pytae 2.3.3__tar.gz → 2.3.4__tar.gz

{pytae-2.3.3 → pytae-2.3.4}/.ipynb_checkpoints/pyproject-checkpoint.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "pytae"
-version = "2.3.3"
+version = "2.3.4"
 description = "A package to enhance common day to day tasks in the life of a data scientist"
 authors = [{ name = "Madhukar Kumar Jha", email = "madhukar.k.jha@gmail.com" }]
 readme = "README.md"

{pytae-2.3.3 → pytae-2.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pytae
-Version: 2.3.3
+Version: 2.3.4
 Dynamic: Requires-Dist
 Summary: A package to enhance common day to day tasks in the life of a data scientist
 Project-URL: Homepage, https://github.com/maddytae/pytae

{pytae-2.3.3 → pytae-2.3.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "pytae"
-version = "2.3.3"
+version = "2.3.4"
 description = "A package to enhance common day to day tasks in the life of a data scientist"
 authors = [{ name = "Madhukar Kumar Jha", email = "madhukar.k.jha@gmail.com" }]
 readme = "README.md"

pytae-2.3.4/src/.ipynb_checkpoints/other_utilities-checkpoint.ipynb

@@ -0,0 +1,152 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "af0e75c1-7748-44e7-974e-34112d92d813",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import pytae as pt\n",
+    "import seaborn as sns\n",
+    "penguins = sns.load_dataset('penguins')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e42e01b5-4b00-4f95-acec-274deda67a3c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# get a list of columns\n",
+    "penguins.cols()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7136bed-d2e1-48c5-a337-8e31fc020a98",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#add a group count\n",
+    "df = (\n",
+    "    penguins\n",
+    "    .group_x()\n",
+    ")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "87e3dd20-d5e1-4219-8aee-e842a3d52194",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# handle missing i.e. str missing or NaN is changed to . and numeric NaN to 0\n",
+    "\n",
+    "df = (\n",
+    "    penguins\n",
+    "    .handle_missing(fillna='$')\n",
+    ")\n",
+    "df.head()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b17a9574-35ff-4fe2-b40f-054a0b5e5003",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.clip()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b39ba218-6361-47eb-91b2-c6f35b7a130e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "penguins\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cf3bf0ae-b4ea-45ad-a358-c3eb5042e039",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "penguins.select('spe|sex|^n|^bi')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3a74dbdf-4afa-4b9c-af1e-22cd016bc39a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "penguins.select(['species','n'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f29560f9-bb6e-4b0f-a143-8c75be726609",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame(np.arange(12).reshape(3, 4),\n",
+    "                  columns=['A', 'B_X', 'B', 'C'])\n",
+    "\n",
+    "print('original df')\n",
+    "print(df)\n",
+    "\n",
+    "print('\\nselect using a list')\n",
+    "print(df.select(['A','B_X']))\n",
+    "\n",
+    "print('\\nselect using a regex')\n",
+    "print(df.select('^B|C'))\n",
+    "\n",
+    "print('\\nselect using a tuple of list and  regex')\n",
+    "print(df.select((['A','B_X'],'^B|C')))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "efde3bab-b430-4785-bfff-6ff1f515e6a6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "py_env",
+   "language": "python",
+   "name": "py_env"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

{pytae-2.3.3 → pytae-2.3.4}/src/.ipynb_checkpoints/plot_x-checkpoint.ipynb

@@ -141,7 +141,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "4c45df2e-49f3-4540-a1bf-caf19a3a6d45",
    "metadata": {},
    "outputs": [
@@ -152,7 +152,7 @@
        "<Figure size 1200x600 with 1 Axes>"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }

{pytae-2.3.3 → pytae-2.3.4}/src/other_utilities.ipynb

@@ -7,6 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import numpy as np\n",
     "import pandas as pd\n",
     "import pytae as pt\n",
     "import seaborn as sns\n",
@@ -783,9 +784,62 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "f29560f9-bb6e-4b0f-a143-8c75be726609",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "original df\n",
+      "   A  B_X   B   C\n",
+      "0  0    1   2   3\n",
+      "1  4    5   6   7\n",
+      "2  8    9  10  11\n",
+      "\n",
+      "select using a list\n",
+      "   A  B_X\n",
+      "0  0    1\n",
+      "1  4    5\n",
+      "2  8    9\n",
+      "\n",
+      "select using a regex\n",
+      "   B_X   B   C\n",
+      "0    1   2   3\n",
+      "1    5   6   7\n",
+      "2    9  10  11\n",
+      "\n",
+      "select using a tuple of list and  regex\n",
+      "    B   C  A  B_X\n",
+      "0   2   3  0    1\n",
+      "1   6   7  4    5\n",
+      "2  10  11  8    9\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = pd.DataFrame(np.arange(12).reshape(3, 4),\n",
+    "                  columns=['A', 'B_X', 'B', 'C'])\n",
+    "\n",
+    "print('original df')\n",
+    "print(df)\n",
+    "\n",
+    "print('\\nselect using a list')\n",
+    "print(df.select(['A','B_X']))\n",
+    "\n",
+    "print('\\nselect using a regex')\n",
+    "print(df.select('^B|C'))\n",
+    "\n",
+    "print('\\nselect using a tuple of list and  regex')\n",
+    "print(df.select((['A','B_X'],'^B|C')))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "efde3bab-b430-4785-bfff-6ff1f515e6a6",
+   "metadata": {},
    "outputs": [],
    "source": []
   }

{pytae-2.3.3 → pytae-2.3.4}/src/plot_x.ipynb

@@ -141,7 +141,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "4c45df2e-49f3-4540-a1bf-caf19a3a6d45",
    "metadata": {},
    "outputs": [
@@ -152,7 +152,7 @@
        "<Figure size 1200x600 with 1 Axes>"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }

{pytae-2.3.3 → pytae-2.3.4}/src/pytae/.ipynb_checkpoints/other_utilities-checkpoint.py

@@ -23,50 +23,48 @@ def handle_missing(self,fillna='.'):
 def cols(self):#this is for more general situations
     return sorted(self.columns.to_list())
 
-#select is more intuitive than filter. It needs a regex expression which is quite powerful
-#ex 
-def select(self, cols_or_regex):       
+#select is more intuitive than filter. It can handle a list or a regex or a tuple containing list and regex
+def select(self, cols_or_regex=None):
     '''
-    Select columns based on a list of column names or a regex pattern.
+    Select columns based on a list of column names, a regex pattern, or a tuple of both.
     
     Parameters:
     self (pd.DataFrame): The DataFrame from which to select columns.
-    cols_or_regex (list or str): List of column names or a regex pattern.
+    cols_or_regex (list, str, or tuple): 
+        - List of column names
+        - Regex pattern
+        - Tuple containing a list of column names and a regex pattern
     
     Returns:
     pd.DataFrame: A DataFrame with the selected columns.
     '''
-    if isinstance(cols_or_regex, list):
-        # Ensure all columns in the list exist in the DataFrame
+    
+    if isinstance(cols_or_regex, tuple):
+        if len(cols_or_regex) != 2:
+            raise ValueError("Tuple must contain exactly two elements: a list of columns and a regex pattern")
+        cols, regex = cols_or_regex
+        if not isinstance(cols, list) or not isinstance(regex, str):
+            raise TypeError("First element of tuple must be a list, and the second element must be a string (regex pattern)")
+        # Select columns based on the list and regex independently
+        selected_cols = list(set(cols + self.filter(regex=regex).columns.tolist()))
+        return self[selected_cols]
+    
+    elif isinstance(cols_or_regex, list):
         missing_cols = [col for col in cols_or_regex if col not in self.columns]
         if missing_cols:
             raise KeyError(f"Columns not found in the DataFrame: {missing_cols}")
         return self[cols_or_regex]
+    
     elif isinstance(cols_or_regex, str):
         return self.filter(regex=cols_or_regex)
+    
     else:
-        raise TypeError("cols_or_regex must be a list or a string")
-
-# # Example usage
-# data = {
-#     'apple': [1, 2, 3],
-#     'banana': [4, 5, 6],
-#     'apricot': [7, 8, 9],
-#     'cherry': [10, 11, 12]
-# }
-
-# # Create a DataFrame
-# df = pd.DataFrame(data)
-
-# # Select columns using a list of column names
-# selected_cols_list = select(df, ['apple', 'banana'])
-# print("Selected columns using list:")
-# print(selected_cols_list)
-
-# # Select columns using a regex pattern
-# selected_cols_regex = select(df, '^(apple|banana|cherry)$')
-# print("\nSelected columns using regex:")
-# print(selected_cols_regex)
+        raise TypeError("cols_or_regex must be a list, a regex string, or a tuple of (list, regex)")
+
+# Add the method to the DataFrame class
+pd.DataFrame.select = select
+
+
 
 
 

{pytae-2.3.3 → pytae-2.3.4}/src/pytae/other_utilities.py

@@ -23,50 +23,48 @@ def handle_missing(self,fillna='.'):
 def cols(self):#this is for more general situations
     return sorted(self.columns.to_list())
 
-#select is more intuitive than filter. It needs a regex expression which is quite powerful
-#ex 
-def select(self, cols_or_regex):       
+#select is more intuitive than filter. It can handle a list or a regex or a tuple containing list and regex
+def select(self, cols_or_regex=None):
     '''
-    Select columns based on a list of column names or a regex pattern.
+    Select columns based on a list of column names, a regex pattern, or a tuple of both.
     
     Parameters:
     self (pd.DataFrame): The DataFrame from which to select columns.
-    cols_or_regex (list or str): List of column names or a regex pattern.
+    cols_or_regex (list, str, or tuple): 
+        - List of column names
+        - Regex pattern
+        - Tuple containing a list of column names and a regex pattern
     
     Returns:
     pd.DataFrame: A DataFrame with the selected columns.
     '''
-    if isinstance(cols_or_regex, list):
-        # Ensure all columns in the list exist in the DataFrame
+    
+    if isinstance(cols_or_regex, tuple):
+        if len(cols_or_regex) != 2:
+            raise ValueError("Tuple must contain exactly two elements: a list of columns and a regex pattern")
+        cols, regex = cols_or_regex
+        if not isinstance(cols, list) or not isinstance(regex, str):
+            raise TypeError("First element of tuple must be a list, and the second element must be a string (regex pattern)")
+        # Select columns based on the list and regex independently
+        selected_cols = list(set(cols + self.filter(regex=regex).columns.tolist()))
+        return self[selected_cols]
+    
+    elif isinstance(cols_or_regex, list):
         missing_cols = [col for col in cols_or_regex if col not in self.columns]
         if missing_cols:
             raise KeyError(f"Columns not found in the DataFrame: {missing_cols}")
         return self[cols_or_regex]
+    
     elif isinstance(cols_or_regex, str):
         return self.filter(regex=cols_or_regex)
+    
     else:
-        raise TypeError("cols_or_regex must be a list or a string")
-
-# # Example usage
-# data = {
-#     'apple': [1, 2, 3],
-#     'banana': [4, 5, 6],
-#     'apricot': [7, 8, 9],
-#     'cherry': [10, 11, 12]
-# }
-
-# # Create a DataFrame
-# df = pd.DataFrame(data)
-
-# # Select columns using a list of column names
-# selected_cols_list = select(df, ['apple', 'banana'])
-# print("Selected columns using list:")
-# print(selected_cols_list)
-
-# # Select columns using a regex pattern
-# selected_cols_regex = select(df, '^(apple|banana|cherry)$')
-# print("\nSelected columns using regex:")
-# print(selected_cols_regex)
+        raise TypeError("cols_or_regex must be a list, a regex string, or a tuple of (list, regex)")
+
+# Add the method to the DataFrame class
+pd.DataFrame.select = select
+
+