introducing chapter 11 and some other modifications

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,25 @@
+# Effective XGBoost by Matt Harrison - My Personal Take
+
+This repository contains my personal notes, examples, and code implementations based on the book "Effective XGBoost" by Matt Harrison. The purpose of this repo is to document my journey as I peer thru the mind of a master displaying his craft so I could glean some insights myself into building models that I could use for my projects.
+
+## Table of Contents
+
+2 Datasets 
+
+3 Exploratory Data Analysis 
+
+4 Tree Creation 
+
+5 Stumps on Real Data 
+
+6 Model Complexity & Hyperparameters 
+
+7 Tree Hyperparameters 
+
+8 Random Forest 
+
+9 XGBoost
+
+10 Early Stopping
+
+11 XGBoost Hyperparameters

.ipynb_checkpoints/chp11_XGBoostHyperparameters-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

README.md

@@ -6,25 +6,20 @@ This repository contains my personal notes, examples, and code implementations b
 
 2 Datasets 
 
-
 3 Exploratory Data Analysis 
 
-
 4 Tree Creation 
 
-
 5 Stumps on Real Data 
 
-
 6 Model Complexity & Hyperparameters 
 
-
 7 Tree Hyperparameters 
 
-
 8 Random Forest 
 
 9 XGBoost
 
 10 Early Stopping
 
+11 XGBoost Hyperparameters

chp10_EarlyStopping.ipynb

@@ -169,7 +169,8 @@
       "[28]\tvalidation_0-logloss:0.38837\tvalidation_1-logloss:0.51135\n",
       "[29]\tvalidation_0-logloss:0.38569\tvalidation_1-logloss:0.51202\n",
       "[30]\tvalidation_0-logloss:0.37945\tvalidation_1-logloss:0.51352\n",
-      "[31]\tvalidation_0-logloss:0.37840\tvalidation_1-logloss:0.51545\n"
+      "[31]\tvalidation_0-logloss:0.37840\tvalidation_1-logloss:0.51545\n",
+      "[32]\tvalidation_0-logloss:0.37538\tvalidation_1-logloss:0.51581\n"
      ]
     },
     {
@@ -331,7 +332,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 6,
    "id": "88e90c50-2933-4822-9d5e-b18e9bfce7d7",
    "metadata": {},
    "outputs": [
@@ -404,7 +405,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 7,
    "id": "f22011c4-74af-4447-be73-0a1e2fe70a09",
    "metadata": {},
    "outputs": [
@@ -433,7 +434,7 @@
        "0.7558011049723757"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -458,7 +459,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 8,
    "id": "f4058e18-de3e-412c-8391-568c771bf77a",
    "metadata": {},
    "outputs": [
@@ -468,7 +469,7 @@
        "0.7458563535911602"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -500,7 +501,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 9,
    "id": "0d0042a9-f9ee-4982-899a-3e12e9cd4ad7",
    "metadata": {},
    "outputs": [
@@ -545,8 +546,7 @@
       "[34]\tvalidation_0-error:0.15261\tvalidation_1-error:0.25525\n",
       "[35]\tvalidation_0-error:0.15213\tvalidation_1-error:0.25525\n",
       "[36]\tvalidation_0-error:0.15166\tvalidation_1-error:0.25525\n",
-      "[37]\tvalidation_0-error:0.14550\tvalidation_1-error:0.25525\n",
-      "[38]\tvalidation_0-error:0.14597\tvalidation_1-error:0.25083\n"
+      "[37]\tvalidation_0-error:0.14550\tvalidation_1-error:0.25525\n"
      ]
     },
     {
@@ -555,7 +555,7 @@
        "0.7624309392265194"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -569,7 +569,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 10,
    "id": "e3887492-68a4-4711-8f0c-b2b9fc0dc5d0",
    "metadata": {},
    "outputs": [
@@ -579,7 +579,7 @@
        "19"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }

img/xg_depth2_tree0.dot

@@ -0,0 +1,28 @@
+digraph {
+    graph [ rankdir=TB ];
+  node [fontname = "Roboto Condensed"];
+    edge [fontname = "Roboto Thin"];
+    label = "Learning Rate set to 1"
+    fontname = "Roboto Condensed"
+
+
+    0 [ label="r<0.5" ]
+    0 -> 1 [label="yes, missing" color="#0000FF"]
+    0 -> 2 [label="no" color="#FF0000"]
+
+    1 [ label="major_cs<0.5" ]
+    1 -> 3 [label="yes, missing" color="#0000FF"]
+    1 -> 4 [label="no" color="#FF0000"]
+
+    3 [ label="leaf=-0.282548487" ]
+
+    4 [ label="leaf=0.727272749" ]
+
+    2 [ label="major_cs<0.5" ]
+    2 -> 5 [label="yes, missing" color="#0000FF"]
+    2 -> 6 [label="no" color="#FF0000"]
+
+    5 [ label="leaf=-1.50783002" ]
+
+    6 [ label="leaf=-0.395721912" ]
+}

img/xg_depth2_tree0_lr001.dot

@@ -0,0 +1,28 @@
+digraph {
+    graph [ rankdir=TB ];
+  node [fontname = "Roboto Condensed"];
+    edge [fontname = "Roboto Thin"];
+    label = "Learning Rate set to .001"
+    fontname = "Roboto Condensed"
+
+
+    0 [ label="r<0.5" ]
+    0 -> 1 [label="yes, missing" color="#0000FF"]
+    0 -> 2 [label="no" color="#FF0000"]
+
+    1 [ label="major_cs<0.5" ]
+    1 -> 3 [label="yes, missing" color="#0000FF"]
+    1 -> 4 [label="no" color="#FF0000"]
+
+    3 [ label="leaf=-0.000282548513" ]
+
+    4 [ label="leaf=0.000727272767" ]
+
+    2 [ label="major_cs<0.5" ]
+    2 -> 5 [label="yes, missing" color="#0000FF"]
+    2 -> 6 [label="no" color="#FF0000"]
+
+    5 [ label="leaf=-0.00150783011" ]
+
+    6 [ label="leaf=-0.000395721931" ]
+}