Kaggle Module

Kaggle ML Project

This script introduces the first use of csv and numpy to manipulate the dataset of the Kaggle Titanic Project.

• I want first to read the datas,
• then to use them to compute some statistics about the datas,
• and also use them to plot some graphics : on the Plot_*.py files,

---

About

This script is still in development. The reference page here on Kaggle.

Documentation

The doc is available on-line, on one of my own pages :

• on the cr@ns network besson/publis/kaggle/,
• on the CS department at ENS de Cachan ~lbesson/publis/kaggle/,

Copyrigths

(c) Avril-Mai 2013 By Lilian BESSON, ENS de Cachan (M1 Mathematics & M1 Computer Science MPRI) mailto:lbesson@ens-cachan.fr

Kaggle.csv_file_object = <_csv.reader object at 0x38b1910>

Load in the csv file

Kaggle.data = array([['0', '3', 'Braund, Mr. Owen Harris', ..., '7.25', '', 'S'], ['1', '1', 'Cumings, Mrs. John Bradley (Florence Briggs Thayer)', ..., '71.2833', 'C85', 'C'], ['1', '3', 'Heikkinen, Miss. Laina', ..., '7.925', '', 'S'], ..., ['0', '3', 'Johnston, Miss. Catherine Helen "Carrie"', ..., '23.45', '', 'S'], ['1', '1', 'Behr, Mr. Karl Howell', ..., '30', 'C148', 'C'], ['0', '3', 'Dooley, Mr. Patrick', ..., '7.75', '', 'Q']], dtype='|S82')

Then convert from a list to an array

Kaggle.names_columns_train = ['survived', 'pclass', 'name', 'sex', 'age', 'sibsp', 'parch', 'ticket', 'fare', 'cabin', 'embarked']

Nom des attributs.

Kaggle.survived = 0

ce qu’on veut réussir à prédire !

Kaggle.pclass = 1

moyenne + influence, cf Plot_pclass.py

Kaggle.name = 2

aucune influence ?

Kaggle.sex = 3

grande influence, cf Plot_gender.py

Kaggle.age = 4

moyenne influence, cf Plot_age.py

Kaggle.sibsp = 5

moyenne + influence, cf Plot_sibsp.py

Kaggle.parch = 6

moyenne + influence, cf Plot_parch.py

Kaggle.ticket = 7

complexe: numéro du ticket

Kaggle.fare = 8

grande influence, cf Plot_fare.py

Kaggle.cabin = 9

complexe: localisation dans le bateau

Kaggle.embarked = 10

moyenne - influence, cf Plot_port.py

Kaggle.number_passengers = 891

Nombre de données d’apprentissage

Kaggle.number_survived = 342.0

Nombre de survivants

Kaggle.number_dead = 549.0

Nombre de victimes

Kaggle.proportion_survivors = 0.38383838383838381

Proportion de survivants

Kaggle.proportion_women = 0.35241301907968575

Proportion de femmes

Kaggle.proportion_women_survived = 0.7420382165605095

Proportion de femmes ayant survécues

Kaggle.proportion_men = 0.6475869809203143

Proportion d’hommes

Kaggle.proportion_men_survived = 0.18890814558058924

Proportion d’hommes ayant survécus

Kaggle.proportion_s_survived = 0.33695652173913043

Proportion de survivants dans les passagers venant de Southampton

Kaggle.proportion_c_survived = 0.5535714285714286

Proportion de survivants dans les passagers venant de Cherbourg

Kaggle.proportion_q_survived = 0.38961038961038963

Proportion de survivants dans les passagers venant de Queenstown

Kaggle.proportion_known_ages = 0.8013468013468014

On ne connais pas l’âge de tous les passagers

Kaggle.age_min = 0.41999999999999998

Age minimum

Kaggle.age_max = 80.0

Age max

Kaggle.age_mean = 29.69911764705882

Age moyen, utilisé pour compléter les données

Kaggle.fare_min = 0.0

Prix min

Kaggle.fare_max = 512.32920000000001

Prix max

Kaggle.fare_mean = 32.2042079685746

Prix moyen, utilisé pour compléter les données

Kaggle.header = ['pclass', 'name', 'sex', 'age', 'sibsp', 'parch', 'ticket', 'fare', 'cabin', 'embarked']

Skip the fist line as it is a header