titanic_keras.py

import os

import numpy as np
import pandas as pd

from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical

features = ["Pclass", "Sex", "SibSp", "Parch"]
raw_train_data = pd.read_csv("./input/train.csv")
train_data = raw_train_data[features]
# train_data.head()

raw_test_data = pd.read_csv("./input/test.csv")
test_data = raw_test_data[features]
# test_data.head()
y = raw_train_data["Survived"]
d = {'female': 1, 'male': 0}


#one-hotify
train_data["Sex"] = train_data["Sex"].replace(d)
one_hot_pclass = pd.get_dummies(train_data['Pclass'])
train_data = train_data.drop('Pclass', axis = 1)
train_data = train_data.join(one_hot_pclass)

X = pd.get_dummies(train_data)
X_test = pd.get_dummies(test_data)

model = Sequential()

model.add(Dense(32, activation='relu', input_shape=(len(train_data.columns),)))
model.add(Dense(4, activation='relu'))
model.add(Dense(1, activation='relu'))

model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['accuracy'])

model.fit(train_data, y, epochs=25, validation_split=0.4)