In [80]:
#https://github.com/HanXiaoyang/Kaggle_Titanic/blob/master/Titanic.ipynb
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
In [81]:
data_train = pd.read_csv("train.csv")
print (data_train.describe())
In [82]:
from sklearn.ensemble import RandomForestRegressor
### 使用 RandomForestClassifier 填补缺失的年龄属性
def set_missing_ages(df):
# 把已有的数值型特征取出来丢进Random Forest Regressor中
age_df = df[['Age','Fare', 'Parch', 'SibSp', 'Pclass']]
# 乘客分成已知年龄和未知年龄两部分
known_age = age_df[age_df.Age.notnull()].as_matrix()
unknown_age = age_df[age_df.Age.isnull()].as_matrix()
# y即目标年龄
y = known_age[:, 0]
# X即特征属性值
X = known_age[:, 1:]
# fit到RandomForestRegressor之中
rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1)
rfr.fit(X, y)
# 用得到的模型进行未知年龄结果预测
predictedAges = rfr.predict(unknown_age[:, 1::])
# 用得到的预测结果填补原缺失数据
df.loc[ (df.Age.isnull()), 'Age' ] = predictedAges
return df, rfr
def set_Cabin_type(df):
df.loc[ (df.Cabin.notnull()), 'Cabin' ] = "Yes"
df.loc[ (df.Cabin.isnull()), 'Cabin' ] = "No"
return df
data_train, rfr = set_missing_ages(data_train)
data_train = set_Cabin_type(data_train)
In [83]:
dummies_Cabin = pd.get_dummies(data_train['Cabin'], prefix= 'Cabin')
dummies_Embarked = pd.get_dummies(data_train['Embarked'], prefix= 'Embarked')
dummies_Sex = pd.get_dummies(data_train['Sex'], prefix= 'Sex')
dummies_Pclass = pd.get_dummies(data_train['Pclass'], prefix= 'Pclass')
df = pd.concat([data_train, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)
df
Out[83]:
In [84]:
# 接下来我们要接着做一些数据预处理的工作，比如scaling，将一些变化幅度较大的特征化到[-1,1]之内
# 这样可以加速logistic regression的收敛
'''
import sklearn.preprocessing as preprocessing
scaler = preprocessing.StandardScaler()
age_scale_param = scaler.fit(df['Age'])
age_scale_param
df['Age_scaled'] = scaler.fit_transform(df['Age'], age_scale_param)
fare_scale_param = scaler.fit(df['Fare'])
df['Fare_scaled'] = scaler.fit_transform(df['Fare'], fare_scale_param)
df
'''
Out[84]:
In [85]:
# 我们把需要的feature字段取出来，转成numpy格式，使用scikit-learn中的LogisticRegression建模
from sklearn import linear_model
train_df = df.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
train_np = train_df.as_matrix()
# y即Survival结果
y = train_np[:, 0]
# X即特征属性值
X = train_np[:, 1:]
# fit到RandomForestRegressor之中
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
clf.fit(X, y)
clf
Out[85]:
In [86]:
data_test = pd.read_csv("test.csv")
data_test.loc[ (data_test.Fare.isnull()), 'Fare' ] = 0
# 接着我们对test_data做和train_data中一致的特征变换
# 首先用同样的RandomForestRegressor模型填上丢失的年龄
tmp_df = data_test[['Age','Fare', 'Parch', 'SibSp', 'Pclass']]
null_age = tmp_df[data_test.Age.isnull()].as_matrix()
# 根据特征属性X预测年龄并补上
X = null_age[:, 1:]
predictedAges = rfr.predict(X)
data_test.loc[ (data_test.Age.isnull()), 'Age' ] = predictedAges
data_test = set_Cabin_type(data_test)
dummies_Cabin = pd.get_dummies(data_test['Cabin'], prefix= 'Cabin')
dummies_Embarked = pd.get_dummies(data_test['Embarked'], prefix= 'Embarked')
dummies_Sex = pd.get_dummies(data_test['Sex'], prefix= 'Sex')
dummies_Pclass = pd.get_dummies(data_test['Pclass'], prefix= 'Pclass')
df_test = pd.concat([data_test, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df_test.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)
#df_test['Age_scaled'] = scaler.fit_transform(df_test['Age'], age_scale_param)
#df_test['Fare_scaled'] = scaler.fit_transform(df_test['Fare'], fare_scale_param)
df_test
Out[86]:
In [87]:
test = df_test.filter(regex='Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
predictions = clf.predict(test)
result = pd.DataFrame({'PassengerId':data_test['PassengerId'].as_matrix(), 'Survived':predictions.astype(np.int32)})
result.to_csv("logistic_regression_predictions.csv", index=False)
In [88]:
# validation
#predicted_home_prices = melbourne_model.predict(val_x)
#print mean_absolute_error(val_y,predicted_home_prices)
In [ ]: