diff --git a/notebooks/classification/preprocessing_ishwari.ipynb b/notebooks/classification/preprocessing_ishwari.ipynb index 7d7ed0956b9507e525c4625fd62cb1f40917f46b..38437f75320089099424a9d9fdf8dd32a3a83cdb 100644 --- a/notebooks/classification/preprocessing_ishwari.ipynb +++ b/notebooks/classification/preprocessing_ishwari.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 172, + "execution_count": 42, "metadata": {}, "outputs": [ { @@ -161,7 +161,7 @@ "4 0 0 40 Cuba <=50K " ] }, - "execution_count": 172, + "execution_count": 42, "metadata": {}, "output_type": "execute_result" } @@ -175,7 +175,7 @@ }, { "cell_type": "code", - "execution_count": 173, + "execution_count": 43, "metadata": {}, "outputs": [ { @@ -213,7 +213,7 @@ }, { "cell_type": "code", - "execution_count": 174, + "execution_count": 44, "metadata": {}, "outputs": [ { @@ -245,7 +245,7 @@ }, { "cell_type": "code", - "execution_count": 175, + "execution_count": 45, "metadata": {}, "outputs": [ { @@ -288,7 +288,7 @@ }, { "cell_type": "code", - "execution_count": 176, + "execution_count": 46, "metadata": {}, "outputs": [ { @@ -329,7 +329,7 @@ }, { "cell_type": "code", - "execution_count": 177, + "execution_count": 47, "metadata": {}, "outputs": [ { @@ -347,7 +347,7 @@ }, { "cell_type": "code", - "execution_count": 178, + "execution_count": 48, "metadata": {}, "outputs": [ { @@ -368,7 +368,7 @@ }, { "cell_type": "code", - "execution_count": 179, + "execution_count": 49, "metadata": {}, "outputs": [], "source": [ @@ -394,7 +394,7 @@ }, { "cell_type": "code", - "execution_count": 180, + "execution_count": 50, "metadata": {}, "outputs": [ { @@ -522,7 +522,7 @@ "Income 0.227687 1.000000 " ] }, - "execution_count": 180, + "execution_count": 50, "metadata": {}, "output_type": "execute_result" } @@ -557,7 +557,7 @@ }, { "cell_type": "code", - "execution_count": 181, + "execution_count": 51, "metadata": {}, "outputs": [ { @@ -609,7 +609,7 @@ }, { "cell_type": "code", - "execution_count": 182, + "execution_count": 52, "metadata": {}, "outputs": [ { @@ -664,7 +664,7 @@ }, { "cell_type": "code", - "execution_count": 183, + "execution_count": 53, "metadata": {}, "outputs": [ { @@ -732,7 +732,7 @@ }, { "cell_type": "code", - "execution_count": 184, + "execution_count": 54, "metadata": {}, "outputs": [], "source": [ @@ -748,7 +748,7 @@ }, { "cell_type": "code", - "execution_count": 185, + "execution_count": 55, "metadata": {}, "outputs": [], "source": [ @@ -764,7 +764,7 @@ }, { "cell_type": "code", - "execution_count": 186, + "execution_count": 56, "metadata": {}, "outputs": [], "source": [ @@ -773,14 +773,14 @@ }, { "cell_type": "code", - "execution_count": 187, + "execution_count": 57, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "✅ Dropped 7655 duplicate rows.\n" + "Dropped 7655 duplicate rows.\n" ] } ], @@ -789,7 +789,7 @@ "before = df.shape[0]\n", "df.drop_duplicates(inplace=True)\n", "after = df.shape[0]\n", - "print(f\"✅ Dropped {before - after} duplicate rows.\")" + "print(f\"Dropped {before - after} duplicate rows.