Last active
September 16, 2018 12:48
-
-
Save raytroop/2492bad9091ad5339b562ecec36663c3 to your computer and use it in GitHub Desktop.
[Data-Science-Decal-Fall-2017/Day5-DecisionTrees/DecisionTrees.ipynb](https://github.com/mlberkeley/Data-Science-Decal-Fall-2017/blob/master/Day5-DecisionTrees/DecisionTrees.ipynb)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"# Building Decision Trees and Random Forests\n", | |
"In this notebook we will build decision tree and random forest classes that will act as classifiers on the Titanic dataset. The features of the dataset describe the passenger, and the label describes whether or not they survived. \n", | |
"\n", | |
"Dataset Credits: Professor Shewchuk's CS189 Spring 2017" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"import numpy as np\n", | |
"import matplotlib.pyplot as plt\n", | |
"import math\n", | |
"import pandas as pd\n", | |
"%matplotlib inline" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": { | |
"collapsed": false | |
}, | |
"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>survived</th>\n", | |
" <th>pclass</th>\n", | |
" <th>sex</th>\n", | |
" <th>age</th>\n", | |
" <th>sibsp</th>\n", | |
" <th>parch</th>\n", | |
" <th>ticket</th>\n", | |
" <th>fare</th>\n", | |
" <th>cabin</th>\n", | |
" <th>embarked</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>0.0</td>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>NaN</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>SOTON/OQ 392086</td>\n", | |
" <td>8.0500</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>0.0</td>\n", | |
" <td>1.0</td>\n", | |
" <td>male</td>\n", | |
" <td>22.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>PC 17760</td>\n", | |
" <td>135.6333</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>0.0</td>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>23.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>SC/PARIS 2133</td>\n", | |
" <td>15.0458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>0.0</td>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>42.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>211535</td>\n", | |
" <td>13.0000</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>0.0</td>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>20.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>7534</td>\n", | |
" <td>9.8458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" survived pclass sex age sibsp parch ticket fare \\\n", | |
"0 0.0 3.0 male NaN 0.0 0.0 SOTON/OQ 392086 8.0500 \n", | |
"1 0.0 1.0 male 22.0 0.0 0.0 PC 17760 135.6333 \n", | |
"2 0.0 2.0 male 23.0 0.0 0.0 SC/PARIS 2133 15.0458 \n", | |
"3 0.0 2.0 male 42.0 0.0 0.0 211535 13.0000 \n", | |
"4 0.0 3.0 male 20.0 0.0 0.0 7534 9.8458 \n", | |
"\n", | |
" cabin embarked \n", | |
"0 NaN S \n", | |
"1 NaN C \n", | |
"2 NaN C \n", | |
"3 NaN S \n", | |
"4 NaN S " | |
] | |
}, | |
"execution_count": 2, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"from scipy.io import loadmat as loadmat\n", | |
"import matplotlib.pyplot as plt\n", | |
"\n", | |
"titanicDataFrame = pd.read_csv('titanic_training.csv')\n", | |
"titanicDataFrame.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": {}, | |
"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>survived</th>\n", | |
" <th>pclass</th>\n", | |
" <th>sex</th>\n", | |
" <th>age</th>\n", | |
" <th>sibsp</th>\n", | |
" <th>parch</th>\n", | |
" <th>fare</th>\n", | |
" <th>cabin</th>\n", | |
" <th>embarked</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>0.0</td>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>NaN</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>8.0500</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>0.0</td>\n", | |
" <td>1.0</td>\n", | |
" <td>male</td>\n", | |
" <td>22.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>135.6333</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>0.0</td>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>23.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>15.0458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>0.0</td>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>42.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>13.0000</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>0.0</td>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>20.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>9.8458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" survived pclass sex age sibsp parch fare cabin embarked\n", | |
"0 0.0 3.0 male NaN 0.0 0.0 8.0500 NaN S\n", | |
"1 0.0 1.0 male 22.0 0.0 0.0 135.6333 NaN C\n", | |
"2 0.0 2.0 male 23.0 0.0 0.0 15.0458 NaN C\n", | |
"3 0.0 2.0 male 42.0 0.0 0.0 13.0000 NaN S\n", | |
"4 0.0 3.0 male 20.0 0.0 0.0 9.8458 NaN S" | |
] | |
}, | |
"execution_count": 3, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"titanicDataFrame.drop('ticket', axis=1, inplace=True)\n", | |
"titanicDataFrame.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": {}, | |
"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>survived</th>\n", | |
" <th>pclass</th>\n", | |
" <th>sex</th>\n", | |
" <th>age</th>\n", | |
" <th>sibsp</th>\n", | |
" <th>parch</th>\n", | |
" <th>fare</th>\n", | |
" <th>cabin</th>\n", | |
" <th>embarked</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>0.0</td>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>NaN</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>8.0500</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>0.0</td>\n", | |
" <td>1.0</td>\n", | |
" <td>male</td>\n", | |
" <td>22.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>135.6333</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>0.0</td>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>23.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>15.0458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>0.0</td>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>42.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>13.0000</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>0.0</td>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>20.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>9.8458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" survived pclass sex age sibsp parch fare cabin embarked\n", | |
"0 0.0 3.0 male NaN 0.0 0.0 8.0500 NaN S\n", | |
"1 0.0 1.0 male 22.0 0.0 0.0 135.6333 NaN C\n", | |
"2 0.0 2.0 male 23.0 0.0 0.0 15.0458 NaN C\n", | |
"3 0.0 2.0 male 42.0 0.0 0.0 13.0000 NaN S\n", | |
"4 0.0 3.0 male 20.0 0.0 0.0 9.8458 NaN S" | |
] | |
}, | |
"execution_count": 4, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"titanicDataFrame.dropna(axis=0, how=\"all\", inplace=True)\n", | |
"titanicDataFrame.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"titanicLabels = titanicDataFrame.iloc[:,0]\n", | |
"titanicData = titanicDataFrame.iloc[:,1:]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": {}, | |
"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>pclass</th>\n", | |
" <th>sex</th>\n", | |
" <th>age</th>\n", | |
" <th>sibsp</th>\n", | |
" <th>parch</th>\n", | |
" <th>fare</th>\n", | |
" <th>cabin</th>\n", | |
" <th>embarked</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>NaN</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>8.0500</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>1.0</td>\n", | |
" <td>male</td>\n", | |
" <td>22.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>135.6333</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>23.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>15.0458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>42.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>13.0000</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>20.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>9.8458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" pclass sex age sibsp parch fare cabin embarked\n", | |
"0 3.0 male NaN 0.0 0.0 8.0500 NaN S\n", | |
"1 1.0 male 22.0 0.0 0.0 135.6333 NaN C\n", | |
"2 2.0 male 23.0 0.0 0.0 15.0458 NaN C\n", | |
"3 2.0 male 42.0 0.0 0.0 13.0000 NaN S\n", | |
"4 3.0 male 20.0 0.0 0.0 9.8458 NaN S" | |
] | |
}, | |
"execution_count": 6, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"titanicData.head()" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"```python\n", | |
" pd.isnull = pd.isna\n", | |
"```" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"metadata": {}, | |
"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>pclass</th>\n", | |
" <th>sex</th>\n", | |
" <th>age</th>\n", | |
" <th>sibsp</th>\n", | |
" <th>parch</th>\n", | |
" <th>fare</th>\n", | |
" <th>cabin</th>\n", | |
" <th>embarked</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>NaN</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>8.0500</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>1.0</td>\n", | |
" <td>male</td>\n", | |
" <td>22.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>135.6333</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>23.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>15.0458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>42.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>13.0000</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>20.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>9.8458</td>\n", | |
" <td>NaN</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" pclass sex age sibsp parch fare cabin embarked\n", | |
"0 3.0 male NaN 0.0 0.0 8.0500 NaN S\n", | |
"1 1.0 male 22.0 0.0 0.0 135.6333 NaN C\n", | |
"2 2.0 male 23.0 0.0 0.0 15.0458 NaN C\n", | |
"3 2.0 male 42.0 0.0 0.0 13.0000 NaN S\n", | |
"4 3.0 male 20.0 0.0 0.0 9.8458 NaN S" | |
] | |
}, | |
"execution_count": 7, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"titanicData['cabin'] = titanicData[~titanicData.cabin.isnull()].cabin.str[0]\n", | |
"titanicData.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 8, | |
"metadata": {}, | |
"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>pclass</th>\n", | |
" <th>sex</th>\n", | |
" <th>age</th>\n", | |
" <th>sibsp</th>\n", | |
" <th>parch</th>\n", | |
" <th>fare</th>\n", | |
" <th>cabin</th>\n", | |
" <th>embarked</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>NaN</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>8.0500</td>\n", | |
" <td>H</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>1.0</td>\n", | |
" <td>male</td>\n", | |
" <td>22.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>135.6333</td>\n", | |
" <td>H</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>23.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>15.0458</td>\n", | |
" <td>H</td>\n", | |
" <td>C</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>2.0</td>\n", | |
" <td>male</td>\n", | |
" <td>42.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>13.0000</td>\n", | |
" <td>H</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>3.0</td>\n", | |
" <td>male</td>\n", | |
" <td>20.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>9.8458</td>\n", | |
" <td>H</td>\n", | |
" <td>S</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" pclass sex age sibsp parch fare cabin embarked\n", | |
"0 3.0 male NaN 0.0 0.0 8.0500 H S\n", | |
"1 1.0 male 22.0 0.0 0.0 135.6333 H C\n", | |
"2 2.0 male 23.0 0.0 0.0 15.0458 H C\n", | |
"3 2.0 male 42.0 0.0 0.0 13.0000 H S\n", | |
"4 3.0 male 20.0 0.0 0.0 9.8458 H S" | |
] | |
}, | |
"execution_count": 8, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"titanicData['cabin'].fillna(value='H', inplace=True)\n", | |
"titanicData.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 9, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array(['H', 'E', 'B', 'D', 'F', 'C', 'A', 'T', 'G'], dtype=object)" | |
] | |
}, | |
"execution_count": 9, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"titanicData.cabin.unique()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 10, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"(999, 16)\n" | |
] | |
}, | |
{ | |
"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>pclass</th>\n", | |
" <th>age</th>\n", | |
" <th>sibsp</th>\n", | |
" <th>parch</th>\n", | |
" <th>fare</th>\n", | |
" <th>sex_male</th>\n", | |
" <th>cabin_B</th>\n", | |
" <th>cabin_C</th>\n", | |
" <th>cabin_D</th>\n", | |
" <th>cabin_E</th>\n", | |
" <th>cabin_F</th>\n", | |
" <th>cabin_G</th>\n", | |
" <th>cabin_H</th>\n", | |
" <th>cabin_T</th>\n", | |
" <th>embarked_Q</th>\n", | |
" <th>embarked_S</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>3.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>8.0500</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>1.0</td>\n", | |
" <td>22.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>135.6333</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>2.0</td>\n", | |
" <td>23.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>15.0458</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>2.0</td>\n", | |
" <td>42.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>13.0000</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>3.0</td>\n", | |
" <td>20.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>0.0</td>\n", | |
" <td>9.8458</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" pclass age sibsp parch fare sex_male cabin_B cabin_C cabin_D \\\n", | |
"0 3.0 0.0 0.0 0.0 8.0500 1 0 0 0 \n", | |
"1 1.0 22.0 0.0 0.0 135.6333 1 0 0 0 \n", | |
"2 2.0 23.0 0.0 0.0 15.0458 1 0 0 0 \n", | |
"3 2.0 42.0 0.0 0.0 13.0000 1 0 0 0 \n", | |
"4 3.0 20.0 0.0 0.0 9.8458 1 0 0 0 \n", | |
"\n", | |
" cabin_E cabin_F cabin_G cabin_H cabin_T embarked_Q embarked_S \n", | |
"0 0 0 0 1 0 0 1 \n", | |
"1 0 0 0 1 0 0 0 \n", | |
"2 0 0 0 1 0 0 0 \n", | |
"3 0 0 0 1 0 0 1 \n", | |
"4 0 0 0 1 0 0 1 " | |
] | |
}, | |
"execution_count": 10, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"titanicData = pd.get_dummies(titanicData, drop_first=True).fillna(value=0, axis=1)\n", | |
"print(titanicData.shape)\n", | |
"titanicData.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 11, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"image/png": "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\n", | |
"text/plain": [ | |
"<Figure size 576x576 with 1 Axes>" | |
] | |
}, | |
"metadata": { | |
"needs_background": "light" | |
}, | |
"output_type": "display_data" | |
} | |
], | |
"source": [ | |
"x = np.arange(800)\n", | |
"plt.figure(figsize=(8,8))\n", | |
"plt.plot(x, np.sort(titanicData['fare'].values)[:800], 'ro')\n", | |
"plt.show()\n", | |
"#easily split on 1/10 of the values for fare " | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Cross Entropy Code\n", | |
"Try to understand the different parts of the code. \n", | |
"- What do a, b, c, d represent?\n", | |
"- What do t1, t2 represent?" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 12, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def cross_entropy(l1, l0, r1, r0):\n", | |
" \"\"\"\n", | |
" Calculate the entropy H_after, if after the split we have:\n", | |
" l1, l0 -> The left split, broken into the sets that are 1's and 0's.\n", | |
" r1, r0 -> The right split, broken into the sets that are 1's and 0's.\n", | |
" \"\"\"\n", | |
" t1 = 0\n", | |
" lsize = l1 + l0\n", | |
" if lsize > 0:\n", | |
" a = float(l1) / lsize \n", | |
" b = 1 - a\n", | |
" a = np.clip(a, 1e-7, 1-1e-7)\n", | |
" b = np.clip(b, 1e-7, 1-1e-7)\n", | |
" if a != 0 and b != 0:\n", | |
" t1 += a * np.log(a)\n", | |
" t1 += b * np.log(b)\n", | |
" t1 *= lsize\n", | |
" \n", | |
" t2 = 0\n", | |
" rsize = r1 + r0\n", | |
" if rsize > 0:\n", | |
" c = float(r1) / rsize\n", | |
" d = 1 - c\n", | |
" c = np.clip(c, 1e-7, 1-1e-7)\n", | |
" d = np.clip(d, 1e-7, 1-1e-7)\n", | |
" if c != 0 and d != 0:\n", | |
" t2 += c * np.log(c)\n", | |
" t2 += d * np.log(d)\n", | |
" t2 *= rsize\n", | |
" #returns weighted total entropy\n", | |
" return -1 * (t1 + t2) / (lsize + rsize)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Decision Tree Code\n", | |
"Recall that in a tree, all children are also classified as \"trees,\" i.e. A decision tree is always a tree of decision trees. " | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 13, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"class DecisionTree: \n", | |
" def __init__(self, dataSet, labels, stopCriterion, depth, fselection=False, printer=False):\n", | |
" \"\"\"\n", | |
" Initialize a Decision Tree using the arguments:\n", | |
" dataSet, labels : will be used to determine next split\n", | |
" stopCriterion : [(majority/depth), value]\n", | |
" depth : the depth of this Decision Tree \n", | |
" fselection : whether this tree will employ random feature selection\n", | |
" Also create instance variables:\n", | |
" stopCriterion : turns from argument to a function. Use this function to judge when to stop.\n", | |
" stopParam : this will be the argument to the stopCriterion function\n", | |
" leftNode, rightNode : the tree's children\n", | |
" leaf, val : leaf is whether the node is a leaf, val is what value the leaf holds\n", | |
" decision, decisionString: branching rule and string representation of the rule\n", | |
" Then proceed to growTree() \n", | |
" \"\"\"\n", | |
" self.dataSet = dataSet\n", | |
" self.labels = labels\n", | |
" self.depth = depth\n", | |
" self.fselection = fselection\n", | |
" \n", | |
" self.stopParam = None\n", | |
" self.stopCritString = stopCriterion[0]\n", | |
" assert stopCriterion[0] in ['majorityCriterion', 'maxDepth'], \"StopCritertion must be maxDepth or majorityCriterion\"\n", | |
" self.stopCriterion = getattr(self, self.stopCritString)\n", | |
" self.stopParam = stopCriterion[1]\n", | |
" \n", | |
" self.leftNode = None\n", | |
" self.rightNode = None\n", | |
" self.leaf = False\n", | |
" self.val = None\n", | |
" self.entropy = cross_entropy(np.sum(self.labels.values), self.labels.values.size - np.sum(self.labels.values), 0, 0)\n", | |
" \n", | |
" self.decision = None\n", | |
" self.decisionString = \"\"\n", | |
" self.growTree()\n", | |
" if depth == 0 and printer:\n", | |
" print(\"Finished making Decision Tree with criteria: \" + str(stopCriterion))\n", | |
" \n", | |
" def majorityCriterion(self, value):\n", | |
" \"\"\"\n", | |
" Determines if the larger part of the set is majority by at least the fraction \"value\"\n", | |
" \"\"\"\n", | |
" thesum = np.sum(self.labels.values)\n", | |
" thesize = self.labels.values.size\n", | |
" return thesum <= (1 - value) * thesize or thesum >= value * thesize\n", | |
" \n", | |
" def maxDepth(self, value):\n", | |
" \"\"\"\n", | |
" An OR between hitting max depth and some majority value (no need to split further needlessly)\n", | |
" \"\"\"\n", | |
" if self.depth == value:\n", | |
" return True\n", | |
"\n", | |
" return self.majorityCriterion(0.85)\n", | |
" \n", | |
" def growTree(self):\n", | |
" \"\"\"\n", | |
" growTree() as described in lecture.\n", | |
" \"\"\"\n", | |
" # dataSet is a pandas dataframe\n", | |
" workingData = self.dataSet\n", | |
" workingLabels = self.labels\n", | |
" dataLength = self.labels.size\n", | |
"\n", | |
" featureNames = list(workingData.columns.values)\n", | |
" nb_features = len(featureNames)\n", | |
" if self.fselection:\n", | |
" numFeatures = min(max(int(np.sqrt(nb_features)), 9) + 1, nb_features) # at least 10 features\n", | |
" np.random.shuffle(featureNames)\n", | |
" featureNames = featureNames[:numFeatures]\n", | |
" \n", | |
" bestEntropy = self.entropy # starting value of entropy is the entropy of the node itself\n", | |
" totalOnes = np.sum(workingLabels)\n", | |
" bestFeatureSplit = []\n", | |
" \n", | |
" if self.stopCriterion(self.stopParam):\n", | |
" # don't actually grow tree in this case.\n", | |
" self.val = round(np.sum(self.labels.values)/self.labels.values.size)\n", | |
" self.leaf = True\n", | |
" return\n", | |
" \n", | |
" for feature in featureNames:\n", | |
" joined = pd.concat([workingData[feature], workingLabels], axis=1).sort_values(feature) # sort by feature\n", | |
" uniqueValues = joined[feature].unique()\n", | |
" numValues = uniqueValues.size # how many unique values\n", | |
"\n", | |
" splitNumber = min(max(int(0.1 * numValues), 50), numValues) - 1 # get a reasonable number of splits \n", | |
" \n", | |
" featureVals = joined[feature].values\n", | |
" labelVals = joined.iloc[:,1].values\n", | |
" \n", | |
" ind = 0\n", | |
" leftones = 0\n", | |
" rightones = totalOnes\n", | |
" for i in range(splitNumber):\n", | |
" # now we grab indices off the uniqueValues, scan lists\n", | |
" # split on a less than or equal to criteria at that value\n", | |
" nextValue = uniqueValues[int(i / splitNumber * numValues)]\n", | |
" while not (featureVals[ind] == nextValue and not featureVals[ind + 1] == nextValue):\n", | |
" leftones += labelVals[ind] # adjusts count of each label for each side of split\n", | |
" ind += 1\n", | |
" # we are at the index that we will be splitting on \n", | |
" leftones += labelVals[ind]\n", | |
" ind += 1\n", | |
" \n", | |
" # calculate cross entropy\n", | |
" rightones -= leftones\n", | |
" leftzeroes = ind - leftones\n", | |
" rightzeroes = dataLength - leftones - rightones - leftzeroes\n", | |
" entropy = cross_entropy(leftones, leftzeroes, rightones, rightzeroes)\n", | |
" if entropy < bestEntropy:\n", | |
" # update bestEntropy if new split is superior\n", | |
" bestEntropy = entropy\n", | |
" bestFeatureSplit = [feature, ind, nextValue] # all the data required to describe a split\n", | |
" \n", | |
" # we have determined the best split by this point. \n", | |
" if len(bestFeatureSplit) < 3:\n", | |
" # this is if for some reason we were unable to find a split better than the current node's composition itself.\n", | |
" self.val = round(np.sum(self.labels.values)/self.labels.values.size)\n", | |
" self.leaf = True\n", | |
" return\n", | |
" self.decision = lambda x : x[bestFeatureSplit[0]] <= bestFeatureSplit[2] # create decision function\n", | |
" self.decisionString = \"Is \" + bestFeatureSplit[0] + \" less than or equal to \" + str(bestFeatureSplit[2]) + \"?\"\n", | |
" \n", | |
" preparedData = pd.concat([workingLabels, workingData], axis=1).sort_values(bestFeatureSplit[0])\n", | |
" # join the data back with labels, sort by feature\n", | |
" nextData = preparedData.iloc[:,1:]\n", | |
" nextLabels = preparedData.iloc[:,0]\n", | |
" \n", | |
" # take the 'ind' from 'bestFeatureSplit' to split into left and right parts. \n", | |
" # note the recursive definition of leftNode, rightNode\n", | |
" leftData = nextData.iloc[:bestFeatureSplit[1],:]\n", | |
" leftLabels = nextLabels.iloc[:bestFeatureSplit[1]]\n", | |
" self.leftNode = DecisionTree(leftData, leftLabels, [self.stopCritString, self.stopParam], self.depth + 1)\n", | |
" \n", | |
" rightData = nextData.iloc[bestFeatureSplit[1]:,:]\n", | |
" rightLabels = nextLabels.iloc[bestFeatureSplit[1]:]\n", | |
" self.rightNode = DecisionTree(rightData, rightLabels, [self.stopCritString, self.stopParam], self.depth + 1)\n", | |
" \n", | |
" def classifyPoint(self, point, verbose=False):\n", | |
" \"\"\"\n", | |
" Recursively send a point through the decision tree until it reaches a leaf. \n", | |
" Return value at the leaf.\n", | |
" \"\"\"\n", | |
" if self.leaf:\n", | |
" return self.val\n", | |
" elif self.decision(point):\n", | |
" if verbose:\n", | |
" print(self.decisionString, \" (Yes)\")\n", | |
" return self.leftNode.classifyPoint(point, verbose)\n", | |
" else:\n", | |
" if verbose:\n", | |
" print(self.decisionString, \" (No)\")\n", | |
" return self.rightNode.classifyPoint(point, verbose)\n", | |
" \n", | |
" def score(self, data, labels):\n", | |
" \"\"\"\n", | |
" Get accuracy of classifier on data.\n", | |
" \"\"\"\n", | |
" score = 0\n", | |
" for i in range(labels.size):\n", | |
" res = self.classifyPoint(data.iloc[i])\n", | |
" if res == labels.iloc[i]:\n", | |
" score += 1\n", | |
" return float(score) / labels.size\n" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"<br>\n", | |
"\n", | |
"`score` function is used for evaluation\n", | |
"\n", | |
"<br>" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Random Forest Code" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 14, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"class RandomForest:\n", | |
" def __init__(self, dataSet, labels, numPoints, numTrees, stopCriterion, printer=False):\n", | |
" \"\"\"\n", | |
" Create a random forest classifier. Arguments are mostly same/self-explanatory. \n", | |
" numPoints: number of points to use in training (basically bootstrap aggregating)\n", | |
" \"\"\"\n", | |
" self.numTrees = numTrees\n", | |
" self.stopCriterion = stopCriterion\n", | |
" self.trees = []\n", | |
" self.dataSet = dataSet\n", | |
" self.labels = labels\n", | |
" self.numPoints = numPoints\n", | |
" \n", | |
" self.growTrees()\n", | |
" if printer:\n", | |
" print(\"Finished Random Forest with %s trees\" % (numTrees))\n", | |
" \n", | |
" def growTrees(self):\n", | |
" for i in range(self.numTrees):\n", | |
" selected = [int(self.labels.size * np.random.rand()) for j in range(self.numPoints)]\n", | |
" sliceData = self.dataSet.iloc[selected]\n", | |
" sliceLabels = self.labels.iloc[selected]\n", | |
" tree = DecisionTree(sliceData, sliceLabels, self.stopCriterion, 0, fselection=True)\n", | |
" self.trees.append(tree)\n", | |
" \n", | |
" def classifyPoint(self, point):\n", | |
" score = 0\n", | |
" for i in range(self.numTrees):\n", | |
" score += self.trees[i].classifyPoint(point)\n", | |
" return round(float(score) / self.numTrees)\n", | |
" \n", | |
" def score(self, data, labels):\n", | |
" score = 0\n", | |
" for i in range(labels.size):\n", | |
" res = self.classifyPoint(data.iloc[i])\n", | |
" if res == labels.iloc[i]:\n", | |
" score += 1\n", | |
" return float(score) / labels.size " | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Try the Classifiers Out" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 15, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"Training Score for Titanic with Decision Tree was 0.9249061326658323\n", | |
"Training Score for Titanic with Random Forest was 0.8823529411764706\n", | |
"***************\n", | |
"Validation Score for Titanic with Decision Tree was 0.675\n", | |
"Validation Score for Titanic with Random Forest was 0.76\n" | |
] | |
} | |
], | |
"source": [ | |
"def makeValSplits(data, labels):\n", | |
" indices = np.arange(labels.size)\n", | |
" np.random.shuffle(indices)\n", | |
" length = int(0.8 * indices.size)\n", | |
" return (data.iloc[indices[:length]], labels.iloc[indices[:length]],\n", | |
" data.iloc[indices[length:]], labels.iloc[indices[length:]])\n", | |
"\n", | |
"trainData, trainLabels, valData, valLabels = makeValSplits(titanicData, titanicLabels)\n", | |
"tree = DecisionTree(trainData, trainLabels, ['maxDepth', 12], 0)\n", | |
"#print(\"***************\")\n", | |
"forest = RandomForest(trainData, trainLabels, int(0.7 * trainLabels.size), 7, ['maxDepth', 12])\n", | |
"#print(\"***************\")\n", | |
"print(\"Training Score for Titanic with Decision Tree was \" + str(tree.score(trainData, trainLabels)))\n", | |
"print(\"Training Score for Titanic with Random Forest was \" + str(forest.score(trainData, trainLabels)))\n", | |
"print(\"***************\")\n", | |
"print(\"Validation Score for Titanic with Decision Tree was \" + str(tree.score(valData, valLabels)))\n", | |
"print(\"Validation Score for Titanic with Random Forest was \" + str(forest.score(valData, valLabels)))" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Graph Accuracies as Function of Depth" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 16, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"image/png": "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\n", | |
"text/plain": [ | |
"<Figure size 504x504 with 1 Axes>" | |
] | |
}, | |
"metadata": { | |
"needs_background": "light" | |
}, | |
"output_type": "display_data" | |
} | |
], | |
"source": [ | |
"train_accuracies = []\n", | |
"val_accuracies = []\n", | |
"max_depth = 10\n", | |
"for i in range(max_depth + 1):\n", | |
" new_tree = DecisionTree(trainData, trainLabels, ['maxDepth', i], 0)\n", | |
" train_accuracies.append(new_tree.score(trainData, trainLabels))\n", | |
" val_accuracies.append(new_tree.score(valData, valLabels))\n", | |
"\n", | |
"plt.figure(figsize=[7,7])\n", | |
"plt.plot(np.arange(max_depth + 1), train_accuracies, 'r--', label='train_accuracies')\n", | |
"plt.plot(np.arange(max_depth + 1), val_accuracies, 'b-.', label='val_accuracies')\n", | |
"plt.title('Training/Validation Accuracy versus Tree Depth')\n", | |
"plt.ylabel('Accuracy')\n", | |
"plt.xlabel('Depth')\n", | |
"plt.legend()\n", | |
"plt.show()" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Accuracies as a Function of Tree Count" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 17, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"Finished Random Forest with 1 trees\n", | |
"Finished Random Forest with 3 trees\n", | |
"Finished Random Forest with 5 trees\n", | |
"Finished Random Forest with 7 trees\n", | |
"Finished Random Forest with 9 trees\n", | |
"Finished Random Forest with 11 trees\n", | |
"Finished Random Forest with 13 trees\n", | |
"Finished Random Forest with 15 trees\n", | |
"Finished Random Forest with 17 trees\n", | |
"Finished Random Forest with 19 trees\n" | |
] | |
}, | |
{ | |
"data": { | |
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAcoAAAG5CAYAAAAOKnSzAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJzs3Xd4lFX2wPHvoSVIb4oKUqQl9Bak2BBXRLBgwa6wrmJfXfva229lVda1oyhgR12UYEERsCMERJGO1CDSew3J+f1x30kmYWYySaYkmfN5nnkm87a5UzLnvfe991xRVYwxxhgTWIV4F8AYY4wpzSxQGmOMMSFYoDTGGGNCsEBpjDHGhGCB0hhjjAnBAqUxxhgTggVKg4hUFJFdInJMJLeNNRF5U0Qe9P4+SUTmh7NtMZ6n1L4HxpjIs0BZBnk/0r5bjojs9Xt8SVGPp6rZqlpdVVdHcttwichoEblfRHaKyGEB1v8qIsOLckxVna6qbSNUvu9E5Eq/Y0f8PQjynJtEpEq0nsOER0Su8Pv/2uv9z/keb4tRGeqIyLMissZ73mUi8qSI1I3y8w4XkSnRfI6ywAJlGeT9SFdX1erAamCQ37K3Cm4vIpViX8rwiIgA/YFXgPXA4ALrOwGtgPdiX7r4EJEWQE/c/+cZMX7uUvtdCSbaZVbVsX7/b4OA1X7/b7WjXR4RqQpMB44F+gE1gd7AHqBLJJ/LBGaBshwSkUdF5D0ReUdEdgKXikhPEZkhIttEZJ2I/FdEKnvbVxIRFZGm3uM3vfWfebW8H0WkWVG39dafLiJLRGS7d0b8vX/tDOgMrFfVdcA44PICL+dyIF1Vt4pIBRH5QET+9F7HdBFJCfIe9BORlX6Pu4rIXK+M7wBJfuvqicinIrJRRLaKSLqIHO2tewIXtF7yzuT/E+A9qO29DxtFZKWI3O2dACAiV4nI1yIy0ivzchH5SyEf4eXAd8CbwBUFXtdh3rFWe+/pNyKS5K07wfuMt3s1j8u85flqxF6Zpnt/+17LdSKyDFjkLX9ORDJFZIeIzBKRXn77VxKR+0Tkd299hogcJSIve++Xf3k/FZEbA3w+r4jIvwos+0REbvL+biQiE7z3dIWIXO+3XaDv93EiMscrz3oR+be3bb7vgbcsU0RO8v4OuF9Red/J28Q19+/wljUWkY/FtQwsF79WEXHN9/d5yzeJyFsickjQ9fwVqAecq6qLVTVHVder6v2qOsU7XnsR+db7jv0qIqf7PdcMEbnU73FuLVFEkr3P/2rv89wqIiO9dZ2B/wAned/9P4vz3pQLqmq3MnwDVgL9Cix7FDiAO/utAFQFugM9gEpAc2AJcIO3fSVAgabe4zeBTUA3oDKuNvdmMbY9HNgJnOWtuxXIAq70K+u9wCPe30299Ud5jysC64CB3uMKwJVADSAZeA7I8DvWm8CD3t/9gJXe30lAJnCTV44LvefxbdsAOMd7n2oC/wM+8DvudwXKXPA9eNvbp4b33i4DrvDWXeU91zDv9dwIrAnxeQqwArja+7wOAPX91r8MfAUc6R2vj/eamgG7gAu88tUHOgUp/1XA9AKv5XOgDlDVW34ZUNdbfyewFkjy1t0N/AK09D6TTt62vXAtHOJtdwSu1lM/wOvsi/vu+ratB+z19qkAzAXuAaoALbxtTwnx/Z4FXOStrwH0KPg98HvuTOAk7++A+4X4fA45nrf8T+9YR3nlqQjM8967KrhWkdXAid72dwLfetsnA2OA14M850fAyyHKlOwd+x/ed+E077vQzFs/A7jUb/vhwBS/fRX3/a3pfY+2+b0/udsm8s1qlOXXd6qaru7sc6+qzlLVn1T1oKouB0YBJ4bY/wNVzVDVLOAt3I9hUbcdCMxV1Y+9dSNxQdXfGcCnAKq6Evge8J39/gX3Q/i5tz5HVceo6k5V3Qc8CHQVkWqFvBe9cT8Gz6pqlqq+C/zsW6mqG1V1gvc+7QAeJ/R7k0tcrfwC4C6vXMu913mZ32a/q+prqpoNjAUaiUj9IIc8ETga957+hPsBvMh7roq4E4WbVHWdumul33nv7aXAZ6o63vuMN6nq3HBeg+dxVd2qqnu99+QNVd2iqgeBEbgf0RbetlcB96jqUu8zmett+wOwDzjJ2+4i3I9swc8cXFNiZVxtHdx7+K2qrveW1VTVx1X1gKouA0bjTnB88n2/cScjLUWknvc5/BTm6y7ufoGMVNU/vPL0AZJV9QnvNSwBXvd7DcNx35k/vO/yQ8AQX0tEAfVwJ4zBHI/7fj/tfb8nA18CQ4pQ9sdVdYeqrgC+IfT/e8KxQFl+rfF/ICJtvKatP0VkB/AwrtYRjH8zyx6gejG2Pcq/HKqquLN5X5nq4Wpg/j9OY8kLMpcBb3s/1r7mqhFec9UOXM2NQl6HrxyZ3vP7rPIrR3URedVrztwBTA3jmD6H42oPq/yWrcIFO5+C7w8Efz+vwAW8Ld7jt8lrfj0CVzv5PcB+jYMsD1fB78sdIrJIRLYDW4Fq5L0noZ5rHHknOpcCbwTaSFVzcK0PF3mLLsadZAE0AY7xmhG3ieswcwfQMFh5gaFAKrBYRGaKyICgrzQy+wXiX6YmQNMCr+FWoKEXDBsDn/qt+xn3e1wvwHE341oQgjkKd9204Pf76CDbB1KU//eEY4Gy/Co4LczLwG9AC1WtCdyPa+aLpnVAI98D7wfC/5+3P67GkeO37AOguYicCJyNC5w+lwMDcM12tcir4RT2OvKVw+M/tON2XJNTmvfe9C2wbagpdjYA2bgfRv9jry2kTIfwasbnAad4JzR/4ppqu4pIW1xnpwO4Th0FrQmyHGA34N+buGGAbXJfo4icjPtRPxeojWuS3UXe+xzqud4AzvGubx0LpAfZDuAd4Hxx17S74Jr/fMdfqqq1/W41VHVQoPICqLt2dyHuxOUp4EMRSS742sV1tKkXxn7F4V+mNcCiAK/hHC+grQX6FlifHKT2PQUYEKJcf5D/+wz5v4PhfP7hvKaEZYEycdQAtgO7xXWAuSYGzzkJ6CIig7wfqJtx1wN9BgCf+O+gqjtxP5hjcT+W/s2HNYD9uDPsw4DHwizHd0AFEbnB64hyAfl7C9bAnUVv9Wq59xfYfz2u5nsIr9nzA+Bxr2baDLgFd720qAbjXl8bXNNXJyAF+BG43Gu6HQP8R0QaejXs3l7z75tAfxE513uN9UWko3fcucC5IlJVRFrhrpeGUgM4iGsmr4xr4vZv3n4VeFREjhWnk3jDFFR1Fe765Vjgfa9ZMSBVnYXr+DIK+NT77PFe7wER+YfX2aSi11mla7BjichlIlLfO+najvuBz8F1TqohIqd579MD3msqbL+S+s47/t+911BJRDqIiO979xLwLxFp7G13uIgMCnKs0cAW4H0RaeW95w1E5AEROQV3rbOC91yVRORU3GWL8d7+c4HzvHK0wTXfh2s90Nh77xKWBcrE8Q9cE95OXO0y6sMtvOtNQ4CnccHtWFwT034RqQCcCkwOsOtYXA1tXIHlr+POnv8A5gM/hFmO/bjOOn/DNSOeg+sg4fM0roa62TvmZwUO8R/gIq+Z7OkAT3Edrqa3EvjaK3/BsofjCmC0qmaq6p++G67T0qXeNcpbgIXAbNyP5+O4DjErcJ1b7vSWzwHae8d9EhcANgCvUXgQ/xRXi1nqvaYd5L9G9m/c+/cVeYHOv7Yz1nvugM2uBbyD6yDztm+B19Q+AEjznn8T7jtbM8RxBgALxfWCfRIY4l0b3IqrlY/F1bC2kL+ZMeB+YZQ7JO8EagCug9MqYCPwInlNmiNw7/FU77l/IMhQD++a50necabi/od/xJ28zPFORgbiWiM2477PQ7zr5b7nquSVYRRFO4n7HPcZbBCRzEK2Lbd8Pc6MiTrvh/4P3D90NvCkqvYKvZcpa0SkL64W1FztB8aUA1ajNFElIv3FjTNMAu7D9TKciWveeiiuhTMRJy6T0M3AKxYkTXlhgdJEWx9gOa7Z5zTgHFXdr6ozvG7sppwQkfa4pu26wH/jXBxjIsaaXo0xxpgQrEZpjDHGhFDmEiAXR/369bVp06bxLoYxxphSYvbs2ZtUtUHhWyZIoGzatCkZGRnxLoYxxphSQkRWFb6VY02vxhhjTAgWKI0xxpgQLFAaY4wxISTENUpjjAHIysoiMzOTffuCpqA15UxycjKNGjWicuXip6u1QGmMSRiZmZnUqFGDpk2bEnjqR1OeqCqbN28mMzOTZs2aFfs41vRqjEkY+/bto169ehYkE4SIUK9evRK3IFigNMYkFAuSiSUSn7cFSmOMMSYEC5TGGGNMCBYojTEmhv773/+SkpLCJZdccsi66dOn88MPYc1Hnk9GRgY33XRTJIpXqlx11VUsWLAg3sWwXq/GGBNLL7zwAlOmTKFRo0aHrJs+fTrVq1enV69D5zM/ePAglSoF/snu1q0b3bp1i3hZIylU+YN59dVXo1SaorEapTEmcZ100qG3F15w6/bsCbx+zBi3ftOmQ9cVYvjw4SxfvpzTTz+dkSNH5lu3cuVKXnrpJUaOHEmnTp349ttvufLKKxk+fDg9evTgjjvuYObMmfTs2ZPOnTvTq1cvFi9eDLgAO3DgQAAefPBBhg0bxkknnUTz5s35739DTw169tln07VrV9q2bcuoUaNyl3/++ed06dKFjh07csoppwCwa9cuhg4dSvv27enQoQMffvghANWrV8/d74MPPuDKK68ECLv82dnZ3HbbbbRr144OHTrw7LPPeh/PSbl5ur/44gt69uxJly5dOP/889m1axcAd911F6mpqXTo0IHbbrut0M+gOKxGaYwxMfLSSy/x+eefM23aNOrXr59vXdOmTRk+fDjVq1fP/cEfPXo0mZmZ/PDDD1SsWJEdO3bw7bffUqlSJaZMmcI999yTG6z8LVq0iGnTprFz505at27NtddeG3TA/WuvvUbdunXZu3cv3bt359xzzyUnJ4e//e1vfPPNNzRr1owtW7YA8Mgjj1CrVi3mzZsHwNatWwt9zeGUf9SoUaxcuZK5c+dSqVKl3Ofz2bRpE48++ihTpkyhWrVqPPHEEzz99NNcf/31TJgwgUWLFiEibNu2rfAPoRgsUBpjEtf06cHXHXZY6PX164deHyHnn38+FStWBGD79u1cccUVLF26FBEhKysr4D5nnHEGSUlJJCUlcfjhh7N+/fqATb3grplOmDABgDVr1rB06VI2btzICSeckDtIv27dugBMmTKFd999N3ffOnXqRKT8U6ZMYfjw4blNs77n85kxYwYLFiygd+/eABw4cICePXtSq1YtkpOT+etf/8rAgQNza9WRZk2vJvo2b453CYwps6pVq5b793333cfJJ5/Mb7/9Rnp6etCB9ElJSbl/V6xYkYMHDwbcbvr06UyZMoUff/yRX375hc6dOxdrcL7/WMWC+xen/AWpKqeeeipz585l7ty5LFiwgNGjR1OpUiVmzpzJeeedx6RJk+jfv3+Ryx4OC5QmuiZPjtmZtzFlXY0aNdi5c2fQ9du3b+foo48GYIzvWmkJbN++nTp16nDYYYexaNEiZsyYAcBxxx3HN998w4oVKwBym0JPPfVUnn/++dz9fU2vRxxxBAsXLiQnJye3dlqU8p966qm8/PLLuQG9YNPrcccdx/fff8+yZcsA2L17N0uWLGHXrl1s376dAQMGMHLkSH755ZeSvB1BWaA0UaWfT+Yn0tAvvox3UYwp9QYNGsSECRNyO/MUdMcdd3D33XfTuXPnoLXEoujfvz8HDx4kJSWFu+66i+OOOw6ABg0aMGrUKAYPHkzHjh0ZMmQIAPfeey9bt26lXbt2dOzYkWnTpgHwr3/9i4EDB9KrVy+OPPLIoM8XrPxXXXUVxxxzDB06dKBjx468/fbb+fZr0KABY8aM4aKLLqJDhw707NmTRYsWsXPnTgYOHEiHDh3o06cPTz/9dInfk0BEVaNy4NKkW7du6us5ZWLr5a4vM3zONUy6Jp0zXhoU7+KYBLdw4UJSUlLiXQwTY4E+dxGZraphjamxGqWJqgl/uDPUJa0tSBpjyibr9WqiJjsb5mR3BKBLZ4UchQp2bmbM66+/zjPPPJNvWe/evfNd/4ukzZs3546F9PfVV19Rr169qDxneWKB0kTNrFmwcSO8PWINJ16UBqNHw4AB8S6WMXE3dOhQhg4dGrPnq1evHnPnzo3Z85U3dnpvoib9nzOoyEH6nV2DZetrwMyZ8S6SMcYUmQVKEzXpGQ3pU3U24ybWpqUuYfN3C+NdJGOMKTILlCYqVq2CeTuaMqj1UgYMgNePf40qP/8ECdDL2hhTvkQ1UIpIfxFZLCLLROSuAOtHishc77ZERLZ5yzuJyI8iMl9EfhWRIX77jBGRFX77dYrmazDFk/XnZq5gDGf2P0BKClx5SRY1tqwCbwCzMcaUFVELlCJSEXgeOB1IBS4SkVT/bVT1FlXtpKqdgGeB/3mr9gCXq2pboD/wHxGp7bfr7b79VNWuUJdCLbbMZAxDaXl6CwB+OeIvZFz0FHg5H41JVKHmoyyqMWPGcMMNN0SgVLFXlubQjGav1zRgmaouBxCRd4GzgGCzcF4EPACgqkt8C1X1DxHZADQAopMa3kTUnj3w+8aGtBt8LtK5MwDDHmlG/fq3MrlJnAtnTJyFmo+yrFJVVJUKRRj+VRbm0PSJZtPr0cAav8eZ3rJDiEgToBkwNcC6NKAK8Lvf4se8JtmRIpJUcB8TX59/Dh2u6Mz3t3wANWoAkJoKCxYoLFoU59IZkyfQdJMFb08+mX/7EkxHGXI+ypycHJo2bZpvqqiWLVuyfv160tPT6dGjB507d6Zfv36sX78+rNcXbL9g80oGmoPywQcf5Em/N6Fdu3asXLmSlStX0rp1ay6//HLatWvHmjVruPbaa+nWrRtt27blgQceyN1n1qxZ9OrVi44dO5KWlsbOnTvzzaG5e/duhg0bRlpaGp07d+bjjz8GYP78+aSlpdGpUyc6dOjA0qVLw3rdkVZaxlFeCHygqtn+C0XkSOAN4ApVzfEW3w38iQueo4A7gYcLHlBErgauBjjmmGOiV3JziD594JWnd9KjR43cZamp8Oabwo7OJ1Jz51oo4kznxpQHoeajrFChAmeddRYTJkxg6NCh/PTTTzRp0oQjjjiCPn36MGPGDESEV199lREjRvDUU08V+nzB9gs0r+TGjRsDzkEZytKlSxk7dmxujtjHHnuMunXrkp2dzSmnnMKvv/5KmzZtGDJkCO+99x7du3dnx44dVK1aNd9xHnvsMfr27ctrr73Gtm3bSEtLo1+/frz00kvcfPPNXHLJJRw4cIDs7OxAxYi6aP5arQUa+z1u5C0L5ELgev8FIlIT+AT4p6rO8C1X1XXen/tF5HUg4JTWqjoKF0jp1q2bdbWMocOz13HVrUfBYS/BNdcA4EuzuGhfE9Lmz4eOHeNYQmOcok5q4799NCbFGTJkCA8//DBDhw7l3XffzU1GnpmZyZAhQ1i3bh0HDhzInSeyMMH2CzSvZHp6esA5KENp0qRJbpAEGD9+PKNGjeLgwYOsW7eOBQsWICIceeSRdO/eHYCaNWsecpwvvviCiRMn5tZc9+3bx+rVq+nZsyePPfYYmZmZDB48mJYtW4b1uiMtmk2vs4CWItJMRKrgguHEghuJSBugDvCj37IqwARgnKp+UGD7I717Ac4GfovaKzBFtmABjHpsIzupDm3b5i5P9bpxLSTFEg8YE0TPnj1ZtmwZGzdu5KOPPmLw4MEA3Hjjjdxwww3MmzePl19+Oex5HIu7n79KlSqRk5OT+9j/GP5zTa5YsYInn3ySr776il9//ZUzzjijSPNNfvjhh7nzTa5evZqUlBQuvvhiJk6cSNWqVRkwYABTpx5ydS4mohYoVfUgcAMwGVgIjFfV+SLysIic6bfphcC7mn8akwuAE4ArAwwDeUtE5gHzgPrAo9F6Dabo3n4brnuhHVmSBJ3yRu40bw5VqigLkrpYoDQmCBHhnHPO4dZbbyUlJSU3D6v/PI5jx44N+3jB9gs0r2SwOSibNm3KnDlzAJgzZ07u+oJ27NhBtWrVqFWrFuvXr+ezzz4DoHXr1qxbt45Zs2YBsHPnzkOmCDvttNN49tln8YWBn3/+GYDly5fTvHlzbrrpJs466yx+/fXXsF97JEX1QpGqfgp8WmDZ/QUePxhgvzeBN4Mcs28Ei2giLD0deteZT90jG0L16rnLK1WCVq2Ehet7wMzX4lhCY0q3IUOG0L1793wTGz/44IOcf/751KlTh759+wYNVgUF2+/ee+/l+uuvp127dlSsWJEHHniAwYMH585BmZOTw+GHH86XX37Jueeey7hx42jbti09evSgVatWAZ+rY8eOdO7cmTZt2tC4cWN69+4NQJUqVXjvvfe48cYb2bt3L1WrVmXKlCn59r3vvvv4+9//TocOHcjJyaFZs2ZMmjSJ8ePH88Ybb1C5cmUaNmzIPffcU4x3tORsPkoTMatWQdOm8O8aD3Hb4BV53QM9F1wAc37Yy7I3ZsDJJ8eljCax2XyUicnmozSlxqRJ7n7QPR0gwMwIqamw/I+q7D3OgqQxpuywPvomYtLToWVLaH3XOQHXX3klnDFAqfzVZKhbE3r1im0BjSklIj0f5WOPPcb777+fb9n555/PP//5z2KX0eSxplcTEbt2Qb16cMMFG3jqzg3Qrl3wjZs2hR494L33YlY+Y8A1wbVp0wbXad4kAlVl0aJF1vRq4u/LL+HAARi45GkIkcPy7bfhyyZ/dbM6GxNjycnJbN68mUSoIBgXJDdv3kxycnKJjmNNryYi0tOhVi2lz/JxcObpQbd78EHomHwBp664HzZuhAYNYldIk/AaNWpEZmYmGzdujHdRTIwkJyeXOK+uBUoTEQcOwNmn7qbyB+sgRKLjadPg8EXroR+uVjlgQOwKaRJe5cqVw85qY4yPNb2aiHjzTXj9wi/cg65dg2539NFQuUcXqFDBml+NMWWC1ShNiR04AFWqgMzOcJkFOnQIuu3ixfDss9W57culND3R5twyxpR+VqM0JdajB9x4I/CPf8DUqRDiwvnOnfD88zBnW3ObxNkYUyZYoDQlkpMD55zjDYmsVw+OPz7k9m3auPuF326E666D1aujX0hjjCkBC5SmRCpUgPvvh4tO/AP+7/9gzZqQ21evDsccAwsWV4QXX4Qffwy5vTHGxJsFSlMiM2bAnj3A99/DPffAhg2F7pOaCgv+qOOaaG0mEWNMKWeB0hTbrl1w4omuRklGhuvREyojjyc1FRYtFrI7d7NAaYwp9SxQmmLLzcYzEJg9G9q3h6SkQvdLSYF9+2BVm9PcfgXmpjPGmNLEAqUptvR0qF0bevdSV6MMkWjAX2qqu19Q73iXmeePP6JYSmOMKRkLlKZYcnLgk0+gf3+ovGEt7N0bdqD05SZe2OAEN4nlMcdEsaTGGFMylnDAFMusWa7fzqBBQKNGboBkdnZY+9ap42Lj1m02g4MxpvSzQGmKJT3d5Qs43Zf/vEqVIu2/YoUbWsLjj7ses598EvEyGmNMJFjTqymW9HTo08fVDrn5ZigwCW1hKvi+efv2weTJsHt3xMtojDGRYIHSFNmqVfDrr15v15wceP11WLKkSMf45hvo2xf+OPZ412T788/RKawxxpSQBUpTZN9+6+4HDQKWLnXXJ8PsyONTsaLr/7OtWWe3wMZTGmNKKbtGaYrs0kvhhBO8zqpvZbiFRQyUvXv7stfVhyZNLFAaY0otC5SmWHJHdMyeDVWr5o35KI5LLgkrUYExxsSDBUpTJJ9+Cq+9Bi+8AIcfjsvXetppbh7KIvrb31yugU8+eSzyBTXGmAixQGmKZNMmWLjQ6+0KbnhHMYn4tbhmZ7sesNWqlbiMxhgTSdaZxxTJ5ZfD/PlQuTKgWqJjpaa6wLtxzT6oWxeefDIyhTTGmAiyQGnCtnevGw2S6803oWVLWLu2WMfLTWW3Itld9LQOPcaYUsgCpQnbY49Bs2awf7+3YNYsd5GxYcNiHS83OfoCIC3NBcoS1lKNMSbSLFCasKWnQ9Omfh1UZ8+GLl3coMhiaNQIqlf3AmX37q4dduXKCJXWGGMiwwKlCYsvG8+gQd6CgwddNp0ijp/0J+KaXxcuxNUowZpfjTGljgVKE5ZJk9x9bqBctKhIU2sFk5Li1Sjbt4cHH3T3xhhTiligNGGZNAlatIBWrbwFlSvDVVdBz54lOm5qqrvMuX1PZXjggbwLl8YYU0pYoDSF2rULpk51tUnxTSHZujW88go0b16iY/fuDX/9q6ucsnMnTJnimnWNMaaUsEBpCvXll3DggF+zK8Dq1QXGihRPnz7w6qtex9n0dDj1VK8t1hhjSgcLlKZQ6elQq5YLagBkZbk22Hvuicjxc3Jg+3asQ48xplSyQGlCysmBTz6B00/3svGAS82zfz906hSR5+jVCy6+GDj2WJcbzwKlMaYUsVyvplATJrgJQnLNnu3uS9jj1ee667yxmSJ5iQeMMaaUsEBpQqpQwdX48snIcG2xxx4bkee4/HK/B927w//9H+zebQnSjTGlgjW9mpAefzxABS8jw9Umc7vAlkxWFvz2G2zZAgwbBj/95KbvMsaYUsBqlCaoLVvg0UehSpW8fjaASwyQe8Gy5JYudXkG3ngDLr20mUsoa4wxpYQFShNU3bou/Wp2doEVZ5wR0edp0cLN+7xwobdg0iTYvBmuuCKiz2OMMcUR1aZXEekvIotFZJmI3BVg/UgRmevdlojINr91V4jIUu92hd/yriIyzzvmf0Ui1P5nAjrsMKhRw2/Br7/CN99EZAylT5UqLljmDp8cOxYeeihixzfGmJKIWqAUkYrA88DpQCpwkYjky0+mqreoaidV7QQ8C/zP27cu8ADQA0gDHhCROt5uLwJ/A1p6t/7Reg2JbNcul51u8uQCK557Ds4+O2LXJ31SU/1qlGlpsGIFbNwY0ecwxpjiiGaNMg1YpqrLVfUA8C5wVojtLwLe8f4+DfhSVbeo6lbgS6C/iBwJ1FTVGaqqwDjg7Oi9hMQ1ZQrMmOFqe/lEuCOPT0oKLFvmMgDlXhCdNSuiz2EhDa1PAAAgAElEQVSMMcURzUB5NLDG73Gmt+wQItIEaAZMLWTfo72/wznm1SKSISIZG61mUmSHZOMB2LcP5s2L2PhJf6mp7lro0qVA165uXIoFSmNMKVBahodcCHygqgW7jRSbqo5S1W6q2q1BgwaROmxC8GXj6d+/QOfWefNcwvKuXSP+nCkp7n7BAtxszikpsHhxxJ/HGGOKKpq9XtcCjf0eN/KWBXIhcH2BfU8qsO90b3mjMI9pimnWLFi/vkASdHDNrhCVGmXr1q41N7dDz/ffQ82aEX8eY4wpqmjWKGcBLUWkmYhUwQXDiQU3EpE2QB3gR7/Fk4G/iEgdrxPPX4DJqroO2CEix3m9XS8HPo7ia0hI6elQsaLL75rPlVe6C5fHHBPx5zzsMDd8MrdDT61aEb8OaowxxRG1QKmqB4EbcEFvITBeVeeLyMMicqbfphcC73qdc3z7bgEewQXbWcDD3jKA64BXgWXA78Bn0XoNiWrSJDdPZN26BVZUrQo9ekQtgD3/PNx5p/dg0yaXKf0z+3iNMfElfvGp3OrWrZtm+JoNTUirV0OTJjBiBNx+u9+KvXtdRp5LL3VpdKItK8sN4Lz+enjqqeg/nzEmoYjIbFUN6zpSaenMY0qJSZPc/SHXJ3/5xUXP5cuj9tybN8N773nDJytXhi5dbCYRY0zcWaA0+XToAP/4h+tck08UO/L4LFsGF14IP/quVqelwZw5rqetMcbEiQVKk0+fPvDkkwEuQ2ZkwBFHwFFHRe25O3aEuXPhL3/xFqSlwZ49fl1hjTEm9iwpusm1eLG7NNi2bZBAGYWMPP6Sk12wzNWjh6vibt8etec0xpjCWI3S5BoxwtUoD2npPHAANmyIarOrz+efw8iR3oNjj3XXRo8/PurPa4wxwViN0uR65BG46KIAU01WqeIyEBw4EPUyfPYZjB4Nf/+7X+VV1cZUGmPixmqUJtdRR0G/fkFWikBSUtTLkJICu3fDGl+m39dfhwYN3EJjjIkDC5QGgLffdjW5gP75T7jttpiUI9WbiC03Q0/9+m7cyM8/x+T5jTGmIAuUBnDXJ8eODbLyf/+DJUtiUo58ydEBund39zae0hgTJxYoDatXuz4zhyQZANi503WHjUFHHnCtrPXr+9UoGzZ0uWUtUBpj4sQCpeGTT9x9wED588+uM02MAiW45td8QyfT0ixQGmPixnq9GtLT3UiMQ7LxQF5GnijMQRlMSgqMH+/X2XXIEGjVys3sXLFizMphjDFgNcqEt3s3TJ3qapMBR2BUrQp9+7qsPDGSmgpbt7qhmwCcdx489pgFSWNMXFigTHBffgn79wdpdgW49lr46quYliklBSpUgN9/91u4a5ffmBFjjIkda3pNcJMmQc2aQZLf5OS4amaMB/ufdJKr6SYn+y3s1QsaN867oGqMMTFiNcoElpPjAmX//gGy8QB8/TUcfnjedcoYqVy5QJAE15lo5kx34dIYY2LIAmUC27LFJSEfPDjIBhkZsGkTNG0ay2IB8OyzcOedfgvS0lxZVq6MeVmMMYnNml4TWP36MHlyiA0yMlyQrF8/VkXKtXixm58yV1qau585E5o1i3l5jDGJy2qUCWzr1kI2mD07puMn/T33nJtJJFf79i7XrI2nNMbEmAXKBLV6tasojhsXZIOtW1230zgFykNUrgxjxsCVV8a7JMaYBGOBMkElJcH997vOpAFlZblE6EGnE4muLVugd2+XrD3XhRe6mqUxxsSQaAL0IuzWrZtmxLjnpimZnByoXh2GD4enn/YW7tgBX3wBxx0HjRrFtXzGmLJNRGaralhNZlajTEC7d7u0dXv2hNho2TLYty9mZSqoQgVo08YvOTq4yaPPP7/AxUtjjIkuC5QJaMoUOPNMmDEjxEb9+sX9euAhydFbtIData1DjzEmpixQJqD0dKhVK0g2HnDjFVetimki9EBSUlyno127vAUiNpOIMSbmLFAmmEKz8YAbFgJx7/GamuruFy3yW5iWBr/95tqPjTEmBixQJpjZs92lvqBJ0CEvZV2XLjEpUzApKe7+kLkps7PdPJnGGBMDlpknwaSnu44y/fuH2Gj2bDf/Y61aMStXIMce62q9+Tr09O3rxndadh5jTIxYoEww6elufGK9eiE2uvNOd50yzipXdvE6X42yWjVo3jxuZTLGJB4LlAlkzRqYOxdGjChkwx49YlKecAwa5K6r5vPFFy5J7VNPxaVMxpjEYtcoE8ikSe4+5PXJJUtg4sS4jqH093//B088UWDhL7+4LASloNZrjCn/LFAmkHnz3FDE1q1DbPTee3D22S6FXSmh6vrv5Ore3d3PmhWX8hhjEosFygTywguun45IiI0yMlxKnBo1YlauUH7/HerWhfff91vYtat7ETae0hgTAxYoE0zNmoVskJER9/GT/o4+2uVCz9fJtUYNN8jSAqUxJgasM0+CuOUWl1N89OgQG/3xh7vFOSOPv+RkePHFACt69IClS2NeHmNM4rFAmSCqVStwnS+QUpKRp6CDB2HtWmjSxG/hK6+4AaHGGBNlFigTxKOPhrHRGWe40f2lbDD//ffDk0+6rHW5afcsSBpjYsR+bRLA+vWu52ihfHNbJSVFvUxF0aaN64T7++9+C1Xh3HPhkUfiVi5jTGKwQJkA+veHwYML2UjVXcicPj0WRSoSX3L0fKnsRGDdOvjyy7iUyRiTOCxQlnO+bDw9exay4dq18J//uJk5Spk2bdx9vlR24MZTzp7tLmIaY0yUWKAs58LKxgN5M4aUso48ANWrwzHHFKhRgptJZM+eABHUGGMixwJlOZee7mbh8NXKgpo9GypWhI4dY1KuokpJCRAP09LcvY2nNMZEUVQDpYj0F5HFIrJMRO4Kss0FIrJAROaLyNvespNFZK7fbZ+InO2tGyMiK/zWdYrmayjLdu+GqVNdbTJkNh5wNcq2baFq1ZiUrahSU90EzvkSpLdoAQMGQJ06cSuXMab8i9rwEBGpCDwPnApkArNEZKKqLvDbpiVwN9BbVbeKyOEAqjoN6ORtUxdYBnzhd/jbVfWDaJW9vJgyBfbvh4EDw9h4y5ZS2ezqk5oKe/fCqlV+o1dE4JNP4louY0z5F81xlGnAMlVdDiAi7wJnAf4NaH8DnlfVrQCquiHAcc4DPlPVPVEsa7mUnu5S1h1/fBgb//RTGBkJ4iclxd0vWBBgmOe+fVCpkrsZY0yERbPp9Whgjd/jTG+Zv1ZAKxH5XkRmiEj/AMe5EHinwLLHRORXERkpIgEH/YnI1SKSISIZGzduLO5rKLNyclxHnv79oUqVMHeqWDGqZSqJ9u3hueegXbsCK77+2p0N/PRTXMpljCn/4t2ZpxLQEjgJuAh4RURq+1aKyJFAe2Cy3z53A22A7kBd4M5AB1bVUaraTVW7NWjQIDqlL8Vmz3aJBgrt7Qou7c3554eZlSA+ataE668vkMYO3JxhWVnWoccYEzXRDJRrgcZ+jxt5y/xlAhNVNUtVVwBLcIHT5wJggqrmTo6oquvU2Q+8jmviNQV06QLffx9moPziC5f2ptAeP/G1alWAfAgNG7qxIxYojTFREs1AOQtoKSLNRKQKrgl1YoFtPsLVJhGR+rim2OV+6y+iQLOrV8tERAQ4Gyh9I+RLgYoVoVcvqFWrkA1VS93UWsGMGAFnnRWg4puWZoHSGBM1UQuUqnoQuAHXbLoQGK+q80XkYRE509tsMrBZRBYA03C9WTcDiEhTXI306wKHfktE5gHzgPpAOOm+E0pmJtx4IyxfXvi2rFgBW7eWiUB5002uJ+8h0tLci920KeZlMsaUf1HtJqiqnwKfFlh2v9/fCtzq3Qruu5JDO/+gqn0jXtBy5pdf4NVX4brrwti4FGfkKah16yArTj/d3duMIsaYKLD+9OXQGWe4YZHJyWFsnJTkxo8c0p209MnOhrffdpmGevXyW9GuXZkovzGmbLJT8HKqatUw++acdRZ8800RxpDET4UKrvn1jTcCrFy/HmbMiHmZjDHlnwXKcmbiROjaFVauDGNjVTe0oowQcRl6DkmODnD33XDmmaV6iIsxpmyyQFnOTJwIy5bBUUeFsfGyZVCjBnz0UdTLFSkBk6OD69CzcaMbQ2KMMRFkgbIc8WXjOe20MFtSMzJcMtimTaNdtIhJTXXx8JAOrjaTiDEmSixQliNFysbj2yEpyc0aUkakprr7Q5pf27d3r8UCpTEmwixQliPp6a7Dy4ABYe6QkQGdOkHlylEtVyT5J0fPp3Jl6NzZAqUxJuJseEg5kp7uhk3UqxfGxjk5MGcOXH551MsVSY0bQ7VqQTr0PPNMGKmIjDGmaCxQlhNr1sDcufDEE2HusH8/3Hkn9OwZ1XJFWoUK0KZNiA49xhgTYRYoywnf/MVhTdIMbqDlP/8ZtfJEU2oqTJsWYEVWFowd6yJpnz4xL5cxpnyya5TlRHo6NG+edw2vUIsXl9ncqP/+d5Cm10qV4Pbbg2QkMMaY4rEaZTlxzTWwa1cRZsq66iqXE+6HH6Jarmg44oggK0RsJhFjTMRZjbKcOPNMuPjiMDfOznYdebp3j2qZomX3brjrLvjqqwAr09Jg3jzYsyfm5TLGlE8WKMuBTz8N0rklmMWLXSApAzOGBJKUBC+84GL9Ibp3dycCP/8c83IZY8ona3ot47Ky3AiP008vwqW5MjS1ViCVKrkpNCtWDLDSV0uePx96945puYwx5ZMFyjKucmX49Vc32iNsGRlQvTq0ahW1ckVbwCAJcOSRsHkz1K0b0/IYY8ova3otB446Cpo1K8ION9zgJnYMGm1Kv08/hb59g1yKtCBpjIkgC5Rl2JIlcOqpRbw+Ca4mGXZC2NJp9243lnLJkgArZ8yAs88us8NfjDGliwXKMmz0aBcsilSBWrMGxo1zF/nKMF9y9IAnCfv2wccf512LNcaYErBAWUZlZcGYMS4TT8OGRdhxyhS44grYsCFaRYuJli1dy3HAQNm1qxtTaeMpjTERYIGyjPrkExfrrrqqiDtmZLjJmlu2jEq5YqVKFWjRIkiGnho1XJXTAqUxJgIsUJZRr77qOvH071/EHTMyXI2rQtn/6FNSQlyf7d7dBUrVmJbJGFP+lP1fywSUmQmffQZDh7oxhWHLyoJffnGBshxITYVly+DAgQArjz8ejj0Wtm+PebmMMeWLBcoyaMwYN53ksGFF3HHhQjfgsowmGigoNRUOHnTB8hDDhsGPP0Lt2jEvlzGmfLGEA2VMTg689pobQ9i8eRF37tAB1q1zMx+XA76ZUhYuzOsFewjVImSKN8aYQ1mNsoyZNg1WrChGJx6fhg1dZ5dyoE0baN8+xGXIa65xuf2MMaYErEZZxnTvDi+/DOecU4yd77oLunSBCy6IeLni4bDDXPq+oJKT4dtvXftskS7mGmNMHqtRljE1a8LVV7sYUCT798PTTweZcqOcSktzOe4CjiExxpjwWKAsQ8aPhxdfdNcpi+y331yv13LSkcfnxRehSRM3s9Yh0tLcvY2nNMaUgAXKMmTCBHj99WIOgfSlcysnQ0N8jjnG5bvdvTvAyhYtXK9XC5TGmBKwCzdlyNtvl2BYYEaGSwrbtGkkixR3Z5zhbgGJwM03uyqnMcYUkwXKMsLXH6XYwwL37IFevcrlUImcHPfyqlcPsPLBB2NdHGNMOWNNr2XArl3QuLEbP1lsb70FEydGrEylSZs2cP31ITbYvLnMz5ZijImfQgOliNwoInViURgT2Pvvw59/QuvWJTxQOaxNgmtZDdqxdeNGqF/fpTMyxphiCKdGeQQwS0TGi0h/kXL6a1uKvfqqqzX16lXMA7z+Opx4IuzYEdFylRYpKS5QBkw80KCBq45bhx5jTDEVGihV9V6gJTAauBJYKiKPi8ixUS6bwc2O8cMPLhNPsU9Rvv3WRZJykpGnoNRU1zydmRlkg7Q0C5TGmGIL6xqlqirwp3c7CNQBPhCREVEsmwFGj4bKleGyy0pwEN/UWuW0McCX5zXolFtpabB8ubtWaYwxRRTONcqbRWQ2MAL4HmivqtcCXYFzo1y+hLZ/P4wbB2eeCYcfXsyD7NnjIkg5SzTgzz85ekC+xAOzZsWkPMaY8iWc4SF1gcGqusp/oarmiMjA6BTLgOukumlTCRKgg5t/Mju7XAfKBg1cf52gNcpu3WDUKDd7ijHGFFE4gfIzYIvvgYjUBFJU9SdVtSSaUTR6tOuHcuqpJThIhQpuBo1yHCjB1SqDBsrq1eFvf4tpeYwx5Uc41yhfBHb5Pd7lLTNRtH49fPmlm3+4YsUSHKhHD/j0Uzj66IiVrTRKTXWBMuiUW5mZLrVR0A2MMSawcAKleJ15ANfkSpgZfbzhJItFZJmI3BVkmwtEZIGIzBeRt/2WZ4vIXO820W95MxH5yTvmeyJSJZyylDVHHAFLlsB115XwQAGToJY/558P994bJDk6QHo6XHIJrFoVZANjjAksnEC5XERuEpHK3u1mYHlhO4lIReB54HQgFbhIRFILbNMSuBvoraptgb/7rd6rqp2825l+y58ARqpqC2Ar8NcwXkOZdOyxJejEA27MRO3a8MwzEStTaXXKKXDrrSGmnbSZRIwxxRROoBwO9ALWAplAD+DqMPZLA5ap6nJVPQC8C5xVYJu/Ac+r6lYAVd0Q6oBesoO+wAfeorHA2WGUpUz58ks4+2xYt66EB5o71yWJPbb8D3lVhZUrYfXqIBu0bw9JSdbz1RhTZOEkHNigqheq6uGqeoSqXlxYQPMcDazxe5zpLfPXCmglIt+LyAwR6e+3LllEMrzlvmBYD9imqgdDHBMAEbna2z9j48aNYRS39NiwAX7/3U32USLldGqtYDp0gH//O8jKKlWgc2erURpjiqzQa40ikoxr3mwLJPuWq+qwCD1/S+AkoBHwjYi0V9VtQBNVXSsizYGpIjIPCHuSKVUdBYwC6NatW5nqwXHJJXDxxRHIDzB7tuvEc+SRESlXaSYCY8e6KSiDSktz+QCzs0vYQ8oYk0jCaXp9A2gInAZ8jQtoO8PYby3Q2O9xI2+Zv0xgoqpmqeoKYAkucKKqa7375cB0oDOwGagtIpVCHLNMW73a/Y5HJIlORka5Hxbi75xzXAtrUHfcAcuWWZA0xhRJOIGyhareB+xW1bHAGbjrlIWZBbT0eqlWAS4ECs7z9BGuNomI1Mc1xS4XkToikuS3vDewwOt9Ow04z9v/CuDjMMpSJqjCaafBBRdE6GA33QR/Lbd9nQ6xfj2MH+/6MAWUILVrY0xkhRMos7z7bSLSDqgFFNoX07uOeAMwGVgIjFfV+SLysIj4erFOBjaLyAJcALxdVTcDKUCGiPziLf+XqvqGk98J3Coiy3DXLEeH80LLgh9+gEWL4IwzInAwEbj2Whg0KAIHKxtmzYIhQ2DevBAbvfQSvPJKzMpkjCn7RAsZgC0iVwEfAu2BMUB14D5VfTnqpYuQbt26aYavY0spNnQofPCB6+1avXoJD7Z4sRsrkQA9Xn1+/91do3z11RAV6b/8xc1R+fPPMS2bMaZ0EZHZqhrWtamQNUoRqQDsUNWtqvqNqjb3er+WmSBZVuzY4ZoNL7ooAkES4MEH4eSTI3CgsqNpU0hODpEcHVyHnnnzXLJ4Y4wJQ8hA6WXhuSNGZUlo777rfrtLlADd3+zZCdWRB1wfnTZtQuR8BRcos7OtRmmMCVs41yiniMhtItJYROr6blEvWYJ59VXXY7N79wgcbNs2WLo04QIlFJIcHfLeYBtPaYwJUzg5W4d499f7LVOgeeSLk5h+/dV1RHnmmQgNC5kzx90nYKBMTYV33nEpbqtVC7DBkUdC8+Yuq4MxxoSh0ECpqs1iUZBENnq0y6526aUROuDs2e4+QTLy+PNN4rxoUYiXv2SJjaU0xoQtnMw8lwdarqrjIl+cxKMKP/0EgwdHIGWdz2WXuapVvXoROmDZkeql3V+4MESgtCBpjCmCcJpe/a+aJQOnAHMAC5QRIAI//uh6vUZMw4YRGoxZ9rRo4UbFhLxOuXy5m+jzvvvctCPGGBNCOE2vN/o/FpHauJlATARkZUHlylCrVoQOuG0bjBvn8rk1blz49uVM5cowY0YhOV/r14dvvoHvv7dAaYwpVDi9XgvaDdh1ywj4/XfXt2Ty5AgeNCMDbr7ZXYdLUF27FnLiUbOmu5hpPV+NMWEI5xplOq6XK7jAmgqMj2ahEkV2Npx6KrRtG8GD+jIQdekSwYOWLfPmuQxH99zjOkkFlJYGn3ziLhJHpKuxMaa8Cuca5ZN+fx8EVqlqZpTKk1BatXJDGSIqI8O1O9apE+EDlx3z58Ojj7osR23aBNkoLQ3GjIFVq1xKH2OMCSKcQLkaWKeq+wBEpKqINFXVlVEtWTn3229QoUJeL82IyciAnj0jfNCy5eyz3TjK5OQQG/XqBf37uw2NMSaEcK5Rvg/k+D3O9paZErj3XujbFw4ejOBBt26FNWsScvykv+TkQoIkQMeO8NlnEW73NsaUR+HUKCup6gHfA1U94M0vaYpp3TqYNAn+8Q83lCFi6tRx40yysyN40LLpiScgJwfuvruQDffuhapVY1ImY0zZFM7P9EYROVNVJwKIyFnApugWq3wbN87FsqjMqRwwb1vi+f57WLGikED52GMuom7ZEuEzlhLIzobt213rwNatrsmhU6cwqsgmnx07XO9mcD3A167Nv14ETjrJ/b1wIfz5Z/71lSrB8ce7v3/7zU3N5i85Oe8Sx9y57rPyV62auw4OLlNWwYHSFSpAjx72uRbRhAkwfTqMHOnewlgJ59dhOPCWiDznPc4EAmbrMYVTdQnQTzjBdeaJqIcfduMibr45wgcue1JS4PPPXZwJGgObNoWdO90PZfv2kXliVTcNzLZt7sfTd3/CCe6zmTED3nsvb51v/SefQKNGMGKE667rLynJJUk46ijYtMkdp3LlyJS3vNi+3Y2NnTrV3RYvdidAhx0Gzz4Lzz2Xf/sqVWD/fvf3E0/A2LH519etC5s3u78feAD+97/865s0gZUr3d933AFffpl/fbt2eTOI33CD+9z9HX88fPVVsV5qIsvMdHmx9+1zH22shJNw4HfgOBGp7j3eFfVSlWPffAPLlsH990fh4K+84n6QDampLpnD8uUhTkh8Z/wzZ+YPlFlZhwa6Dh3coNelS11y3oLrn33W1RDee891ty3oxx/huONcEtrRo10zee3a7tasmQuwAP36uV8A3/rsbFdjOfJIt/7mm+Hjj93nfPLJ7kJ3p06Jl5Zv9273mpOTXZAbNsy1tScnQ58+MGQIHDjg3subboLzzsu/v/+QoLvucrOm+/M/u3r4YXcMf/7jjp58MnCN0ueFFw6tUTZr5k52Nm50Pwrnnhve605QvkkObrwRrr02Dg1AqhryBjwO1PZ7XAd4tLD9StOta9euWlpceqlqzZqqu3dH+MDr1qmC6tNPR/jAZdNPP7m3Y8KEEBvl5KjWrq161FF5G86c6XYseHvrLbd++nTVypVVDz9ctXVr1R49VPv3d/upqi5erPrEE6ovv6w6frzqF1+ozpqlumtXZF7YZ5+pXn+9akpKXtmOOy5v/erV7nWVN3v3qk6bpnr//ap9+rjP4MMP3br5893y6dNV9+2LazGL7Lbb3Gd4442q+/fHuzSl0ldfqTZooPrjj5E9LpChYcaQcOLy6aqa2xakqltFZABwbxTidrm2dasbCD90aBSaDRJ4xpBAfLOILFzohosEJAK33w5TpuTVMJo0cTWI2rXzanV16uQNyDzhBNdkFyxJQatWrikuWvr3dzdwvcKmTctbl53tasZJSa626atxtmhR9pIqHDzomlPr1XM9uVu1cu1tFSq47/itt0Lr1m7b1FR46KH4lre4Hn/cfW4jR7o2xfHjEzL1ZDDffguDBrmZ8UKmpYy2wiIp8CuQ5Pe4KjA/3EhcGm6lpUb53HPu5HH27Cgc/KGHVEVUd+yIwsHLpkaNXA0+Yezbp/raa+5FH3VUXo3zkUfc+v37VVetim8Zgzl40P1jPPmk6oABqtWrq15xhVuXk6N6zz2qEyeqbtsW12JGzfvvq9aooVq/vmsOMfrDD+5r0KaN6p9/Rv74RLhG+RbwlYi8DghwJTA25B4moL173Ul+VLLLZWW5a2A1akTh4GVTaqqrUSaMpCTXXDF0qAuRS5e6ji3HHefWf/+9q2Eee2xebfPkk91sM7GmCn/8AUcf7R736pWXe7d1azdV3KBB7rGI66Fcnp13nrsOfsstrvqU4GbNcg0nDRu6Pk9HHBHf8ogLrIVsJNIf6IfL+boDaKiq10e5bBHTrVs3zfDlQI0ztdSiMXPLLTBqlOvYGsuu5KXW2rWu7X/qVPj6a9e0Ca7ZvksX15SblBTBiVH9qLpZAKZOdc3F06a5k7uNG92H88Yb7v7kk13v3kSXleWmgbv99oSbV/bnn905XJ067msarZZoEZmtqt3C2Tbcn4/1uCB5PtAXSKTz9IhYscKCZKy1b+9GXPh6+Se8o4/O6zW7ebM7bR8xIq/H74gRbgqyLl3gttvg00/dWUZxrVnjfvDBXfdt2RKuucb9+vXrB//+d15qqssug0susSDpM3Omu27ZpYv7nBLEvHluooiaNd051SFBcsUK1zISa8HaZIFWwAPAIuA74EZcQvS4X3Ms6i3e1yh373Y9XW+7LUpP8Mknqh06qC5bFqUnMAlhzhx3PfPkk1WTktz1zaOOyutFu2BB6O7a69ervvuu6tVXq7Zo4fb/5hu3bvZs1RdeUF20qHz2yi2isN6CmTNVmzRRrVLFvXfl/H3btk31iCPcV+6Qn7KdO9116qQk1bZtI/JeUIRrlKECZQ7wNdDCb9nycA9cmm7xDpR797o+FhkZUXqC++9XrVAhCmNOTMLas8f1y3/33bxlzZq5H+0TTlB98EHVqVPzes79v80AACAASURBVFn4D6upWVN10CDVkSNV166NT/lLqeeeUz3xRNXkZNXzz1fdvr2QHTZtUj39dPe+3n13LIoYV2PHunOpXNnZquPGqR55pHsPLr1UNTMzIs8VqUB5NvAusAZ4BTgFWBHugUvTLd6BMqqys1W7dVNt3z7eJSmVLr5Y9c47412KciAnR/XTT1Vvv121a1fXwxrymkn273fjR2fOVM3Kim9ZS5GJE1UvvDCvAnTllapduqhedplqxYqqLVuq/vprIQfJzlZ99FHVX36Jennj4fffVb/+OsjKKVPc96x7d9cNNoIiEihzN4BqwMVAOrAbeBH4S7hPUBpu8QyUS5e6E+tCzxyLa9Qo9zG+9lqUnqBsu+YaN3LGRNiWLS4KRGWsU9mTna06d67L9zFokOqKFW75qFGupXDjxrztfL7+WrVhQ9WqVV1NKmy33OKSWZQTAwa4oVy5uSLWrs1LAJKT4y4t+b9xERLRQJlvY5eV52rgq6LsF+9bPAPlHXe4M8d166Jw8G3bXGaZE08s99cvjClNcnLcJdvnn1c991zVevU0t+W5RQvV777L2y6UdetUTzrJ7Xf11e4yTUi7d7tMTKD697+rHjgQkdcTTxs2uJMM3btX9fHHVatVc79rO3dG9XmjFijL6i1egfLAAZfp7Oyzo/gkn31WoFHfFJSTE5UTUpOA1q51zfkNG+YFxmOOcU2qY8e6DIJFlZWletdd7ljDh4exw/79LuUdqPbuHbFrdrH0xx+uYrx/v7p/0A8/dNfAQfWcc1x7bJQVJVCGNY6yrIvXOMoJE2DwYDf35BlnRPjgWVk2g0QYZs923c3ffx9OOSXepTFljSpcfbXLBXDjjS45d2oq9O6dl6+hefPIDPuaNAk6d3ajeLKzw8hz/+67cNVVLmH+woWlZ6q4QmzY4GY4W73azRXQvspil3OybVv4z39i9o9alHGUZeOdLaNGj3Zf+tNOi/CB9+1z+S6vuw6uLzN5H+LiqKNcjt0FCyxQmtA2bHBzHU6d6s5DR492AXDt2rzJW6pVc7NrRWM89MCB7j472/3ds2chswxdeCF07OgKVKlSXgr/UpxdY/NmN4R25Urls79/Qfv2pwGtXfqd448vtcG+dJaqHMjMhM8+cxMHR/yzf/xx98vvSwptgmrY0OU1T6hUdiYsW7fmn8Lyt9/c8ho1XPo09RKEfPpp/v2inTTk4EGXKCOszIIpKXkzALzwgpuEddw4l9amlNm6FU7tpyxZmM2kpPM48d+fwLXLXVaBk0+Od/FCskAZJWPGuOnxhg2L8IEXLoR//QsuvdSdmpmQRNzvyIIF8S6JKS3eesslvZkzxwXDqlXdFJaXXOJ+r7t2jW/FJinJTS3rM2ECHH64a+4NqUIFmDzZvYAPPohSUuni2b4dTjtuO/OXVuVjPZN+J+fAyLllZqaU0ltHL8NyclyzzSmnRDi/sSoMHw7Vq8NTT0XwwOVbwiVHN/n8+KMLMqtXu8f797sm1AcecNn0tm6FL75w8zf36FG6Wv9yctwMYied5IJ7yC4l117rqshZWS7J/KuvFrJDbOzcCQP+ksXPSw7jgyNuoP/H17mA3rZtvIsWNguUUTBtmrtscNVVET7w7Nkuz+GIEe4U04QlNdVdf9q0Kd4lMbGwapX73/vgA/e4Rg0XcHyf/7BhLkA+8ICbXjQpKX5lLUyFCu666cCBbgrOCy6AHTtC7HDcca6qfMIJrhfSvHmxKuqhduxg91MvMXCg8tPsyrz7+AoGrXwWzjyzzCW9tkAZBTVqwJAhISYMLq5u3WD+/Ci055Zv/pM4m/Jr7VrXt61lSzcZya5dbnm7dq5WWYpaIoukdm343//c+fGECdC9eyHxr0ED10FiyhTXXRdKlty+qLKzXZNay5bsu+2f7Nm4mzffhHPvblW6z0pCsEAZBWlprud2cnIED+q7yNa6danu1VYapaa6ewuU5dOGDa62deyxblq1YcNg2TK48sp4lyxyRNyMW1Onuhpljx7uZCCoihXd+BVwVdKmTeGjj6Jf0O++g7Q09l91Hfubp1Bv1mRmzKvOhRdG/6mjyX5xI+zHH12za0RNm+ba88ePj/CBE0PjxnDYYdahp7zZvNldV2zWDJ55Bi6+GJYsgZdeKjN9RIrshBPcfI3du8Pll7suC/v2FbJTs2aus8Q558Add+RNbRZpWVlwySXo+g1c0PV3zqs/jZwu3QofD1oGWKCMsOHDiezZ0/797qDNm+fN+G6KpEIFV+Po2TPeJTGR8t137vd/xAh3iWPhQnjtNbesvGvY0A07vOMONxJk2bJCdmjSxL1h117r5gA95RQ3SXck7NnjOhbu3+8SoKSnI4sXccbVjTj9dCk/jV/hpvApy7dYprBbtSrC02k99JAbRvz55xE8qDFlz44deTNt7NqlOmyY6m+/xbdM8bZmTd7f8+aFscMbb7gs7CNHluyJc3JU33lHtXFj9/v0v/9pVlYYM6GUIlgKu/zilcKuxJYscbPPDx4M77wT79KUaaruJLp+fahSJd6lMcXRr58b4rFwYRjp3RLMRx+5ltXPPw8jE9jy5a7qLQK//170HHxz5sDNN7taaqdO8MwzZPc+gaFDXU/jhQtdJba0K0oKu/JSMY67XbtcPItoPF6yxOXOGjkyggdNTOnpLp3g3LnxLokJ1/798PzzsG2be/zQQ64DiwXJQ512mmuG9qVpDFn/8QXG9evdxc7Bg11GgHCouq7Fixe7nlMZGeT0OYFrrnGfzT33lI0gWWThVj2LcwP6w/+3d+dhUlZXHse/hwYElU1BRXBBbWRRRCUoOkaNGy4RB8FlRpQMrSaOSzQxkXHUjMlIoo5rjINpRjGiRClFXBBNNCpuERVRQARRI4uCKBhFaaDP/HGrQ4NNdXX1W32run6f5+mnq9+ueutUVXeduve97znMAxYAl23mOqcAc4DZwL3pbf2Bl9LbZgGn1rr+XcD7wMz0V//64miKqddx48IMxAsvJLzjZtBGpxAsWeJ+662h+4MUtqoq97FjQ49CCD0dJXuffOI+cGAW70XV1WEKtmXL0Bts5sy6r7dmTWi0uWxZ+Hn+fPfPP//HLn70o/A6XXFFco+hKVAIbbaAMuA9YDegNfAm0GeT65QDbwCd0j9vl/7eEyhPX94RWAp09A2JclhDYmmKRDlokHvv3gm1hfz009CIWb2hpISsXet+550bui0NGhQa3KvVasPMmeO+++4h/914YxbP3/Tp7jvu6N6mTXgBalRXuz/yiHt5eXhBbr11o5tVV7tfdFH41c9+VnyvU0MSZT6nXgcCC9x9obtXAROBIZtc52zgNnf/HMDdl6W/v+vu89OXlwDLgC55jLVRZs8Op4VUVCRUcOLnP4ezz4b58xPYmdR4/314+eXYUcimqqvDIfi+feEHPwj1vB97LBShOuKIoiviEl3v3uEQ0AknwMUXh+InGav5HHxwOO44aFCo5eceDjQee2xYad+iRagMf/75/7iJe3ibuvlm+PGPQ/npZv06ZZtRG/oFDAMqa/08AvjtJteZDFwLvAC8DAyuYz8DgblAC98wopxHmJK9EdhiM/d/DjADmLHzzjsn+UHkWy6+2L1Vqw0zE43y3HPhI9qllyawM6lt+PDwSVsKx7PPuvftG/7k99rL/aGHim9kUqiqq92vvda9rMy9Z88sVsWuXeu+enW4fNpp7h06hCFpHYd//vM/w2t23nnF+3pRIFOv2STKR4GHgFZAD+Aj0lOs6d93TSfFAzfZZsAWwHjgyvpiyefU6zffuHfu7D5sWAI7W7MmzN/usktY/y6Juuoq9xYtNrwXSBzV1Rteg+nT3Xv1cp84UUca8uUvf3HfYQf3LbcMZ4dkZcmSzX7yf+MNdzP3iorifs0akijzOfW6GKhdH6N7eltti4Ap7r7W3d8H3iUct8TM2gOPAZe7+z8mzNx9afpxrgHuJIw4o5kyJRRbTqQA+nXXhSmP3/0utDeQRPXpE6b53n03diSla/16OPTQUAACwqzf7NlherDZnJxeYA49NMysDhgAI0aERate31mBXbuGmrF16N8/FJUfO7Z0XrN8PsxXgXIz62FmrYHTgCmbXGcycBiAmXUmLOJZmL7+Q8Dd7j6p9g3MrGv6uwEnAW/n8THUq7ISdt45odaQ++8fDiocd1wCO5NN1RRHVym7pvfmm+F7WVn4XxlY6+NtqbzZxtS164ZqPh075nY88dZbQ3csgEMOKa3XLW+d19x9nZmdD0wjrID9P3efbWZXE4a8U9K/O9rM5gDrgUvdfYWZnQF8F9jWzEamdznS3WcCE8ysC2H6dSbww3w9hvp88AE89RRceWVC53YNHhy+JC969gz/3CqO3nRefhmuuCI0spg+PYwgr7wydlSlqWVL+M1vNowmn38+3Ssyi8/la9bAnXeGD5v1FjRohlSZpxG++ALGj4chQ8KoMmf33w+zZoV3EJWNyauePUPnoUmT6r+u5O7118Of82OPhRm80aNDyeK2bWNHJjWOOy6sBJ81K5Rp3Rz3MAJduTI0F2gub1GqzNNE2reHCy5oZJL8/HO48MIwp6GSI3nXp49GlPn01luh0Mv++8OLL8KYMaFi2sUXK0kWmlQqnPXRqhV8/TUsX/7t64wfH4rOf/NNmLJtLkmyoZQoc/TSS+H45Jo1jdzR6NHhL/SOO5Qom0Dv3mExz9q1sSNpXubNg9NPh332CcfCfvGLMFq57DLYeuvY0Uld2rbd0G3lkktg333Dh5sa990XenuuXp3F4p9mTokyRxMnhhzXqJNsX3opLB276KLwVyp516dPaMf33nuxI2leJkwI9XRHjw4J8qqroEOH2FFJts49F7bYIqyQvemmcGhixIjQ//LhhzUboGOUOXKHRYsa0SDWPcxPffppWIapj91N4pNPwtN9wAHheIvk7qqrwikH3/9+OF6/Zs1mzyiQIrByJZx1VjjlDcLCqyeeaL5vTQ05Rpm3Va/NWc3B7UZ1UTeDu+4Kxyib619iAdp++/AljVNVFVo7LVsWEmX79rEjksbq2DG8pjfcAH/9K/z+93prqqFE2UDuoSTiqaeGBQo5qaoKR8X79Us0NsnOU0/BV1+FRQqSm9atw7mR69bFjkSSZAY/+UnsKAqPjlE20IsvwiuvhE9fOXEP79A/+lGicUn2brwxLDaR3NUkyJb6qC0lQImygSoroV07GD48xx1MmgRTp8KeeyYal2TvjjvCydaSmxUrYLvtwoI2kVKgz4MNsGpVqA1wxhk5zt2vWhXOmdxvv41a1kjT6t49dgTFbcqUcGi9vDx2JCJNQyPKBpg4MZxTlHMB9MsvD6sfxo7VnFVEn34aTmN49dXYkRSnVAp23TV83hMpBUqUDVBZCXvvHZbEN9jnn8O994aRZE47kKS0bBkazT7zTOxIis+qVaG379ChzbxRr0gtGtZkaebM0DX85ptzfIPo1Cn0E1L7rOg6dgzdFFTKruEefTRUNRo2LHYkIk1HI8osjRsXKleccUYON549OzRC7NpVJ5wViN691W4rF6kU7LhjKNggUiqUKLNQVRVKdA0dCtts08Ab/+1vofneFVfkJTbJTU1x9BIoTJWYL78MC7aHDi2tXoQimnrNQuvW4fzJBk+5um9Y3XrOOYnHJbnr3Tv04lu8WKtgszV1augicfLJsSMRaVpKlFnq1SuHG02eHCpFX3cd7LJL4jFJ7vr0Cd/nzFGizFYqFWq5HnJI7EhEmpYmUPLl738PzSr79QvdQaSg1CRKLejJ3i9/GfoTqhuclBqNKPPlgw/C6p+xYzO3D5counQJx5u1oCd75eUqMiClSYkyX/beO3SzVWGBgmQGffvCZ5/FjqQ43H576JZzwgmxIxFpepp6Tdr69fDb38LXXytJFrinn4YHHogdReFzD+cPT5oUOxKROPROnrTbbgvHJLt1g3/+59jRSAb6HJMds3Aq8BdfxI5EJA6NKJO0aFGo5zp4sJodFoEFC+DEE0OTWsmsrCwUlxIpRUqUSbrootCo77bbVAizCLRpAwsXhjK8Urd160Jp4nvuiR2JSDyafErKI4/Agw/CmDGw226xo5EsdO8Ob78dO4rC9vzz8Npr0LZt7EhE4tGIMim77gpnnQU/+UnsSKSBVq9WKbvNSaVCkhw8OHYkIvEoUSZl773hrrt0zmSRmT491KpXb8pvq64OkyTHHqumN1LalCgba+ZMOPNMWLEidiSSg379wnG4ysrYkRSel1+GpUtV21VEibIx1q+Hc8+FadO0eKdItW8Pp54K990XumPIBpMmhYYAKjIgpU6JsjHGjg3nFtxwQw79t6RQVFSEJHn//bEjKRzuYdr1qKPUQlVEiTJXS5bA6NFw5JHwL/8SOxpphEGDQtutceNiR1I4XnsNPvxQ064ioESZu8svhzVrQhFMTbsWNTMYNSr0HFWR9CCVCpWLhgyJHYlIfEqUuRozJhzY2mOP2JFIAkaMCAuWNaoMTj451HfVEQURMC+BE8gGDBjgM2bMSGZnVVXho3YLfcZoboYPh7/8JVQi3GKL2NGISD6Z2WvuPiCb6+rdvqGuugoOOyxMu0qzMmoUfPopPPdc7EjieuKJcH6piAQqYdcQb78N118f5uk05Gh2jjoK5s6FXr1iRxLX5ZdDu3ZhdC0iSpTZq64O50x26ADXXhs7GsmDsjIlSQgJ8uOPY0chUjg09ZqtysqwLPJ//gc6d44djeTJ+vVw+ulwzTWxI4mnXTsoL48dhUjhUKLMhjv87/+GY5Nnnhk7GsmjsrKwTqtUz/gZORLuvTd2FCKFRVOv2TAL/YZWrSrdd9ASMmFC7AjiWLgQxo+HvfaKHYlIYdGIMltbbQU77hg7Cmki1dWl16vywQfDd1XjEdmYEqVIHX71K9h3X1i2LHYkTSeVgv32gx49YkciUljymijNbLCZzTOzBWZ22Wauc4qZzTGz2WZ2b63tZ5nZ/PTXWbW2729mb6X3eYuZ5kIlecOGhfZbd98dO5KmsWhRaKul0aTIt+UtUZpZGXAbcCzQBzjdzPpscp1yYDRwsLv3BX6c3r4NcBVwADAQuMrMOqVvdjtwNlCe/lLvdUlcnz5w0EGhpF0JFK/ioYfCdyVKkW/L54hyILDA3Re6exUwEdi0xPLZwG3u/jmAu9dMdB0DPOXun6V/9xQw2My6Au3d/WUPtffuBk7K42OQElZRAe+8E84Kau5SKejbF/bcM3YkIoUnn4myG/BRrZ8XpbfV1hPoaWYvmNnLZja4ntt2S1/OtE+RRAwfHs4prKyMHUl+ffJJKNun0aRI3WIv5mlJmD49DDgd+L2ZdUxix2Z2jpnNMLMZy5cvT2KXUmK23hpOOy00dF61KnY0+TN5cpheVqIUqVs+E+ViYKdaP3dPb6ttETDF3de6+/vAu4TEubnbLk5fzrRPANz9Dncf4O4DunTp0qgHIqWrogJWr4aJE2NHkj+9e8MFF8Dee8eORKQw5TNRvgqUm1kPM2sNnAZM2eQ6kwmjScysM2EqdiEwDTjazDqlF/EcDUxz96XAF2Z2YHq165nAw3l8DFLivvOdkECa8/Trd78Lt9yiWhoim5O3ROnu64DzCUlvLnC/u882s6vN7MT01aYBK8xsDvAMcKm7r3D3z4BfEpLtq8DV6W0A5wGVwALgPWBqvh6DiFkYVS5fDitWxI4mebNmwfz5saMQKWxq3CxSjzVroFWr5tmr+4QTQgWi99/XiFJKS0MaN6vWq0g9alqPVlWFZNKqVdx4knT77UqSIvVphp+RRZL33nvQvTs88EDsSJK1007hGKWIbJ4SpUgWevSAoUNht91iR5KcX/96QyF0Edk8JUqRLLRoEVqSHnhg7EiS8dVXcPXV8PTTsSMRKXxKlCINMH8+PPlk7Cgab+pU+PprFRkQyYYW84g0wCWXwOuvw4cfQssi/u9JpaBzZzjkkNiRiBQ+jShFGmDUKFiyBJ54InYkufvmG3j0UTjppOJO9iJNRYlSpAGOPx623764K/U89RR8+WXouSki9VOiFGmAVq1g5MgwIlu6NHY0uUmloGNHOPzw2JGIFAclSpEGGjUK1q+H8eNjR9JwVVXw8MNw4onQunXsaESKgxKlSAOVl4eT9MeNC+2piskzz8DKlVrtKtIQSpQiOaiogAULQsPjYtKqFRxzDBx9dOxIRIqHEqVIDk4+GTp0KL5FPd/7Xlix26ZN7EhEiocSpUgOttwSzj03LIopFkuXwmef1X89EdmYzqISydFvfhM7goa55hq4++7QW1MLeUSyp0Qp0gjuofnxPvvEjqR+FRUwcKCSpEhDaepVpBEmTID+/UNZu0K3zz4wYkTsKESKjxKlSCOccEJofrzHHrEjyWzSJPjzn2NHIVKcNPUq0ggdO8IPfxg7iszc4ac/hb594YgjYkcjUnw0ohRppLVr4Xe/g8cfjx1J3Wq6najIgEhuNKIUaaSWLeGmm2CHHeC442JH822pFJSVwZAhsSMRKU4aUYo0klmo//r88zBvXuxoNuYejk8efjhsu23saESKkxKlSALOOiuM2saNix3Jxt5+G+bP17SrSGMoUYokYIcd4PvfDx1F1q6NHc0GqVQY8Z50UuxIRIqXEqVIQioqYNmy0KuyUKRS8E//FBK5iORGiVIkIcccA926FU6h9HnzwtSrpl1FGkeJUiQhLVvCyJGhO8dHH8WOBj7+GHr1gqFDY0ciUtyUKEUS9G//BtXVcNddsSOBQw+FuXNhp51iRyJS3JQoRRK0225w2WUwYEDcOL76Cqqq4sYg0lwoUYokbMwYOPbYuDGMHQvbbQcrVsSNQ6Q5UKIUyYPFi+HBB+Pd/wEHwAUXqMiASBJUwk4kD669Nozqli2D9u2b/v4PPjh8iUjjaUQpkgeXXgqzZ8dJkq+8EppJi0gyNKIUyYPu3ePd92WXhZHs7NnxYhBpTjSiFMmTDz8MpeP++temu89ly+C551RkQCRJGlGK5Mk228Cf/gRdusDAgU1zn5Mnh/M4lShFkqMRpUietGsHp5wCEyfCl182zX2mUrD77tCvX9Pcn0gpUKIUyaOKipAk778///f1+efw9NMwbFjoGCIiyVCiFMmjQYOgd++mKZQ+ZQqsW6dpV5GkKVGK5JFZGFW+9FL+V6GmUrDzzvHL54k0N0qUInk2YgS0agXjxuXvPr74Ap58MnQK0bSrSLKUKEXyrEsXGDIE7r4b1qzJz3288w5stZWmXUXyIa+J0swGm9k8M1tgZpfV8fuRZrbczGamvyrS2w+vtW2mmX1jZielf3eXmb1f63f98/kYRJJQUREKlE+Zkp/9DxwY+k8edFB+9i9SyvJ2HqWZlQG3AUcBi4BXzWyKu8/Z5Kp/dPfza29w92eA/un9bAMsAJ6sdZVL3X1SvmIXSdqRR8Ktt8JhhyW/7+rqMN3aqlXy+xaR/I4oBwIL3H2hu1cBE4EhOexnGDDV3VcnGp1IEyorg/PPD9OwSZs8GfbYAxYuTH7fIpLfRNkN+KjWz4vS2zZ1spnNMrNJZlZXL/bTgPs22fbf6dvcaGZb1HXnZnaOmc0wsxnLly/P6QGIJG3CBBg/Ptl9duoE++8fVryKSPJiL+Z5BNjV3fsBTwEbvYWYWVdgb2Barc2jgV7Ad4BtgJ/XtWN3v8PdB7j7gC75+BgvkoM//CH5RHn44aGgQUsVpBTJi3wmysVA7RFi9/S2f3D3Fe5esw6wEth/k32cAjzk7mtr3WapB2uAOwlTvCJF4d574c9/Tm5/H3wAS5cmtz8R+bZ8JspXgXIz62FmrQlTqBut+UuPGGucCMzdZB+ns8m0a81tzMyAk4C3E45bJG+22SYsvFm/Ppn9/dd/Qd++oSKPiORH3hKlu68DzidMm84F7nf32WZ2tZmdmL7ahWY228zeBC4ERtbc3sx2JYxIn91k1xPM7C3gLaAz8Kt8PQaRfJg8Gbp1Cy2xGmPtWnj4YTj+eE27iuRTXv+93P1x4PFNtl1Z6/JowjHHum77AXUs/nH37yUbpUjT2nNP+OSTUIDgpz/NfT/PPBMKoavIgEh+xV7MI1JyevcOhQEqK8E99/2kUqEazzHHJBebiHybEqVIBBUVMG8evPBCbrdfvz5M4R5/PLRtm2xsIrIxJUqRCIYPD42dc22/NX16OMapaVeR/FOiFIlg663h9NPhgQdg1aqG3z6VgjZt4Ljjko9NRDamRCkSSUUFrF4NEyc27HbV1fDggzB4cEi4IpJfSpQikQwYAP36NXz69d13Ne0q0pSUKEUiMYNRo2DGjNBPMlu9esHy5UqUIk1FiVIkojPPhDffDMmvITp00GpXkaaiRCkSUceOYfo1W2+8Ec7BfFuFG0WajBKlSGSrVsEZZ4QVsPVZuRKqqmCHHfIfl4gESpQikbVrB3PnhrJ29Tn88HBMs3Pn/MclIoFKKYtE1qJFSH5mma+3ciW0bg1bbtk0cYlIoBGlSAEwC3VfFy3a/HVuuQW23x6++KLp4hIRJUqRgnHeeTBw4OZ7S06aBP37Q/v2TRuXSKlTohQpEIMHw9KlMHXqt383fz689ZbOnRSJQYlSpEAcd1xYzVpXpZ5UKnwfOrRpYxIRJUqRgtGqFZx1Fjz2GCxZsvHvUqkwLbvzznFiEyllSpQiBWTUqNBrcvz4Dds+/DCsitW0q0gcSpQiBaS8HA49FMaNC6tgYcO0qxKlSBxKlCIFpqIC3nsPnn02/JxKhdWuu+8eNy6RUqVEKVJgTj45FD2vrAxdQl56SaNJkZhUmUekwLRtC//6rzBtGnTqFEaXqsYjEo9GlCIF6JprYN48aNkSevQIFXlEJA4lSpEC1KEDfPYZnHRS6FcpIvEoUYoUqJkz4eGHN6x+FZE4dIxSpEAdeWSYfu3ZM3YkIqVNI0qRAmWmJClSCJQoRUREMlCiFBERqU5CPwAABZZJREFUyUCJUkREJAMlShERkQyUKEVERDJQohQREclAiVJERCQDJUoREZEMlChFREQyUKIUERHJQIlSREQkAyVKERGRDJQoRUREMlCiFBERyUCJUkREJAPzEmifbmbLgQ8T2FVn4NME9lNq9LzlTs9d7vTc5a4Unrtd3L1LNlcsiUSZFDOb4e4DYsdRbPS85U7PXe703OVOz93GNPUqIiKSgRKliIhIBkqUDXNH7ACKlJ633Om5y52eu9zpuatFxyhFREQy0IhSREQkAyVKERGRDJQos2Bmg81snpktMLPLYsdTLMxsJzN7xszmmNlsM7sodkzFxszKzOwNM3s0dizFxMw6mtkkM3vHzOaa2aDYMRULM7s4/f/6tpndZ2ZtYscUmxJlPcysDLgNOBboA5xuZn3iRlU01gE/cfc+wIHAv+u5a7CLgLmxgyhCNwNPuHsvYB/0HGbFzLoBFwID3H0voAw4LW5U8SlR1m8gsMDdF7p7FTARGBI5pqLg7kvd/fX05b8T3qy6xY2qeJhZd+B4oDJ2LMXEzDoA3wXGAbh7lbuvjBtVUWkJtDWzlsCWwJLI8USnRFm/bsBHtX5ehN7sG8zMdgX2BV6JG0lRuQn4GVAdO5Ai0wNYDtyZnrauNLOtYgdVDNx9MXA98DdgKbDK3Z+MG1V8SpSSd2a2NZACfuzuX8SOpxiY2QnAMnd/LXYsRaglsB9wu7vvC3wFaG1BFsysE2HGrAewI7CVmZ0RN6r4lCjrtxjYqdbP3dPbJAtm1oqQJCe4+4Ox4ykiBwMnmtkHhOn+75nZPXFDKhqLgEXuXjN7MYmQOKV+RwLvu/tyd18LPAgcFDmm6JQo6/cqUG5mPcysNeHA9pTIMRUFMzPCcaK57n5D7HiKibuPdvfu7r4r4W/uaXcv+U/22XD3j4GPzGzP9KYjgDkRQyomfwMONLMt0/+/R6CFULSMHUChc/d1ZnY+MI2wAuz/3H125LCKxcHACOAtM5uZ3vYf7v54xJikNFwATEh/uF0I/CByPEXB3V8xs0nA64RV62+gcnYqYSciIpKJpl5FREQyUKIUERHJQIlSREQkAyVKERGRDJQoRUREMlCiFInMzLY1s5npr4/NbHGtn1snfF8j010h3jKz183s4oT330IddqS50ekhIgXEzH4BfOnu12+y3Qj/rznXfU2XxfsFcIK7f5xun3SGuydWdD1dSPtTd++Y1D5FYtOIUqRAmdke6V6eE4DZQFczO9bMXkqPBv9YU+zbzL5jZs+a2WtmNtXMtq9jl/8BXJKuXIO7f1OTJM1sPzN7xcxmmVkq3YEDM5tuZv3Tl3cwswXpyxXpfo/TzGy+mY1J38evgXbp0fDd+Xx+RJqKEqVIYesF3Jju6bmWUNz7CHffD5gFXGRmWxD6L57s7vsD9wC/rGNffYHNFVm/h5BE+wHzgCuyiG0fYDjQDzjDzHZMx/d3d+/v7mdm+yBFCplK2IkUtvfcfUb68kGE5uEvhplYWgPTgd6EJPin9PYyQmHwrJjZtkAbd38hvWk88Icsbvqnmm4wZvYOsDOwLNv7FSkWSpQihe2rWpcNeMLdR9S+gpntC8xy90Pq2dccYH/guQbc/zo2zDy12eR3a2pdXo/eT6SZ0tSrSPF4ETjUzHYDMLOtzKyckAC7mdnA9PbWZta3jtuPAa6vOX5pZluY2Sh3XwF8bWY17ZRGAM+mL39ASK4Aw+oL0N3XpfetpCnNhhKlSJFw90+AUcAfzexNQuLs6e5rCEnsBjObRej4cEAdt58CjAWeNrPZhOOVW6d/PQK4MX37PsCv0tuvIxwHfR3olGWo44BZWswjzYVODxEREclAI0oREZEMlChFREQyUKIUERHJQIlSREQkAyVKERGRDJQoRUREMlCiFBERyeD/ASBboezstNKaAAAAAElFTkSuQmCC\n", | |
"text/plain": [ | |
"<Figure size 504x504 with 1 Axes>" | |
] | |
}, | |
"metadata": { | |
"needs_background": "light" | |
}, | |
"output_type": "display_data" | |
} | |
], | |
"source": [ | |
"f_train_accuracies = []\n", | |
"f_val_accuracies = []\n", | |
"max_trees = 20\n", | |
"for i in range(1, max_trees + 1, 2):\n", | |
" new_forest = RandomForest(trainData, trainLabels, int(0.7 * trainLabels.size), i, ['maxDepth', 4], True)\n", | |
" f_train_accuracies.append(new_forest.score(trainData, trainLabels))\n", | |
" f_val_accuracies.append(new_forest.score(valData, valLabels))\n", | |
"\n", | |
"plt.figure(figsize=[7,7])\n", | |
"plt.plot(np.arange(len(f_train_accuracies)), f_train_accuracies, 'r--', label='f_train_accuracies')\n", | |
"plt.plot(np.arange(len(f_train_accuracies)), f_val_accuracies, 'b-.', label='f_val_accuracies')\n", | |
"plt.title('Training/Validation Accuracy versus Tree Count')\n", | |
"plt.ylabel('Accuracy')\n", | |
"plt.xlabel('Tree Count')\n", | |
"plt.legend()\n", | |
"plt.show()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.6.6" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
survived | pclass | sex | age | sibsp | parch | ticket | fare | cabin | embarked | |
---|---|---|---|---|---|---|---|---|---|---|
