gistfile1.txt

# Gather some data that is of interest to you.
# Analyze the data using a scatterplot matrix. List at least 3 non-trivial
#findings about the data, along with plot pictures that show the findings.


### Imports ###
import numpy as np
import pandas as pd
from pandas import Series, DataFrame
import os
os.chdir('/home/edward/workspace/school/datavis')
os.getcwd()
from scipy import stats
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
from numpy.random import randn


#
#I chose the titanic.csv dataset, because the cmda club is using this dataset
#to learn python and data science. We have not begun to use the dataset in the
#club, but when we begin, I will be extremely familiar with it. I talked with
#Dr. Davanloo, and he approved my usage of this dataset for this problem.
#
#Inside the titanic.csv file there are 891 records and there are 12 columns.
#In summary the columns list attributes about the passengers that rode on the
#titanic, as well as, whether or not the passenger survived the wreckage.
#
#The columns of data that I will be focusing on are the following:
#'Survived': 0 if the passenger did not survive, 1 if the passenger survived
#'Pclass': The class of the passenger from third to first class.
#'Age': The age of the passenger
#'Fare': The amount of money the passenger paid for their passage
#
### Data Reading & Cleaning ###

#df = sns.load_dataset("iris")

titanic_df = pd.read_csv('./datafiles/titanic.csv')

cleaned_titanic_df = titanic_df.drop('Name',1).drop('Sex',1).drop('Parch',1).drop('Ticket',1).drop('Cabin',1).drop('Embarked',1)
scatter_matrix(cleaned_titanic_df, alpha=0.5, figsize=(5, 5), diagonal='hist')
### Scatterplot Analysis ###

#This first plot displays the age of the passenger on the y-axis and whether or
#not the passenger survived on the x axis. From this plot, one can observe a
#slight trend where the younger a passenger is, the more likely they are to
#survive the wreckage. This makes sense, since generally passengers let children
#on to the lifeboats first.
sns.lmplot('Survived','Age',titanic_df)

#The second plot displays the passenger class of the passenger on the y-axis and
#whether or not the passenger survived on the x axis. From this plot, one can
#observe a trend where passengers were more likely to survive if they were
#in first class. This makes sense, because third class passengers had their
#sleeping compartments located deeper within the ship, and those compartments
#flooded sooner than the upper compartments
sns.lmplot('Survived','Pclass',titanic_df)

#The second plot displays the ticket fare paid for the passenger on the y-axis and
#whether or not the passenger survived on the x axis. From this plot, one can
#observe a trend where passengers were more likely to survive if they paid
#more money for their ticket. This makes sense, because the amount they paid
#for their ticket likely correlates with what passenger class the passenger was
#in, and so the lower class passengers were more likely to reside in a
#compartment that flooded sooner.
sns.lmplot('Survived','Fare', titanic_df)

plt.show()