泰坦尼克号之灾分析

# data analysis and wrangling
import pandas as pd
import numpy as np
import random as rnd

# visualization
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

# machine learning
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier

train_df = pd.read_csv(‘../input/train.csv‘)
test_df = pd.read_csv(‘../input/test.csv‘)
combine = [train_df, test_df]

print(train_df.columns.values)

# preview the data
train_df.head()

train_df.info()
print(‘_‘*40)
test_df.info()

train_df.describe()
# Review survived rate using `percentiles=[.61, .62]` knowing our problem description mentions 38% survival rate.
# Review Parch distribution using `percentiles=[.75, .8]`
# SibSp distribution `[.68, .69]`
# Age and Fare `[.1, .2, .3, .4, .5, .6, .7, .8, .9, .99]`

train_df.describe(include=[‘O‘]) #参数O代表只列出object类型的列

//as_index参数为false时输出表格为SQL的风格
train_df[[‘Pclass‘, ‘Survived‘]].groupby([‘Pclass‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)

train_df[["Sex", "Survived"]].groupby([‘Sex‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)

train_df[["SibSp", "Survived"]].groupby([‘SibSp‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)

train_df[["Parch", "Survived"]].groupby([‘Parch‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)

g = sns.FacetGrid(train_df, col=‘Survived‘)
g.map(plt.hist, ‘Age‘, bins=20)

#grid = sns.FacetGrid(train_df, col=‘Pclass‘, hue=‘Survived‘)
grid = sns.FacetGrid(train_df, col=‘Survived‘, row=‘Pclass‘, size=2.2, aspect=1.6)
grid.map(plt.hist, ‘Age‘, alpha=.5, bins=20)
grid.add_legend();

grid = sns.FacetGrid(train_df, col=‘Embarked‘)
#grid = sns.FacetGrid(train_df, row=‘Embarked‘, size=2.2, aspect=1.6)
grid.map(sns.pointplot, ‘Pclass‘, ‘Survived‘, ‘Sex‘, palette=‘deep‘)
grid.add_legend()

grid = sns.FacetGrid(train_df, col=‘Embarked‘, hue=‘Survived‘)
#grid = sns.FacetGrid(train_df, row=‘Embarked‘, col=‘Survived‘, size=2.2, aspect=1.6)
grid.map(sns.barplot, ‘Sex‘, ‘Fare‘, alpha=.5, ci=None)
grid.add_legend()

print("Before", train_df.shape, test_df.shape, combine[0].shape, combine[1].shape)

train_df = train_df.drop([‘Ticket‘, ‘Cabin‘], axis=1)
test_df = test_df.drop([‘Ticket‘, ‘Cabin‘], axis=1)
combine = [train_df, test_df]

print("After", train_df.shape, test_df.shape, combine[0].shape, combine[1].shape)

for dataset in combine:
    dataset[‘Title‘] = dataset.Name.str.extract(‘ ([A-Za-z]+)\.‘, expand=False) # 参数expand=false 标志返回一个df

pd.crosstab(train_df[‘Title‘], train_df[‘Sex‘])

for dataset in combine:
    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‘)
    
train_df[[‘Title‘, ‘Survived‘]].groupby([‘Title‘], as_index=False).mean()

title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5}
for dataset in combine:
    dataset[‘Title‘] = dataset[‘Title‘].map(title_mapping)
    dataset[‘Title‘] = dataset[‘Title‘].fillna(0)

train_df.head()

train_df = train_df.drop([‘Name‘, ‘PassengerId‘], axis=1)
test_df = test_df.drop([‘Name‘], axis=1)
combine = [train_df, test_df]
train_df.shape, test_df.shape

for dataset in combine:
    dataset[‘Sex‘] = dataset[‘Sex‘].map( {‘female‘: 1, ‘male‘: 0} ).astype(int)

train_df.head()

#grid = sns.FacetGrid(train_df, col=‘Pclass‘, hue=‘Gender‘)
grid = sns.FacetGrid(train_df, row=‘Pclass‘, col=‘Sex‘, size=2.2, aspect=1.6)
grid.map(plt.hist, ‘Age‘, alpha=.5, bins=20)
grid.add_legend()

guess_ages = np.zeros((2,3))

for dataset in combine:
    for i in range(0, 2):
        for j in range(0, 3):
            guess_df = dataset[(dataset[‘Sex‘] == i) &                                   (dataset[‘Pclass‘] == j+1)][‘Age‘].dropna()

            # age_mean = guess_df.mean()
            # age_std = guess_df.std()
            # age_guess = rnd.uniform(age_mean - age_std, age_mean + age_std)

            age_guess = guess_df.median()

            # Convert random age float to nearest .5 age
            guess_ages[i,j] = int( age_guess/0.5 + 0.5 ) * 0.5
            
    for i in range(0, 2):
        for j in range(0, 3):
            dataset.loc[ (dataset.Age.isnull()) & (dataset.Sex == i) & (dataset.Pclass == j+1),                    ‘Age‘] = guess_ages[i,j]

    dataset[‘Age‘] = dataset[‘Age‘].astype(int)

train_df.head()

train_df[‘AgeBand‘] = pd.cut(train_df[‘Age‘], 5) #把Age列等间隔分成5个区间
train_df[[‘AgeBand‘, ‘Survived‘]].groupby([‘AgeBand‘], as_index=False).mean().sort_values(by=‘AgeBand‘, ascending=True)

for dataset in combine:    
    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‘]
train_df.head()

train_df = train_df.drop([‘AgeBand‘], axis=1)
combine = [train_df, test_df]
train_df.head()

for dataset in combine:
    dataset[‘FamilySize‘] = dataset[‘SibSp‘] + dataset[‘Parch‘] + 1

train_df[[‘FamilySize‘, ‘Survived‘]].groupby([‘FamilySize‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)

for dataset in combine:
    dataset[‘IsAlone‘] = 0
    dataset.loc[dataset[‘FamilySize‘] == 1, ‘IsAlone‘] = 1

train_df[[‘IsAlone‘, ‘Survived‘]].groupby([‘IsAlone‘], as_index=False).mean()

train_df = train_df.drop([‘Parch‘, ‘SibSp‘, ‘FamilySize‘], axis=1)
test_df = test_df.drop([‘Parch‘, ‘SibSp‘, ‘FamilySize‘], axis=1)
combine = [train_df, test_df]

train_df.head()

for dataset in combine:
    dataset[‘Age*Class‘] = dataset.Age * dataset.Pclass

train_df.loc[:, [‘Age*Class‘, ‘Age‘, ‘Pclass‘]].head(10)

freq_port = train_df.Embarked.dropna().mode()[0]
freq_port # ‘S‘

for dataset in combine:
    dataset[‘Embarked‘] = dataset[‘Embarked‘].fillna(freq_port)
    
train_df[[‘Embarked‘, ‘Survived‘]].groupby([‘Embarked‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)