0.0 | 3.0 | male | 0.0 | 0.0 | SOTON/OQ 392086 | 8.05 | S | |||
0.0 | 1.0 | male | 22.0 | 0.0 | 0.0 | PC 17760 | 135.6333 | C | ||
0.0 | 2.0 | male | 23.0 | 0.0 | 0.0 | SC/PARIS 2133 | 15.0458 | C | ||
0.0 | 2.0 | male | 42.0 | 0.0 | 0.0 | 211535 | 13.0 | S | ||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | 7534 | 9.8458 | S | ||
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 350410 | 7.8542 | S | ||
1.0 | 2.0 | female | 36.0 | 1.0 | 0.0 | 226875 | 26.0 | S | ||
0.0 | 3.0 | male | 26.0 | 0.0 | 0.0 | 341826 | 8.05 | S | ||
1.0 | 3.0 | male | 30.0 | 0.0 | 0.0 | 345774 | 9.5 | S | ||
1.0 | 1.0 | female | 64.0 | 0.0 | 2.0 | PC 17756 | 83.1583 | E45 | C | |
1.0 | 2.0 | female | 28.0 | 0.0 | 0.0 | 240929 | 12.65 | S | ||
1.0 | 2.0 | male | 30.0 | 0.0 | 0.0 | C.A. 34644 | 12.7375 | C | ||
1.0 | 2.0 | female | 30.0 | 1.0 | 0.0 | SC/PARIS 2148 | 13.8583 | C | ||
1.0 | 3.0 | male | 9.0 | 1.0 | 1.0 | C.A. 37671 | 15.9 | S | ||
1.0 | 1.0 | female | 27.0 | 1.0 | 1.0 | PC 17558 | 247.5208 | B58 B60 | C | |
0.0 | 1.0 | male | 65.0 | 0.0 | 1.0 | 113509 | 61.9792 | B30 | C | |
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | A/4. 39886 | 7.8 | S | ||
0.0 | 1.0 | male | 46.0 | 0.0 | 0.0 | 694 | 26.0 | S | ||
0.0 | 1.0 | male | 54.0 | 0.0 | 0.0 | 17463 | 51.8625 | E46 | S | |
0.0 | 3.0 | male | 24.0 | 0.0 | 0.0 | SOTON/O.Q. 3101311 | 7.05 | S | ||
0.0 | 2.0 | male | 23.0 | 0.0 | 0.0 | 29751 | 13.0 | S | ||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | 6563 | 9.225 | S | ||
1.0 | 1.0 | female | 30.0 | 0.0 | 0.0 | PC 17761 | 106.425 | C | ||
1.0 | 2.0 | female | 14.0 | 1.0 | 0.0 | 237736 | 30.0708 | C | ||
0.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | STON/O 2. 3101291 | 7.925 | S | ||
1.0 | 1.0 | female | 52.0 | 1.0 | 0.0 | 36947 | 78.2667 | D20 | C | |
1.0 | 2.0 | male | 3.0 | 1.0 | 1.0 | 230080 | 26.0 | F2 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | Fa 265302 | 7.3125 | S | |||
1.0 | 1.0 | male | 36.0 | 0.0 | 0.0 | PC 17474 | 26.3875 | E25 | S | |
1.0 | 3.0 | female | 24.0 | 0.0 | 0.0 | 382653 | 7.75 | Q | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349218 | 7.8958 | S | |||
0.0 | 2.0 | male | 29.0 | 1.0 | 0.0 | 2003 | 26.0 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | SOTON/O.Q. 3101314 | 7.25 | S | |||
0.0 | 3.0 | female | 24.0 | 0.0 | 0.0 | 349236 | 8.85 | S | ||
1.0 | 3.0 | male | 0.0 | 0.0 | 3470 | 7.8875 | S | |||
1.0 | 2.0 | female | 0.9167 | 1.0 | 2.0 | C.A. 34651 | 27.75 | S | ||
0.0 | 3.0 | female | 20.0 | 0.0 | 0.0 | 347471 | 7.8542 | S | ||
1.0 | 1.0 | female | 31.0 | 0.0 | 2.0 | 36928 | 164.8667 | C7 | S | |
0.0 | 3.0 | male | 60.5 | 0.0 | 0.0 | 3701 | S | |||
0.0 | 2.0 | male | 18.0 | 0.0 | 0.0 | 29108 | 11.5 | S | ||
0.0 | 3.0 | male | 15.0 | 1.0 | 1.0 | 2695 | 7.2292 | C | ||
1.0 | 1.0 | male | 32.0 | 0.0 | 0.0 | 13214 | 30.5 | B50 | C | |
0.0 | 3.0 | female | 0.0 | 0.0 | 65305 | 8.1125 | S | |||
0.0 | 2.0 | male | 21.0 | 0.0 | 0.0 | S.O.C. 14879 | 73.5 | S | ||
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | STON/O 2. 3101275 | 7.125 | S | ||
1.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 330920 | 7.8208 | Q | ||
0.0 | 1.0 | male | 38.0 | 0.0 | 0.0 | 19972 | 0.0 | S | ||
1.0 | 2.0 | male | 34.0 | 0.0 | 0.0 | 248698 | 13.0 | D56 | S | |
1.0 | 1.0 | female | 19.0 | 0.0 | 0.0 | 112053 | 30.0 | B42 | S | |
0.0 | 3.0 | male | 4.0 | 4.0 | 1.0 | 382652 | 29.125 | Q | ||
1.0 | 2.0 | male | 3.0 | 1.0 | 1.0 | 29106 | 18.75 | S | ||
0.0 | 2.0 | male | 0.0 | 0.0 | 239853 | 0.0 | S | |||
1.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 345501 | 7.775 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 330931 | 7.8792 | Q | |||
0.0 | 1.0 | male | 71.0 | 0.0 | 0.0 | PC 17609 | 49.5042 | C | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 14313 | 7.75 | Q | |||
1.0 | 1.0 | female | 23.0 | 1.0 | 0.0 | 21228 | 82.2667 | B45 | S | |
1.0 | 1.0 | female | 40.0 | 1.0 | 1.0 | 16966 | 134.5 | E34 | C | |
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | SOTON/O.Q. 3101307 | 7.05 | S | ||
0.0 | 1.0 | male | 27.0 | 1.0 | 0.0 | 13508 | 136.7792 | C89 | C | |
0.0 | 3.0 | male | 1.0 | 0.0 | 371110 | 24.15 | Q | |||
1.0 | 3.0 | female | 0.0 | 2.0 | 2661 | 15.2458 | C | |||
1.0 | 1.0 | female | 28.0 | 3.0 | 2.0 | 19950 | 263.0 | C23 C25 C27 | S | |
0.0 | 3.0 | male | 14.0 | 5.0 | 2.0 | CA 2144 | 46.9 | S | ||
1.0 | 2.0 | male | 62.0 | 0.0 | 0.0 | S.W./PP 752 | 10.5 | S | ||
0.0 | 3.0 | male | 1.0 | 0.0 | 2621 | 6.4375 | C | |||
1.0 | 1.0 | male | 4.0 | 0.0 | 2.0 | 33638 | 81.8583 | A34 | S | |
0.0 | 3.0 | male | 48.0 | 0.0 | 0.0 | 350047 | 7.8542 | S | ||
1.0 | 2.0 | female | 23.0 | 0.0 | 0.0 | SC/AH Basle 541 | 13.7917 | D | C | |
0.0 | 3.0 | male | 21.0 | 2.0 | 0.0 | A/4 48871 | 24.15 | S | ||
1.0 | 2.0 | female | 24.0 | 2.0 | 1.0 | 243847 | 27.0 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 2676 | 7.225 | C | |||
0.0 | 2.0 | male | 31.0 | 1.0 | 1.0 | C.A. 31921 | 26.25 | S | ||
0.0 | 1.0 | female | 25.0 | 1.0 | 2.0 | 113781 | 151.55 | C22 C26 | S | |
1.0 | 3.0 | female | 18.0 | 0.0 | 1.0 | 392091 | 9.35 | S | ||
0.0 | 1.0 | male | 56.0 | 0.0 | 0.0 | 113792 | 26.55 | S | ||
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | A/5. 13032 | 7.7333 | Q | ||
1.0 | 2.0 | male | 24.0 | 0.0 | 0.0 | 28034 | 10.5 | S | ||
1.0 | 2.0 | female | 24.0 | 1.0 | 0.0 | SC/PARIS 2167 | 27.7208 | C | ||
0.0 | 1.0 | male | 57.0 | 1.0 | 1.0 | 36928 | 164.8667 | S | ||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | A/5. 2151 | 8.05 | S | ||
0.0 | 3.0 | female | 1.0 | 0.0 | 2660 | 14.4542 | C | |||
0.0 | 3.0 | male | 0.0 | 0.0 | SOTON/OQ 3101316 | 8.05 | S | |||
0.0 | 3.0 | male | 0.0 | 0.0 | 367655 | 7.7292 | Q | |||
1.0 | 2.0 | female | 18.0 | 0.0 | 2.0 | 250652 | 13.0 | S | ||
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | 350052 | 7.7958 | S | ||
1.0 | 3.0 | female | 33.0 | 1.0 | 2.0 | C.A. 2315 | 20.575 | S | ||
0.0 | 3.0 | male | 8.0 | 2.0 | CA. 2343 | 69.55 | S | |||
1.0 | 3.0 | female | 31.0 | 0.0 | 0.0 | 349244 | 8.6833 | S | ||
1.0 | 1.0 | female | 33.0 | 1.0 | 0.0 | 19928 | 90.0 | C78 | Q | |
0.0 | 3.0 | male | 13.0 | 4.0 | 2.0 | 347077 | 31.3875 | S | ||
1.0 | 1.0 | male | 35.0 | 0.0 | 0.0 | PC 17755 | 512.3292 | B101 | C | |
0.0 | 3.0 | female | 31.0 | 0.0 | 0.0 | 350407 | 7.8542 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | A/S 2816 | 8.05 | S | |||
1.0 | 3.0 | female | 24.0 | 0.0 | 3.0 | 2666 | 19.2583 | C | ||
0.0 | 3.0 | male | 16.0 | 2.0 | 0.0 | 345764 | 18.0 | S | ||
0.0 | 1.0 | male | 60.0 | 0.0 | 0.0 | 113800 | 26.55 | S | ||
1.0 | 1.0 | female | 76.0 | 1.0 | 0.0 | 19877 | 78.85 | C46 | S | |
0.0 | 3.0 | male | 1.0 | 0.0 | 367227 | 7.75 | Q | |||
0.0 | 3.0 | male | 26.0 | 2.0 | 0.0 | 315151 | 8.6625 | S | ||
1.0 | 1.0 | male | 53.0 | 1.0 | 1.0 | 33638 | 81.8583 | A34 | S | |
0.0 | 1.0 | male | 42.0 | 0.0 | 0.0 | 110489 | 26.55 | D22 | S | |
1.0 | 3.0 | female | 47.0 | 1.0 | 0.0 | 363272 | 7.0 | S | ||
0.0 | 2.0 | male | 29.0 | 1.0 | 0.0 | SC/PARIS 2167 | 27.7208 | C | ||
0.0 | 3.0 | female | 11.0 | 4.0 | 2.0 | 347082 | 31.275 | S | ||
0.0 | 3.0 | female | 22.0 | 2.0 | 0.0 | 315152 | 8.6625 | S | ||
1.0 | 1.0 | male | 0.0 | 0.0 | 111427 | 26.55 | S | |||
0.0 | 3.0 | male | 0.0 | 0.0 | 345498 | 7.775 | S | |||
1.0 | 1.0 | female | 40.0 | 0.0 | 0.0 | PC 17582 | 153.4625 | C125 | S | |
1.0 | 3.0 | female | 0.0 | 0.0 | 383123 | 7.75 | Q | |||
0.0 | 3.0 | male | 19.0 | 0.0 | 0.0 | 349205 | 7.8958 | S | ||
0.0 | 1.0 | male | 45.0 | 0.0 | 0.0 | 113784 | 35.5 | T | S | |
1.0 | 3.0 | female | 22.0 | 0.0 | 0.0 | C 7077 | 7.25 | S | ||
0.0 | 3.0 | female | 36.0 | 0.0 | 2.0 | 350405 | 12.1833 | S | ||
0.0 | 2.0 | male | 28.0 | 0.0 | 0.0 | C.A./SOTON 34068 | 10.5 | S | ||
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | STON/O 2. 3101294 | 7.925 | S | ||
1.0 | 3.0 | female | 21.0 | 0.0 | 0.0 | 343120 | 7.65 | S | ||
1.0 | 1.0 | female | 47.0 | 1.0 | 0.0 | W.E.P. 5734 | 61.175 | E31 | S | |
0.0 | 3.0 | male | 33.0 | 0.0 | 0.0 | 345780 | 9.5 | S | ||
1.0 | 3.0 | male | 32.0 | 0.0 | 0.0 | 1601 | 56.4958 | S | ||
1.0 | 3.0 | male | 0.8333 | 0.0 | 1.0 | 392091 | 9.35 | S | ||
1.0 | 1.0 | male | 0.0 | 0.0 | 16988 | 30.0 | D45 | S | ||
1.0 | 2.0 | female | 35.0 | 0.0 | 0.0 | F.C.C. 13528 | 21.0 | S | ||
0.0 | 1.0 | male | 64.0 | 1.0 | 0.0 | 110813 | 75.25 | D37 | C | |
0.0 | 2.0 | male | 36.5 | 0.0 | 2.0 | 230080 | 26.0 | F2 | S | |
0.0 | 1.0 | male | 0.0 | 0.0 | 113056 | 26.0 | A19 | S | ||
0.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | SOTON/O.Q. 3101312 | 7.05 | S | ||
0.0 | 2.0 | male | 32.0 | 2.0 | 0.0 | S.O.C. 14879 | 73.5 | S | ||
0.0 | 3.0 | male | 1.0 | 4.0 | 1.0 | 3101295 | 39.6875 | S | ||
0.0 | 2.0 | male | 23.0 | 0.0 | 0.0 | 28425 | 13.0 | S | ||
1.0 | 1.0 | female | 43.0 | 1.0 | 0.0 | 11778 | 55.4417 | C116 | C | |
0.0 | 3.0 | male | 29.0 | 0.0 | 0.0 | 347067 | 7.775 | S | ||
0.0 | 3.0 | female | 18.0 | 0.0 | 0.0 | 347087 | 7.775 | S | ||
1.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 350053 | 7.7958 | S | ||
1.0 | 1.0 | male | 45.0 | 1.0 | 1.0 | 16966 | 134.5 | E34 | C | |
0.0 | 3.0 | male | 0.0 | 0.0 | 12460 | 7.75 | Q | |||
0.0 | 3.0 | male | 1.0 | 2.0 | W./C. 6607 | 23.45 | S | |||
1.0 | 3.0 | male | 24.0 | 0.0 | 0.0 | C 17369 | 7.1417 | S | ||
1.0 | 3.0 | female | 26.0 | 1.0 | 1.0 | 315153 | 22.025 | S | ||
1.0 | 2.0 | female | 24.0 | 1.0 | 2.0 | 220845 | 65.0 | S | ||
0.0 | 3.0 | female | 47.0 | 1.0 | 0.0 | A/5. 3337 | 14.5 | S | ||
1.0 | 1.0 | female | 51.0 | 0.0 | 1.0 | PC 17592 | 39.4 | D28 | S | |
1.0 | 1.0 | female | 19.0 | 1.0 | 0.0 | 11967 | 91.0792 | B49 | C | |
0.0 | 3.0 | male | 2.0 | 0.0 | 2662 | 21.6792 | C | |||
0.0 | 3.0 | male | 0.0 | 0.0 | A4. 54510 | 8.05 | S | |||
0.0 | 3.0 | male | 55.5 | 0.0 | 0.0 | A.5. 11206 | 8.05 | S | ||
0.0 | 3.0 | male | 27.0 | 1.0 | 0.0 | 2659 | 14.4542 | C | ||
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | PP 4348 | 9.35 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 371110 | 24.15 | Q | |||
0.0 | 1.0 | male | 46.0 | 1.0 | 0.0 | W.E.P. 5734 | 61.175 | E31 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 349215 | 7.8958 | S | |||
0.0 | 3.0 | male | 23.0 | 0.0 | 0.0 | 347468 | 7.8542 | S | ||
1.0 | 2.0 | female | 31.0 | 0.0 | 0.0 | CA 31352 | 21.0 | S | ||
0.0 | 2.0 | male | 34.0 | 1.0 | 0.0 | 244367 | 26.0 | S | ||
1.0 | 1.0 | female | 54.0 | 1.0 | 1.0 | 33638 | 81.8583 | A34 | S | |
0.0 | 3.0 | male | 45.0 | 0.0 | 0.0 | 347061 | 6.975 | S | ||
0.0 | 2.0 | male | 36.0 | 1.0 | 2.0 | C.A. 34651 | 27.75 | S | ||
0.0 | 3.0 | female | 28.0 | 1.0 | 1.0 | 347080 | 14.4 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 383121 | 7.75 | F38 | Q | ||
0.0 | 3.0 | male | 1.0 | 0.0 | 2689 | 14.4583 | C | |||
0.0 | 3.0 | male | 65.0 | 0.0 | 0.0 | 336439 | 7.75 | Q | ||
1.0 | 1.0 | female | 44.0 | 0.0 | 0.0 | PC 17610 | 27.7208 | B4 | C | |
1.0 | 2.0 | female | 34.0 | 0.0 | 0.0 | C.A. 34260 | 10.5 | F33 | S | |
1.0 | 1.0 | female | 0.0 | 0.0 | 17421 | 110.8833 | C | |||
0.0 | 3.0 | male | 0.0 | 0.0 | 364851 | 7.75 | Q | |||
0.0 | 1.0 | male | 37.0 | 1.0 | 0.0 | 113803 | 53.1 | C123 | S | |
0.0 | 3.0 | male | 18.0 | 0.0 | 0.0 | 350036 | 7.7958 | S | ||
0.0 | 3.0 | male | 32.0 | 0.0 | 0.0 | 349242 | 7.8958 | S | ||
1.0 | 1.0 | male | 27.0 | 0.0 | 0.0 | PC 17572 | 76.7292 | D49 | C | |
0.0 | 2.0 | female | 38.0 | 0.0 | 0.0 | 237671 | 13.0 | S | ||
1.0 | 3.0 | female | 22.0 | 0.0 | 0.0 | 370373 | 7.75 | Q | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349234 | 7.8958 | S | |||
0.0 | 1.0 | male | 61.0 | 0.0 | 0.0 | 111240 | 33.5 | B19 | S | |
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | 350416 | 7.8542 | S | ||
0.0 | 3.0 | female | 10.0 | 5.0 | 2.0 | CA 2144 | 46.9 | S | ||
0.0 | 3.0 | female | 2.0 | 3.0 | 2.0 | 347088 | 27.9 | S | ||
1.0 | 2.0 | male | 0.6667 | 1.0 | 1.0 | 250649 | 14.5 | S | ||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | 350050 | 7.8542 | S | ||
0.0 | 3.0 | female | 39.0 | 1.0 | 5.0 | 347082 | 31.275 | S | ||
0.0 | 3.0 | male | 29.0 | 0.0 | 0.0 | 347467 | 7.8542 | S | ||
1.0 | 1.0 | female | 30.0 | 0.0 | 0.0 | 110152 | 86.5 | B77 | S | |
1.0 | 1.0 | female | 55.0 | 0.0 | 0.0 | 112377 | 27.7208 | C | ||
0.0 | 1.0 | male | 42.0 | 0.0 | 0.0 | 113038 | 42.5 | B11 | S | |
1.0 | 3.0 | female | 22.0 | 1.0 | 0.0 | 347072 | 13.9 | S | ||
1.0 | 2.0 | female | 0.0 | 0.0 | 226593 | 12.35 | E101 | Q | ||
1.0 | 1.0 | male | 34.0 | 0.0 | 0.0 | 113794 | 26.55 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349217 | 7.8958 | S | |||
1.0 | 1.0 | female | 55.0 | 0.0 | 0.0 | PC 17760 | 135.6333 | C32 | C | |
0.0 | 3.0 | male | 0.0 | 0.0 | 349201 | 7.8958 | S | |||
1.0 | 3.0 | male | 19.0 | 0.0 | 0.0 | A/5. 10482 | 8.05 | S | ||
0.0 | 3.0 | female | 0.0 | 0.0 | SOTON/O.Q. 392087 | 8.05 | S | |||
1.0 | 3.0 | female | 0.75 | 2.0 | 1.0 | 2666 | 19.2583 | C | ||
1.0 | 2.0 | female | 28.0 | 1.0 | 0.0 | 2003 | 26.0 | S | ||
0.0 | 3.0 | female | 38.0 | 4.0 | 2.0 | 347091 | 7.775 | S | ||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | 345769 | 9.5 | S | ||
1.0 | 1.0 | female | 47.0 | 1.0 | 1.0 | 11751 | 52.5542 | D35 | S | |
0.0 | 3.0 | female | 8.0 | 2.0 | CA. 2343 | 69.55 | S | |||
0.0 | 3.0 | male | 17.0 | 1.0 | 1.0 | 2690 | 7.2292 | C | ||
1.0 | 1.0 | female | 18.0 | 2.0 | 2.0 | PC 17608 | 262.375 | B57 B59 B63 B66 | C | |
0.0 | 3.0 | male | 0.0 | 0.0 | 36209 | 7.725 | Q | |||
0.0 | 1.0 | male | 28.0 | 0.0 | 0.0 | 113059 | 47.1 | S | ||
1.0 | 1.0 | female | 38.0 | 1.0 | 0.0 | PC 17599 | 71.2833 | C85 | C | |
0.0 | 3.0 | female | 26.0 | 1.0 | 0.0 | A/5. 3336 | 16.1 | S | ||
0.0 | 3.0 | male | 24.0 | 0.0 | 0.0 | 371109 | 7.25 | Q | ||
0.0 | 1.0 | female | 63.0 | 1.0 | 0.0 | PC 17483 | 221.7792 | C55 C57 | S | |
1.0 | 1.0 | female | 1.0 | 0.0 | PC 17569 | 146.5208 | B78 | C | ||
0.0 | 1.0 | male | 57.0 | 1.0 | 0.0 | PC 17569 | 146.5208 | B78 | C | |
0.0 | 3.0 | female | 21.0 | 0.0 | 0.0 | 315087 | 8.6625 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 2674 | 7.225 | C | |||
0.0 | 3.0 | male | 26.5 | 0.0 | 0.0 | 2656 | 7.225 | C | ||
1.0 | 2.0 | female | 22.0 | 1.0 | 1.0 | 248738 | 29.0 | S | ||
0.0 | 2.0 | male | 52.0 | 0.0 | 0.0 | 250647 | 13.0 | S | ||
1.0 | 3.0 | male | 0.4167 | 0.0 | 1.0 | 2625 | 8.5167 | C | ||
0.0 | 3.0 | male | 28.0 | 0.0 | 0.0 | 363611 | 8.05 | S | ||
0.0 | 2.0 | male | 70.0 | 0.0 | 0.0 | C.A. 24580 | 10.5 | S | ||
0.0 | 1.0 | male | 28.0 | 1.0 | 0.0 | PC 17604 | 82.1708 | C | ||
0.0 | 3.0 | male | 18.0 | 1.0 | 1.0 | 350404 | 7.8542 | S | ||
1.0 | 1.0 | female | 35.0 | 1.0 | 0.0 | 36973 | 83.475 | C83 | S | |
0.0 | 3.0 | female | 23.0 | 0.0 | 0.0 | 315085 | 8.6625 | S | ||
1.0 | 1.0 | male | 48.0 | 1.0 | 0.0 | PC 17572 | 76.7292 | D33 | C | |
0.0 | 3.0 | male | 0.0 | 0.0 | 3410 | 8.7125 | S | |||
1.0 | 1.0 | female | 60.0 | 0.0 | 0.0 | 11813 | 76.2917 | D15 | C | |
1.0 | 2.0 | female | 19.0 | 1.0 | 0.0 | 2908 | 26.0 | S | ||
0.0 | 3.0 | male | 38.0 | 0.0 | 0.0 | 315089 | 8.6625 | S | ||
0.0 | 1.0 | male | 54.0 | 0.0 | 1.0 | 35281 | 77.2875 | D26 | S | |
0.0 | 3.0 | male | 2.0 | 4.0 | 1.0 | 3101295 | 39.6875 | S | ||
1.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | 345768 | 9.5 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | A/5 2466 | 8.05 | S | |||
1.0 | 1.0 | male | 36.0 | 0.0 | 1.0 | PC 17755 | 512.3292 | B51 B53 B55 | C | |
0.0 | 3.0 | male | 14.5 | 8.0 | 2.0 | CA. 2343 | 69.55 | S | ||
1.0 | 1.0 | female | 26.0 | 1.0 | 0.0 | 13508 | 136.7792 | C89 | C | |
0.0 | 3.0 | male | 0.0 | 0.0 | 32302 | 8.05 | S | |||
1.0 | 1.0 | female | 35.0 | 0.0 | 0.0 | 113503 | 211.5 | C130 | C | |
1.0 | 2.0 | female | 8.0 | 1.0 | 1.0 | 26360 | 26.0 | S | ||
1.0 | 1.0 | female | 22.0 | 1.0 | 0.0 | 113776 | 66.6 | C2 | S | |
0.0 | 3.0 | male | 29.0 | 0.0 | 0.0 | STON/O 2. 3101268 | 7.925 | S | ||
0.0 | 1.0 | male | 65.0 | 0.0 | 0.0 | 13509 | 26.55 | E38 | S | |
1.0 | 2.0 | female | 40.0 | 1.0 | 1.0 | 29750 | 39.0 | S | ||
0.0 | 3.0 | male | 51.0 | 0.0 | 0.0 | 347064 | 7.75 | S | ||
0.0 | 3.0 | male | 28.0 | 0.0 | 0.0 | 392095 | 7.25 | S | ||
0.0 | 3.0 | male | 8.0 | 4.0 | 1.0 | 382652 | 29.125 | Q | ||
1.0 | 1.0 | female | 51.0 | 1.0 | 0.0 | 13502 | 77.9583 | D11 | S | |
1.0 | 2.0 | female | 21.0 | 0.0 | 1.0 | S.O./P.P. 2 | 21.0 | S | ||
1.0 | 1.0 | male | 17.0 | 0.0 | 2.0 | 17421 | 110.8833 | C70 | C | |
0.0 | 3.0 | female | 29.0 | 0.0 | 0.0 | 3101297 | 7.925 | S | ||
0.0 | 3.0 | male | 14.0 | 4.0 | 1.0 | 3101295 | 39.6875 | S | ||
