数据分析（三）

这篇将前面的内容写成.py文件，对各个机器学习算法的正确率进行评估，然后选择具有较高正确率的算法生成模型。
这篇只是作者对sklearn库学习过后的简单的应用，之后会更深入的去学习。

第一个代码主要是将数据进行整理，变成前文说的形式。

titanic1.py

import pandas as pd
import numpy as np
import re


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


def data_cleaning():
    train = pd.read_csv('train.csv', header=0, dtype={'Age': np.float64})
    test = pd.read_csv('test.csv', header=0, dtype={'Age': np.float64})
    full_data = [train, test]

    title_mapping = {"Mr": 3, "Miss": 2, "Mrs": 4, "Master": 1, "Rare": 5}

    for dataset in full_data:
        dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch'] + 1
        dataset['IsAlone'] = 0
        dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1

        dataset['Embarked'] = dataset['Embarked'].fillna('S')

        dataset['Title'] = dataset['Name'].apply(get_title)
        dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess', 'Capt', 'Col', \
                                                     'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')
        dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
        dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
        dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')
        dataset['Title'] = dataset['Title'].map(title_mapping)
        dataset['Title'] = dataset['Title'].fillna(0)

    for dataset in full_data:
        age_avg = dataset.groupby('Title').Age.mean()
        age_std = dataset.groupby('Title').Age.std()
        for i in range(1, 6):
            dataset.loc[(dataset.Age.isnull()) & (dataset.Title == i), 'Age'] = np.random.randint(
                age_avg[i] - age_std[i], age_avg[i] + age_std[i])

        fare_avg = dataset.Fare.mean()
        dataset.loc[(dataset.Fare.isnull()), 'Fare'] = fare_avg
        dataset['Age'] = dataset['Age'].astype(int)
        dataset['Fare'] = dataset['Fare'].astype(int)

    for dataset in full_data:
        dataset.loc[dataset['Age'] <= 16, 'Age'] = 0
        dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 32), 'Age'] = 1
        dataset.loc[(dataset['Age'] > 32) & (dataset['Age'] <= 48), 'Age'] = 2
        dataset.loc[(dataset['Age'] > 48) & (dataset['Age'] <= 64), 'Age'] = 3
        dataset.loc[dataset['Age'] > 64, 'Age'] = 4

        dataset.loc[dataset['Fare'] <= 7.91, 'Fare'] = 0
        dataset.loc[(dataset['Fare'] > 7.91) & (dataset['Fare'] <= 14.454), 'Fare'] = 1
        dataset.loc[(dataset['Fare'] > 14.454) & (dataset['Fare'] <= 31), 'Fare'] = 2
        dataset.loc[dataset['Fare'] > 31, 'Fare'] = 3

    train = train.drop(['Name', 'Ticket', 'Cabin', 'SibSp', 'FamilySize', 'Parch', 'PassengerId'], axis=1)
    train = pd.get_dummies(train, columns=["Embarked", "Sex"])
    test = test.drop(['Name', 'Ticket', 'Cabin', 'SibSp', 'FamilySize', 'Parch'], axis=1)
    test = pd.get_dummies(test, columns=["Embarked", "Sex"])

    return train, test


train, test = data_cleaning()

if __name__ == "__main__":
    print(train.head())
    print(test.head())

下面是对各个机器学习算法的效果的评估，代码来自Kaggle

titanic2.py

from sklearn.model_selection import StratifiedShuffleSplit
from sklearn.metrics import accuracy_score
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
from sklearn.linear_model import LogisticRegression

import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
from titanic1 import train
import warnings

warnings.filterwarnings("ignore")

classifiers = [
    KNeighborsClassifier(3),
    SVC(probability=True),
    DecisionTreeClassifier(),
    RandomForestClassifier(),
    AdaBoostClassifier(),
    GradientBoostingClassifier(),
    GaussianNB(),
    LinearDiscriminantAnalysis(),
    QuadraticDiscriminantAnalysis(),
    LogisticRegression()]

log_cols = ["Classifier", "Accuracy"]
log = pd.DataFrame(columns=log_cols)

sss = StratifiedShuffleSplit(n_splits=10, test_size=0.1, random_state=0)

train = train.values
X = train[0::, 1::]
y = train[0::, 0]

acc_dict = {}

for train_index, test_index in sss.split(X, y):
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]

    for clf in classifiers:
        name = clf.__class__.__name__
        clf.fit(X_train, y_train)
        train_predictions = clf.predict(X_test)
        acc = accuracy_score(y_test, train_predictions)
        if name in acc_dict:
            acc_dict[name] += acc
        else:
            acc_dict[name] = acc

for clf in acc_dict:
    acc_dict[clf] = acc_dict[clf] / 10.0
    log_entry = pd.DataFrame([[clf, acc_dict[clf]]], columns=log_cols)
    log = log.append(log_entry)

if __name__ == "__main__":
    plt.figure()
    plt.xlabel('Accuracy')
    plt.title('Classifier Accuracy')

    sns.set_color_codes("muted")
    sns.barplot(x='Accuracy', y='Classifier', data=log, color="b")
    plt.show()

SVC的准确率较高，就它了。

titanic3.py

import numpy as np
import pandas as pd
from titanic1 import train, test
from sklearn.svm import SVC

train = train.values
X = train[0::, 1::]
y = train[0::, 0]

test = test.values
real_test = test[0::, 1::]

clf = SVC(probability=True)
clf.fit(X, y)
predictions = clf.predict(real_test)
result = pd.DataFrame({'PassengerId': test[0::, 0],  'Survived': predictions.astype(np.int32)})
result.to_csv("predictions.csv", index=False)

将生成的csv文件提交就可以看到成绩了。这里只用了sklearn的SVC，并没有做更进一步的优化，我第一次提交排在2000多名，所以，努力学习，再接再厉。