
+			.str.decode('ascii')
+			.str.replace(r'[^a-z0-9_]', '_', regex=True)
+			.str.replace(r'_+', '_', regex=True)
+			.str.strip('_')
+		)
+		df = df.loc[:, ~df.columns.str.lower().str.startswith("unnamed")]
+		df = df.replace([np.inf, -np.inf], np.nan)
+		for col in df.select_dtypes(include=['str']).columns:
+			try:
+				cleaned_str = df[col].astype(str).str.strip().str.lower()
+				is_null = cleaned_str.isin(chaos_nulls) | cleaned_str.isin(['nan', 'none', 'nat', 'inf', '-inf'])
+				df.loc[is_null, col] = np.nan
+				df[col] = df[col].astype(str).str.strip().str.replace(r'\s+', ' ', regex=True)
+				df.loc[df[col].isin(['nan', 'None', 'NAT']), col] = np.nan
+			except Exception:
+				continue
+		binary_map = {'yes': 1, 'y': 1, 'true': 1, 't': 1, 'no': 0, 'n': 0, 'false': 0, 'f': 0}
+		for col in df.select_dtypes(include=['str']).columns:
+			try:
+				non_nulls = df[col].dropna()
+				if len(non_nulls) > 0:
+					unique_vals = non_nulls.astype(str).str.lower().unique()
+					if len(unique_vals) > 0 and set(unique_vals).issubset(binary_map.keys()):
+						df[col] = df[col].astype(str).str.lower().map(binary_map)
+			except Exception:
+				continue
+		for col in df.columns:
+			if df[col].dtype == 'str':
+				try:
+					cleaned_series = (
+						df[col].astype(str)
+						.str.replace(r'[\$,%\s]', '', regex=True)
+						.str.replace(r'^\((.*)\)$', r'-\1', regex=True)
+						.str.replace(r'--+', '-', regex=True)
+					)
+					numeric_converted = pd.to_numeric(cleaned_series, errors='coerce')
+					if numeric_converted.notnull().sum() / max(df[col].notnull().sum(), 1) > 0.5:
+						df[col] = numeric_converted
+				except Exception:
+					continue
+		for col in df.select_dtypes(include=['str']).columns:
+			try:
+				sample = df[col].dropna().head(30)
+				if len(sample) > 3:
+					parsed_dates = pd.to_datetime(sample, errors='coerce')
+					if parsed_dates.notnull().sum() / len(sample) > 0.6:
+						df[col] = pd.to_datetime(df[col], errors='coerce')
+			except Exception:
+				continue
+		df = df.dropna(how='all', axis=0).dropna(how='all', axis=1)
+		if not df.empty and len(df.columns) > 0:
+			col_thresh = int((1 - missing_threshold) * len(df))
+			df = df.dropna(axis=1, thresh=col_thresh)
+		if not df.empty and len(df) > 0:
+			row_thresh = int((1 - missing_threshold) * len(df.columns))
+			df = df.dropna(axis=0, thresh=row_thresh)
+		if not df.empty:
+			cols_to_drop = []
+			for col in df.columns:
+				if df[col].dtype == 'str':
+					norm_series = df[col].astype(str).str.strip().str.lower()
+					if norm_series.nunique(dropna=False) <= 1:
+						cols_to_drop.append(col)
+				else:
+					if df[col].nunique(dropna=False) <= 1:
+						cols_to_drop.append(col)
+			df = df.drop(columns=cols_to_drop)
+			df = df.drop_duplicates()
+		return df
+
 def _safe_casefold(key: Any) -> Any:
 	if isinstance(key, str):
 		return key.strip().casefold()
@@ -74,7 +194,9 @@ try:
 			except AttributeError:
 				if cf_name in self.__dict__:
 					return self.__dict__[cf_name]
-				raise AttributeError(f"CustomSeries object has no attribute '{name}'")
+				raise AttributeError(
+					f"CustomSeries object has no attribute '{name}'"
+				)
 		def __setattr__(self, name: str, value: Any) -> None:
 			if name.startswith('_') or name in ('index', 'name', 'values'):
 				super().__setattr__(name, value)
@@ -413,7 +535,7 @@ try:
 				return self[
 					*items
 				]
-			self.quick_clean(
+			self.clean(
 				inplace=True,
 				**kwargs
 			)
@@ -442,13 +564,18 @@ try:
 			return self if in_place else result
 		drop = giraao = girao
 		bharona = bharo_na = bharonull = bharo_null = pd.DataFrame.fillna
-		def quick_clean(
+		def clean(
 			self,
+			deep: bool = True,
 			rows: bool = True,
 			index: bool = True,
 			inplace: bool = True
 		) -> pd.DataFrame:
 				df_copy: pd.DataFrame = self.copy()
+				if deep:
+					df_copy = deep_cleaned(
+						df_copy
+					)
 				minimal_column_cleaner = lambda c:\
 					re.sub(
 						r"\W",
@@ -490,10 +617,16 @@ try:
 						df_copy
 					)
 				return df_copy
-		pd.DataFrame.quick_clean =\
-			pd.DataFrame.qc =\
+		pd.DataFrame.clean =\
+			clean
+		quick_clean =\
 			qc =\
-			quick_clean
+			pd.DataFrame.quick_clean =\
+			pd.DataFrame.qc =\
+				partialmethod(
+					clean,
+					deep=False
+				)
 		@classmethod
 		def rcsv(cls, filepath_or_buffer, *args, **kwargs):
 			if isinstance(
@@ -551,7 +684,7 @@ try:
 						pd.DataFrame(
 							self
 						),
-						dtype=kwargs.get(
+						dtype=kwargs.pop(
 							"dtype",
 							int
 						),
@@ -1026,10 +1159,10 @@ print(tips["tip.darmyan(1..3)"])
 print(tips["tip.darmyan(1..3)"] == tips["tip darmyan 1..3"])
 print(len(tips["tip.darmyan(1..3)"]) == len(tips["tip darmyan 1..3"]))
 print(tips["tip darmyan [1, 3, 5]"])
-new_df = pd.DF({"####@$ . Tenant ID": [f"@D00{n}" for n in range(1, 3+1)]}, index=[f"$$$$   ....Apartment {n}" for n in range(1, 3+1)])
+new_df = pd.DF({"test92)___": ["-5000", "-5.5", "+20.52"], "####@$ . Tenant ID (USD)": [f"$@D00{n}" for n in range(1, 3+1)]}, index=[f"$$$$   ....Apartment {n}" for n in range(1, 3+1)])
 new_df_clean = new_df()
 tips.ohe(col="sex", inplace=True)
 print(tips.remove_ohe(cols="day|smoker|sex|time", inplace=True).columns.tolist())
 print(tips.head(3))
-
+print(new_df.clean())
 """