From 4c021de75b27832b965bc4b70a008f1107f6ff1f Mon Sep 17 00:00:00 2001
From: oldoc63 <leopoldo.olmos@gmail.com>
Date: Wed, 27 Oct 2021 12:58:06 -0400
Subject: [PATCH] Summarizin an ordinal category #211

---
 summAutoEval/autoEval.ipynb | 84 +++++++++++++++++++++++++++++--------
 summAutoEval/script.py      | 13 ++++++
 2 files changed, 80 insertions(+), 17 deletions(-)

diff --git a/summAutoEval/autoEval.ipynb b/summAutoEval/autoEval.ipynb
index 4582000..56cac88 100644
--- a/summAutoEval/autoEval.ipynb
+++ b/summAutoEval/autoEval.ipynb
@@ -3,17 +3,18 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "f961e22b",
+   "id": "3892cc84",
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd"
+    "import pandas as pd\n",
+    "import numpy as np"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "eec8cecf",
+   "execution_count": 2,
+   "id": "56982b85",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -22,8 +23,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "4d1c9e0c",
+   "execution_count": 3,
+   "id": "46cc7da7",
    "metadata": {},
    "outputs": [
     {
@@ -52,8 +53,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "da5fed0d",
+   "execution_count": 4,
+   "id": "eb961155",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -62,8 +63,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "id": "319136c5",
+   "execution_count": 5,
+   "id": "06be8102",
    "metadata": {},
    "outputs": [
     {
@@ -87,8 +88,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "496ac1d4",
+   "execution_count": 6,
+   "id": "2628a909",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -97,8 +98,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "03b74363",
+   "execution_count": 7,
+   "id": "54a2862a",
    "metadata": {},
    "outputs": [
     {
@@ -115,8 +116,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "57684edc",
+   "execution_count": 8,
+   "id": "c65115f2",
    "metadata": {},
    "outputs": [
     {
@@ -137,10 +138,59 @@
     "print(manufacturer_country_proportions.head())"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "a61c8ee1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['vhigh' 'med' 'low' 'high']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(car_eval.buying_cost.unique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "ee72e36c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "buying_cost_categories = ['low', 'med', 'high', 'vhigh']\n",
+    "car_eval['buying_cost'] = pd.Categorical(car_eval['buying_cost'], buying_cost_categories, ordered=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "1ef72999",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "buying_cost_median = np.median(car_eval['buying_cost'].cat.codes)\n",
+    "\n",
+    "print(buying_cost_median)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "af9a3594",
+   "id": "719fa00f",
    "metadata": {},
    "outputs": [],
    "source": []
diff --git a/summAutoEval/script.py b/summAutoEval/script.py
index cfc4637..623482c 100644
--- a/summAutoEval/script.py
+++ b/summAutoEval/script.py
@@ -1,4 +1,5 @@
 import pandas as pd
+import numpy as np
 
 car_eval = pd.read_csv('car_eval_dataset.csv')
 print(car_eval.head())
@@ -11,3 +12,15 @@
 
 manufacturer_country_proportions = car_eval.manufacturer_country.value_counts(normalize=True)
 print(manufacturer_country_proportions.head())
+
+print(car_eval.buying_cost.unique())
+
+buying_cost_categories = ['low', 'med', 'high', 'vhigh']
+
+car_eval['buying_cost'] = pd.Categorical(car_eval['buying_cost'], buying_cost_categories, ordered=True)
+
+buying_cost_median = np.median(car_eval['buying_cost'].cat.codes)
+
+print(buying_cost_median)
+
+