pytae 2.2.2__tar.gz → 2.2.4__tar.gz

pytae-2.2.4/.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-2.2.2 → pytae-2.2.4}/.ipynb_checkpoints/pyproject-checkpoint.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "pytae"
-version = "2.2.2"
+version = "2.2.4"
 authors = [
   { name="Madhukar Kumar Jha", email="madhukar.k.jha@gmail.com" },
 ]

{pytae-2.2.2 → pytae-2.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pytae
-Version: 2.2.2
+Version: 2.2.4
 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
@@ -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-2.2.4/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-2.2.2 → pytae-2.2.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "pytae"
-version = "2.2.2"
+version = "2.2.4"
 authors = [
   { name="Madhukar Kumar Jha", email="madhukar.k.jha@gmail.com" },
 ]

{pytae-2.2.2 → pytae-2.2.4}/src/.ipynb_checkpoints/agg_df-checkpoint.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 17,
    "id": "e1e35300-a92f-47dd-b448-83861e79eedf",
    "metadata": {},
    "outputs": [],
@@ -15,7 +15,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 18,
    "id": "c3f73408-8dc7-4ea5-899b-e3b23a692cd8",
    "metadata": {},
    "outputs": [],
@@ -27,7 +27,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 19,
    "id": "db20c1c7-c11f-431d-ae9c-d0c424f0d423",
    "metadata": {},
    "outputs": [
@@ -139,18 +139,18 @@
        "6  f           45           20          22.5           25  2"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df[['id','balance']].agg_df(type=['sum','min','mean','min','max','n'])"
+    "df[['id','balance']].agg_df(aggfunc=['sum','min','mean','min','max','n'])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 20,
    "id": "66cb16ac-30b8-491e-94b4-0a2065d1e29b",
    "metadata": {},
    "outputs": [
@@ -230,7 +230,7 @@
        "6  f           45"
       ]
      },
-     "execution_count": 32,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -243,7 +243,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 21,
    "id": "cbf32f4b-5f41-4ea7-bfa4-9f884d714f31",
    "metadata": {},
    "outputs": [
@@ -419,13 +419,13 @@
        "9                13514.0         334575.0  "
       ]
      },
-     "execution_count": 23,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "penguins.agg_df(type=['n','sum']) # notice n is not repeated"
+    "penguins.agg_df(aggfunc=['n','sum']) "
    ]
   },
   {

{pytae-2.2.2 → pytae-2.2.4}/src/.ipynb_checkpoints/get_data-checkpoint.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 9,
    "id": "0fe64a26-2fb9-4272-b389-768653879781",
    "metadata": {},
    "outputs": [],
@@ -18,7 +18,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 10,
    "id": "71ff2554-e610-4592-a019-c3bc2b0c536d",
    "metadata": {},
    "outputs": [
@@ -104,7 +104,7 @@
        "4   Dream     NaN  Adelie       2975.0            37.5"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -117,7 +117,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 11,
    "id": "9ed6f23b-f588-4651-9db4-3cfb56b37a9b",
    "metadata": {},
    "outputs": [
@@ -197,7 +197,7 @@
        "4  Torgersen  Male     Adelie      92800.0"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }

pytae-2.2.2/src/.ipynb_checkpoints/shape-checkpoint.ipynb → pytae-2.2.4/src/.ipynb_checkpoints/other_utilities-checkpoint.ipynb