1.0 | 1.0 | female | 24.0 | 3.0 | 2.0 | 19950 | 263.0 | C23 C25 C27 | S | |
1.0 | 3.0 | female | 4.0 | 0.0 | 2.0 | 315153 | 22.025 | S | ||
1.0 | 2.0 | female | 24.0 | 0.0 | 2.0 | 250649 | 14.5 | S | ||
0.0 | 3.0 | male | 17.0 | 0.0 | 0.0 | STON/O 2. 3101274 | 7.125 | S | ||
1.0 | 1.0 | female | 50.0 | 0.0 | 1.0 | PC 17558 | 247.5208 | B58 B60 | C | |
0.0 | 2.0 | male | 36.0 | 0.0 | 0.0 | C.A. 17248 | 10.5 | S | ||
1.0 | 1.0 | female | 35.0 | 1.0 | 0.0 | 13236 | 57.75 | C28 | C | |
1.0 | 1.0 | female | 58.0 | 0.0 | 0.0 | 113783 | 26.55 | C103 | S | |
1.0 | 1.0 | female | 16.0 | 0.0 | 1.0 | PC 17592 | 39.4 | D28 | S | |
1.0 | 3.0 | female | 0.0 | 0.0 | A. 2. 39186 | 8.05 | S | |||
0.0 | 3.0 | male | 13.0 | 0.0 | 2.0 | C.A. 2673 | 20.25 | S | ||
1.0 | 1.0 | female | 35.0 | 1.0 | 0.0 | 113789 | 52.0 | S | ||
1.0 | 2.0 | female | 55.0 | 0.0 | 0.0 | 248706 | 16.0 | S | ||
0.0 | 1.0 | male | 61.0 | 1.0 | 3.0 | PC 17608 | 262.375 | B57 B59 B63 B66 | C | |
0.0 | 1.0 | male | 41.0 | 1.0 | 0.0 | 17464 | 51.8625 | D21 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 359306 | 8.05 | S | |||
1.0 | 1.0 | male | 54.0 | 1.0 | 0.0 | 11778 | 55.4417 | C116 | C | |
0.0 | 1.0 | male | 18.0 | 1.0 | 0.0 | PC 17758 | 108.9 | C65 | C | |
0.0 | 2.0 | male | 48.0 | 0.0 | 0.0 | 234360 | 13.0 | S | ||
1.0 | 3.0 | male | 20.0 | 1.0 | 0.0 | STON/O 2. 3101285 | 7.925 | S | ||
1.0 | 3.0 | female | 18.0 | 0.0 | 0.0 | 3101265 | 7.4958 | S | ||
0.0 | 3.0 | male | 17.0 | 1.0 | 0.0 | 350048 | 7.0542 | S | ||
0.0 | 2.0 | male | 23.0 | 1.0 | 0.0 | 28666 | 10.5 | S | ||
0.0 | 3.0 | male | 35.0 | 0.0 | 0.0 | 349213 | 7.8958 | C | ||
1.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 350034 | 7.7958 | S | ||
0.0 | 3.0 | male | 27.0 | 0.0 | 0.0 | 349219 | 7.8958 | S | ||
0.0 | 1.0 | male | 64.0 | 0.0 | 0.0 | 693 | 26.0 | S | ||
0.0 | 3.0 | male | 39.0 | 0.0 | 0.0 | A/4 48871 | 24.15 | S | ||
0.0 | 3.0 | male | 17.0 | 0.0 | 0.0 | 349232 | 7.8958 | S | ||
0.0 | 1.0 | male | 55.0 | 0.0 | 0.0 | 680 | 50.0 | C39 | S | |
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 54636 | 16.1 | S | ||
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | 350045 | 7.7958 | S | ||
0.0 | 3.0 | male | 19.0 | 0.0 | 0.0 | 365222 | 6.75 | Q | ||
0.0 | 3.0 | female | 16.0 | 5.0 | 2.0 | CA 2144 | 46.9 | S | ||
1.0 | 1.0 | male | 31.0 | 0.0 | 0.0 | 2543 | 28.5375 | C53 | C | |
0.0 | 3.0 | male | 5.0 | 4.0 | 2.0 | 347077 | 31.3875 | S | ||
0.0 | 1.0 | male | 0.0 | 0.0 | 112052 | 0.0 | S | |||
1.0 | 1.0 | female | 38.0 | 0.0 | 0.0 | 113572 | 80.0 | B28 | ||
0.0 | 3.0 | male | 49.0 | 0.0 | 0.0 | LINE | 0.0 | S | ||
1.0 | 2.0 | female | 42.0 | 1.0 | 0.0 | SC/AH 3085 | 26.0 | S | ||
0.0 | 2.0 | male | 25.0 | 0.0 | 0.0 | 244361 | 13.0 | S | ||
0.0 | 1.0 | male | 56.0 | 0.0 | 0.0 | 17764 | 30.6958 | A7 | C | |
1.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | LINE | 0.0 | S | ||
0.0 | 2.0 | male | 0.0 | 0.0 | 239855 | 0.0 | S | |||
0.0 | 3.0 | female | 0.0 | 0.0 | 364856 | 7.75 | Q | |||
1.0 | 1.0 | female | 64.0 | 1.0 | 1.0 | 112901 | 26.55 | B26 | S | |
1.0 | 3.0 | female | 1.0 | 1.0 | 2668 | 22.3583 | F E69 | C | ||
1.0 | 1.0 | female | 45.0 | 0.0 | 0.0 | PC 17608 | 262.375 | C | ||
0.0 | 3.0 | female | 3.0 | 1.0 | 4133 | 25.4667 | S | |||
0.0 | 2.0 | male | 40.0 | 1.0 | 0.0 | 2926 | 26.0 | S | ||
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 349211 | 7.8958 | S | ||
0.0 | 3.0 | female | 18.5 | 0.0 | 0.0 | 329944 | 7.2833 | Q | ||
0.0 | 3.0 | female | 32.0 | 1.0 | 1.0 | 364849 | 15.5 | Q | ||
0.0 | 2.0 | male | 0.0 | 0.0 | SC/PARIS 2159 | 12.875 | S | |||
0.0 | 3.0 | male | 28.0 | 0.0 | 0.0 | 345770 | 9.5 | S | ||
0.0 | 3.0 | male | 1.0 | 0.0 | 65303 | 19.9667 | S | |||
0.0 | 3.0 | male | 31.0 | 0.0 | 0.0 | 347063 | 7.775 | S | ||
1.0 | 1.0 | female | 45.0 | 0.0 | 1.0 | PC 17759 | 63.3583 | D10 D12 | C | |
0.0 | 2.0 | male | 66.0 | 0.0 | 0.0 | C.A. 24579 | 10.5 | S | ||
1.0 | 3.0 | male | 1.0 | 1.0 | 2661 | 15.2458 | C | |||
1.0 | 1.0 | male | 38.0 | 1.0 | 0.0 | 19943 | 90.0 | C93 | S | |
0.0 | 3.0 | female | 25.0 | 0.0 | 0.0 | 347071 | 7.775 | S | ||
1.0 | 2.0 | female | 28.0 | 0.0 | 0.0 | 237668 | 13.0 | S | ||
1.0 | 3.0 | male | 24.0 | 0.0 | 0.0 | S.O./P.P. 752 | 7.55 | S | ||
0.0 | 3.0 | female | 1.0 | 9.0 | CA. 2343 | 69.55 | S | |||
1.0 | 2.0 | female | 36.0 | 0.0 | 0.0 | 28551 | 13.0 | D | S | |
0.0 | 1.0 | male | 45.0 | 1.0 | 0.0 | 36973 | 83.475 | C83 | S | |
0.0 | 3.0 | male | 33.0 | 0.0 | 0.0 | 349241 | 7.8958 | C | ||
0.0 | 1.0 | male | 0.0 | 0.0 | 113767 | 50.0 | A32 | S | ||
0.0 | 3.0 | male | 36.0 | 0.0 | 0.0 | 349210 | 7.4958 | S | ||
0.0 | 3.0 | male | 38.0 | 0.0 | 0.0 | 349249 | 7.8958 | S | ||
0.0 | 1.0 | male | 38.0 | 0.0 | 1.0 | PC 17582 | 153.4625 | C91 | S | |
1.0 | 3.0 | female | 38.0 | 1.0 | 5.0 | 347077 | 31.3875 | S | ||
1.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | 350033 | 7.7958 | S | ||
0.0 | 2.0 | male | 42.0 | 1.0 | 0.0 | 243847 | 27.0 | S | ||
1.0 | 3.0 | female | 5.0 | 2.0 | 1.0 | 2666 | 19.2583 | C | ||
0.0 | 2.0 | male | 21.0 | 0.0 | 0.0 | 29107 | 11.5 | S | ||
0.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | 2672 | 7.225 | C | ||
0.0 | 3.0 | male | 0.0 | 0.0 | A/5 2817 | 8.05 | S | |||
0.0 | 3.0 | female | 0.0 | 0.0 | 364859 | 7.75 | Q | |||
0.0 | 3.0 | male | 0.0 | 0.0 | A./5. 3235 | 8.05 | S | |||
1.0 | 3.0 | female | 2.0 | 0.0 | 367226 | 23.25 | Q | |||
1.0 | 1.0 | female | 62.0 | 0.0 | 0.0 | 113572 | 80.0 | B28 | ||
0.0 | 1.0 | male | 0.0 | 0.0 | 113028 | 26.55 | C124 | S | ||
1.0 | 2.0 | male | 1.0 | 0.0 | 2.0 | S.C./PARIS 2079 | 37.0042 | C | ||
0.0 | 2.0 | male | 30.0 | 0.0 | 0.0 | 233478 | 13.0 | S | ||
0.0 | 3.0 | male | 36.0 | 1.0 | 0.0 | 349910 | 15.55 | S | ||
1.0 | 2.0 | female | 22.0 | 0.0 | 0.0 | W./C. 14266 | 10.5 | F33 | S | |
1.0 | 1.0 | female | 35.0 | 0.0 | 0.0 | PC 17760 | 135.6333 | C99 | S | |
1.0 | 3.0 | female | 29.0 | 0.0 | 2.0 | 2650 | 15.2458 | C | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 330959 | 7.8792 | Q | |||
0.0 | 3.0 | male | 1.0 | 9.0 | CA. 2343 | 69.55 | S | |||
0.0 | 2.0 | male | 18.0 | 0.0 | 0.0 | S.O.C. 14879 | 73.5 | S | ||
0.0 | 3.0 | male | 33.0 | 0.0 | 0.0 | 349239 | 8.6625 | C | ||
1.0 | 1.0 | female | 53.0 | 2.0 | 0.0 | 11769 | 51.4792 | C101 | S | |
0.0 | 3.0 | male | 44.0 | 0.0 | 0.0 | 363592 | 8.05 | S | ||
0.0 | 3.0 | female | 26.0 | 0.0 | 2.0 | SOTON/O.Q. 3101315 | 13.775 | S | ||
1.0 | 2.0 | female | 19.0 | 0.0 | 0.0 | 250655 | 26.0 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 372622 | 7.75 | Q | |||
1.0 | 1.0 | female | 30.0 | 0.0 | 0.0 | 113798 | 31.0 | C | ||
0.0 | 1.0 | male | 21.0 | 0.0 | 1.0 | 35281 | 77.2875 | D26 | S | |
1.0 | 2.0 | male | 0.8333 | 1.0 | 1.0 | 29106 | 18.75 | S | ||
0.0 | 3.0 | female | 40.0 | 1.0 | 0.0 | 7546 | 9.475 | S | ||
1.0 | 3.0 | female | 36.0 | 0.0 | 2.0 | C.A. 37671 | 15.9 | S | ||
0.0 | 3.0 | male | 32.0 | 0.0 | 0.0 | 8471 | 8.3625 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 1222 | 7.8792 | S | |||
0.0 | 3.0 | male | 11.0 | 5.0 | 2.0 | CA 2144 | 46.9 | S | ||
0.0 | 3.0 | female | 1.0 | 1.0 | 1.0 | 350405 | 12.1833 | S | ||
1.0 | 3.0 | male | 27.0 | 0.0 | 0.0 | 315098 | 8.6625 | S | ||
1.0 | 3.0 | female | 23.0 | 0.0 | 0.0 | 347469 | 7.8542 | S | ||
1.0 | 1.0 | male | 45.0 | 0.0 | 0.0 | 111428 | 26.55 | S | ||
0.0 | 2.0 | male | 30.0 | 1.0 | 0.0 | CA 31352 | 21.0 | S | ||
0.0 | 3.0 | female | 27.0 | 0.0 | 0.0 | 330844 | 7.8792 | Q | ||
0.0 | 3.0 | male | 42.0 | 0.0 | 1.0 | 4579 | 8.4042 | S | ||
0.0 | 3.0 | female | 0.0 | 0.0 | 365237 | 7.75 | Q | |||
0.0 | 2.0 | male | 38.0 | 1.0 | 0.0 | 28664 | 21.0 | S | ||
0.0 | 1.0 | male | 50.0 | 0.0 | 0.0 | 113044 | 26.0 | E60 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | A.5. 3236 | 8.05 | S | |||
0.0 | 2.0 | male | 36.0 | 0.0 | 0.0 | SC/Paris 2163 | 12.875 | D | C | |
1.0 | 3.0 | male | 14.0 | 0.0 | 0.0 | 7538 | 9.225 | S | ||
0.0 | 3.0 | male | 2.0 | 3.0 | 1.0 | 349909 | 21.075 | S | ||
1.0 | 2.0 | female | 3.0 | 1.0 | 2.0 | SC/Paris 2123 | 41.5792 | C | ||
1.0 | 2.0 | male | 0.0 | 0.0 | SC/PARIS 2146 | 13.8625 | C | |||
0.0 | 3.0 | male | 24.0 | 0.0 | 0.0 | 7266 | 9.325 | S | ||
1.0 | 1.0 | male | 48.0 | 1.0 | 0.0 | 19996 | 52.0 | C126 | S | |
0.0 | 3.0 | male | 40.0 | 1.0 | 1.0 | 364849 | 15.5 | Q | ||
0.0 | 3.0 | male | 4.0 | 4.0 | 2.0 | 347082 | 31.275 | S | ||
0.0 | 3.0 | female | 8.0 | 2.0 | CA. 2343 | 69.55 | S | |||
0.0 | 3.0 | male | 2.0 | 0.0 | 2662 | 21.6792 | C | |||
0.0 | 3.0 | male | 26.0 | 0.0 | 0.0 | 330910 | 7.8792 | Q | ||
1.0 | 3.0 | female | 15.0 | 1.0 | 0.0 | 2659 | 14.4542 | C | ||
0.0 | 3.0 | male | 17.0 | 2.0 | 0.0 | A/4 48873 | 8.05 | S | ||
1.0 | 2.0 | male | 2.0 | 1.0 | 1.0 | 29103 | 23.0 | S | ||
0.0 | 1.0 | male | 19.0 | 1.0 | 0.0 | 113773 | 53.1 | D30 | S | |
0.0 | 2.0 | male | 21.0 | 1.0 | 0.0 | 28133 | 11.5 | S | ||
1.0 | 3.0 | female | 0.0 | 2.0 | 2668 | 22.3583 | C | |||
0.0 | 2.0 | male | 59.0 | 0.0 | 0.0 | 237442 | 13.5 | S | ||
0.0 | 3.0 | male | 3.0 | 1.0 | 4133 | 25.4667 | S | |||
1.0 | 1.0 | female | 25.0 | 1.0 | 0.0 | 11765 | 55.4417 | E50 | C | |
0.0 | 1.0 | male | 29.0 | 0.0 | 0.0 | 113501 | 30.0 | D6 | S | |
1.0 | 3.0 | female | 18.0 | 0.0 | 0.0 | 4138 | 9.8417 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 2626 | 7.2292 | C | |||
0.0 | 1.0 | male | 0.0 | 0.0 | 112379 | 39.6 | C | |||
1.0 | 2.0 | male | 0.8333 | 0.0 | 2.0 | 248738 | 29.0 | S | ||
1.0 | 2.0 | female | 31.0 | 1.0 | 1.0 | C.A. 31921 | 26.25 | S | ||
1.0 | 1.0 | female | 38.0 | 0.0 | 0.0 | PC 17757 | 227.525 | C45 | C | |
0.0 | 2.0 | male | 28.0 | 0.0 | 0.0 | 248740 | 13.0 | S | ||
0.0 | 2.0 | male | 29.0 | 1.0 | 0.0 | 11668 | 21.0 | S | ||
0.0 | 3.0 | male | 26.0 | 0.0 | 0.0 | 347075 | 7.775 | S | ||
1.0 | 3.0 | female | 5.0 | 4.0 | 2.0 | 347077 | 31.3875 | S | ||
1.0 | 1.0 | female | 17.0 | 1.0 | 0.0 | 17474 | 57.0 | B20 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 349222 | 7.8958 | S | |||
0.0 | 3.0 | male | 6.0 | 1.0 | 1.0 | 2678 | 15.2458 | C | ||
0.0 | 3.0 | male | 9.0 | 5.0 | 2.0 | CA 2144 | 46.9 | S | ||
0.0 | 1.0 | male | 0.0 | 0.0 | PC 17605 | 27.7208 | C | |||
1.0 | 2.0 | female | 48.0 | 0.0 | 2.0 | C.A. 33112 | 36.75 | S | ||
1.0 | 3.0 | male | 0.0 | 0.0 | 1601 | 56.4958 | S | |||
1.0 | 3.0 | male | 25.0 | 1.0 | 0.0 | 347083 | 7.775 | S | ||
0.0 | 3.0 | male | 1.0 | 0.0 | 370371 | 15.5 | Q | |||
1.0 | 1.0 | female | 48.0 | 1.0 | 0.0 | 11755 | 39.6 | A16 | C | |
0.0 | 3.0 | male | 59.0 | 0.0 | 0.0 | 364500 | 7.25 | S | ||
0.0 | 3.0 | male | 16.0 | 1.0 | 1.0 | C.A. 2673 | 20.25 | S | ||
0.0 | 3.0 | female | 8.0 | 2.0 | CA. 2343 | 69.55 | S | |||
0.0 | 3.0 | female | 22.0 | 0.0 | 0.0 | 3101295 | 39.6875 | S | ||
0.0 | 3.0 | male | 28.0 | 0.0 | 0.0 | 347464 | 7.8542 | S | ||
0.0 | 3.0 | female | 0.0 | 4.0 | 4133 | 25.4667 | S | |||
0.0 | 2.0 | male | 18.0 | 0.0 | 0.0 | 231945 | 11.5 | S | ||
1.0 | 2.0 | female | 1.0 | 1.0 | 2.0 | SC/Paris 2123 | 41.5792 | C | ||
0.0 | 3.0 | male | 74.0 | 0.0 | 0.0 | 347060 | 7.775 | S | ||
1.0 | 1.0 | female | 58.0 | 0.0 | 1.0 | PC 17755 | 512.3292 | B51 B53 B55 | C | |
0.0 | 3.0 | male | 18.5 | 0.0 | 0.0 | 2682 | 7.2292 | C | ||
0.0 | 3.0 | male | 18.0 | 0.0 | 0.0 | 347090 | 7.75 | S | ||
1.0 | 3.0 | female | 27.0 | 0.0 | 2.0 | 347742 | 11.1333 | S | ||
0.0 | 1.0 | male | 31.0 | 0.0 | 0.0 | PC 17590 | 50.4958 | A24 | S | |
1.0 | 1.0 | male | 24.0 | 1.0 | 0.0 | 21228 | 82.2667 | B45 | S | |
0.0 | 1.0 | male | 51.0 | 0.0 | 1.0 | PC 17597 | 61.3792 | C | ||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | 315094 | 8.6625 | S | ||
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 342684 | 8.05 | S | ||
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | 324669 | 8.05 | S | ||
0.0 | 2.0 | male | 18.0 | 0.0 | 0.0 | S.O.C. 14879 | 73.5 | S | ||
1.0 | 1.0 | male | 49.0 | 0.0 | 0.0 | 112058 | 0.0 | B52 B54 B56 | S | |
0.0 | 2.0 | male | 0.0 | 0.0 | SC/A.3 2861 | 15.5792 | C | |||
0.0 | 3.0 | female | 1.0 | 0.0 | 2689 | 14.4583 | C | |||
1.0 | 2.0 | female | 40.0 | 0.0 | 0.0 | C.A. 33595 | 15.75 | S | ||
1.0 | 3.0 | female | 36.0 | 1.0 | 0.0 | 345572 | 17.4 | S | ||
0.0 | 3.0 | male | 19.0 | 0.0 | 0.0 | 347069 | 7.775 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349255 | 7.8958 | C | |||
0.0 | 3.0 | male | 23.0 | 0.0 | 0.0 | SOTON/O.Q. 3101309 | 7.05 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 7935 | 7.75 | Q | |||
0.0 | 3.0 | male | 33.0 | 0.0 | 0.0 | 347062 | 7.775 | S | ||
0.0 | 1.0 | male | 17.0 | 0.0 | 0.0 | 113059 | 47.1 | S | ||
1.0 | 3.0 | male | 0.0 | 0.0 | 1601 | 56.4958 | S | |||
0.0 | 3.0 | male | 40.5 | 0.0 | 2.0 | A/5. 851 | 14.5 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | A/4. 34244 | 7.25 | S | |||
1.0 | 2.0 | female | 2.0 | 1.0 | 1.0 | 26360 | 26.0 | S | ||
0.0 | 3.0 | male | 23.0 | 0.0 | 0.0 | 7267 | 9.225 | S | ||
0.0 | 3.0 | male | 42.0 | 0.0 | 0.0 | 315088 | 8.6625 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349220 | 7.8958 | S | |||
1.0 | 2.0 | male | 22.0 | 0.0 | 0.0 | W./C. 14260 | 10.5 | S | ||
1.0 | 1.0 | male | 25.0 | 1.0 | 0.0 | 11967 | 91.0792 | B49 | C | |
1.0 | 1.0 | female | 35.0 | 0.0 | 0.0 | PC 17755 | 512.3292 | C | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 315037 | 8.6625 | S | |||
0.0 | 2.0 | male | 54.0 | 0.0 | 0.0 | 29011 | 14.0 | S | ||
1.0 | 2.0 | male | 0.0 | 0.0 | 244373 | 13.0 | S | |||
0.0 | 3.0 | male | 0.0 | 0.0 | 2647 | 7.225 | C | |||
0.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | 36864 | 7.7417 | Q | ||
1.0 | 1.0 | female | 45.0 | 1.0 | 0.0 | 11753 | 52.5542 | D19 | S | |
0.0 | 3.0 | female | 0.0 | 0.0 | W./C. 6609 | 7.55 | S | |||
0.0 | 3.0 | female | 45.0 | 1.0 | 4.0 | 347088 | 27.9 | S | ||
0.0 | 3.0 | male | 4.0 | 3.0 | 2.0 | 347088 | 27.9 | S | ||
0.0 | 2.0 | male | 35.0 | 0.0 | 0.0 | 28206 | 10.5 | S | ||
1.0 | 1.0 | male | 60.0 | 1.0 | 1.0 | 13567 | 79.2 | B41 | C | |
1.0 | 3.0 | female | 0.0 | 0.0 | 36866 | 7.7375 | Q | |||
0.0 | 1.0 | male | 49.0 | 0.0 | 0.0 | 19924 | 26.0 | S | ||
1.0 | 1.0 | female | 53.0 | 0.0 | 0.0 | PC 17606 | 27.4458 | C | ||
1.0 | 1.0 | female | 43.0 | 0.0 | 1.0 | 24160 | 211.3375 | B3 | S | |
1.0 | 3.0 | female | 31.0 | 1.0 | 1.0 | 363291 | 20.525 | S | ||
0.0 | 3.0 | male | 31.0 | 0.0 | 0.0 | 335097 | 7.75 | Q | ||
0.0 | 3.0 | female | 3.0 | 1.0 | 1.0 | SOTON/O.Q. 3101315 | 13.775 | S | ||
1.0 | 3.0 | male | 26.0 | 0.0 | 0.0 | 347070 | 7.775 | S | ||
1.0 | 3.0 | female | 14.0 | 1.0 | 0.0 | 2651 | 11.2417 | C | ||
1.0 | 2.0 | female | 42.0 | 0.0 | 0.0 | 236852 | 13.0 | S | ||
1.0 | 2.0 | female | 30.0 | 0.0 | 0.0 | 234818 | 12.35 | Q | ||
1.0 | 1.0 | female | 17.0 | 1.0 | 0.0 | PC 17758 | 108.9 | C65 | C | |
0.0 | 3.0 | male | 36.0 | 0.0 | 0.0 | LINE | 0.0 | S | ||
0.0 | 2.0 | male | 34.0 | 1.0 | 0.0 | 31027 | 21.0 | S | ||
1.0 | 1.0 | male | 11.0 | 1.0 | 2.0 | 113760 | 120.0 | B96 B98 | S | |
0.0 | 3.0 | female | 1.0 | 2.0 | W./C. 6607 | 23.45 | S | |||
0.0 | 2.0 | male | 32.5 | 1.0 | 0.0 | 237736 | 30.0708 | C | ||
1.0 | 1.0 | male | 80.0 | 0.0 | 0.0 | 27042 | 30.0 | A23 | S | |
1.0 | 3.0 | male | 1.0 | 1.0 | 2661 | 15.2458 | C | |||
0.0 | 3.0 | male | 26.0 | 1.0 | 2.0 | C.A. 2315 | 20.575 | S | ||
0.0 | 3.0 | male | 42.0 | 0.0 | 0.0 | 348121 | 7.65 | F G63 | S | |
0.0 | 3.0 | male | 43.0 | 0.0 | 0.0 | 349226 | 7.8958 | S | ||
0.0 | 1.0 | male | 33.0 | 0.0 | 0.0 | 695 | 5.0 | B51 B53 B55 | S | |
1.0 | 3.0 | female | 24.0 | 0.0 | 2.0 | PP 9549 | 16.7 | G6 | S | |
0.0 | 3.0 | female | 18.0 | 0.0 | 0.0 | 330963 | 7.8792 | Q | ||
1.0 | 3.0 | male | 2.0 | 0.0 | 367226 | 23.25 | Q | |||
0.0 | 2.0 | male | 31.0 | 1.0 | 1.0 | S.C./PARIS 2079 | 37.0042 | C | ||
0.0 | 2.0 | female | 30.0 | 0.0 | 0.0 | 237249 | 13.0 | S | ||
0.0 | 3.0 | male | 16.0 | 1.0 | 3.0 | W./C. 6608 | 34.375 | S | ||
0.0 | 2.0 | male | 0.0 | 0.0 | 239854 | 0.0 | S | |||
0.0 | 2.0 | male | 30.0 | 1.0 | 1.0 | 250651 | 26.0 | S | ||
1.0 | 3.0 | female | 26.0 | 0.0 | 0.0 | STON/O2. 3101282 | 7.925 | S | ||
0.0 | 3.0 | female | 27.0 | 1.0 | 0.0 | STON/O2. 3101270 | 7.925 | S | ||
1.0 | 2.0 | female | 15.0 | 0.0 | 2.0 | 29750 | 39.0 | S | ||
0.0 | 2.0 | male | 52.0 | 0.0 | 0.0 | 248731 | 13.5 | S | ||
0.0 | 3.0 | male | 33.0 | 0.0 | 0.0 | 349257 | 7.8958 | S | ||
0.0 | 3.0 | male | 30.5 | 0.0 | 0.0 | 364499 | 8.05 | S | ||
0.0 | 2.0 | female | 22.0 | 0.0 | 0.0 | F.C.C. 13534 | 21.0 | S | ||
0.0 | 2.0 | male | 28.0 | 0.0 | 0.0 | 244358 | 26.0 | S | ||
1.0 | 1.0 | female | 30.0 | 0.0 | 0.0 | 12749 | 93.5 | B73 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 2652 | 7.2292 | C | |||
