Titanic获救的随机森林，集成学习实现

import pandas as pd
import numpy as np




#数据预处理-------------------------------------------------------------------------------------------------------------
DATA = pd.read_csv("titanic_train.csv")
print(DATA.describe())
DATA["Age"] = DATA["Age"].fillna(DATA["Age"].mean())#fillna()函数的用法

DATA.loc[DATA["Sex"] == "male", "Sex"] = 0#str变int
DATA.loc[DATA["Sex"] == "female", "Sex"] = 1

DATA["Embarked"] = DATA["Embarked"].fillna("S")
DATA.loc[DATA["Embarked"] == "S", "Embarked"] = 0
DATA.loc[DATA["Embarked"] == "C", "Embarked"] = 1
DATA.loc[DATA["Embarked"] == "Q", "Embarked"] = 2




#线性回归的预测---------------------------------------------------------------------------------------------------------
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import KFold

predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]
alg = LinearRegression()
kf = KFold(n_splits=3, random_state=1)

predictions = []
for train, test in kf.split(DATA):
    train_predictors = DATA[predictors].iloc[train, :]
    train_target = DATA["Survived"].iloc[train]
    alg.fit(train_predictors.values, train_target.values)
    test_predictions = alg.predict(DATA[predictors].iloc[test, :])
    predictions.append(test_predictions)
predictions = np.concatenate(predictions, axis=0)
predictions[predictions > .5] = 1
predictions[predictions <= .5] = 0
correct = [1 if (a == 1 and b == 1) or (a == 0 and b == 0) else 0 for (a, b) in zip(predictions, DATA["Survived"])]
accuracy = sum(correct) / len(predictions)
print(accuracy)





#逻辑回归的预测------------------------------------------------------------------------------------------------------------------------------------------------------------------
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression

alg = LogisticRegression(random_state=1)
scores = cross_val_score(alg, DATA[predictors], DATA["Survived"], cv=3)
print(scores)
print(scores.mean())

from sklearn.ensemble import RandomForestClassifier

alg = RandomForestClassifier(random_state=1, n_estimators=10, min_samples_split=2, min_samples_leaf=1)
kf = KFold(3, random_state=1)
scores = cross_val_score(alg, DATA[predictors], DATA["Survived"], cv=kf.split(DATA["Survived"]))
print(scores)
print(scores.mean())

alg = RandomForestClassifier(random_state=1, n_estimators=50, min_samples_split=4, min_samples_leaf=2)
kf = KFold(3, random_state=1)
scores = cross_val_score(alg, DATA[predictors], DATA["Survived"], cv=kf.split(DATA["Survived"]))
print(scores)
print(scores.mean())

DATA["FamilySize"] = DATA["SibSp"] + DATA["Parch"]
DATA["NameLength"] = DATA["Name"].apply(lambda x: len(x))







#加入了两个特征-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
import re


def get_title(name):
    title_search = re.search("([A-Za-z]+)\.", name)
    if title_search:
        return title_search.group(1)
    return ""


titles = DATA["Name"].apply(get_title)
print(titles.value_counts())
title_map = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4}
for k, v in title_map.items():
    titles[titles == k] = v


def title_change(name):
    if isinstance(name, str):
        return 0
    else:
        return name


titles = titles.apply(title_change)

DATA["Title"] = titles








#特征选择----------------------------------------------------------------------------------------------------------------------------------------------
from sklearn.feature_selection import SelectKBest, f_classif
import matplotlib.pyplot as plt

predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked", "FamilySize", "Title", "NameLength"]
selector = SelectKBest(f_classif, k=6)
selector.fit(DATA[predictors], DATA["Survived"])
scores = -np.log10(selector.pvalues_)
plt.bar(range(len(predictors)), scores)
plt.xticks(range(len(predictors)), predictors, rotation="vertical")
plt.show()






#随机森林的实现----------------------------------------------------------------------------------------------------------------------
kf = KFold(3, random_state=1)
alg = RandomForestClassifier(random_state=1, n_estimators=30, min_samples_split=8, min_samples_leaf=4)
full_predictions = []
scores = 0
for train, test in kf.split(DATA):
    X_train = DATA[predictors].iloc[train, :]
    Y_train = DATA["Survived"].iloc[train]
    X_test = DATA[predictors].iloc[test, :]
    alg.fit(X_train, Y_train)
    scores += alg.score(DATA[predictors].iloc[test, :], DATA["Survived"].iloc[test])
print(scores / 3)






#集成学习的方法做出预测------------------------------------------------------------------------------------------------------------------------------------------------------
from sklearn.ensemble import GradientBoostingClassifier
import numpy as np

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"]]
]
print(type(algorithms))

kf = KFold(n_splits=3, random_state=1)
predictions = []
for train, test in kf.split(DATA):
    full_test_predictions = []
    y_train = DATA["Survived"].iloc[train]
    for alg, predictors in algorithms:#注意这种取法可以取到第二层列表中的两个值
        X_train = DATA[predictors].iloc[train, :]
        alg.fit(X_train, y_train)
        X_test = DATA[predictors].iloc[test, :]
        test_predictions = alg.predict_proba(X_test.astype(float))[:, 1]#predict_proba函数会返回属于不同类别的proba
        full_test_predictions.append(test_predictions)
    test_predictions = (full_test_predictions[0] + full_test_predictions[1]) / 2
    test_predictions[test_predictions <= .5] = 0
    test_predictions[test_predictions > .5] = 1
    predictions.append(test_predictions)

predictions = np.concatenate(predictions,axis = 0)
correct = [1 if (a == 1 and b == 1) or (a == 0 and b == 0) else 0 for (a, b) in zip(predictions, DATA["Survived"])]
accuracy = sum(correct) / len(predictions)
print(accuracy)

注意取值的时候，DataFrame通过 DATA.loc[DATA[“Embarked”] == “S”, “Embarked”]，即既指定行又指定列
Series通过 titles[titles == k] = v，即可以直接等于
DataFrame只取一列中的某几个值的时候y_train = DATA[“Survived”].iloc[train]，不需要制定列名