@@ -2,8 +2,8 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "b6976e0e-c64e-457a-9f28-6728d6ff75cd",
+   "execution_count": 6,
+   "id": "af0e75c1-7748-44e7-974e-34112d92d813",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -15,8 +15,36 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "ce167daa-5219-47a4-9c5c-e857f45f8457",
+   "execution_count": 7,
+   "id": "e42e01b5-4b00-4f95-acec-274deda67a3c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['bill_depth_mm',\n",
+       " 'bill_length_mm',\n",
+       " 'body_mass_g',\n",
+       " 'flipper_length_mm',\n",
+       " 'island',\n",
+       " 'sex',\n",
+       " 'species']"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# get a list of columns\n",
+    "penguins.cols()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e7136bed-d2e1-48c5-a337-8e31fc020a98",
    "metadata": {},
    "outputs": [
     {
@@ -126,78 +154,159 @@
        "4       3450.0  Female  24  "
       ]
      },
-     "execution_count": 4,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "\n",
-    "\n",
-    "\n",
+    "#add a group count\n",
     "df = (\n",
     "    penguins\n",
-    "    # .pipe(pt.group_n,group=['species', 'island', 'sex'],dropna=False)\n",
     "    .pipe(pt.group_n,dropna=False)\n",
-    "    # .pipe(pt.handle_missing) #NaN in str is replaced with . and in numeric with 0\n",
-    "    # .pipe(pt.clip)\n",
-    "\n",
     ")\n",
-    "#notice that penguins dataset has multiple rows for same group\n",
     "df.head()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "1f6c2d54-67d9-48b1-b25d-e405269c84ee",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df.long(col='features').head() #if value is not provided then default is value"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c83b26a1-fe4e-450a-95a1-292116562dff",
+   "execution_count": 9,
+   "id": "87e3dd20-d5e1-4219-8aee-e842a3d52194",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "df.long(col='features',value='measure').head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2582f05d-ddf4-46ae-8362-34aaa5d05fe4",
-   "metadata": {},
-   "outputs": [],
+   "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>bill_length_mm</th>\n",
+       "      <th>bill_depth_mm</th>\n",
+       "      <th>flipper_length_mm</th>\n",
+       "      <th>body_mass_g</th>\n",
+       "      <th>sex</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Torgersen</td>\n",
+       "      <td>39.1</td>\n",
+       "      <td>18.7</td>\n",
+       "      <td>181.0</td>\n",
+       "      <td>3750.0</td>\n",
+       "      <td>Male</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Torgersen</td>\n",
+       "      <td>39.5</td>\n",
+       "      <td>17.4</td>\n",
+       "      <td>186.0</td>\n",
+       "      <td>3800.0</td>\n",
+       "      <td>Female</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Torgersen</td>\n",
+       "      <td>40.3</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>195.0</td>\n",
+       "      <td>3250.0</td>\n",
+       "      <td>Female</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Torgersen</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Adelie</td>\n",
+       "      <td>Torgersen</td>\n",
+       "      <td>36.7</td>\n",
+       "      <td>19.3</td>\n",
+       "      <td>193.0</td>\n",
+       "      <td>3450.0</td>\n",
+       "      <td>Female</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  species     island  bill_length_mm  bill_depth_mm  flipper_length_mm  \\\n",
+       "0  Adelie  Torgersen            39.1           18.7              181.0   \n",
+       "1  Adelie  Torgersen            39.5           17.4              186.0   \n",
+       "2  Adelie  Torgersen            40.3           18.0              195.0   \n",
+       "3  Adelie  Torgersen             0.0            0.0                0.0   \n",
+       "4  Adelie  Torgersen            36.7           19.3              193.0   \n",
+       "\n",
+       "   body_mass_g     sex  \n",
+       "0       3750.0    Male  \n",
+       "1       3800.0  Female  \n",
+       "2       3250.0  Female  \n",
+       "3          0.0       .  \n",
+       "4       3450.0  Female  "
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "df.long(col='features').wide(col='features').head()\n",
-    "# you will get back original df because penguins has been aggregated in the very beginning. "
+    "# handle missing i.e. str missing or NaN is changed to . and numeric NaN to 0\n",
+    "# add a group count\n",
+    "df = (\n",
+    "    penguins\n",
+    "    .pipe(pt.handle_missing)\n",
+    ")\n",
+    "df.head()\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "2a6e93dc-703a-4ae4-84de-6364728b6e6f",
+   "execution_count": 10,
+   "id": "b17a9574-35ff-4fe2-b40f-054a0b5e5003",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Had it not been the case, we could not get original df back because wide uses pivot_table that would aggregate the results\n",
-    "penguins.long(col='features').wide(col='features')"
+    "df.clip()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "37cbef19-3391-4ec0-be90-4d4d333d3987",
+   "id": "b39ba218-6361-47eb-91b2-c6f35b7a130e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "df.cols()"
-   ]
+   "source": []
   }
  ],
  "metadata": {