1.0 | 3.0 | female | 2.0 | 0.0 | 1.0 | 3101298 | 12.2875 | S | ||
1.0 | 2.0 | female | 25.0 | 1.0 | 1.0 | 237789 | 30.0 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | A/5 1478 | 8.05 | S | |||
0.0 | 3.0 | male | 19.0 | 0.0 | 0.0 | LINE | 0.0 | S | ||
1.0 | 3.0 | male | 0.0 | 0.0 | 383162 | 7.75 | Q | |||
0.0 | 2.0 | male | 27.0 | 0.0 | 0.0 | 244358 | 26.0 | S | ||
0.0 | 3.0 | male | 40.0 | 1.0 | 5.0 | 347077 | 31.3875 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 2684 | 7.225 | C | |||
1.0 | 1.0 | female | 48.0 | 1.0 | 1.0 | 13567 | 79.2 | B41 | C | |
1.0 | 3.0 | male | 39.0 | 0.0 | 0.0 | STON/O 2. 3101289 | 7.925 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 392092 | 8.05 | S | |||
0.0 | 3.0 | male | 1.0 | 2.0 | W./C. 6607 | 23.45 | S | |||
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | A/5 21174 | 7.25 | S | ||
0.0 | 1.0 | male | 36.0 | 0.0 | 0.0 | 13049 | 40.125 | A10 | C | |
1.0 | 1.0 | female | 1.0 | 0.0 | PC 17611 | 133.65 | S | |||
0.0 | 1.0 | male | 32.5 | 0.0 | 0.0 | 113503 | 211.5 | C132 | C | |
0.0 | 3.0 | male | 45.5 | 0.0 | 0.0 | 2628 | 7.225 | C | ||
0.0 | 3.0 | male | 26.0 | 0.0 | 0.0 | 349224 | 7.8958 | S | ||
0.0 | 2.0 | male | 51.0 | 0.0 | 0.0 | S.O.P. 1166 | 12.525 | S | ||
1.0 | 3.0 | male | 20.0 | 1.0 | 1.0 | 2653 | 15.7417 | C | ||
0.0 | 3.0 | male | 35.0 | 0.0 | 0.0 | 349230 | 7.8958 | S | ||
1.0 | 2.0 | female | 34.0 | 1.0 | 1.0 | 28220 | 32.5 | S | ||
0.0 | 3.0 | male | 19.0 | 0.0 | 0.0 | 323951 | 8.05 | S | ||
0.0 | 3.0 | female | 35.0 | 0.0 | 0.0 | 9232 | 7.75 | Q | ||
1.0 | 1.0 | male | 0.0 | 0.0 | PC 17607 | 39.6 | S | |||
0.0 | 2.0 | male | 0.0 | 0.0 | 239853 | 0.0 | S | |||
0.0 | 3.0 | male | 24.0 | 0.0 | 0.0 | 343275 | 8.05 | S | ||
0.0 | 3.0 | female | 19.0 | 1.0 | 0.0 | 376566 | 16.1 | S | ||
0.0 | 2.0 | female | 26.0 | 1.0 | 1.0 | 250651 | 26.0 | S | ||
1.0 | 2.0 | female | 29.0 | 0.0 | 2.0 | 29103 | 23.0 | S | ||
0.0 | 3.0 | female | 0.0 | 0.0 | 370368 | 7.75 | Q | |||
0.0 | 3.0 | male | 18.0 | 2.0 | 2.0 | W./C. 6608 | 34.375 | S | ||
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | 14973 | 8.05 | S | ||
0.0 | 3.0 | male | 32.0 | 0.0 | 0.0 | STON/O 2. 3101292 | 7.925 | S | ||
0.0 | 3.0 | male | 34.0 | 1.0 | 1.0 | 347080 | 14.4 | S | ||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | SOTON/O2 3101287 | 7.925 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349253 | 7.8958 | C | |||
0.0 | 2.0 | male | 30.0 | 0.0 | 0.0 | 250653 | 13.0 | S | ||
1.0 | 1.0 | male | 43.0 | 1.0 | 0.0 | 17765 | 27.7208 | D40 | C | |
0.0 | 3.0 | female | 22.0 | 0.0 | 0.0 | 7552 | 10.5167 | S | ||
0.0 | 3.0 | male | 27.0 | 0.0 | 0.0 | 349229 | 7.8958 | S | ||
0.0 | 2.0 | male | 43.0 | 0.0 | 1.0 | S.O./P.P. 2 | 21.0 | S | ||
1.0 | 3.0 | male | 29.0 | 0.0 | 0.0 | 345779 | 9.5 | S | ||
1.0 | 3.0 | male | 1.0 | 1.0 | 2668 | 22.3583 | C | |||
0.0 | 3.0 | male | 30.0 | 0.0 | 0.0 | 2694 | 7.225 | C | ||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | 2648 | 4.0125 | C | ||
0.0 | 2.0 | male | 42.0 | 1.0 | 1.0 | 28220 | 32.5 | S | ||
0.0 | 3.0 | male | 27.0 | 0.0 | 0.0 | 2670 | 7.225 | C | ||
0.0 | 3.0 | male | 7.0 | 4.0 | 1.0 | 3101295 | 39.6875 | S | ||
0.0 | 2.0 | male | 16.0 | 0.0 | 0.0 | S.O./P.P. 3 | 10.5 | S | ||
0.0 | 3.0 | male | 23.5 | 0.0 | 0.0 | 2693 | 7.2292 | C | ||
0.0 | 1.0 | male | 55.0 | 1.0 | 1.0 | 12749 | 93.5 | B69 | S | |
1.0 | 3.0 | female | 0.0 | 0.0 | 342712 | 8.05 | S | |||
0.0 | 3.0 | male | 34.0 | 0.0 | 0.0 | 3101264 | 6.4958 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 370375 | 7.75 | Q | |||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | 2679 | 7.225 | C | ||
0.0 | 1.0 | male | 23.0 | 0.0 | 0.0 | 12749 | 93.5 | B24 | S | |
0.0 | 2.0 | male | 26.0 | 0.0 | 0.0 | 237670 | 13.0 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 370377 | 7.75 | Q | |||
1.0 | 3.0 | female | 0.0 | 0.0 | 330919 | 7.8292 | Q | |||
0.0 | 3.0 | female | 1.0 | 0.0 | 370371 | 15.5 | Q | |||
1.0 | 3.0 | female | 30.0 | 0.0 | 0.0 | 382650 | 6.95 | Q | ||
0.0 | 3.0 | male | 7.0 | 4.0 | 1.0 | 382652 | 29.125 | Q | ||
0.0 | 1.0 | male | 36.0 | 1.0 | 0.0 | 19877 | 78.85 | C46 | S | |
0.0 | 2.0 | male | 26.0 | 0.0 | 0.0 | 248659 | 13.0 | S | ||
1.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | 348122 | 7.65 | F G63 | S | |
1.0 | 3.0 | female | 22.0 | 0.0 | 0.0 | 7548 | 8.9625 | S | ||
1.0 | 1.0 | female | 45.0 | 1.0 | 1.0 | 36928 | 164.8667 | S | ||
1.0 | 2.0 | female | 0.0 | 0.0 | 248727 | 33.0 | S | |||
0.0 | 3.0 | male | 0.0 | 0.0 | 1601 | 56.4958 | S | |||
0.0 | 2.0 | female | 24.0 | 0.0 | 0.0 | 248747 | 13.0 | S | ||
0.0 | 1.0 | male | 36.0 | 0.0 | 0.0 | 13050 | 75.2417 | C6 | C | |
1.0 | 2.0 | female | 5.0 | 1.0 | 2.0 | C.A. 34651 | 27.75 | S | ||
0.0 | 3.0 | male | 8.0 | 2.0 | CA. 2343 | 69.55 | S | |||
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 350029 | 7.8542 | S | ||
0.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | 347466 | 7.8542 | S | ||
0.0 | 2.0 | male | 24.0 | 2.0 | 0.0 | S.O.C. 14879 | 73.5 | S | ||
1.0 | 2.0 | female | 26.0 | 0.0 | 0.0 | 220844 | 13.5 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349214 | 7.8958 | S | |||
1.0 | 3.0 | female | 23.0 | 0.0 | 0.0 | SOTON/OQ 392083 | 8.05 | S | ||
1.0 | 1.0 | male | 0.0 | 0.0 | F.C. 12998 | 25.7417 | C | |||
0.0 | 2.0 | male | 25.0 | 0.0 | 0.0 | C.A. 31029 | 31.5 | S | ||
0.0 | 3.0 | female | 25.0 | 1.0 | 0.0 | STON/O2. 3101271 | 7.925 | S | ||
0.0 | 1.0 | male | 55.0 | 0.0 | 0.0 | 113787 | 30.5 | C30 | S | |
0.0 | 3.0 | female | 30.5 | 0.0 | 0.0 | 364850 | 7.75 | Q | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 345777 | 9.5 | S | |||
1.0 | 3.0 | female | 33.0 | 3.0 | 0.0 | 3101278 | 15.85 | S | ||
0.0 | 3.0 | male | 30.0 | 0.0 | 0.0 | C 7076 | 7.25 | S | ||
0.0 | 3.0 | female | 18.0 | 2.0 | 0.0 | 345764 | 18.0 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 2681 | 6.4375 | C | |||
1.0 | 3.0 | male | 0.0 | 0.0 | 367228 | 7.75 | Q | |||
0.0 | 2.0 | male | 0.0 | 0.0 | 239853 | 0.0 | S | |||
0.0 | 3.0 | female | 14.5 | 1.0 | 0.0 | 2665 | 14.4542 | C | ||
0.0 | 3.0 | male | 40.0 | 0.0 | 0.0 | 2623 | 7.225 | C | ||
0.0 | 3.0 | male | 21.0 | 1.0 | 0.0 | 3101266 | 6.4958 | S | ||
1.0 | 1.0 | male | 35.0 | 0.0 | 0.0 | 111426 | 26.55 | C | ||
0.0 | 3.0 | female | 41.0 | 0.0 | 2.0 | 370129 | 20.2125 | S | ||
0.0 | 2.0 | male | 36.0 | 0.0 | 0.0 | 242963 | 13.0 | S | ||
1.0 | 2.0 | female | 4.0 | 2.0 | 1.0 | 230136 | 39.0 | F4 | S | |
1.0 | 3.0 | female | 16.0 | 0.0 | 0.0 | 348125 | 7.65 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 368573 | 7.75 | Q | |||
1.0 | 2.0 | female | 20.0 | 0.0 | 0.0 | C.A. 33112 | 36.75 | S | ||
1.0 | 2.0 | male | 31.0 | 0.0 | 0.0 | 244270 | 13.0 | S | ||
0.0 | 3.0 | male | 24.0 | 0.0 | 0.0 | 342441 | 8.05 | S | ||
0.0 | 2.0 | male | 61.0 | 0.0 | 0.0 | 235509 | 12.35 | Q | ||
1.0 | 2.0 | female | 25.0 | 0.0 | 1.0 | 230433 | 26.0 | S | ||
0.0 | 3.0 | male | 29.0 | 0.0 | 0.0 | 343276 | 8.05 | S | ||
1.0 | 1.0 | female | 48.0 | 0.0 | 0.0 | 17466 | 25.9292 | D17 | S | |
0.0 | 2.0 | male | 24.0 | 0.0 | 0.0 | C.A. 29566 | 10.5 | S | ||
0.0 | 2.0 | male | 33.0 | 0.0 | 0.0 | SCO/W 1585 | 12.275 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349254 | 7.8958 | C | |||
1.0 | 1.0 | female | 39.0 | 0.0 | 0.0 | PC 17758 | 108.9 | C105 | C | |
0.0 | 2.0 | male | 30.0 | 1.0 | 0.0 | P/PP 3381 | 24.0 | C | ||
1.0 | 3.0 | male | 20.0 | 0.0 | 0.0 | SOTON/O2 3101284 | 7.925 | S | ||
0.0 | 1.0 | male | 0.0 | 0.0 | PC 17483 | 221.7792 | C95 | S | ||
0.0 | 3.0 | male | 27.0 | 0.0 | 0.0 | 350408 | 7.8542 | S | ||
0.0 | 2.0 | male | 26.0 | 0.0 | 0.0 | 31028 | 10.5 | S | ||
0.0 | 1.0 | male | 30.0 | 0.0 | 0.0 | 113801 | 45.5 | S | ||
1.0 | 2.0 | female | 20.0 | 1.0 | 0.0 | 236853 | 26.0 | S | ||
1.0 | 1.0 | male | 0.9167 | 1.0 | 2.0 | 113781 | 151.55 | C22 C26 | S | |
1.0 | 1.0 | female | 19.0 | 0.0 | 2.0 | 11752 | 26.2833 | D47 | S | |
0.0 | 3.0 | male | 1.0 | 1.0 | A/5. 851 | 14.5 | S | |||
0.0 | 1.0 | male | 19.0 | 3.0 | 2.0 | 19950 | 263.0 | C23 C25 C27 | S | |
1.0 | 1.0 | male | 56.0 | 0.0 | 0.0 | 13213 | 35.5 | A26 | C | |
1.0 | 1.0 | male | 37.0 | 1.0 | 1.0 | 11751 | 52.5542 | D35 | S | |
0.0 | 3.0 | male | 28.0 | 0.0 | 0.0 | 349243 | 7.8958 | S | ||
0.0 | 3.0 | female | 2.0 | 1.0 | 1.0 | 370129 | 20.2125 | S | ||
0.0 | 2.0 | male | 28.0 | 0.0 | 1.0 | 248727 | 33.0 | S | ||
1.0 | 2.0 | female | 4.0 | 1.0 | 1.0 | 29103 | 23.0 | S | ||
0.0 | 2.0 | male | 39.0 | 0.0 | 0.0 | 28213 | 13.0 | S | ||
0.0 | 2.0 | male | 0.0 | 0.0 | SC/PARIS 2131 | 15.05 | C | |||
1.0 | 1.0 | male | 53.0 | 0.0 | 0.0 | 113780 | 28.5 | C51 | C | |
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 2692 | 7.225 | C | ||
0.0 | 3.0 | female | 20.0 | 1.0 | 0.0 | 4136 | 9.825 | S | ||
0.0 | 1.0 | male | 39.0 | 0.0 | 0.0 | 112050 | 0.0 | A36 | S | |
1.0 | 1.0 | female | 39.0 | 0.0 | 0.0 | 24160 | 211.3375 | S | ||
0.0 | 3.0 | male | 33.0 | 1.0 | 1.0 | 363291 | 20.525 | S | ||
0.0 | 1.0 | male | 48.0 | 0.0 | 0.0 | PC 17591 | 50.4958 | B10 | C | |
0.0 | 1.0 | male | 0.0 | 0.0 | 112058 | 0.0 | B102 | S | ||
1.0 | 1.0 | female | 18.0 | 0.0 | 2.0 | 110413 | 79.65 | E68 | S | |
0.0 | 1.0 | male | 0.0 | 0.0 | 113778 | 26.55 | D34 | S | ||
1.0 | 3.0 | female | 1.0 | 1.0 | 1.0 | 347742 | 11.1333 | S | ||
1.0 | 2.0 | male | 26.0 | 1.0 | 1.0 | 248738 | 29.0 | S | ||
1.0 | 1.0 | female | 36.0 | 1.0 | 2.0 | 113760 | 120.0 | B96 B98 | S | |
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | A/5 21172 | 7.25 | S | ||
1.0 | 1.0 | male | 30.0 | 1.0 | 0.0 | 13236 | 57.75 | C78 | C | |
0.0 | 3.0 | male | 0.0 | 0.0 | 349223 | 7.8958 | S | |||
1.0 | 1.0 | female | 30.0 | 0.0 | 0.0 | 36928 | 164.8667 | C7 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | C.A. 6212 | 15.1 | S | |||
1.0 | 3.0 | female | 1.0 | 1.0 | 1.0 | PP 9549 | 16.7 | G6 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 2673 | 7.2292 | C | |||
0.0 | 3.0 | male | 0.0 | 0.0 | C.A. 49867 | 7.55 | S | |||
1.0 | 2.0 | female | 54.0 | 1.0 | 3.0 | 29105 | 23.0 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 14311 | 7.75 | Q | |||
1.0 | 3.0 | male | 29.0 | 0.0 | 0.0 | 382651 | 7.75 | Q | ||
0.0 | 3.0 | female | 37.0 | 0.0 | 0.0 | 368364 | 7.75 | Q | ||
1.0 | 1.0 | female | 33.0 | 1.0 | 0.0 | 113806 | 53.1 | E8 | S | |
0.0 | 3.0 | male | 39.0 | 0.0 | 0.0 | 3101296 | 7.925 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 359309 | 8.05 | S | |||
1.0 | 1.0 | male | 0.0 | 0.0 | 19947 | 35.5 | C52 | S | ||
1.0 | 1.0 | female | 41.0 | 0.0 | 0.0 | 16966 | 134.5 | E40 | C | |
0.0 | 3.0 | male | 0.0 | 0.0 | 374910 | 8.05 | S | |||
0.0 | 3.0 | male | 30.0 | 0.0 | 0.0 | 2685 | 7.2292 | C | ||
0.0 | 2.0 | male | 40.0 | 0.0 | 0.0 | 239059 | 16.0 | S | ||
0.0 | 3.0 | male | 33.0 | 0.0 | 0.0 | A./5. 3338 | 8.05 | S | ||
1.0 | 2.0 | male | 8.0 | 1.0 | 1.0 | C.A. 33112 | 36.75 | S | ||
0.0 | 2.0 | male | 47.0 | 0.0 | 0.0 | C.A. 30769 | 10.5 | S | ||
0.0 | 3.0 | male | 25.0 | 1.0 | 0.0 | 347076 | 7.775 | S | ||
0.0 | 3.0 | female | 3.0 | 3.0 | 1.0 | 349909 | 21.075 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 335677 | 7.75 | Q | |||
0.0 | 1.0 | male | 50.0 | 1.0 | 0.0 | 13507 | 55.9 | E44 | S | |
1.0 | 1.0 | female | 39.0 | 1.0 | 1.0 | 17421 | 110.8833 | C68 | C | |
1.0 | 1.0 | female | 36.0 | 0.0 | 2.0 | WE/P 5735 | 71.0 | B22 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 330979 | 7.8292 | Q | |||
1.0 | 2.0 | female | 24.0 | 2.0 | 3.0 | 29106 | 18.75 | S | ||
1.0 | 1.0 | female | 22.0 | 0.0 | 1.0 | 113509 | 61.9792 | B36 | C | |
1.0 | 1.0 | female | 54.0 | 1.0 | 0.0 | PC 17603 | 59.4 | C | ||
1.0 | 2.0 | female | 41.0 | 0.0 | 1.0 | 250644 | 19.5 | S | ||
1.0 | 1.0 | female | 23.0 | 1.0 | 0.0 | 35273 | 113.275 | D36 | C | |
1.0 | 1.0 | male | 31.0 | 1.0 | 0.0 | 17474 | 57.0 | B20 | S | |
0.0 | 3.0 | male | 31.0 | 0.0 | 0.0 | 21332 | 7.7333 | Q | ||
1.0 | 3.0 | male | 0.0 | 0.0 | 2677 | 7.2292 | C | |||
0.0 | 3.0 | female | 17.0 | 0.0 | 0.0 | AQ/3. 30631 | 7.7333 | Q | ||
0.0 | 1.0 | male | 42.0 | 0.0 | 0.0 | 17475 | 26.55 | S | ||
1.0 | 1.0 | female | 52.0 | 1.0 | 1.0 | 12749 | 93.5 | B69 | S | |
0.0 | 1.0 | male | 47.0 | 0.0 | 0.0 | 110465 | 52.0 | C110 | S | |
1.0 | 1.0 | female | 26.0 | 0.0 | 0.0 | 19877 | 78.85 | S | ||
0.0 | 3.0 | female | 31.0 | 1.0 | 0.0 | 345763 | 18.0 | S | ||
0.0 | 3.0 | female | 29.0 | 0.0 | 4.0 | 349909 | 21.075 | S | ||
1.0 | 2.0 | female | 24.0 | 1.0 | 0.0 | 244367 | 26.0 | S | ||
1.0 | 3.0 | male | 44.0 | 0.0 | 0.0 | STON/O 2. 3101269 | 7.925 | S | ||
0.0 | 1.0 | male | 42.0 | 1.0 | 0.0 | 113789 | 52.0 | S | ||
0.0 | 1.0 | male | 50.0 | 1.0 | 1.0 | 113503 | 211.5 | C80 | C | |
0.0 | 2.0 | male | 47.0 | 0.0 | 0.0 | 237565 | 15.0 | S | ||
0.0 | 3.0 | male | 32.0 | 0.0 | 0.0 | STON/O 2. 3101293 | 7.925 | S | ||
1.0 | 2.0 | female | 8.0 | 0.0 | 2.0 | C.A. 31921 | 26.25 | S | ||
0.0 | 3.0 | male | 28.0 | 0.0 | 0.0 | 1601 | 56.4958 | S | ||
1.0 | 1.0 | female | 35.0 | 1.0 | 0.0 | 113803 | 53.1 | C123 | S | |
0.0 | 1.0 | male | 62.0 | 0.0 | 0.0 | 113807 | 26.55 | S | ||
1.0 | 3.0 | female | 23.0 | 0.0 | 0.0 | CA. 2314 | 7.55 | S | ||
0.0 | 3.0 | male | 10.0 | 3.0 | 2.0 | 347088 | 27.9 | S | ||
1.0 | 2.0 | female | 34.0 | 0.0 | 1.0 | 231919 | 23.0 | S | ||
1.0 | 3.0 | female | 0.1667 | 1.0 | 2.0 | C.A. 2315 | 20.575 | S | ||
0.0 | 1.0 | male | 45.0 | 0.0 | 0.0 | 113050 | 26.55 | B38 | S | |
0.0 | 3.0 | male | 47.0 | 0.0 | 0.0 | A/5 3902 | 7.25 | S | ||
1.0 | 2.0 | female | 29.0 | 1.0 | 0.0 | 26707 | 26.0 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 376563 | 8.05 | S | |||
0.0 | 3.0 | female | 24.0 | 0.0 | 0.0 | 368702 | 7.75 | Q | ||
1.0 | 3.0 | female | 17.0 | 4.0 | 2.0 | 3101281 | 7.925 | S | ||
0.0 | 1.0 | male | 0.0 | 0.0 | 112051 | 0.0 | S | |||
1.0 | 3.0 | male | 0.0 | 0.0 | 65306 | 8.1125 | S | |||
0.0 | 3.0 | male | 43.0 | 0.0 | 0.0 | C 7075 | 6.45 | S | ||
0.0 | 3.0 | male | 30.0 | 1.0 | 0.0 | A/5. 3336 | 16.1 | S | ||
0.0 | 3.0 | male | 8.0 | 2.0 | CA. 2343 | 69.55 | S | |||
0.0 | 2.0 | male | 44.0 | 1.0 | 0.0 | 26707 | 26.0 | S | ||
1.0 | 2.0 | female | 48.0 | 1.0 | 2.0 | 220845 | 65.0 | S | ||
0.0 | 2.0 | male | 27.0 | 0.0 | 0.0 | 220367 | 13.0 | S | ||
0.0 | 2.0 | male | 16.0 | 0.0 | 0.0 | 239865 | 26.0 | S | ||
0.0 | 1.0 | male | 30.0 | 0.0 | 0.0 | 110469 | 26.0 | C106 | S | |
0.0 | 3.0 | female | 45.0 | 0.0 | 0.0 | 347073 | 7.75 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 330932 | 7.7875 | Q | |||
0.0 | 2.0 | male | 21.0 | 0.0 | 0.0 | 236854 | 13.0 | S | ||
1.0 | 1.0 | female | 31.0 | 0.0 | 0.0 | 16966 | 134.5 | E39 E41 | C | |
1.0 | 3.0 | male | 32.0 | 0.0 | 0.0 | 350403 | 7.5792 | S | ||
1.0 | 1.0 | female | 22.0 | 0.0 | 0.0 | 113781 | 151.55 | S | ||
1.0 | 3.0 | female | 35.0 | 1.0 | 1.0 | C.A. 2673 | 20.25 | S | ||
1.0 | 3.0 | male | 16.0 | 0.0 | 0.0 | SOTON/OQ 392089 | 8.05 | S | ||
1.0 | 1.0 | female | 60.0 | 1.0 | 4.0 | 19950 | 263.0 | C23 C25 C27 | S | |
0.0 | 3.0 | male | 70.5 | 0.0 | 0.0 | 370369 | 7.75 | Q | ||
1.0 | 3.0 | male | 36.5 | 1.0 | 0.0 | 345572 | 17.4 | S | ||
1.0 | 1.0 | female | 32.0 | 0.0 | 0.0 | 11813 | 76.2917 | D15 | C | |
1.0 | 1.0 | female | 15.0 | 0.0 | 1.0 | 24160 | 211.3375 | B5 | S | |
0.0 | 3.0 | male | 47.0 | 0.0 | 0.0 | 345765 | 9.0 | S | ||
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | A./5. 2152 | 8.05 | S | ||
0.0 | 3.0 | male | 32.0 | 1.0 | 0.0 | 3101278 | 15.85 | S | ||
0.0 | 3.0 | male | 28.0 | 0.0 | 0.0 | 350042 | 7.7958 | S | ||
0.0 | 2.0 | male | 19.0 | 0.0 | 0.0 | 28424 | 13.0 | S | ||
0.0 | 2.0 | male | 30.0 | 0.0 | 0.0 | W/C 14208 | 10.5 | S | ||
0.0 | 2.0 | male | 24.0 | 0.0 | 0.0 | 233866 | 13.0 | S | ||
0.0 | 3.0 | male | 34.0 | 0.0 | 0.0 | 363294 | 8.05 | S | ||
0.0 | 2.0 | male | 31.0 | 0.0 | 0.0 | C.A. 18723 | 10.5 | S | ||
0.0 | 2.0 | male | 30.0 | 0.0 | 0.0 | 250646 | 13.0 | S | ||
1.0 | 1.0 | female | 39.0 | 1.0 | 1.0 | 110413 | 79.65 | E67 | S | |
1.0 | 1.0 | female | 33.0 | 0.0 | 0.0 | PC 17613 | 27.7208 | A11 | C | |
1.0 | 1.0 | female | 23.0 | 3.0 | 2.0 | 19950 | 263.0 | C23 C25 C27 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 36865 | 7.7375 | Q | |||
0.0 | 1.0 | male | 0.0 | 0.0 | 17463 | 51.8625 | E46 | S | ||
0.0 | 3.0 | male | 11.5 | 1.0 | 1.0 | A/5. 851 | 14.5 | S | ||
1.0 | 2.0 | female | 24.0 | 1.0 | 2.0 | 220845 | 65.0 | S | ||
0.0 | 3.0 | male | 1.0 | 0.0 | 65304 | 19.9667 | S | |||
1.0 | 2.0 | female | 17.0 | 0.0 | 0.0 | SO/C 14885 | 10.5 | S | ||
