#import numpy as np
#import pandas as pd

##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)

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

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

# 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

train_df = pd.read_csv('../input/train.csv')
test_df = pd.read_csv('../input/test.csv')
combine = [train_df, test_df]

#print("Before", train_df.shape, test_df.shape, combine[0].shape, combine[1].shape)

train_df = train_df.drop(['Ticket', 'Cabin'], axis=1)
test_df = test_df.drop(['Ticket', 'Cabin'], axis=1)
combine = [train_df, test_df]

#print("After", train_df.shape, test_df.shape, combine[0].shape, combine[1].shape)


for dataset in combine:
    dataset['Title'] = dataset.Name.str.extract(' ([A-Za-z]+)\.', expand=False)

#pd.crosstab(train_df['Title'], train_df['Sex'])


for dataset in combine:
    dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',\
 	'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')

    dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')
    
#print(train_df[['Title', 'Survived']].groupby(['Title'], as_index=False).mean())


title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5}
for dataset in combine:
    dataset['Title'] = dataset['Title'].map(title_mapping)
    dataset['Title'] = dataset['Title'].fillna(0)

#print(train_df.head())


train_df = train_df.drop(['Name', 'PassengerId'], axis=1)
test_df = test_df.drop(['Name'], axis=1)
combine = [train_df, test_df]
#print(train_df.shape, test_df.shape)


for dataset in combine:
    dataset['Sex'] = dataset['Sex'].map( {'female': 1, 'male': 0} ).astype(int)

#print(train_df.head(6))


guess_ages = np.zeros((2,3))
#print(guess_ages)


for dataset in combine:
    for i in range(0, 2):
        for j in range(0, 3):
            guess_df = dataset[(dataset['Sex'] == i) & \
                                  (dataset['Pclass'] == j+1)]['Age'].dropna()

            # age_mean = guess_df.mean()
            # age_std = guess_df.std()
            # age_guess = rnd.uniform(age_mean - age_std, age_mean + age_std)

            age_guess = guess_df.median()

            # Convert random age float to nearest .5 age
            guess_ages[i,j] = int( age_guess/0.5 + 0.5 ) * 0.5
            
    for i in range(0, 2):
        for j in range(0, 3):
            dataset.loc[ (dataset.Age.isnull()) & (dataset.Sex == i) & (dataset.Pclass == j+1),\
                    'Age'] = guess_ages[i,j]

    dataset['Age'] = dataset['Age'].astype(int)

#print(train_df.head(6))


train_df['AgeBand'] = pd.cut(train_df['Age'], 5)
#print(train_df[['AgeBand', 'Survived']].groupby(['AgeBand'], as_index=False).mean().sort_values(by='AgeBand', ascending=True))


for dataset in combine:    
    dataset.loc[ dataset['Age'] <= 16, 'Age'] = 0
    dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 32), 'Age'] = 1
    dataset.loc[(dataset['Age'] > 32) & (dataset['Age'] <= 48), 'Age'] = 2
    dataset.loc[(dataset['Age'] > 48) & (dataset['Age'] <= 64), 'Age'] = 3
    dataset.loc[ dataset['Age'] > 64, 'Age'] = 4
#print(train_df.head())


train_df = train_df.drop(['AgeBand'], axis=1)
combine = [train_df, test_df]
#print(train_df.head())


for dataset in combine:
    dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch'] + 1

#print(train_df[['FamilySize', 'Survived']].groupby(['FamilySize'], as_index=False).mean().sort_values(by='Survived', ascending=False))


for dataset in combine:
    dataset['IsAlone'] = 0
    dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1

#print(train_df[['IsAlone', 'Survived']].groupby(['IsAlone'], as_index=False).mean())

train_df = train_df.drop(['Parch', 'SibSp', 'FamilySize'], axis=1)
test_df = test_df.drop(['Parch', 'SibSp', 'FamilySize'], axis=1)
combine = [train_df, test_df]

#print(train_df.head())


for dataset in combine:
    dataset['Age*Class'] = dataset.Age * dataset.Pclass

#print(train_df.loc[:, ['Age*Class', 'Age', 'Pclass']].head(10))


freq_port = train_df.Embarked.dropna().mode()[0]
#print(freq_port)

for dataset in combine:
    dataset['Embarked'] = dataset['Embarked'].fillna(freq_port)
    
#print(train_df[['Embarked', 'Survived']].groupby(['Embarked'], as_index=False).mean().sort_values(by='Survived', ascending=False))


for dataset in combine:
    dataset['Embarked'] = dataset['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)

#print(train_df.head())


test_df['Fare'].fillna(test_df['Fare'].dropna().median(), inplace=True)
#print(test_df.head())


train_df['FareBand'] = pd.qcut(train_df['Fare'], 4)
#print(train_df[['FareBand', 'Survived']].groupby(['FareBand'], as_index=False).mean().sort_values(by='FareBand', ascending=True))


for dataset in combine:
    dataset.loc[ dataset['Fare'] <= 7.91, 'Fare'] = 0
    dataset.loc[(dataset['Fare'] > 7.91) & (dataset['Fare'] <= 14.454), 'Fare'] = 1
    dataset.loc[(dataset['Fare'] > 14.454) & (dataset['Fare'] <= 31), 'Fare']   = 2
    dataset.loc[ dataset['Fare'] > 31, 'Fare'] = 3
    dataset['Fare'] = dataset['Fare'].astype(int)

train_df = train_df.drop(['FareBand'], axis=1)
combine = [train_df, test_df]
    
print(train_df.head(10))
print(test_df.head(10))


X_train = train_df.drop("Survived", axis=1)
Y_train = train_df["Survived"]
X_test  = test_df.drop("PassengerId", axis=1).copy()
#print(X_train.shape, Y_train.shape, X_test.shape)


logreg = LogisticRegression()
logreg.fit(X_train, Y_train)
Y_pred = logreg.predict(X_test)
acc_log = round(logreg.score(X_train, Y_train)*100, 2)
#print("Logistic regression: ", acc_log)


coeff_df = pd.DataFrame(train_df.columns.delete(0))
coeff_df.columns = ['Feature']
coeff_df["Correlation"] = pd.Series(logreg.coef_[0])

#print (coeff_df.sort_values(by='Correlation', ascending=False))


svc = SVC()
svc.fit(X_train, Y_train)
Y_pred = svc.predict(X_test)
acc_svc = round(svc.score(X_train, Y_train) * 100, 2)
#print("SVC: ",acc_svc)


knn = KNeighborsClassifier(n_neighbors = 3)
knn.fit(X_train, Y_train)
Y_pred = knn.predict(X_test)
acc_knn = round(knn.score(X_train, Y_train) * 100, 2)
#print("k-Nearest Neighbours: ", acc_knn)


gaussian = GaussianNB()
gaussian.fit(X_train, Y_train)
Y_pred = gaussian.predict(X_test)
acc_gaussian = round(gaussian.score(X_train, Y_train) * 100, 2)
#print("Gaussian Naive Bayes: ",acc_gaussian)


perceptron = Perceptron()
perceptron.fit(X_train, Y_train)
Y_pred = perceptron.predict(X_test)
acc_perceptron = round(perceptron.score(X_train, Y_train) * 100, 2)
#print("Perceptron: ",acc_perceptron)


linear_svc = LinearSVC()
linear_svc.fit(X_train, Y_train)
Y_pred = linear_svc.predict(X_test)
acc_linear_svc = round(linear_svc.score(X_train, Y_train) * 100, 2)
#print("Linear SVC: ", acc_linear_svc)


sgd = SGDClassifier()
sgd.fit(X_train, Y_train)
Y_pred = sgd.predict(X_test)
acc_sgd = round(sgd.score(X_train, Y_train) * 100, 2)
#print("Stochastic Gradient Descent: ",acc_sgd)


decision_tree = DecisionTreeClassifier()
decision_tree.fit(X_train, Y_train)
Y_pred = decision_tree.predict(X_test)
acc_decision_tree = round(decision_tree.score(X_train, Y_train) * 100, 2)
#print("Desicion tree: ", acc_decision_tree)


random_forest = RandomForestClassifier(n_estimators=100)
random_forest.fit(X_train, Y_train)
Y_pred = random_forest.predict(X_test)
random_forest.score(X_train, Y_train)
acc_random_forest = round(random_forest.score(X_train, Y_train) * 100, 2)
#print("Random Forest: ", acc_random_forest)


models = pd.DataFrame({
    'Model': ['Support Vector Machines', 'KNN', 'Logistic Regression', 
              'Random Forest', 'Naive Bayes', 'Perceptron', 
              'Stochastic Gradient Decent', 'Linear SVC', 
              'Decision Tree', 'SVC'],
    'Score': [acc_svc, acc_knn, acc_log, 
              acc_random_forest, acc_gaussian, acc_perceptron, 
              acc_sgd, acc_linear_svc, acc_decision_tree, acc_svc]})
print(models.sort_values(by='Score', ascending=False))


submission = pd.DataFrame({
        "PassengerId": test_df["PassengerId"],
        "Survived": Y_pred
    })
    
print(submission.head())
submission.to_csv('../output/submission.csv', index=False)