import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from sklearn.ensemble import RandomForestClassifier
train_data = pd.read_csv("/kaggle/input/titanic/train.csv")
test_data = pd.read_csv("/kaggle/input/titanic/test.csv")
train_data.head()
women = train_data.loc[train_data.Sex == 'female']["Survived"]
rate_women = sum(women)/len(women)
print("% of women who survived:", rate_women)
train_data[train_data.Sex == 'male']
men = train_data.loc[train_data.Sex == 'male']["Survived"]
rate_men = sum(men)/len(men)
print("% of men who survived:", rate_men)
target = train_data["Survived"]
features = ["Sex","Parch","SibSp"]
X = pd.get_dummies(train_data[features])
X_test = pd.get_dummies(test_data[features])
model = RandomForestClassifier(n_estimators=100, max_depth=5, random_state=1)
model.fit(X, target)
predictions = model.predict(X_test)
output = pd.DataFrame({"PassengerId": test_data.PassengerId, "Survived": predictions})
output.to_csv("my_submission.csv", index=False)
output.head()
