import numpy as np
import pandas as pd

# Modelling Algorithms
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import RandomForestClassifier , GradientBoostingClassifier

# Modelling Helpers
from sklearn.preprocessing import Imputer , Normalizer , scale
from sklearn.cross_validation import train_test_split , StratifiedKFold
from sklearn.feature_selection import RFECV

# Visualisation
import matplotlib as mpl
import matplotlib.pyplot as plt
import matplotlib.pylab as pylab
import seaborn as sns

#Print you can execute arbitrary python code
train = pd.read_csv("../input/train.csv", dtype={"Age": np.float64}, )
test = pd.read_csv("../input/test.csv", dtype={"Age": np.float64}, )

#Print to standard output, and see the results in the "log" section below after running your script
print("\n\nTop of the training data:")
print(train.head())

print("\n\nSummary statistics of training data")
print(train.describe())

#Any files you save will be available in the output tab below
train.to_csv('copy_of_the_training_data.csv', index=False)
str(train)
full = train.append( test , ignore_index = True )
titanic = full[ :891 ]

del train , test

print ('Datasets:' , 'full:' , full.shape , 'titanic:' , titanic.shape)