KL-Py 0.3.3__tar.gz → 0.3.5__tar.gz

{kl_py-0.3.3 → kl_py-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: KL_Py
-Version: 0.3.3
+Version: 0.3.5
 Summary: A Python simplification module
 Author-email: Abbaskhurram255 <abbaskhurram255@gmail.com>
 Classifier: Programming Language :: Python :: 3

{kl_py-0.3.3 → kl_py-0.3.5}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "KL_Py"
-version = "0.3.3"
+version = "0.3.5"
 authors = [
     { name = "Abbaskhurram255", email = "abbaskhurram255@gmail.com" }
 ]

{kl_py-0.3.3 → kl_py-0.3.5}/src/KL_Py/_custom_pandas.py

@@ -162,79 +162,257 @@ try:
 			x = translate_for_jupyter(x)
 			x = replace(x, r"\bf(?=[\"'])", "")
 			if re.search(r"\bra?nge?\(.+(?<!\){2})\)", x):
-				rng_as_str: str = re.search(r"\bra?nge?\(.+(?<!\){2})\)", x).group()
+				rng_as_str: str = re.search(
+					r"\bra?nge?\(.+(?<!\){2})\)",
+					x
+				)\
+					.group()
 				evaled_rng: list[int] = []
 				try:
-					evaled_rng = list(eval(rng_as_str))
+					evaled_rng = list(
+						eval(
+							rng_as_str
+						)
+					)
 				except Exception:
 					...
-				x = replace(x, r"\bra?nge?\(.+(?<!\){2})\)", str(evaled_rng))
-			strings: list[str] = find_matches(x, r"(?<![\"\\])[kflerb]*(?:\"{3}|\"{1})[^\"]*(?:\"{1}|\"{3})(?!\")") + find_matches(x, r"(?<![\'\\])[kflerb]*(?:\'{1}|\'{3})[^\'\"]*(?:\'{1}|\'{3})(?!\')")
+				x = replace(
+					x,
+					r"\bra?nge?\(.+(?<!\){2})\)",
+					str(
+						evaled_rng
+					)
+				)
+			strings: list[str] = find_matches(
+				x,
+				r"(?<![\"\\])[kflerb]*(?:\"{3}|\"{1})[^\"]*(?:\"{1}|\"{3})(?!\")"
+			) +\
+				find_matches(
+					x,
+					r"(?<![\'\\])[kflerb]*(?:\'{1}|\'{3})[^\'\"]*(?:\'{1}|\'{3})(?!\')"
+				)
 			for i, string in enumerate(strings):
-				if re.search(r"^\w+(?=[\"\'])", strings[i]):
-					strings[i] = replace(strings[i], r"^\w+(?=[\"\'])", "")
-				strings[i] = replace(strings[i], r"\{(.*)\}", "$${1}")
-				x = x.replace(string, f"__STRING_{i}__")
-			x = replace(x, r", (?=[A-Za-z_])", " and ")
+				if re.search(
+					r"^\w+(?=[\"\'])",
+					strings[i]
+				):
+						strings[i] = replace(
+							strings[i],
+							r"^\w+(?=[\"\'])",
+							""
+						)
+				strings[i] = replace(
+					strings[i],
+					r"\{(.*)\}",
+					"$${1}"
+				)
+				x = x.replace(
+					string,
+					f"__STRING_{i}__"
+				)
+			x = replace(
+				x,
+				r", (?=[A-Za-z_])",
+				" and "
+			)
 			for j, string in enumerate(strings):
-				x = x.replace(f"__STRING_{j}__", string)
-			return self.__old_df_query__(x, *args, **kwargs)
-		query = choose_where = chuno = chuno_agar = chuno_jahan = chuno_jahaan = jahan = jahaan = select
+				x = x.replace(
+					f"__STRING_{j}__",
+					string
+				)
+			return self.__old_df_query__(
+				x,
+				*args,
+				**kwargs
+			)
+		query =\
+			choose_where =\
+			chuno =\
+			chuno_agar =\
+			chuno_jahan =\
+			chuno_jahaan =\
+			jahan =\
+			jahaan =\
+			select
 		def __getitem__(self, item: Any):
 			if isinstance(item, str):
 				item = item.strip()
 				return self.select(item)
 			if isinstance(item, (list, tuple)):
 				if type(item) == tuple:
-					stringified_slice: str = str(item)
-					if re.search(r"[\"\'](?=[,\)])", stringified_slice):
-						if re.search(r"slice\([\"\']", stringified_slice) and Counter(re.split(r"\W", stringified_slice))["slice"] != 2:
-							return self.loc[:, item]
+					stringified_slice: str = str(
+						item
+					)
+					if re.search(
+						r"[\"\'](?=[,\)])",
+						stringified_slice
+					):
+							if re.search(
+								r"slice\([\"\']",
+								stringified_slice
+							)\
+								and Counter(
+									re.split(
+										r"\W",
+										stringified_slice
+									)
+								)\
+									["slice"]\
+										!= 2:
+											return self\
+												.loc[:, item]
+							return self.loc[
+								item
+							]
+				if all(
+					isinstance(
+						sub_item,
+						str
+					)\
+							for sub_item\
+							in item
+				):
+								return self.select(
+									list(
+										item
+									)
+								)
+			if isinstance(
+				item,
+				slice
+			):
+					stringified_slice: str = str(
+						item
+					)
+					if re.search(
+						r"[\"\'](?=[,\)])",
+						stringified_slice
+					):
+						if re.search(
+							r"slice\([\"\']",
+							stringified_slice
+						)\
+							and Counter(
+								re.split(
+									r"\W",
+									stringified_slice
+								)
+							)\
+								["slice"]\
+									!= 2:
+										return self\
+											.loc[:, item]
 						return self.loc[item]
-				if all(isinstance(sub_item, str) for sub_item in item):
-					return self.select(list(item))
-			if isinstance(item, slice):
-				stringified_slice: str = str(item)
-				if re.search(r"[\"\'](?=[,\)])", stringified_slice):
-					if re.search(r"slice\([\"\']", stringified_slice) and Counter(re.split(r"\W", stringified_slice))["slice"] != 2:
-						return self.loc[:, item]
-					return self.loc[item]
-				return self.iloc[item]
-			if (isinstance(item, int) and -len(self.index) <= item < len(self.index)) or (isinstance(item, (list, tuple)) and all(isinstance(sub_item, int) for sub_item in item)):
-				return self.iloc[item]
-			return super().__getitem__(_safe_casefold(item))
+					return self.iloc[item]
+			if (
+				isinstance(item, int)\
+					and -len(
+						self.index
+					) <= item <\
+						len(
+							self.index
+						)
+			)\
+				or (
+					isinstance(
+						item,
+						(
+							list,
+							tuple
+						)
+					)\
+					and all(
+						isinstance(
+							sub_item,
+							int
+						)\
+							for sub_item\
+							in item
+					)
+				):
+						return self.iloc[
+							item
+						]
+			return super().__getitem__(
+				_safe_casefold(
+					item
+				)
+			)
 		ka = ke = ki = __getitem__
-		def __setitem__(self, key: Any, value: Any) -> None:
-			super().__setitem__(_safe_casefold(key), value)
-		def __getattr__(self, name: str) -> Any:
-			if name.startswith('_') or name in self.__dict__:
-				return super().__getattribute__(name)
-			cf_name = name.casefold()
-			if hasattr(self, 'columns')\
-				and cf_name in self.columns:
-					return self[cf_name]
-			try:
-				return super().__getattribute__(name)
-			except AttributeError:
-				if cf_name in self.__dict__:
-					return self.__dict__[cf_name]
-				raise AttributeError(f"CustomDataFrame object has no attribute '{name}'")
+		def __setitem__(
+			self,
+			key: Any,
+			value: Any
+		) -> None:
+				super().__setitem__(
+					_safe_casefold(
+						key
+					),
+					value
+				)
+		def __getattr__(
+			self,
+			name: str
+		) -> Any:
+				if name.startswith('_')\
+					or name in self.__dict__:
+						return super()\
+							.__getattribute__(
+								name
+							)
+				cf_name = name\
+					.casefold()
+				if hasattr(self, 'columns')\
+					and cf_name in self.columns:
+						return self[
+							cf_name
+						]
+				try:
+					return super().__getattribute__(
+						name
+					)
+				except AttributeError:
+					if cf_name in self.__dict__:
+						return self.__dict__[
+							cf_name
+						]
+					raise AttributeError(
+						f"CustomDataFrame object has no attribute '{name}'"
+					)
 		def __setattr__(self, name: str, value: Any) -> None:
-			if name.startswith('_') or name in ('columns', 'index', 'values'):
-				super().__setattr__(name, value)
-				return
+			if name.startswith('_')\
+				or name in (
+					'columns',
+					'index',
+					'values'
+				):
+					super().__setattr__(
+						name,
+						value
+					)
+					return
 			cf_name = name.casefold()
 			if hasattr(self, 'columns')\
-				and cf_name in self.columns:
-					self[cf_name] = value
+				and cf_name\
+					in self.columns:
+						self[
+							cf_name
+						] = value
 			else:
-				super().__setattr__(name, value)
+				super().__setattr__(
+					name,
+					value
+				)
 		def __call__(self, *items, **kwargs):
 			if items:
 				if len(items) == 1:
 					item = items[0]
-					return self[item]
-				return self[*items]
+					return self[
+						item
+					]
+				return self[
+					*items
+				]
 			self.quick_clean(
 				inplace=True,
 				**kwargs
@@ -340,33 +518,144 @@ try:
 			pd.read_csv =\
 			pd.parho_csv =\
 				rcsv
+		def ohe(
+			self,
+			col=None,
