diff --git a/notebooks/induction logic programming (ILP)/aleph_preprocessing_ishwari.ipynb b/notebooks/induction logic programming (ILP)/aleph_preprocessing_ishwari.ipynb index d0789ee458c93ed16394d494cd52f1203a70925b..857cd136c287a2e66ecb90e0314279ff1a51be7a 100644 --- a/notebooks/induction logic programming (ILP)/aleph_preprocessing_ishwari.ipynb +++ b/notebooks/induction logic programming (ILP)/aleph_preprocessing_ishwari.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 229, + "execution_count": 17, "id": "5ce379e5", "metadata": {}, "outputs": [ @@ -162,7 +162,7 @@ "4 0 0 40 Cuba <=50K " ] }, - "execution_count": 229, + "execution_count": 17, "metadata": {}, "output_type": "execute_result" } @@ -174,6 +174,45 @@ "df.head()\n" ] }, + { + "cell_type": "code", + "execution_count": 18, + "id": "ebc33264", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "<class 'pandas.core.frame.DataFrame'>\n", + "RangeIndex: 48842 entries, 0 to 48841\n", + "Data columns (total 15 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 age 48842 non-null int64 \n", + " 1 workclass 47879 non-null object\n", + " 2 fnlwgt 48842 non-null int64 \n", + " 3 education 48842 non-null object\n", + " 4 education-num 48842 non-null int64 \n", + " 5 marital-status 48842 non-null object\n", + " 6 occupation 47876 non-null object\n", + " 7 relationship 48842 non-null object\n", + " 8 race 48842 non-null object\n", + " 9 sex 48842 non-null object\n", + " 10 capital-gain 48842 non-null int64 \n", + " 11 capital-loss 48842 non-null int64 \n", + " 12 hours-per-week 48842 non-null int64 \n", + " 13 native-country 48568 non-null object\n", + " 14 Income 48842 non-null object\n", + "dtypes: int64(6), object(9)\n", + "memory usage: 5.6+ MB\n" + ] + } + ], + "source": [ + "df.info()" + ] + }, { "cell_type": "markdown", "id": "d38ce2f8", @@ -189,7 +228,7 @@ }, { "cell_type": "code", - "execution_count": 230, + "execution_count": 19, "id": "0c0ed369", "metadata": {}, "outputs": [], @@ -199,7 +238,7 @@ }, { "cell_type": "code", - "execution_count": 231, + "execution_count": 20, "id": "2f6717e5", "metadata": {}, "outputs": [ @@ -238,7 +277,7 @@ }, { "cell_type": "code", - "execution_count": 232, + "execution_count": 21, "id": "f5c9a812", "metadata": {}, "outputs": [ @@ -367,7 +406,7 @@ "4 wife black female 40 cuba <=50k " ] }, - "execution_count": 232, + "execution_count": 21, "metadata": {}, "output_type": "execute_result" } @@ -397,7 +436,7 @@ }, { "cell_type": "code", - "execution_count": 233, + "execution_count": 22, "id": "656aac7c", "metadata": {}, "outputs": [ @@ -412,7 +451,7 @@ "Name: income, dtype: object" ] }, - "execution_count": 233, + "execution_count": 22, "metadata": {}, "output_type": "execute_result" } @@ -439,7 +478,7 @@ }, { "cell_type": "code", - "execution_count": 234, + "execution_count": 23, "id": "1fb851cd", "metadata": {}, "outputs": [ @@ -568,7 +607,7 @@ "4 wife black female average cuba less_equal_50k " ] }, - "execution_count": 234, + "execution_count": 23, "metadata": {}, "output_type": "execute_result" } @@ -614,7 +653,7 @@ }, { "cell_type": "code", - "execution_count": 235, + "execution_count": 24, "id": "4a920d83", "metadata": {}, "outputs": [ @@ -640,7 +679,7 @@ }, { "cell_type": "code", - "execution_count": 236, + "execution_count": 25, "id": "05ecbbcb", "metadata": {}, "outputs": [], @@ -651,7 +690,7 @@ }, { "cell_type": "code", - "execution_count": 237, + "execution_count": 26, "id": "eb25b6e3", "metadata": {}, "outputs": [], @@ -701,7 +740,7 @@ }, { "cell_type": "code", - "execution_count": 238, + "execution_count": 27, "id": "e9d91ea8", "metadata": {}, "outputs": [ @@ -713,7 +752,7 @@ "Name: income, dtype: int64" ] }, - "execution_count": 238, + "execution_count": 27, "metadata": {}, "output_type": "execute_result" } @@ -744,7 +783,7 @@ }, { "cell_type": "code", - "execution_count": 239, + "execution_count": 28, "id": "972750dc", "metadata": {}, "outputs": [ @@ -792,7 +831,7 @@ }, { "cell_type": "code", - "execution_count": 240, + "execution_count": 29, "id": "1984d074", "metadata": {}, "outputs": [ @@ -862,7 +901,7 @@ }, { "cell_type": "code", - "execution_count": 241, + "execution_count": 30, "id": "8976173c", "metadata": {}, "outputs": [ @@ -912,7 +951,7 @@ }, { "cell_type": "code", - "execution_count": 242, + "execution_count": 31, "id": "10296bac", "metadata": {}, "outputs": [],