In [1]:
import numpy as np
import pandas as pd
In [2]:
train_data = pd.read_csv("/content/train.csv")
train_data.head()
Out[2]:
PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked
0 1 0 3 Braund, Mr. Owen Harris male 22.0 1 0 A/5 21171 7.2500 NaN S
1 2 1 1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 0 PC 17599 71.2833 C85 C
2 3 1 3 Heikkinen, Miss. Laina female 26.0 0 0 STON/O2. 3101282 7.9250 NaN S
3 4 1 1 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 0 113803 53.1000 C123 S
4 5 0 3 Allen, Mr. William Henry male 35.0 0 0 373450 8.0500 NaN S
In [3]:
test_data = pd.read_csv("/content/test.csv")
test_data.head()
Out[3]:
PassengerId Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked
0 892 3 Kelly, Mr. James male 34.5 0 0 330911 7.8292 NaN Q
1 893 3 Wilkes, Mrs. James (Ellen Needs) female 47.0 1 0 363272 7.0000 NaN S
2 894 2 Myles, Mr. Thomas Francis male 62.0 0 0 240276 9.6875 NaN Q
3 895 3 Wirz, Mr. Albert male 27.0 0 0 315154 8.6625 NaN S
4 896 3 Hirvonen, Mrs. Alexander (Helga E Lindqvist) female 22.0 1 1 3101298 12.2875 NaN S
In [4]:
women = train_data.loc[train_data.Sex == 'female']["Survived"]
rate_women = sum(women)/len(women)

print("% of women who survived:", rate_women)

% of women who survived: 0.7420382165605095
In [5]:
men = train_data.loc[train_data.Sex == 'male']["Survived"]
rate_men = sum(men)/len(men)
print("% of men who survived:", rate_men)

% of men who survived: 0.18890814558058924
In [6]:
gender_prediction = np.where(test_data.Sex == "female", 1, 0)
gender_output = pd.DataFrame({"PassengerId": test_data.PassengerId, "Survived": gender_prediction})
gender_output.to_csv("gender_submission.csv", index=False)
In [7]:
from sklearn.ensemble import RandomForestClassifier

y = train_data["Survived"]

features = ["Pclass", "Sex", "SibSp", "Parch"]

X = pd.get_dummies(train_data[features])
X_test = pd.get_dummies(test_data[features])

print(X)

     Pclass  SibSp  Parch  Sex_female  Sex_male
0         3      1      0           0         1
1         1      1      0           1         0
2         3      0      0           1         0
3         1      1      0           1         0
4         3      0      0           0         1
..      ...    ...    ...         ...       ...
886       2      0      0           0         1
887       1      0      0           1         0
888       3      1      2           1         0
889       1      0      0           0         1
890       3      0      0           0         1

[891 rows x 5 columns]
In [8]:
model = RandomForestClassifier(n_estimators=100, max_depth=5, random_state=1)
model.fit(X, y)
predictions = model.predict(X_test)

output = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions})
output.to_csv('rfc_submission.csv', index=False)
In [8]: