KL-Py 0.3.2__tar.gz → 0.3.4__tar.gz

{kl_py-0.3.2 → kl_py-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: KL_Py
-Version: 0.3.2
+Version: 0.3.4
 Summary: A Python simplification module
 Author-email: Abbaskhurram255 <abbaskhurram255@gmail.com>
 Classifier: Programming Language :: Python :: 3

{kl_py-0.3.2 → kl_py-0.3.4}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "KL_Py"
-version = "0.3.2"
+version = "0.3.4"
 authors = [
     { name = "Abbaskhurram255", email = "abbaskhurram255@gmail.com" }
 ]

{kl_py-0.3.2 → kl_py-0.3.4}/src/KL_Py/_custom_pandas.py

@@ -21,6 +21,8 @@ try:
 	ROW, COLUMN = 0, 1
 	pd.ROW = ROW
 	pd.COLUMN = COLUMN
+	__old_ohe__ = pd.get_dummies
+	__old_rcsv__ = pd.read_csv
 	class CustomSeries(pd.Series):
 		@property
 		def _constructor(self):
@@ -64,8 +66,9 @@ try:
 			if name.startswith('_') or name in self.__dict__:
 				return super().__getattribute__(name)
 			cf_name = name.casefold()
-			if cf_name in self.index:
-				return self[cf_name]
+			if hasattr(self, 'index')\
+				and cf_name in self.index:
+					return self[cf_name]
 			try:
 				return super().__getattribute__(name)
 			except AttributeError:
@@ -77,8 +80,9 @@ try:
 				super().__setattr__(name, value)
 				return
 			cf_name = name.casefold()
-			if hasattr(self, 'index') and cf_name in self.index:
-				self[cf_name] = value
+			if hasattr(self, 'index')\
+				and cf_name in self.index:
+					self[cf_name] = value
 			else:
 				super().__setattr__(name, value)
 		bharona = bharo_na = bharonull = bharo_null = pd.Series.fillna
@@ -111,18 +115,25 @@ try:
 			else:
 				new_columns = [x.casefold() if isinstance(x, str) else x for x in new_columns]
 			super(CustomDataFrame, type(self)).columns.__set__(self, new_columns)
-		def __init__(self, data=None, index=None, columns=None, *args, **kwargs) -> None:
-			if isinstance(data, dict):
-				data = {_safe_casefold(k): v for k, v in data.items() if not callable(v)}
-			elif type(data) in (pd.DataFrame, CustomDataFrame):
-				index = data.index if index is None else index
-				columns = data.columns if columns is None else columns
-				data = data.values
-			super().__init__(data, index, columns, *args, **kwargs)
-			if self.columns.map(lambda x: isinstance(x, str)).any():
-				self.columns = self.columns.map(lambda x: x.casefold() if isinstance(x, str) else x)
-			if self.index.map(lambda x: isinstance(x, str)).any():
-				self.index = self.index.map(lambda x: x.casefold() if isinstance(x, str) else x)
+		def __init__(
+			self,
+			data=None,
+			index=None,
+			columns=None,
+			*args,
+			**kwargs
+		) -> None:
+				if isinstance(data, dict):
+					data = {_safe_casefold(k): v for k, v in data.items() if not callable(v)}
+				elif type(data) in (pd.DataFrame, CustomDataFrame):
+					index = data.index if index is None else index
+					columns = data.columns if columns is None else columns
+					data = data.values
+				super().__init__(data, index, columns, *args, **kwargs)
+				if self.columns.map(lambda x: isinstance(x, str)).any():
+					self.columns = self.columns.map(lambda x: x.casefold() if isinstance(x, str) else x)
+				if self.index.map(lambda x: isinstance(x, str)).any():
+					self.index = self.index.map(lambda x: x.casefold() if isinstance(x, str) else x)
 		__old_df_query__ = pd.DataFrame.query
 		def select(self, x: str|list[str], *args, **kwargs) -> None:
 			if isinstance(x, list) and all(isinstance(sub_item, str) for sub_item in x):
@@ -199,8 +210,9 @@ try:
 			if name.startswith('_') or name in self.__dict__:
 				return super().__getattribute__(name)
 			cf_name = name.casefold()
-			if cf_name in self.columns:
-				return self[cf_name]
+			if hasattr(self, 'columns')\
+				and cf_name in self.columns:
+					return self[cf_name]
 			try:
 				return super().__getattribute__(name)
 			except AttributeError:
@@ -212,15 +224,20 @@ try:
 				super().__setattr__(name, value)
 				return
 			cf_name = name.casefold()
-			if hasattr(self, 'columns') and cf_name in self.columns:
-				self[cf_name] = value
+			if hasattr(self, 'columns')\
+				and cf_name in self.columns:
+					self[cf_name] = value
 			else:
 				super().__setattr__(name, value)
-		def __call__(self, item=None):
-			if item is not None:
-				return self[item]
+		def __call__(self, *items, **kwargs):
+			if items:
+				if len(items) == 1:
+					item = items[0]
+					return self[item]
+				return self[*items]
 			self.quick_clean(
-				inplace=True
+				inplace=True,
+				**kwargs
 			)
 			return self
 		def girao(self, labels: list[str] | None = None, *args, **kwargs):
@@ -250,6 +267,7 @@ try:
 		def quick_clean(
 			self,
 			rows: bool = True,
+			index: bool = True,
 			inplace: bool = True
 		) -> pd.DataFrame:
 				df_copy: pd.DataFrame = self.copy()
@@ -258,7 +276,7 @@ try:
 						r"\W",
 						"",
 						re.sub(
-							r"\s{2,}",
+							r"\s+",
 							" ",
 							str(c).strip("_ ")
 						).replace(" ", "_")
@@ -266,28 +284,335 @@ try:
 				df_copy = df_copy.rename(
 					columns=minimal_column_cleaner
 				)
+				# for columns ^
+				if index:
+					df_copy.index = df_copy.index.map(
+						minimal_column_cleaner
+					)
+				# for indices ^
 				if rows:
-					minimal_row_cleaner = lambda x:\
+					minimal_row_cleaner = lambda value:\
 						re.sub(
 							r"^[^\-\.A-Za-z\d]+|[^\-\.A-Za-z\d]+$",
 							"",
 							re.sub(
-								r"\s{2,}",
+								r"\s+",
 								" ",
-								x.strip("_ ")
+								value.strip("_ ")
 							)
 						).strip("_ ")\
-							if isinstance(x, str) else x
+								if isinstance(value, str)\
+								else value
 					df_copy = df_copy.map(
 						minimal_row_cleaner
 					)
+				# for rows ^
 				if inplace:
 					self.__init__(
 						df_copy
 					)
 				return df_copy
-		pd.DataFrame.quick_clean = pd.DataFrame.qc = qc = quick_clean
-	pd.DF = KlDF = KDF = KlangDF = KlangDataFrame = SuperDF = SuperDataFrame = CustomDF = CustomDataFrame
+		pd.DataFrame.quick_clean =\
+			pd.DataFrame.qc =\
+			qc =\
+			quick_clean
+		@classmethod
+		def rcsv(cls, filepath_or_buffer, *args, **kwargs):
+			if isinstance(
+				filepath_or_buffer,
+				str
+			)\
+				and not filepath_or_buffer\
+					.strip()\
+					.lower()\
+					.endswith(".csv"):
+						filepath_or_buffer += ".csv"
+			return cls(
+				__old_rcsv__(
+					filepath_or_buffer=filepath_or_buffer,
+					*args,
+					**kwargs
+				)
+			)
+		read_csv =\
+			parho_csv =\
+			pd.rcsv =\
+			pd.read_csv =\
+			pd.parho_csv =\
+				rcsv
+		make_dummies =\
+			get_dummies =\
+			make_ohe =\
+			ohe =\
+			one_hot_encoding =\
+			make_one_hot_encoding =\
+			pd.make_dummies =\
+			pd.make_ohe =\
+			pd.make_one_hot_encoding =\
+			pd.one_hot_encoding =\
+			pd.ohe =\
+				lambda self, *args, **kwargs:\
+					CustomDataFrame(
+						__old_ohe__(
+							pd.DataFrame(
+								self
+							),
+							*args,
+							**kwargs
+						)
+					)
+		def remove_ohe(
+			self,
+			prefix: str = None,
+			col: str = None
+		) -> "CustomDataFrame":
+				df_copy = self.copy()
+				if not isinstance(prefix, str):
+					prefix = ""
+				if not isinstance(col, str):
+					col = ""
+				prefix_cf = prefix\
+					.strip()\
+					.casefold()
+				col = col.strip()
+				if not prefix_cf\
+					and col:
+						prefix_cf = col
+						col = ""
+				if prefix_cf\
+					and not prefix_cf.endswith(
+						"_"
+					):
+							prefix_cf += "_"
+				if not prefix_cf:
+					print("A prefix is needed")
+					return self
+				if not col\
+					and re.search(
+						r"(?<=.)_$",
+						re.escape(
+							prefix_cf
+						)
+					):
+						col = prefix_cf.rsplit(
+							"_",
+							1
+						)[0]
+				ohe_cols = [
+					col\
+						for col in df_copy\
+							.columns\
+								if str(col)\
+									.lower()\
+									.startswith(
+										prefix_cf
+									)
+				]
+				if not ohe_cols:
+					print(
+						f"WARNING: "\
+							+ f"No columns found matching prefix '{prefix_cf}'"
+					)
+					return self
+				if not col:
+					print("A col(umn) is needed")
+					return self
+				restored_series = df_copy[
+					ohe_cols
+				].idxmax(
+					axis=1
+				).apply(
+					lambda x: str(x)[
+						len(prefix_cf):
+					]\
+						if pd.notna(x)\
+						else None
+				)
+				df_copy[
+					col.strip().casefold()
+				] = restored_series
+				return CustomDataFrame(
+					df_copy.drop(
+						columns=ohe_cols
+					)
+				)
+		drop_ohe =\
+			clear_ohe =\
+			drop_one_hot_encoding =\
+			clear_one_hot_encoding =\
+			remove_one_hot_encoding =\
+			pd.drop_ohe =\
+			pd.clear_ohe =\
+			pd.drop_one_hot_encoding =\
+			pd.clear_one_hot_encoding =\
+			pd.remove_one_hot_encoding =\
+				remove_ohe
+		def mhe(
+			self,
+			col: str,
+			sep: str = "|",
+			min_freq: int = 0
+		) -> "CustomDataFrame":
+				if not isinstance(col, str):
+					col = ""
+				col = col\
+					.strip()\
+					.lower()
+				if not isinstance(sep, str):
+					sep = ""
+				if not sep.strip():
+					sep = "|"
+				if isinstance(min_freq, float):
+					min_freq = int(
+						round(
+							min_freq,
+							0
+						)
+					)
+				if not isinstance(min_freq, int):
+					min_freq = 0
+				if col not in self.columns:
+					raise KeyError(
+						f"Column '{col}' does not exist in CustomDataFrame."
+					)
+				srs = self[col]
+				parsed_rows: list[
+					list[
+						str
+					]
+				] = []
+				all_categories = Counter()
+				for val in srs:
+					row_items = set()
+					if isinstance(val, (list, tuple, set)):
+						for item in val:
+							if item is not None\
+								and not pd.isna(item):
+									row_items.add(
+										str(item)\
+											.strip()\
+											.casefold()
+									)
+					elif isinstance(val, str):
+						if sep and sep in val:
