泰坦尼克号生还预测 第3关：特征工程与生还预测_泰坦尼克号生还预测头歌答案

头歌学习平台

ps：如果出现时间超时，多提交几遍就好。

import pandas as pd
import numpy as np
import sklearn
#********* Begin *********#
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import RandomForestRegressor
titanic = pd.read_csv('./train.csv')
def set_missing_ages(df):
    age_df = df[['Age', 'Fare', 'Parch', 'SibSp', 'Pclass']]
    known_age = age_df[age_df.Age.notnull()].values
    unknown_age = age_df[age_df.Age.isnull()].values
    y = known_age[:, 0]
    X = known_age[:, 1:]
    rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1)
    rfr.fit(X, y)
    predictedAges = rfr.predict(unknown_age[:, 1::])
    df.loc[(df.Age.isnull()), 'Age'] = predictedAges
    return df
titanic = set_missing_ages(titanic)
dummies_Embarked = pd.get_dummies(titanic['Embarked'], prefix= 'Embarked')
dummies_Sex = pd.get_dummies(titanic['Sex'], prefix= 'Sex')
dummies_Pclass = pd.get_dummies(titanic['Pclass'], prefix= 'Pclass')
df = pd.concat([titanic, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)
train_label = df['Survived']
train_titanic = df.drop('Survived', 1)
titanic_test = pd.read_csv('./test.csv')
titanic_test = set_missing_ages(titanic_test)
dummies_Embarked = pd.get_dummies(titanic_test['Embarked'], prefix= 'Embarked')
dummies_Sex = pd.get_dummies(titanic_test['Sex'], prefix= 'Sex')
dummies_Pclass = pd.get_dummies(titanic_test['Pclass'], prefix= 'Pclass')
df_test = pd.concat([titanic_test,dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df_test.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)
model = RandomForestClassifier(n_estimators=10)
model.fit(train_titanic, train_label)
predictions = model.predict(df_test)
result = pd.DataFrame({'Survived':predictions.astype(np.int32)})
result.to_csv("./predict.csv", index=False)
#********* End *********#