1.0 | 3.0 | female | 16.0 | 0.0 | 0.0 | 367231 | 7.75 | Q | ||
0.0 | 3.0 | male | 20.5 | 0.0 | 0.0 | A/5 21173 | 7.25 | S | ||
1.0 | 1.0 | female | 21.0 | 0.0 | 0.0 | 113795 | 26.55 | S | ||
0.0 | 2.0 | male | 23.0 | 0.0 | 0.0 | C.A. 31030 | 10.5 | S | ||
1.0 | 3.0 | female | 1.0 | 0.0 | 386525 | 16.1 | S | |||
0.0 | 3.0 | male | 0.0 | 0.0 | 374746 | 8.05 | S | |||
1.0 | 3.0 | female | 18.0 | 0.0 | 0.0 | 347066 | 7.775 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 366713 | 7.75 | Q | |||
1.0 | 2.0 | female | 33.0 | 1.0 | 2.0 | C.A. 34651 | 27.75 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | S.C./A.4. 23567 | 8.05 | S | |||
1.0 | 1.0 | male | 6.0 | 0.0 | 2.0 | 16966 | 134.5 | E34 | C | |
1.0 | 2.0 | female | 29.0 | 0.0 | 0.0 | C.A. 29395 | 10.5 | F33 | S | |
0.0 | 3.0 | male | 39.0 | 0.0 | 2.0 | 2675 | 7.2292 | C | ||
0.0 | 3.0 | male | 36.0 | 0.0 | 0.0 | 345771 | 9.5 | S | ||
1.0 | 1.0 | male | 27.0 | 0.0 | 0.0 | 113804 | 30.5 | S | ||
0.0 | 3.0 | female | 21.0 | 0.0 | 0.0 | 364846 | 7.75 | Q | ||
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | 349252 | 7.8958 | S | ||
0.0 | 3.0 | male | 18.0 | 0.0 | 0.0 | 347078 | 7.75 | S | ||
1.0 | 1.0 | female | 36.0 | 0.0 | 0.0 | PC 17760 | 135.6333 | C32 | C | |
0.0 | 1.0 | male | 47.0 | 0.0 | 0.0 | 111320 | 38.5 | E63 | S | |
0.0 | 3.0 | male | 17.0 | 0.0 | 0.0 | 315090 | 8.6625 | S | ||
0.0 | 2.0 | male | 27.0 | 0.0 | 0.0 | 211536 | 13.0 | S | ||
0.0 | 3.0 | male | 28.0 | 0.0 | 0.0 | 345783 | 9.5 | S | ||
1.0 | 1.0 | male | 36.0 | 0.0 | 0.0 | PC 17473 | 26.2875 | E25 | S | |
0.0 | 3.0 | male | 32.0 | 0.0 | 0.0 | 370376 | 7.75 | Q | ||
0.0 | 3.0 | male | 40.0 | 1.0 | 4.0 | 347088 | 27.9 | S | ||
1.0 | 1.0 | male | 42.0 | 1.0 | 0.0 | 11753 | 52.5542 | D19 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 394140 | 6.8583 | Q | |||
1.0 | 3.0 | female | 22.0 | 1.0 | 1.0 | 3101298 | 12.2875 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 2664 | 7.225 | C | |||
0.0 | 3.0 | male | 0.0 | 0.0 | 2655 | 7.2292 | F E46 | C | ||
0.0 | 1.0 | male | 0.0 | 0.0 | PC 17318 | 25.925 | S | |||
1.0 | 1.0 | female | 23.0 | 0.0 | 1.0 | 11767 | 83.1583 | C54 | C | |
0.0 | 3.0 | male | 41.0 | 2.0 | 0.0 | 350026 | 14.1083 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 334912 | 7.7333 | Q | |||
0.0 | 3.0 | male | 0.0 | 0.0 | AQ/4 3130 | 7.75 | Q | |||
1.0 | 3.0 | female | 1.0 | 0.0 | 376564 | 16.1 | S | |||
0.0 | 3.0 | male | 34.5 | 0.0 | 0.0 | 2683 | 6.4375 | C | ||
0.0 | 3.0 | male | 31.0 | 3.0 | 0.0 | 345763 | 18.0 | S | ||
0.0 | 1.0 | male | 40.0 | 0.0 | 0.0 | PC 17601 | 27.7208 | C | ||
1.0 | 1.0 | female | 56.0 | 0.0 | 1.0 | 11767 | 83.1583 | C50 | C | |
1.0 | 2.0 | female | 36.0 | 0.0 | 0.0 | 27849 | 13.0 | S | ||
1.0 | 1.0 | female | 33.0 | 0.0 | 0.0 | 113781 | 151.55 | S | ||
0.0 | 2.0 | male | 25.0 | 1.0 | 0.0 | 236853 | 26.0 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 370370 | 7.75 | Q | |||
0.0 | 3.0 | male | 23.0 | 0.0 | 0.0 | 349204 | 7.8958 | S | ||
0.0 | 3.0 | male | 27.0 | 0.0 | 0.0 | 315154 | 8.6625 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 335432 | 7.7333 | Q | |||
1.0 | 3.0 | male | 6.0 | 0.0 | 1.0 | 392096 | 12.475 | E121 | S | |
0.0 | 3.0 | male | 34.0 | 0.0 | 0.0 | 364506 | 8.05 | S | ||
0.0 | 2.0 | male | 39.0 | 0.0 | 0.0 | 250655 | 26.0 | S | ||
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | 347065 | 7.775 | S | ||
1.0 | 3.0 | male | 26.0 | 0.0 | 0.0 | 2699 | 18.7875 | C | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 365235 | 7.75 | Q | |||
0.0 | 3.0 | female | 18.0 | 0.0 | 1.0 | 2691 | 14.4542 | C | ||
0.0 | 2.0 | male | 54.0 | 0.0 | 0.0 | 28403 | 26.0 | S | ||
0.0 | 1.0 | female | 2.0 | 1.0 | 2.0 | 113781 | 151.55 | C22 C26 | S | |
0.0 | 3.0 | male | 35.0 | 0.0 | 0.0 | SOTON/O.Q. 3101310 | 7.05 | S | ||
0.0 | 2.0 | male | 60.0 | 1.0 | 1.0 | 29750 | 39.0 | S | ||
1.0 | 1.0 | female | 21.0 | 0.0 | 0.0 | 13502 | 77.9583 | D9 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 312993 | 7.775 | S | |||
1.0 | 3.0 | female | 22.0 | 0.0 | 0.0 | 334914 | 7.725 | Q | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349238 | 7.8958 | S | |||
0.0 | 3.0 | male | 0.75 | 1.0 | 1.0 | SOTON/O.Q. 3101315 | 13.775 | S | ||
0.0 | 3.0 | male | 50.0 | 0.0 | 0.0 | A/5 3594 | 8.05 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 343271 | 7.0 | S | |||
0.0 | 3.0 | male | 18.0 | 1.0 | 0.0 | 3101267 | 6.4958 | S | ||
1.0 | 3.0 | male | 18.0 | 0.0 | 0.0 | A/5 3540 | 8.05 | S | ||
0.0 | 3.0 | male | 17.0 | 0.0 | 0.0 | 315093 | 8.6625 | S | ||
0.0 | 3.0 | male | 36.0 | 1.0 | 1.0 | 345773 | 24.15 | S | ||
0.0 | 3.0 | male | 35.0 | 0.0 | 0.0 | 364512 | 8.05 | S | ||
1.0 | 2.0 | male | 42.0 | 0.0 | 0.0 | 237798 | 13.0 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 349216 | 7.8958 | S | |||
0.0 | 3.0 | female | 18.0 | 1.0 | 0.0 | 349237 | 17.8 | S | ||
0.0 | 2.0 | male | 21.0 | 1.0 | 0.0 | 28134 | 11.5 | S | ||
0.0 | 3.0 | male | 33.0 | 0.0 | 0.0 | 7540 | 8.6542 | S | ||
0.0 | 2.0 | male | 22.0 | 2.0 | 0.0 | C.A. 31029 | 31.5 | S | ||
1.0 | 2.0 | female | 32.5 | 0.0 | 0.0 | 27267 | 13.0 | E101 | S | |
0.0 | 3.0 | female | 0.0 | 0.0 | 330924 | 7.8792 | Q | |||
1.0 | 2.0 | female | 18.0 | 0.0 | 1.0 | 231919 | 23.0 | S | ||
1.0 | 1.0 | male | 21.0 | 0.0 | 1.0 | PC 17597 | 61.3792 | C | ||
1.0 | 1.0 | male | 28.0 | 0.0 | 0.0 | 110564 | 26.55 | C52 | S | |
0.0 | 3.0 | male | 16.0 | 0.0 | 0.0 | 345778 | 9.5 | S | ||
1.0 | 1.0 | female | 58.0 | 0.0 | 1.0 | PC 17582 | 153.4625 | C125 | S | |
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | STON/O 2. 3101280 | 7.925 | S | ||
1.0 | 3.0 | female | 19.0 | 1.0 | 0.0 | 350046 | 7.8542 | S | ||
0.0 | 3.0 | male | 26.0 | 0.0 | 0.0 | 349202 | 7.8958 | S | ||
0.0 | 2.0 | male | 37.0 | 1.0 | 0.0 | SC/AH 29037 | 26.0 | S | ||
1.0 | 1.0 | male | 50.0 | 2.0 | 0.0 | PC 17611 | 133.65 | S | ||
0.0 | 1.0 | male | 24.0 | 1.0 | 0.0 | 13695 | 60.0 | C31 | S | |
0.0 | 3.0 | male | 30.0 | 0.0 | 0.0 | 349246 | 7.8958 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 36568 | 15.5 | Q | |||
0.0 | 3.0 | female | 45.0 | 0.0 | 1.0 | 2691 | 14.4542 | C | ||
1.0 | 3.0 | female | 16.0 | 0.0 | 0.0 | 35851 | 7.7333 | Q | ||
0.0 | 1.0 | male | 52.0 | 1.0 | 1.0 | 110413 | 79.65 | E67 | S | |
1.0 | 3.0 | male | 26.0 | 0.0 | 0.0 | 1601 | 56.4958 | S | ||
1.0 | 3.0 | female | 1.0 | 0.0 | 367230 | 15.5 | Q | |||
1.0 | 3.0 | female | 0.0 | 0.0 | 14312 | 7.75 | Q | |||
1.0 | 1.0 | female | 31.0 | 1.0 | 0.0 | 35273 | 113.275 | D36 | C | |
1.0 | 3.0 | female | 1.0 | 0.0 | 2.0 | 2653 | 15.7417 | C | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 384461 | 7.75 | Q | |||
1.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | 2620 | 7.225 | C | ||
0.0 | 2.0 | male | 30.0 | 0.0 | 0.0 | 28228 | 13.0 | S | ||
1.0 | 1.0 | male | 27.0 | 1.0 | 0.0 | 113806 | 53.1 | E8 | S | |
0.0 | 2.0 | female | 29.0 | 1.0 | 0.0 | SC/AH 29037 | 26.0 | S | ||
0.0 | 3.0 | male | 16.0 | 4.0 | 1.0 | 3101295 | 39.6875 | S | ||
1.0 | 3.0 | male | 32.0 | 0.0 | 0.0 | 347079 | 7.775 | S | ||
0.0 | 1.0 | male | 29.0 | 1.0 | 0.0 | 113776 | 66.6 | C2 | S | |
1.0 | 1.0 | female | 54.0 | 1.0 | 0.0 | 36947 | 78.2667 | D20 | C | |
1.0 | 2.0 | female | 27.0 | 1.0 | 0.0 | SC/PARIS 2149 | 13.8583 | C | ||
1.0 | 1.0 | female | 49.0 | 1.0 | 0.0 | PC 17572 | 76.7292 | D33 | C | |
1.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | 2654 | 7.2292 | F E57 | C | |
1.0 | 3.0 | male | 27.0 | 0.0 | 0.0 | 350043 | 7.7958 | S | ||
0.0 | 3.0 | male | 51.0 | 0.0 | 0.0 | 21440 | 8.05 | S | ||
1.0 | 3.0 | male | 0.0 | 0.0 | SOTON/O.Q. 3101308 | 7.05 | S | |||
0.0 | 3.0 | male | 44.0 | 0.0 | 1.0 | 371362 | 16.1 | S | ||
0.0 | 2.0 | male | 18.0 | 0.0 | 0.0 | C.A. 15185 | 10.5 | S | ||
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 315097 | 8.6625 | S | ||
0.0 | 2.0 | male | 18.5 | 0.0 | 0.0 | 248734 | 13.0 | F | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 2671 | 7.2292 | C | |||
1.0 | 2.0 | female | 32.0 | 0.0 | 0.0 | 234604 | 13.0 | S | ||
0.0 | 1.0 | male | 67.0 | 1.0 | 0.0 | PC 17483 | 221.7792 | C55 C57 | S | |
0.0 | 2.0 | female | 60.0 | 1.0 | 0.0 | 24065 | 26.0 | S | ||
0.0 | 2.0 | male | 24.0 | 2.0 | 0.0 | C.A. 31029 | 31.5 | S | ||
0.0 | 1.0 | male | 71.0 | 0.0 | 0.0 | PC 17754 | 34.6542 | A5 | C | |
0.0 | 3.0 | male | 0.0 | 0.0 | 3411 | 8.7125 | C | |||
0.0 | 1.0 | male | 55.0 | 1.0 | 0.0 | PC 17603 | 59.4 | C | ||
0.0 | 1.0 | male | 46.0 | 0.0 | 0.0 | PC 17593 | 79.2 | B82 B84 | C | |
1.0 | 1.0 | female | 24.0 | 0.0 | 0.0 | PC 17482 | 49.5042 | C90 | C | |
1.0 | 1.0 | female | 35.0 | 1.0 | 0.0 | 19943 | 90.0 | C93 | S | |
0.0 | 1.0 | male | 47.0 | 0.0 | 0.0 | 36967 | 34.0208 | D46 | S | |
0.0 | 2.0 | male | 35.0 | 0.0 | 0.0 | 239865 | 26.0 | S | ||
0.0 | 3.0 | male | 23.0 | 1.0 | 0.0 | 347072 | 13.9 | S | ||
1.0 | 1.0 | female | 45.0 | 0.0 | 1.0 | 112378 | 59.4 | C | ||
0.0 | 3.0 | male | 26.0 | 0.0 | 0.0 | 3474 | 7.8875 | S | ||
0.0 | 3.0 | male | 24.0 | 0.0 | 0.0 | 349911 | 7.775 | S | ||
1.0 | 1.0 | male | 40.0 | 0.0 | 0.0 | 112277 | 31.0 | A31 | C | |
1.0 | 1.0 | male | 0.0 | 0.0 | 19988 | 30.5 | C106 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 330877 | 8.4583 | Q | |||
1.0 | 3.0 | female | 26.0 | 0.0 | 0.0 | 347470 | 7.8542 | S | ||
0.0 | 1.0 | male | 27.0 | 0.0 | 2.0 | 113503 | 211.5 | C82 | C | |
1.0 | 1.0 | female | 37.0 | 1.0 | 0.0 | 19928 | 90.0 | C78 | Q | |
0.0 | 2.0 | male | 42.0 | 0.0 | 0.0 | 244310 | 13.0 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | C.A. 42795 | 7.55 | S | |||
1.0 | 1.0 | male | 52.0 | 0.0 | 0.0 | 113786 | 30.5 | C104 | S | |
0.0 | 3.0 | female | 48.0 | 1.0 | 3.0 | W./C. 6608 | 34.375 | S | ||
1.0 | 3.0 | female | 0.0 | 0.0 | 2649 | 7.225 | C | |||
0.0 | 3.0 | male | 25.0 | 0.0 | 0.0 | 349250 | 7.8958 | S | ||
0.0 | 2.0 | male | 19.0 | 1.0 | 1.0 | C.A. 33112 | 36.75 | S | ||
1.0 | 2.0 | female | 22.0 | 1.0 | 2.0 | SC/Paris 2123 | 41.5792 | C | ||
1.0 | 2.0 | female | 6.0 | 0.0 | 1.0 | 248727 | 33.0 | S | ||
0.0 | 1.0 | male | 62.0 | 0.0 | 0.0 | 113514 | 26.55 | C87 | S | |
0.0 | 1.0 | male | 70.0 | 1.0 | 1.0 | WE/P 5735 | 71.0 | B22 | S | |
0.0 | 3.0 | female | 30.0 | 1.0 | 1.0 | 345773 | 24.15 | S | ||
1.0 | 2.0 | female | 21.0 | 0.0 | 0.0 | C.A. 31026 | 10.5 | S | ||
0.0 | 3.0 | male | 61.0 | 0.0 | 0.0 | 345364 | 6.2375 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | S.O./P.P. 751 | 7.55 | S | |||
0.0 | 1.0 | male | 64.0 | 1.0 | 4.0 | 19950 | 263.0 | C23 C25 C27 | S | |
0.0 | 2.0 | male | 32.0 | 0.0 | 0.0 | C.A. 33111 | 10.5 | S | ||
1.0 | 2.0 | female | 28.0 | 1.0 | 0.0 | P/PP 3381 | 24.0 | C | ||
1.0 | 3.0 | female | 45.0 | 0.0 | 0.0 | 2696 | 7.225 | C | ||
0.0 | 3.0 | male | 0.0 | 0.0 | SOTON/OQ 392082 | 8.05 | S | |||
0.0 | 3.0 | male | 30.0 | 0.0 | 0.0 | A.5. 18509 | 8.05 | S | ||
1.0 | 1.0 | female | 14.0 | 1.0 | 2.0 | 113760 | 120.0 | B96 B98 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | S.O./P.P. 251 | 7.55 | S | |||
0.0 | 3.0 | male | 35.0 | 0.0 | 0.0 | 373450 | 8.05 | S | ||
0.0 | 3.0 | male | 19.0 | 0.0 | 0.0 | 349212 | 7.8958 | S | ||
0.0 | 3.0 | male | 26.0 | 1.0 | 0.0 | 2680 | 14.4542 | C | ||
1.0 | 1.0 | female | 1.0 | 0.0 | 17464 | 51.8625 | D21 | S | ||
1.0 | 1.0 | female | 36.0 | 0.0 | 0.0 | PC 17608 | 262.375 | B61 | C | |
1.0 | 3.0 | female | 18.0 | 0.0 | 0.0 | 2657 | 7.2292 | C | ||
0.0 | 2.0 | male | 49.0 | 1.0 | 2.0 | 220845 | 65.0 | S | ||
0.0 | 2.0 | male | 25.0 | 0.0 | 0.0 | C.A. 34050 | 10.5 | S | ||
0.0 | 3.0 | female | 22.0 | 0.0 | 0.0 | 7553 | 9.8375 | S | ||
0.0 | 3.0 | male | 42.0 | 0.0 | 0.0 | C.A. 5547 | 7.55 | S | ||
0.0 | 1.0 | male | 28.5 | 0.0 | 0.0 | PC 17562 | 27.7208 | D43 | C | |
1.0 | 3.0 | male | 31.0 | 0.0 | 0.0 | STON/O 2. 3101288 | 7.925 | S | ||
0.0 | 3.0 | male | 38.5 | 0.0 | 0.0 | SOTON/O.Q. 3101262 | 7.25 | S | ||
0.0 | 3.0 | male | 50.0 | 1.0 | 0.0 | A/5. 3337 | 14.5 | S | ||
0.0 | 3.0 | male | 24.0 | 0.0 | 0.0 | 350409 | 7.8542 | S | ||
0.0 | 3.0 | female | 17.0 | 0.0 | 0.0 | 2627 | 14.4583 | C | ||
1.0 | 1.0 | female | 27.0 | 1.0 | 2.0 | F.C. 12750 | 52.0 | B71 | S | |
0.0 | 3.0 | female | 30.0 | 1.0 | 0.0 | 349910 | 15.55 | S | ||
0.0 | 1.0 | male | 49.0 | 1.0 | 1.0 | 17421 | 110.8833 | C68 | C | |
0.0 | 3.0 | male | 1.0 | 0.0 | 386525 | 16.1 | S | |||
0.0 | 3.0 | male | 0.0 | 0.0 | 349227 | 7.8958 | S | |||
0.0 | 2.0 | male | 0.0 | 0.0 | 240261 | 10.7083 | Q | |||
0.0 | 3.0 | male | 24.5 | 0.0 | 0.0 | 342826 | 8.05 | S | ||
1.0 | 2.0 | male | 2.0 | 1.0 | 1.0 | 230080 | 26.0 | F2 | S | |
1.0 | 1.0 | female | 39.0 | 1.0 | 0.0 | 13507 | 55.9 | E44 | S | |
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 364858 | 7.75 | Q | ||
0.0 | 1.0 | male | 0.0 | 0.0 | PC 17757 | 227.525 | C | |||
0.0 | 3.0 | male | 19.0 | 0.0 | 0.0 | 348124 | 7.65 | F G73 | S | |
0.0 | 1.0 | male | 37.0 | 0.0 | 1.0 | PC 17596 | 29.7 | C118 | C | |
0.0 | 3.0 | male | 8.0 | 2.0 | CA. 2343 | 69.55 | S | |||
0.0 | 2.0 | male | 57.0 | 0.0 | 0.0 | 244346 | 13.0 | S | ||
0.0 | 3.0 | male | 35.0 | 0.0 | 0.0 | STON/O 2. 3101273 | 7.125 | S | ||
1.0 | 1.0 | female | 22.0 | 0.0 | 1.0 | 113505 | 55.0 | E33 | S | |
0.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | 345767 | 9.0 | S | ||
0.0 | 3.0 | male | 29.0 | 0.0 | 0.0 | 7545 | 9.4833 | S | ||
1.0 | 3.0 | male | 45.0 | 0.0 | 0.0 | 7598 | 8.05 | S | ||
0.0 | 3.0 | male | 33.0 | 0.0 | 0.0 | 347465 | 7.8542 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 2631 | 7.225 | C | |||
1.0 | 3.0 | female | 27.0 | 0.0 | 1.0 | 392096 | 12.475 | E121 | S | |
1.0 | 1.0 | female | 60.0 | 1.0 | 0.0 | 110813 | 75.25 | D37 | C | |
1.0 | 2.0 | female | 20.0 | 2.0 | 1.0 | 29105 | 23.0 | S | ||
0.0 | 2.0 | male | 34.0 | 1.0 | 0.0 | 28664 | 21.0 | S | ||
1.0 | 2.0 | male | 32.0 | 1.0 | 0.0 | 2908 | 26.0 | S | ||
0.0 | 3.0 | male | 17.0 | 0.0 | 0.0 | 315095 | 8.6625 | S | ||
0.0 | 1.0 | male | 24.0 | 0.0 | 1.0 | PC 17558 | 247.5208 | B58 B60 | C | |
1.0 | 3.0 | female | 4.0 | 1.0 | 1.0 | PP 9549 | 16.7 | G6 | S | |
1.0 | 3.0 | female | 9.0 | 1.0 | 1.0 | 2650 | 15.2458 | C | ||
0.0 | 2.0 | male | 17.0 | 0.0 | 0.0 | S.O.C. 14879 | 73.5 | S | ||
0.0 | 2.0 | male | 25.0 | 1.0 | 2.0 | SC/Paris 2123 | 41.5792 | C | ||
0.0 | 1.0 | male | 30.0 | 1.0 | 2.0 | 113781 | 151.55 | C22 C26 | S | |
0.0 | 3.0 | male | 40.0 | 1.0 | 6.0 | CA 2144 | 46.9 | S | ||
1.0 | 3.0 | male | 29.0 | 0.0 | 0.0 | 349240 | 7.8958 | C | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 36568 | 15.5 | Q | |||
0.0 | 1.0 | male | 58.0 | 0.0 | 2.0 | 35273 | 113.275 | D48 | C | |
1.0 | 3.0 | male | 3.0 | 1.0 | 1.0 | C.A. 37671 | 15.9 | S | ||
1.0 | 3.0 | female | 15.0 | 0.0 | 0.0 | 330923 | 8.0292 | Q | ||
1.0 | 3.0 | male | 9.0 | 0.0 | 1.0 | C 17368 | 3.1708 | S | ||
0.0 | 1.0 | male | 25.0 | 0.0 | 0.0 | 13905 | 26.0 | C | ||
1.0 | 1.0 | male | 51.0 | 0.0 | 0.0 | 113055 | 26.55 | E17 | S | |
1.0 | 1.0 | female | 18.0 | 1.0 | 0.0 | 113773 | 53.1 | D30 | S | |
0.0 | 1.0 | male | 61.0 | 0.0 | 0.0 | 36963 | 32.3208 | D50 | S | |
0.0 | 3.0 | female | 39.0 | 0.0 | 5.0 | 382652 | 29.125 | Q | ||
0.0 | 1.0 | male | 41.0 | 0.0 | 0.0 | 113054 | 30.5 | A21 | S | |
0.0 | 1.0 | male | 0.0 | 0.0 | PC 17600 | 30.6958 | C | |||
0.0 | 3.0 | male | 2.0 | 4.0 | 1.0 | 382652 | 29.125 | Q | ||
0.0 | 3.0 | female | 29.0 | 1.0 | 1.0 | 347054 | 10.4625 | G6 | S | |
0.0 | 3.0 | male | 0.0 | 0.0 | 349221 | 7.8958 | S | |||
1.0 | 1.0 | male | 36.0 | 1.0 | 2.0 | 113760 | 120.0 | B96 B98 | S | |
1.0 | 3.0 | female | 17.0 | 0.0 | 1.0 | 371362 | 16.1 | S | ||
0.0 | 3.0 | male | 21.0 | 0.0 | 0.0 | 312992 | 7.775 | S | ||
0.0 | 3.0 | male | 0.0 | 0.0 | 323592 | 7.25 | S | |||
1.0 | 3.0 | female | 0.0 | 0.0 | 330980 | 7.8792 | Q | |||
1.0 | 2.0 | female | 19.0 | 0.0 | 0.0 | 28404 | 13.0 | S | ||
1.0 | 3.0 | female | 22.0 | 0.0 | 0.0 | 347085 | 7.775 | S | ||
0.0 | 3.0 | male | 36.0 | 0.0 | 0.0 | 349247 | 7.8958 | S | ||
0.0 | 3.0 | male | 16.0 | 0.0 | 0.0 | A/4. 20589 | 8.05 | S | ||
1.0 | 2.0 | female | 45.0 | 0.0 | 2.0 | 237789 | 30.0 | S | ||
1.0 | 2.0 | female | 28.0 | 0.0 | 0.0 | 230434 | 13.0 | S | ||
1.0 | 3.0 | female | 16.0 | 1.0 | 1.0 | 2625 | 8.5167 | C | ||
0.0 | 3.0 | male | 16.0 | 0.0 | 0.0 | 347074 | 7.775 | S | ||
1.0 | 3.0 | male | 22.0 | 0.0 | 0.0 | 2658 | 7.225 | C | ||
0.0 | 2.0 | male | 63.0 | 1.0 | 0.0 | 24065 | 26.0 | S | ||
0.0 | 3.0 | female | 41.0 | 0.0 | 5.0 | 3101295 | 39.6875 | S | ||
0.0 | 2.0 | male | 34.0 | 1.0 | 0.0 | 226875 | 26.0 | S |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment