import numpy as np
import pandas as pd
# data analysis and wrangling
import random as rnd

# visualization
import seaborn as sns
import matplotlib.pyplot as plt

# machine learning
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier
#Print you can execute arbitrary python code
train_df = pd.read_csv("../input/train.csv", dtype={"Age": np.float64}, )
test_df = 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_df.head())

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

#Any files you save will be available in the output tab below
train_df.to_csv('copy_of_the_training_data.csv', index=False)
combine = [train_df, test_df]
## Analyze by pivoting features
train_df[['Pclass', 'Survived']].groupby(['Pclass'], as_index=False).mean().sort_values(by='Survived', ascending=False)