\")" ] }, { @@ -801,7 +801,7 @@ }, { "cell_type": "code", - "execution_count": 188, + "execution_count": 58, "metadata": {}, "outputs": [ { @@ -846,7 +846,7 @@ }, { "cell_type": "code", - "execution_count": 189, + "execution_count": 59, "metadata": {}, "outputs": [], "source": [ @@ -856,7 +856,7 @@ }, { "cell_type": "code", - "execution_count": 190, + "execution_count": 60, "metadata": {}, "outputs": [ { @@ -896,7 +896,7 @@ }, { "cell_type": "code", - "execution_count": 191, + "execution_count": 61, "metadata": {}, "outputs": [ { @@ -925,7 +925,7 @@ }, { "cell_type": "code", - "execution_count": 192, + "execution_count": 62, "metadata": {}, "outputs": [ { @@ -987,7 +987,7 @@ }, { "cell_type": "code", - "execution_count": 193, + "execution_count": 63, "metadata": {}, "outputs": [], "source": [ @@ -1006,7 +1006,7 @@ }, { "cell_type": "code", - "execution_count": 194, + "execution_count": 64, "metadata": {}, "outputs": [], "source": [ @@ -1035,7 +1035,7 @@ }, { "cell_type": "code", - "execution_count": 195, + "execution_count": 65, "metadata": {}, "outputs": [], "source": [ @@ -1062,7 +1062,7 @@ }, { "cell_type": "code", - "execution_count": 196, + "execution_count": 66, "metadata": {}, "outputs": [], "source": [ @@ -1081,7 +1081,7 @@ }, { "cell_type": "code", - "execution_count": 197, + "execution_count": 67, "metadata": {}, "outputs": [ { @@ -1115,7 +1115,7 @@ }, { "cell_type": "code", - "execution_count": 198, + "execution_count": 68, "metadata": {}, "outputs": [], "source": [ @@ -1139,7 +1139,7 @@ }, { "cell_type": "code", - "execution_count": 199, + "execution_count": 69, "metadata": {}, "outputs": [], "source": [ @@ -1150,7 +1150,7 @@ }, { "cell_type": "code", - "execution_count": 200, + "execution_count": 70, "metadata": {}, "outputs": [], "source": [ @@ -1193,7 +1193,7 @@ }, { "cell_type": "code", - "execution_count": 201, + "execution_count": 71, "metadata": {}, "outputs": [], "source": [ @@ -1204,7 +1204,7 @@ }, { "cell_type": "code", - "execution_count": 202, + "execution_count": 72, "metadata": {}, "outputs": [], "source": [ @@ -1214,7 +1214,7 @@ }, { "cell_type": "code", - "execution_count": 203, + "execution_count": 73, "metadata": {}, "outputs": [], "source": [ @@ -1253,7 +1253,7 @@ }, { "cell_type": "code", - "execution_count": 204, + "execution_count": 74, "metadata": {}, "outputs": [], "source": [ @@ -1286,7 +1286,7 @@ }, { "cell_type": "code", - "execution_count": 205, + "execution_count": 75, "metadata": {}, "outputs": [], "source": [ @@ -1306,7 +1306,7 @@ }, { "cell_type": "code", - "execution_count": 206, + "execution_count": 76, "metadata": {}, "outputs": [ { @@ -1372,7 +1372,7 @@ }, { "cell_type": "code", - "execution_count": 207, + "execution_count": 77, "metadata": {}, "outputs": [], "source": [ @@ -1407,7 +1407,7 @@ }, { "cell_type": "code", - "execution_count": 208, + "execution_count": 78, "metadata": {}, "outputs": [ { @@ -1535,7 +1535,7 @@ "4 40 0 Prof-specialty Latin America " ] }, - "execution_count": 208, + "execution_count": 78, "metadata": {}, "output_type": "execute_result" } @@ -1564,7 +1564,7 @@ }, { "cell_type": "code", - "execution_count": 209, + "execution_count": 79, "metadata": {}, "outputs": [ { @@ -1790,7 +1790,7 @@ "[5 rows x 40 columns]" ] }, - "execution_count": 209, + "execution_count": 79, "metadata": {}, "output_type": "execute_result" } @@ -1820,7 +1820,7 @@ }, { "cell_type": "code", - "execution_count": 210, + "execution_count": 80, "metadata": {}, "outputs": [ { @@ -2046,7 +2046,7 @@ "[5 rows x 40 columns]" ] }, - "execution_count": 210, + "execution_count": 80, "metadata": {}, "output_type": "execute_result" } @@ -2060,7 +2060,7 @@ }, { "cell_type": "code", - "execution_count": 211, + "execution_count": 81, "metadata": {}, "outputs": [], "source": [ @@ -2070,7 +2070,7 @@ }, { "cell_type": "code", - "execution_count": 212, + "execution_count": 82, "metadata": {}, "outputs": [], "source": [