Python数据分析与机器学习-泰坦尼克获救预测

源码下载地址：

http://download.csdn.net/download/adam_zs/10189986

import pandas as pd  # pandas数据分析数据处理库

pd.set_option('display.height', 1000)
pd.set_option('display.max_rows', 1000)
pd.set_option('display.max_columns', 1000)
pd.set_option('display.width', 1000)

titanic = pd.read_csv("titanic_train.csv")
'''
PassengerId 乘客id
Survived 是否获救，0未获救，1获救
Pclass 仓位等级
Name 姓名
Sex 性别
Age 年龄
SibSp 多少兄弟姐妹一起的
Parch 老人和孩子
Ticket 票号
Fare 票价
Cabin 座位号
Embarked 上船地点
'''
titanic["Age"] = titanic["Age"].fillna(titanic["Age"].median())
# median 返回给定数值的中值，中值是在一组数值中居于中间的数值
# fillna对缺失值进行填充
'''
mean 平均
std 标准差
'''

# 把性别转换为0,1
titanic.loc[titanic["Sex"] == "male", "Sex"] = 0
titanic.loc[titanic["Sex"] == "female", "Sex"] = 1

# 把上船地点转换为0,1,2
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

'''线性回归'''
from sklearn.linear_model import LinearRegression
from sklearn.cross_validation import KFold

predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]
alg = LinearRegression()
kf = KFold(titanic.shape[0], n_folds=3, random_state=1)

predictions = []
for train, test in kf:
    # print(train)  # 297-890 | 0-296 594-890 | 0-593
    # print(test)  # 0-296 | 297-593 | 594-890
    X_train = titanic[predictors].iloc[train, :]
    y_train = titanic["Survived"].iloc[train]
    alg.fit(X_train, y_train)
    X_test = titanic[predictors].iloc[test, :]
    y_test = alg.predict(X_test)
    predictions.append(y_test)

import numpy as np

predictions = np.concatenate(predictions)
predictions[predictions > .5] = 1
predictions[predictions <= .5] = 0

accuracy = sum(predictions[predictions == titanic["Survived"]]) / len(predictions)
print(accuracy)

'''逻辑回归'''
from sklearn.linear_model import LogisticRegression
from sklearn import cross_validation

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

'''随机森林(优先考虑)'''
from sklearn.ensemble import RandomForestClassifier

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

alg = RandomForestClassifier(random_state=1, n_estimators=10, min_samples_split=2, min_samples_leaf=1)
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)
print("RandomForestClassifier-1:", scores.mean())

'''调节参数'''
alg = RandomForestClassifier(random_state=1, n_estimators=500, min_samples_split=4, min_samples_leaf=2)
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)
print("RandomForestClassifier-2:", scores.mean())

'''完善数据信息'''
# 家里所有成员的人数
titanic["FamilySize"] = titanic["SibSp"] + titanic["Parch"]
# 名字的长度
titanic["NameLength"] = titanic["Name"].apply(lambda x: len(x))

import re


def get_title(name):
    '''从名字中提取出来称谓'''
    name_title = re.search(' ([A-Za-z]+)\.', name)
    if name_title:
        return name_title.group(1)
    return ""


titles = titanic["Name"].apply(get_title)
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
titanic["Title"] = titles

'''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"]
selector = SelectKBest(f_classif)
selector.fit(titanic[predictors], titanic["Survived"])
scores = -np.log10(selector.pvalues_)

plt.bar(range(len(predictors)), scores)
plt.xticks(range(len(predictors)), predictors, rotation="45")
plt.show()

'''只用最重要的属性'''
predictors = ["Pclass", "Sex", "Fare", "Title"]
alg = RandomForestClassifier(random_state=1, n_estimators=500, min_samples_split=4, min_samples_leaf=2)
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)
print("RandomForestClassifier-3:", scores.mean())

# Boosting算法、逻辑回归
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"]]
]

kf = KFold(titanic.shape[0], n_folds=3, random_state=1)
predictions = []
for train, test in kf:
    full_test_predictions = []
    y_train = titanic["Survived"].iloc[train]
    for alg, predictors in algorithms:
        X_train = titanic[predictors].iloc[train, :]
        alg.fit(X_train, y_train)
        X_test = titanic[predictors].iloc[test, :]
        test_predictions = alg.predict_proba(X_test.astype(float))[:, 1]
        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)
accuracy = sum(predictions[predictions == titanic["Survived"]]) / len(predictions)
print(accuracy)