titanic.py

import pandas as pd
import csv as csv
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split, cross_val_score

# load data
train_df = pd.read_csv("train.csv", header=0)

# convert sex to be a dummy val "gender"{male = 0, female = 1}
train_df["Gender"] = train_df["Sex"].map({"male": 0, "female": 1}).astype(int)

# complement the missing values: "age"
median_age = train_df["Age"].dropna().median()
if len(train_df.Age[train_df.Age.isnull()]) > 0:
    train_df.loc[(train_df.Age.isnull()), "Age"] = median_age

# remove unused columns
train_df = train_df.drop(["Name", "Ticket", "Sex", "Embarked",
                          "Fare", "Cabin",
                          "PassengerId"], axis=1)

# load data
test_df = pd.read_csv("test.csv", header=0)

# convert sex to be a dummy val "gender"{male = 0, female = 1}
test_df["Gender"] = test_df["Sex"].map({"male": 0, "female": 1}).astype(int)

# complement the missing values: "age"
median_age = test_df["Age"].dropna().median()
if len(test_df.Age[test_df.Age.isnull()]) > 0:
    test_df.loc[(test_df.Age.isnull()), "Age"] = median_age

# remove unused columns
ids = test_df["PassengerId"].values
test_df = test_df.drop(["Name", "Ticket", "Sex", "Embarked",
                        "Fare", "Cabin",
                        "PassengerId"], axis=1)

train_data = train_df.values
X_train, y_train = train_data[0::, 1::], train_data[0::, 0]
test_data = test_df.values

params = [2**i for i in range(-10, 10)]

best_score = 0
best_params = {}
for gamma in params:
    for C in params:
        svm = SVC(gamma=gamma, C=C)
        scores = cross_val_score(svm, X_train, y_train, cv=5)
        score = np.mean(scores)
        if score > best_score:
            best_score = score
            best_params = {'gamma': gamma, 'C': C}

print(best_score)
print(best_params)

svm = SVC(** best_params)
output = svm.fit(X_train, y_train).predict(test_data).astype(int)

submit_file = open("titanic_submit.csv", 'w')
file_object = csv.writer(submit_file)
file_object.writerow(["PassengerId", "survived"])
file_object.writerows(zip(ids, output))
submit_file.close()