Kaggle入门之泰塔尼克之灾

#导入包
#Pandas
import pandas as pd
from pandas import Series,DataFrame

#Numpy,Matplotlib
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

train_df = pd.read_csv("train.csv")
test_df = pd.read_csv("test.csv")
train_df.info()
print("========我是分割线============")
test_df.info()

#对训练数据进行补全 ---> Embraked
train_df.Embarked.fillna("S")
#plot
sns.factorplot(‘Embarked‘,‘Survived‘,data = train_df,size=4,aspect=3)
#新学习一种画图的方法
fig,(axis1,axis2,axis3) = plt.subplots(1,3,figsize=(15,5))


sns.factorplot(‘Embarked‘,data = train_df,kind=‘count‘,order=[‘S‘,‘C‘,‘Q‘],ax=axis1)
sns.factorplot(‘Survived‘,hue=‘Embarked‘,data = train_df,kind=‘count‘,order=[‘1‘,‘0‘],ax=axis2)


embarked_perc = train_df[["Embarked","Survived"]].groupby(["Embarked"],as_index=False).mean()
sns.barplot(x=‘Embarked‘,y=‘Survived‘,data=embarked_perc,order=[‘S‘,‘C‘,‘Q‘],ax=axis3)
plt.show()
#简单来看C港口登船的生存率更高

#Fare的补全
test_df["Fare"].fillna(test_df["Fare"].median(), inplace=True)

#转换成int格式
train_df.Fare = train_df.Fare.astype(int)
test_df.Fare = test_df.Fare.astype(int)
fare_not_survived = train_df.Fare[train_df.Survived == 0]
fare_survived = train_df.Fare[train_df.Survived == 1]
#查看有无Fare对是否生存的影响
average_fare = DataFrame([fare_not_survived.mean(),fare_survived.mean()])
std_fare = DataFrame([fare_not_survived.std(),fare_survived.std()])
train_df[‘Fare‘].plot(kind=‘hist‘, figsize=(15,3),bins=100, xlim=(0,50))

average_fare.index.names = std_fare.index.names = ["Survived"]
average_fare.plot(yerr=std_fare,kind=‘bar‘,legend=False)
plt.show()

#年龄的补足和可视化
#方法一
fig,(axis1,axis2) = plt.subplots(1,2,figsize=(15,4))
axis1.set_title(‘Original Age values - Titanic‘)
axis2.set_title(‘New Age values - Titanic‘)
average_age_titanic   = train_df["Age"].mean()
std_age_titanic       = train_df["Age"].std()
count_nan_age_titanic = train_df["Age"].isnull().sum()


average_age_test   = test_df["Age"].mean()
std_age_test       = test_df["Age"].std()
count_nan_age_test = test_df["Age"].isnull().sum()

rand_1 = np.random.randint(average_age_titanic - std_age_titanic, average_age_titanic + std_age_titanic, size = count_nan_age_titanic)
rand_2 = np.random.randint(average_age_test - std_age_test, average_age_test + std_age_test, size = count_nan_age_test)

train_df[‘Age‘].dropna().astype(int).hist(bins=70, ax=axis1)

train_df["Age"][np.isnan(train_df["Age"])] = rand_1
test_df["Age"][np.isnan(test_df["Age"])] = rand_2

train_df[‘Age‘] = train_df[‘Age‘].astype(int)
test_df[‘Age‘]    = test_df[‘Age‘].astype(int)
plt.show()

#年龄和生存的关系
facet = sns.FacetGrid(train_df,hue=‘Survived‘,aspect =4)
facet.map(sns.kdeplot,‘Age‘,shade = True)
facet.set(xlim=(0,train_df.Age.max()))
facet.add_legend()
fig, axis1 = plt.subplots(1,1,figsize=(18,4))
average_age = train_df[["Age", "Survived"]].groupby([‘Age‘],as_index=False).mean()
sns.barplot(x=‘Age‘, y=‘Survived‘, data=average_age)
plt.show()

#Pclass对生存的影响
sns.factorplot(‘Pclass‘,‘Survived‘,order = [1,2,3],data=train_df,size=5)
plt.show()

#从年龄看生存率
for i in range(100):
    g = train_df.Name[train_df.Age<i]
    rate = g[train_df.Survived==1].count()/g.count()
    print(i,":",rate)

#采用随机森林补充Age
def age_filled(df):
    age_df = df[["Age","Pclass","SibSp","Fare","Parch"]]
    know_age = age_df[age_df.Age.notnull()].as_matrix()
    unknow_age = age_df[age_df.Age.isnull()].as_matrix()
    
    X = know_age[:,1:]
    y = know_age[:,0]
    rfr = rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs = -1)
    rfr.fit(X,y)
    predict_age = rfr.predict(unknow_age[:,1:])
    df.loc[ (df.Age.isnull()), ‘Age‘ ] = predict_age
    return df

#Age 的补全
age_filled(train_df)
age_filled(test_df)

#按照有没有Cabin分为Yes和No
def cabin_filled(df):
    df.loc[(df.Cabin.isnull()),‘Cabin‘] = "No"
    df.loc[(df.Cabin.notnull()),‘Cabin‘] = "Yes"
    return df

#Cabin的补全
cabin_filled(train_df)
cabin_filled(test_df)

2）为了方便建模，把一些属性因子化。

dummies_Cabin = pd.get_dummies(train_df[‘Cabin‘], prefix= ‘Cabin‘)

dummies_Embarked = pd.get_dummies(train_df[‘Embarked‘], prefix= ‘Embarked‘)

dummies_Sex = pd.get_dummies(train_df[‘Sex‘], prefix= ‘Sex‘)

dummies_Pclass = pd.get_dummies(train_df[‘Pclass‘], prefix= ‘Pclass‘)

df = pd.concat([train_df, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df.drop([‘Pclass‘, ‘Sex‘, ‘Cabin‘, ‘Embarked‘], axis=1, inplace=True)

3）Age和Fare正则化方便跑模型。[    缩放到  [-1,1]   ]

import sklearn.preprocessing as preprocessing
age_df = df[["Age"]]      #注意爽括号，否则会报reshape的错误
fare_df = df[["Fare"]]
scaler = preprocessing.StandardScaler()
age_scale_param = scaler.fit(age_df)
df[‘Age_scaled‘] = scaler.fit_transform(age_df, age_scale_param)
fare_scale_param = scaler.fit(fare_df)
df[‘Fare_scaled‘] = scaler.fit_transform(fare_df, fare_scale_param)

到这里，基本的数据处理完成（对test的处理略去，过程相同）

4）开始跑基础模型，采用RandomForestRegressor

#使用随机森林法建模
from sklearn import linear_model

# 用正则取出我们要的属性值
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

test = df_test.filter(regex=‘Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*‘)
predictions = clf.predict(test)


#看属性
pd.DataFrame({"columns":list(train_df.columns)[1:], "coef":list(clf.coef_.T)})

5）提交

submission = pd.DataFrame({
        "PassengerId": df_test["PassengerId"],
        "Survived": predictions
    })
submission.to_csv(‘titanic.csv‘, index=False)

到这里基础的模型完成。第一次提交排名到6K+，接下来就是对模型的进一步优化。