pytae 2.2.0__tar.gz → 2.2.3__tar.gz

pytae-2.2.3/.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,20 @@
+# This is my day to day util
+
+
+
+## This contains three sets of features:- 
+
+### 1) that does basic data aggregation
+https://github.com/maddytae/pytae/blob/master/src/agg_df.ipynb
+
+### 2) that transforms data long to wide; wide to long etc 
+https://github.com/maddytae/pytae/blob/master/src/shape.ipynb
+
+### 3) that gets aggregated subset of a dataframe 
+https://github.com/maddytae/pytae/blob/master/src/get_data.ipynb
+
+### 4) some addditional utilities
+https://github.com/maddytae/pytae/blob/master/src/other_utilities.ipynb
+
+#### To Do: Documentation and automated Testing features
+

{pytae-2.2.0 → pytae-2.2.3}/.ipynb_checkpoints/pyproject-checkpoint.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "pytae"
-version = "2.2.0"
+version = "2.2.3"
 authors = [
   { name="Madhukar Kumar Jha", email="madhukar.k.jha@gmail.com" },
 ]

pytae-2.2.3/.ipynb_checkpoints/requirements-checkpoint.txt

@@ -0,0 +1,2 @@
+pandas>=1.0.0
+

{pytae-2.2.0 → pytae-2.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pytae
-Version: 2.2.0
+Version: 2.2.3
 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
@@ -15,14 +15,21 @@ Description-Content-Type: text/markdown
 
 # This is my day to day util
 
+
+
 ## This contains three sets of features:- 
 
-### one that extends pandas capabilities 
+### 1) that does basic data aggregation
+https://github.com/maddytae/pytae/blob/master/src/agg_df.ipynb
+
+### 2) that transforms data long to wide; wide to long etc 
+https://github.com/maddytae/pytae/blob/master/src/shape.ipynb
 
-### two that allows to process tar files and some other interesting features and 
+### 3) that gets aggregated subset of a dataframe 
+https://github.com/maddytae/pytae/blob/master/src/get_data.ipynb
 
-### three reconcilliation of two dataframes.
-https://github.com/maddytae/pytae/blob/master/src/recon.ipynb
+### 4) some addditional utilities
+https://github.com/maddytae/pytae/blob/master/src/other_utilities.ipynb
 
 #### To Do: Documentation and automated Testing features
 

pytae-2.2.3/README.md

@@ -0,0 +1,20 @@
+# This is my day to day util
+
+
+
+## This contains three sets of features:- 
+
+### 1) that does basic data aggregation
+https://github.com/maddytae/pytae/blob/master/src/agg_df.ipynb
+
+### 2) that transforms data long to wide; wide to long etc 
+https://github.com/maddytae/pytae/blob/master/src/shape.ipynb
+
+### 3) that gets aggregated subset of a dataframe 
+https://github.com/maddytae/pytae/blob/master/src/get_data.ipynb
+
+### 4) some addditional utilities
+https://github.com/maddytae/pytae/blob/master/src/other_utilities.ipynb
+
+#### To Do: Documentation and automated Testing features
+

{pytae-2.2.0 → pytae-2.2.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "pytae"
-version = "2.2.0"
+version = "2.2.3"
 authors = [
   { name="Madhukar Kumar Jha", email="madhukar.k.jha@gmail.com" },
 ]

pytae-2.2.3/requirements.txt

@@ -0,0 +1,2 @@
+pandas>=1.0.0
+

pytae-2.2.3/src/.ipynb_checkpoints/agg_df-checkpoint.ipynb

@@ -0,0 +1,461 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "e1e35300-a92f-47dd-b448-83861e79eedf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "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": 19,
+   "id": "c3f73408-8dc7-4ea5-899b-e3b23a692cd8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.DataFrame({'id':['a','b','c','d','e','','f','f'],\n",
+    "                  'balance':[10,20,0,21,15,10,20,25],\n",
+    "                  'country':['sg','cn','ca','np','in','in','np','in']})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "db20c1c7-c11f-431d-ae9c-d0c424f0d423",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>balance_sum</th>\n",
+       "      <th>balance_min</th>\n",
+       "      <th>balance_mean</th>\n",
+       "      <th>balance_max</th>\n",
+       "      <th>n</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td></td>\n",
+       "      <td>10</td>\n",
+       "      <td>10</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>10</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>a</td>\n",
+       "      <td>10</td>\n",
+       "      <td>10</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>10</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>b</td>\n",
+       "      <td>20</td>\n",
+       "      <td>20</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>20</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>c</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>d</td>\n",
+       "      <td>21</td>\n",
+       "      <td>21</td>\n",
+       "      <td>21.0</td>\n",
+       "      <td>21</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>e</td>\n",
+       "      <td>15</td>\n",
+       "      <td>15</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>15</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>f</td>\n",
+       "      <td>45</td>\n",
+       "      <td>20</td>\n",
+       "      <td>22.5</td>\n",
+       "      <td>25</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  id  balance_sum  balance_min  balance_mean  balance_max  n\n",
+       "0              10           10          10.0           10  1\n",
+       "1  a           10           10          10.0           10  1\n",
+       "2  b           20           20          20.0           20  1\n",
+       "3  c            0            0           0.0            0  1\n",
+       "4  d           21           21          21.0           21  1\n",
+       "5  e           15           15          15.0           15  1\n",
+       "6  f           45           20          22.5           25  2"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[['id','balance']].agg_df(type=['sum','min','mean','min','max','n'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "66cb16ac-30b8-491e-94b4-0a2065d1e29b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>balance_sum</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td></td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>a</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>b</td>\n",
+       "      <td>20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>c</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>d</td>\n",
+       "      <td>21</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>e</td>\n",
+       "      <td>15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>f</td>\n",
+       "      <td>45</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  id  balance_sum\n",
+       "0              10\n",
+       "1  a           10\n",
+       "2  b           20\n",
+       "3  c            0\n",
+       "4  d           21\n",
+       "5  e           15\n",
+       "6  f           45"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[['id','balance']].agg_df()\n",
+    "# df[['id','balance']].agg_df() by default is returning sum; \n",
+    "# to do: allow it to also work like this df[['id','balance']].agg_df('mean') i.e. passing string instead of a list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "cbf32f4b-5f41-4ea7-bfa4-9f884d714f31",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>species</th>\n",
+       "      <th>island</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>n</th>\n",
+       "      <th>bill_length_mm_sum</th>\n",
+       "      <th>bill_depth_mm_sum</th>\n",
+       "      <th>flipper_length_mm_sum</th>\n",
+       "      <th>body_mass_g_sum</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Biscoe</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>22</td>\n",
+       "      <td>821.9</td>\n",
+       "      <td>389.5</td>\n",
+       "      <td>4118.0</td>\n",
+       "      <td>74125.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Biscoe</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>22</td>\n",
+       "      <td>893.0</td>\n",
+       "      <td>418.8</td>\n",
+       "      <td>4189.0</td>\n",
+       "      <td>89100.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Dream</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>27</td>\n",
+       "      <td>996.6</td>\n",
+       "      <td>475.7</td>\n",
+       "      <td>5072.0</td>\n",
+       "      <td>90300.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Dream</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>28</td>\n",
+       "      <td>1122.0</td>\n",
+       "      <td>527.5</td>\n",
+       "      <td>5374.0</td>\n",
+       "      <td>113275.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Torgersen</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>24</td>\n",
+       "      <td>901.3</td>\n",
+       "      <td>421.2</td>\n",
+       "      <td>4519.0</td>\n",
+       "      <td>81500.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Torgersen</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>23</td>\n",
+       "      <td>933.5</td>\n",
+       "      <td>446.0</td>\n",
+       "      <td>4483.0</td>\n",
+       "      <td>92800.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Chinstrap</td>\n",
+       "      <td>Dream</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>34</td>\n",
+       "      <td>1583.5</td>\n",
+       "      <td>598.0</td>\n",
+       "      <td>6519.0</td>\n",
+       "      <td>119925.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Chinstrap</td>\n",
+       "      <td>Dream</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>34</td>\n",
+       "      <td>1737.2</td>\n",
+       "      <td>654.6</td>\n",
+       "      <td>6797.0</td>\n",
+       "      <td>133925.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Gentoo</td>\n",
+       "      <td>Biscoe</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>58</td>\n",
+       "      <td>2642.7</td>\n",
+       "      <td>825.8</td>\n",
+       "      <td>12337.0</td>\n",
+       "      <td>271425.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Gentoo</td>\n",
+       "      <td>Biscoe</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>61</td>\n",
+       "      <td>3017.9</td>\n",
+       "      <td>958.8</td>\n",
+       "      <td>13514.0</td>\n",
+       "      <td>334575.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     species     island     sex   n  bill_length_mm_sum  bill_depth_mm_sum  \\\n",
+       "0     Adelie     Biscoe  Female  22               821.9              389.5   \n",
+       "1     Adelie     Biscoe    Male  22               893.0              418.8   \n",
+       "2     Adelie      Dream  Female  27               996.6              475.7   \n",
+       "3     Adelie      Dream    Male  28              1122.0              527.5   \n",
+       "4     Adelie  Torgersen  Female  24               901.3              421.2   \n",
+       "5     Adelie  Torgersen    Male  23               933.5              446.0   \n",
+       "6  Chinstrap      Dream  Female  34              1583.5              598.0   \n",
+       "7  Chinstrap      Dream    Male  34              1737.2              654.6   \n",
+       "8     Gentoo     Biscoe  Female  58              2642.7              825.8   \n",
+       "9     Gentoo     Biscoe    Male  61              3017.9              958.8   \n",
+       "\n",
+       "   flipper_length_mm_sum  body_mass_g_sum  \n",
+       "0                 4118.0          74125.0  \n",
+       "1                 4189.0          89100.0  \n",
+       "2                 5072.0          90300.0  \n",
+       "3                 5374.0         113275.0  \n",
+       "4                 4519.0          81500.0  \n",
+       "5                 4483.0          92800.0  \n",
+       "6                 6519.0         119925.0  \n",
+       "7                 6797.0         133925.0  \n",
+       "8                12337.0         271425.0  \n",
+       "9                13514.0         334575.0  "
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "penguins.agg_df(type=['n','sum']) # notice n is not repeated"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "773cca3c-564a-4c3a-bfcf-12b5ddfa6683",
+   "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
+}