import pandas

# 读取数据集
titanic = pandas.read_csv('titanic_train.csv')
titanic.head(10)

# Age 缺失值填充
titanic['Age'] = titanic['Age'].fillna(titanic['Age'].median())
print(titanic.describe())

# print(titanic['Sex'].unique())

# Replace all the occurences of male with the number 0.
# 用数字0替换所有出现的男性。
titanic.loc[titanic["Sex"] == "male", "Sex"] = 0
titanic.loc[titanic["Sex"] == "female", "Sex"] = 1

# print(titanic['Embarked'].unique())

# Embarked：上船港口，有三个取值，C/S/Q，是文字形式，不利于分析，
# 故可能需要映射到数值的值，而且有2个缺失值
titanic['Embarked'] = titanic['Embarked'].fillna('S') # 缺失值填充为这一列的众数'S'
titanic.loc[titanic["Embarked"] == "S", "Embarked"] = 0
titanic.loc[titanic["Embarked"] == "C", "Embarked"] = 1
titanic.loc[titanic["Embarked"] == "Q", "Embarked"] = 2

# Import the linear regression(回归) class
# 注意不要导错库 
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import KFold

# The columns we'll use to predict the target
predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']

# Initialize our algorithm class
alg = LinearRegression()

# Generate cross validation folds for the titanic dataset. It return the row indices
# corresponding(相应的) to train and test.
# 为Titanic数据集生成交叉验证折叠。它返回与训练和测试相对应的行索引。
# We set random_state to ensure we get the same splits every time we run this.
# kf = KFold(titanic.shape[0], n_folds=3, random_state=1) 写法错误已被弃用

# 样本平均分成3份，3折交叉验证
kf = KFold(n_splits=3,shuffle=False, random_state=1)

# 注意这里不是kf.split(titanic.shape[0])，会报如下错误：
# Singleton array array(891) cannot be considered a valid collection.

predictions = []
# 交叉验证 划分训练集 验证集
for train, test in  kf.split(titanic):
    # The predictors we're using the train the algorithm. Note how we only take
    # the rows in the train folds
    # 注意我们只得到训练集的rows
    train_predictors = titanic[predictors].iloc[train, :]
    # The target we're using to train the algorithm.
    train_target = titanic['Survived'].iloc[train]
    # Training the algorithm using the predictors and target
    alg.fit(train_predictors, train_target)
    # We can now make predictions on the test fold
    test_predictions = alg.predict(titanic[predictors].iloc[test, :])
    predictions.append(test_predictions)

import numpy as np

# The predictions are in three separate numpy arrays. Concatenate them into one.
# We concatenate them on asix 0, as they only have one axis.
predictions = np.concatenate(predictions,axis=0)

# Map predictions to outcomes (only possible outcomes are 1 and 0)
predictions[predictions > .5] = 1  # 映射成分类结果 计算准确率
predictions[predictions <= .5] = 0

# 注意这一行与源代码有出入
accuracy = sum(predictions==titanic['Survived'])/len(predictions)

# 验证集的准确率 
print(accuracy)

from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression

alg = LogisticRegression(random_state=1)
# Compute the accuracy score for all the cross validation folds,
# (much simper than what we did before!)
scores = cross_val_score(alg, titanic[predictors], titanic["Survived"], cv=3)
# Take the mean of the scores (because we have one for each fold)
print(scores.mean())

titanic_test = pandas.read_csv("test.csv")
titanic_test["Age"] = titanic_test["Age"].fillna(titanic["Age"].median())
titanic_test["Fare"] = titanic_test["Fare"].fillna(titanic_test["Fare"].median())
titanic_test.loc[titanic_test["Sex"] == "male", "Sex"] = 0 
titanic_test.loc[titanic_test["Sex"] == "female", "Sex"] = 1
titanic_test["Embarked"] = titanic_test["Embarked"].fillna("S")

titanic_test.loc[titanic_test["Embarked"] == "S", "Embarked"] = 0
titanic_test.loc[titanic_test["Embarked"] == "C", "Embarked"] = 1
titanic_test.loc[titanic_test["Embarked"] == "Q", "Embarked"] = 2

from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.ensemble import RandomForestClassifier

predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]

# Initialize our algorithm with the default paramters
# n_estimators is the number of trees we want to make
# min_samples_split is the minimum number of rows we need to make a split
# min_samples_leaf is the minimum number of samples we can have at the place where a
# tree branch(分支) ends (the bottom points of the tree)
alg = RandomForestClassifier(random_state=1,
                             n_estimators=10,
                             min_samples_split=2,
                             min_samples_leaf=1)
# Compute the accuracy score for all the cross validation folds.  (much simpler than what we did before!)
kf = KFold(n_splits=3, shuffle=False, random_state=1)
scores = cross_val_score(alg, titanic[predictors], titanic["Survived"], cv=kf)

# Take the mean of the scores (because we have one for each fold)
print(scores.mean())

alg = RandomForestClassifier(random_state=1,
                             n_estimators=100,
                             min_samples_split=4,
                             min_samples_leaf=2)
# Compute the accuracy score for all the cross validation folds.  (much simpler than what we did before!)
kf = KFold(n_splits=3, shuffle=False, random_state=1)
scores = cross_val_score(alg, titanic[predictors], titanic["Survived"], cv=kf)

# Take the mean of the scores (because we have one for each fold)
print(scores.mean())