Dhruv Kothai and Aadhathmik Varahagiri: Titanic Project

#by Dhruv and Aadhyathmik

from sklearn.linear_model import LinearRegression
from sklearn.feature_selection import RFE
# Compare Algorithms
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

from matplotlib import pyplot
from sklearn.metrics import accuracy_score
from sklearn.model_selection import KFold, train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import LinearRegression
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import AdaBoostClassifier, RandomForestClassifier
import seaborn as sns
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeRegressor, DecisionTreeClassifier
from sklearn.neural_network import MLPClassifier

import warnings

warnings.filterwarnings("ignore")


def sibSpToInt(SibSp):
    if SibSp >= 1:
        SibSp = 'Accompanied'
        return SibSp
    SibSp = 'Alone'
    return SibSp

def ageToInt(age):
    if age < 18:
        age = 1
        return age
    elif age < 38:
        age = 2
        return age
    else:
        age = 3
        return age





cabin_set = set([])

path = '/Users/dhruvk/Desktop/titanic/'
train = pd.read_csv(path + "train.csv")
test = pd.read_csv(path + "test.csv")
submission = pd.read_csv(path + "gender_submission.csv")

df = train
df = df.drop(['Cabin', 'Name', 'Parch', 'Ticket', 'Embarked'], axis=1)
df['Age'] = df['Age'].fillna(df['Age'].median())
df['Age'] = df['Age'].apply(ageToInt)
df['SibSp'] = df['SibSp'].apply(sibSpToInt)
encoded_df = pd.get_dummies(df['SibSp'], prefix='SibSp')
df = pd.concat([df, encoded_df], axis=1)
df = df.drop('SibSp', axis=1)

trainset, testset = train_test_split(df, test_size=0.3, random_state=0)

genderToInt = {'male': 1, 'female': 2}
trainset['Sex'] = trainset['Sex'].map(genderToInt)
testset['Sex'] = testset['Sex'].map(genderToInt)

Y_train = trainset['Survived']
X_train = trainset[['Pclass', 'Sex', 'Age', 'Fare', 'SibSp_Accompanied', 'SibSp_Alone']]
X_test = testset[['Pclass', 'Sex', 'Age', 'Fare', 'SibSp_Accompanied', 'SibSp_Alone']]
Y_test = testset['Survived']

dtreeC = DecisionTreeClassifier()
dtreeC.fit(X_train, Y_train)
y_test1 = dtreeC.predict(X_test)
# print(len(Y_test, y_test))

print("Decision Tree Classifier Accuracy:",accuracy_score(y_test1, Y_test) * 100)

models = []
models.append(("Decision Tree Classifier", dtreeC))

ltree = LogisticRegression()
ltree.fit(X_train, Y_train)
y_test2 = ltree.predict(X_test)

print("Logistic Regression Accuracy:", accuracy_score(y_test2, Y_test) * 100)

models.append(("Logistic Regression", ltree))

ada_clf = AdaBoostClassifier(
    DecisionTreeClassifier(max_depth=5), n_estimators=200,
    algorithm="SAMME.R", learning_rate=.19, random_state=42)
ada_clf.fit(X_train, Y_train)
y_test3 = ada_clf.predict(X_test)

print("Ada Boost Classifier Accuracy:", accuracy_score(y_test3, Y_test) * 100)

models.append(("Ada Boost Classifier", ada_clf))

for depth in [3,4,5, 6]:
    rnd_clf = RandomForestClassifier(n_estimators=500, max_depth=depth, n_jobs=-1, random_state=42)
    rnd_clf.fit(X_train, Y_train)
    y_pred_rf = rnd_clf.predict(X_test)
    print("Random Forest Classifier Depth "+str(depth)+" Accuracy: ", accuracy_score(y_pred_rf, Y_test) * 100)
    models.append(("Random Forest: Depth "+str(depth), rnd_clf))


results = []
names = []
# scoring = 'accuracy'
scoring = 'r2'
for name, model in models:
    kfold = KFold(n_splits=10)  # , random_state=7)
    # kfold = KFold(n_splits=10) #, random_state=None)
    cv_results = cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
    results.append(cv_results)
    names.append(name)
    msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
    print(msg)
# boxplot algorithm comparison
fig = pyplot.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
pyplot.boxplot(results)
ax.set_xticklabels(names)
pyplot.show()