+			cols=None,
+			inplace: bool = False,
+			*args,
+			**kwargs
+		) -> Self:
+				c = kwargs.get(
+					"columns",
+					cols
+				)\
+					or col
+				if isinstance(
+					c,
+					str
+				):
+						if "|"\
+							in str(
+								c
+							):
+								c = re.split(
+									r" *\| *",
+									c
+								)
+						else:
+							c = [c]
+				kwargs["columns"] = c
+				df_copy: CustomDataFrame = CustomDataFrame(
+					__old_ohe__(
+						pd.DataFrame(
+							self
+						),
+						dtype=kwargs.get(
+							"dtype",
+							int
+						),
+						*args,
+						**kwargs
+					)
+				)
+				if inplace:
+					self.__init__(
+						df_copy
+					)
+					return self
+				return df_copy
 		make_dummies =\
 			get_dummies =\
 			make_ohe =\
+			add_ohe =\
 			ohe =\
 			one_hot_encoding =\
 			make_one_hot_encoding =\
 			pd.make_dummies =\
 			pd.make_ohe =\
+			pd.add_ohe =\
 			pd.make_one_hot_encoding =\
 			pd.one_hot_encoding =\
 			pd.ohe =\
-				lambda self, *args, **kwargs:\
-					CustomDataFrame(
-						__old_ohe__(
-							pd.DataFrame(
-								self
-							),
-							*args,
-							**kwargs
-						)
-					)
+				ohe
 		def remove_ohe(
 			self,
 			prefix: str = None,
-			col: str = None
+			col: str = None,
+			cols: Optional[
+				Union[
+					list,
+					tuple,
+					set
+				]
+			] = None,
+			columns: Optional[
+				Union[
+					list,
+					tuple,
+					set
+				]
+			] = None,
+			inplace: bool = False
 		) -> "CustomDataFrame":
-				df_copy = self.copy()
+				df_copy: CustomDataFrame =\
+					self.copy()
+				prefix = prefix\
+					or col\
+					or cols\
+					or columns
+				if isinstance(
+					prefix,
+					str
+				)\
+					and "|"\
+						in str(
+							prefix
+						):
+							prefix = re.split(
+								r" *\| *",
+								prefix
+							)
+				if isinstance(
+					prefix,
+					(
+						list,
+						tuple,
+						set
+					)
+				):
+						items = list(
+							prefix
+						)
+						for i, item in enumerate(
+							items
+						):
+							if not isinstance(
+								item,
+								str
+							):
+									continue
+							if inplace:
+								self\
+									.remove_ohe(
+										prefix=item,
+										col=col,
+										cols=cols,
+										columns=columns,
+										inplace=True
+									)
+							else:
+								df_copy = df_copy\
+									.remove_ohe(
+										prefix=item,
+										col=col,
+										cols=cols,
+										columns=columns
+									)
+						if inplace:
+							return self
+						return df_copy
 				if not isinstance(prefix, str):
 					prefix = ""
 				if not isinstance(col, str):
@@ -385,7 +674,10 @@ try:
 					):
 							prefix_cf += "_"
 				if not prefix_cf:
-					print("A prefix is needed")
+					print(
+						"OHE Removal Failed."+\
+							"\nA prefix is needed!"
+					)
 					return self
 				if not col\
 					and re.search(
@@ -431,11 +723,17 @@ try:
 				df_copy[
 					col.strip().casefold()
 				] = restored_series
-				return CustomDataFrame(
+				df_copy = CustomDataFrame(
 					df_copy.drop(
 						columns=ohe_cols
 					)
 				)
+				if inplace:
+					self.__init__(
+						df_copy
+					)
+					return self
+				return df_copy
 		drop_ohe =\
 			clear_ohe =\
 			drop_one_hot_encoding =\
@@ -451,7 +749,8 @@ try:
 			self,
 			col: str,
 			sep: str = "|",
-			min_freq: int = 0
+			min_freq: int = 0,
+			inplace: bool = False
 		) -> "CustomDataFrame":
 				if not isinstance(col, str):
 					col = ""
@@ -557,7 +856,7 @@ try:
 					],
 					errors="ignore"
 				)
-				return CustomDataFrame(
+				df_copy: CustomDataFrame = CustomDataFrame(
 					pd.concat(
 						[
 							df_retained,
@@ -566,6 +865,12 @@ try:
 						axis=1
 					)
 				)
+				if inplace:
+					self.__init__(
+						df_copy
+					)
+					return self
+				return df_copy
 		multi_hot_encoding =\
 			make_multi_hot_encoding =\
 			make_mhe =\
@@ -723,5 +1028,8 @@ 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_clean = new_df()
-print(lkism(tips))
+tips.ohe(col="sex", inplace=True)
+print(tips.remove_ohe(cols="day|smoker|sex|time", inplace=True).columns.tolist())
+print(tips.head(3))
+
 """