+							for item in val.split(sep):
+								row_items.add(
+									item\
+										.strip()\
+										.casefold()
+								)
+						else:
+							row_items.add(
+								val.strip().casefold()
+							)
+					elif pd.notna(val):
+						row_items.add(
+							str(val).strip().casefold()
+						)
+					row_items.discard('')
+					parsed_rows.append(
+						list(row_items)
+					)
+					all_categories.update(
+						row_items
+					)
+				valid_classes = sorted([
+					cat\
+						for cat, count\
+							in all_categories.items()\
+								if count >= min_freq
+				])
+				class_to_idx = {
+					cls_: idx\
+						for idx, cls_ in enumerate(
+							valid_classes
+						)
+				}
+				matrix = [
+					[0] * len(valid_classes)\
+						for _ in range(
+							len(
+								srs
+							)
+						)
+				]
+				for row_idx, items in enumerate(parsed_rows):
+					for item in items:
+						if item in class_to_idx:
+							matrix[
+								row_idx
+							][
+								class_to_idx[
+									item
+								]
+							] = 1
+				mhe_df: CustomDataFrame = CustomDataFrame(
+					matrix,
+					index=self.index,
+					columns=valid_classes
+				)
+				df_retained = self.drop(
+					columns=[
+						col
+					],
+					errors="ignore"
+				)
+				return CustomDataFrame(
+					pd.concat(
+						[
+							df_retained,
+							mhe_df
+						],
+						axis=1
+					)
+				)
+		multi_hot_encoding =\
+			make_multi_hot_encoding =\
+			make_mhe =\
+			pd.multi_hot_encoding =\
+			pd.make_multi_hot_encoding =\
+			pd.make_mhe =\
+			pd.mhe =\
+				mhe
+	rcsv =\
+		read_csv =\
+		parho_csv =\
+		pd.rcsv =\
+		pd.read_csv =\
+		pd.parho_csv =\
+			CustomDataFrame.rcsv
+	ohe =\
+		one_hot_encoding =\
+		make_ohe =\
+		make_one_hot_encoding =\
+		make_dummies =\
+		get_dummies =\
+		pd.ohe =\
+		pd.one_hot_encoding =\
+		pd.make_ohe =\
+		pd.make_one_hot_encoding =\
+		pd.make_dummies =\
+			CustomDataFrame.ohe
+	mhe =\
+		make_mhe =\
+		make_multi_hot_encoding =\
+		multi_hot_encoding =\
+		get_dummies_for_multi =\
+		pd.mhe =\
+		pd.make_mhe =\
+		pd.make_multi_hot_encoding =\
+		pd.make_dummies_for_multi =\
+		pd.multi_hot_encoding =\
+			CustomDataFrame.mhe
+	pd.DF =\
+		KlDF =\
+		KDF =\
+		KlangDF =\
+		KlangDataFrame =\
+		SuperDF =\
+		SuperDataFrame =\
+		CustomDF =\
+		CustomDataFrame
 	rcsv = pd.rcsv = pd.read_csv
 	rcb = pd.rcb = pd.read_clipboard
 	rxl = pd.rxl = pd.rxls = pd.read_excel
@@ -353,11 +678,11 @@ try:
 	# lets make it global entirely
 except ImportError:
 	pass
-"""
 
+"""
 
 import pandas
-df = pandas.DF({"Name": ["Lois", "Timothy"], "Age": [27, 51]})
+df = pandas.DF({"NamE": ["Lois", "Timothy"], "Age": [27, 51]})
 df.drop(["age"], perma=No)
 #print(df.jahaan("Name nahi he ?"))
 #print(df.jahaan("Name, aur Age"))
@@ -381,7 +706,6 @@ print(tips.query("tip darmyan 3..5"))
 print("break")
 start, end = 1, 2
 print(tips["@start chota tip se joke khud choti ya barabar @end ke"])
-new_df = pd.DataFrame({"Tenant_ID": [f"D00{n}" for n in range(1, 3+1)]}, index=[f"Apartment {n}" for n in range(1, 3+1)])
 
 print(tips[:2, "tip":"day"])
 print(tips[0, 2])
@@ -397,4 +721,7 @@ 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_clean = new_df()
+print(lkism(tips))
 """