决策树、随机森林集成算法（Titanic实例）

#coding:utf-8
import pandas #ipython notebook
titanic = pandas.read_csv("titanic_train.csv")
titanic.head(5)
#print (titanic.describe())
titanic["Age"] = titanic["Age"].fillna(titanic["Age"].median())
print(titanic.describe())

print(titanic["Sex"].unique())#看一下Sex里有几种可能性
#将字符转换成数字
# Replace all the occurences of male with the number 0.
titanic.loc[titanic["Sex"] == "male", "Sex"] = 0
titanic.loc[titanic["Sex"] == "female", "Sex"] = 1
print(titanic["Embarked"].unique())
titanic["Embarked"] = titanic["Embarked"].fillna('S')
titanic.loc[titanic["Embarked"] == "S", "Embarked"] = 0
titanic.loc[titanic["Embarked"] == "C", "Embarked"] = 1
titanic.loc[titanic["Embarked"] == "Q", "Embarked"] = 2



from sklearn.linear_model import LinearRegression
# Sklearn also has a helper that makes it easy to do cross validation
from sklearn.cross_validation import KFold

# The columns we'll use to predict the target我们用来预测目标的列
predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]

# Initialize our algorithm class初始化我们的算法类
alg = LinearRegression()

# Generate cross validation folds for the titanic dataset.  It return the row indices corresponding to train and test.
#为泰坦尼克数据集生成交叉验证折叠。它返回对应于训练和测试的行索引
# We set random_state to ensure we get the same splits every time we run this.
#我们设置随机状态以确保每次运行时都得到相同的分割。
kf = KFold(titanic.shape[0], n_folds=3, random_state=1)

predictions = []
for train, test in kf:#把kf里的前几份当成train，最后一份当成test
    # The predictors we're using the train the algorithm.  Note how we only take the rows in the train folds.
    #我们使用训练的预测器算法，注意我们如何只在训练折叠中取行
    train_predictors = (titanic[predictors].iloc[train,:])
    # The target we're using to train the algorithm.我们用来训练算法的目标
    train_target = titanic["Survived"].iloc[train]
    # Training the algorithm using the predictors and target.使用预测器和目标训练算法。
    alg.fit(train_predictors, train_target)
    # We can now make predictions on the test fold我们现在可以对测试折叠做出预测
    test_predictions = alg.predict(titanic[predictors].iloc[test, :])
    # 这些预测是在三个独立的数字数组中进行的。连接成一个。
    predictions.append(test_predictions)

import numpy as np
#这些预测是在三个独立的数字数组中进行的。连接成一个。
# The predictions are in three separate numpy arrays.  Concatenate them into one.
# We concatenate them on axis 0, as they only have one axis.
#我们将它们连接在轴0上，因为它们只有一个轴。
predictions = np.concatenate(predictions, axis=0)

# Map predictions to outcomes (only possible outcomes are 1 and 0)
#将预测映射到结果（只有可能的结果是1和0）
predictions[predictions > .5] = 1
predictions[predictions <=.5] = 0
#准确率，当[predictions == titanic["Survived"]survived与预测值相等时即预测正确
accuracy = sum(predictions[predictions == titanic["Survived"]]) / len(predictions)
print(accuracy)

#逻辑回归
from sklearn import cross_validation
from sklearn.linear_model import LogisticRegression
# Initialize our algorithm
alg = LogisticRegression(random_state=1)
# Compute the accuracy score for all the cross validation folds.  (much simpler than what we did before!)
scores = cross_validation.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())

#用测试集测试
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

#随机森林
from sklearn import cross_validation
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 ends (the bottom points of the tree)
#决策树10棵，min_samples_leaf=1叶子节点的最小个数为1

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!)
#n_folds=3将训练数据分成三组，两组用于训练，一组用于测试
kf = cross_validation.KFold(titanic.shape[0], n_folds=3, random_state=1)
scores = cross_validation.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())

#对模型进行参数调优
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 = cross_validation.KFold(titanic.shape[0], 3, random_state=1)
scores = cross_validation.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())
#创建两列
# Generating a familysize column
titanic["FamilySize"] = titanic["SibSp"] + titanic["Parch"]
# The .apply method generates a new series
titanic["NameLength"] = titanic["Name"].apply(lambda x: len(x))

import re

# A function to get the title from a name.从名称中获得标题的函数
def get_title(name):
    #使用正则表达式搜索标题。标题总是由大写字母和小写字母组成，以句号结尾。
    # Use a regular expression to search for a title.  Titles always consist of capital and lowercase letters, and end with a period.
    title_search = re.search(' ([A-Za-z]+)\.', name)
    # If the title exists, extract and return it.如果标题存在，提取并返回它
    if title_search:
        return title_search.group(1)
    return ""
#获取所有的标题并打印每一个的频率
titles = titanic["Name"].apply(get_title)
#value_counts返回的是该titles对象中独一无二的元素的个数
print(pandas.value_counts(titles))
#将每个标题映射到一个整数。有些标题非常少见，并且被压缩成与其他标题相同的代码。
# Map each title to an integer.  Some titles are very rare, and are compressed into the same codes as other titles.
title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Dr": 5, "Rev": 6, "Major": 7, "Col": 7, "Mlle": 8, "Mme": 8, "Don": 9, "Lady": 10, "Countess": 10, "Jonkheer": 10, "Sir": 9, "Capt": 7, "Ms": 2}
for k,v in title_mapping.items():
    titles[titles == k] = v
print(pandas.value_counts(titles))

# Add in the title column.添加标题栏
titanic["Title"] = titles

#观察特征的重要性
import numpy as np
from sklearn.feature_selection import SelectKBest, f_classif
import matplotlib.pyplot as plt
predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked", "FamilySize", "Title", "NameLength"]

# Perform feature selection进行特征选择
selector = SelectKBest(f_classif, k=5)
selector.fit(titanic[predictors], titanic["Survived"])
#
# Get the raw p-values for each feature, and transform from p-values into scores
scores = -np.log10(selector.pvalues_)

# Plot the scores.  See how "Pclass", "Sex", "Title", and "Fare" are the best?
plt.bar(range(len(predictors)), scores)
plt.xticks(range(len(predictors)), predictors, rotation='vertical')
plt.show()

# Pick only the four best features.
predictors = ["Pclass", "Sex", "Fare", "Title"]

alg = RandomForestClassifier(random_state=1, n_estimators=50, min_samples_split=8, min_samples_leaf=4)
from sklearn.ensemble import GradientBoostingClassifier
import numpy as np

# The algorithms we want to ensemble.
# We're using the more linear predictors for the logistic regression, and everything with the gradient boosting classifier.
algorithms = [
    [GradientBoostingClassifier(random_state=1, n_estimators=25, max_depth=3), ["Pclass", "Sex", "Age", "Fare", "Embarked", "FamilySize", "Title",]],
    [LogisticRegression(random_state=1), ["Pclass", "Sex", "Fare", "FamilySize", "Title", "Age", "Embarked"]]
]

# Initialize the cross validation folds
kf = KFold(titanic.shape[0], n_folds=3, random_state=1)

predictions = []
for train, test in kf:
    train_target = titanic["Survived"].iloc[train]
    full_test_predictions = []
    # Make predictions for each algorithm on each fold
    for alg, predictors in algorithms:
        # Fit the algorithm on the training data.
        alg.fit(titanic[predictors].iloc[train, :], train_target)
        # Select and predict on the test fold.
        # The .astype(float) is necessary to convert the dataframe to all floats and avoid an sklearn error.
        test_predictions = alg.predict_proba(titanic[predictors].iloc[test, :].astype(float))[:, 1]
        full_test_predictions.append(test_predictions)
    # Use a simple ensembling scheme -- just average the predictions to get the final classification.
    #使用一个简单的组合方案——只是平均预测来得到最终的分类。
    test_predictions = (full_test_predictions[0] + full_test_predictions[1]) / 2
    # Any value over .5 is assumed to be a 1 prediction, and below .5 is a 0 prediction.
    #任何超过0.5的值都被认为是一个1的预测，而低于0.5是一个0的预测。
    test_predictions[test_predictions <= .5] = 0
    test_predictions[test_predictions > .5] = 1
    predictions.append(test_predictions)

# Put all the predictions together into one array.
predictions = np.concatenate(predictions, axis=0)

# Compute accuracy by comparing to the training data.
accuracy = sum(predictions[predictions == titanic["Survived"]]) / len(predictions)
print(accuracy)