The 4 C's of Data Cleaning: 

• Correcting | Nothing

• Completing | Fill, Drop

• Creating | 
  FamilySize, IsAlone, Title, FareBin, AgeBin

• ​Converting | To dummies

Correcting

先不用 XD

Completing

把 Age, Embarked, Fare 補值

把 PassengerId, Cabin, Ticket 丟掉

###COMPLETING: complete or delete missing values in train and test/validation dataset
# data_cleaner 有兩個 dataset: data1, data_val
for dataset in data_cleaner:    
    #complete missing age with median
    dataset['Age'].fillna(dataset['Age'].median(), inplace = True)

    #complete embarked with mode
    dataset['Embarked'].fillna(dataset['Embarked'].mode()[0], inplace = True)

    #complete missing fare with median
    dataset['Fare'].fillna(dataset['Fare'].median(), inplace = True)
    
#delete the cabin feature/column and others previously stated to exclude in train dataset
drop_column = ['PassengerId','Cabin', 'Ticket']
data1.drop(drop_column, axis=1, inplace = True)

print(data1.isnull().sum())
print("-"*10)
print(data_val.isnull().sum())
# 應該都要是零

Creating

###CREATE: Feature Engineering for train and test/validation dataset
for dataset in data_cleaner:    
    #Discrete variables
    dataset['FamilySize'] = dataset ['SibSp'] + dataset['Parch'] + 1

    dataset['IsAlone'] = 1 #initialize to yes/1 is alone
    dataset['IsAlone'].loc[dataset['FamilySize'] > 1] = 0 # now update to no/0 if family size is greater than 1

    #quick and dirty code split title from name: http://www.pythonforbeginners.com/dictionary/python-split
    dataset['Title'] = dataset['Name'].str.split(", ", expand=True)[1].str.split(".", expand=True)[0]


    #Continuous variable bins; qcut vs cut: https://stackoverflow.com/questions/30211923/what-is-the-difference-between-pandas-qcut-and-pandas-cut
    #Fare Bins/Buckets using qcut or frequency bins: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.qcut.html
    dataset['FareBin'] = pd.qcut(dataset['Fare'], 4)

    #Age Bins/Buckets using cut or value bins: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.cut.html
    dataset['AgeBin'] = pd.cut(dataset['Age'].astype(int), 5)


    
#cleanup rare title names
#print(data1['Title'].value_counts())
stat_min = 10 #while small is arbitrary, we'll use the common minimum in statistics: http://nicholasjjackson.com/2012/03/08/sample-size-is-10-a-magic-number/
title_names = (data1['Title'].value_counts() < stat_min) #this will create a true false series with title name as index

#apply and lambda functions are quick and dirty code to find and replace with fewer lines of code: https://community.modeanalytics.com/python/tutorial/pandas-groupby-and-python-lambda-functions/
data1['Title'] = data1['Title'].apply(lambda x: 'Misc' if title_names.loc[x] == True else x)
print(data1['Title'].value_counts())
print("-"*10)


#preview data again
data1.info()
data_val.info()
data1.sample(10)

新增 FamilySize, IsAlone, Title(稱呼), FareBin, AgeBin

Converting

#CONVERT: convert objects to category using Label Encoder for train and test/validation dataset

#code categorical data
label = LabelEncoder()
for dataset in data_cleaner:    
    dataset['Sex_Code'] = label.fit_transform(dataset['Sex'])
    dataset['Embarked_Code'] = label.fit_transform(dataset['Embarked'])
    dataset['Title_Code'] = label.fit_transform(dataset['Title'])
    dataset['AgeBin_Code'] = label.fit_transform(dataset['AgeBin'])
    dataset['FareBin_Code'] = label.fit_transform(dataset['FareBin'])

#define y variable aka target/outcome
Target = ['Survived']

#define x variables for original features aka feature selection
data1_x = ['Sex','Pclass', 'Embarked', 'Title','SibSp', 'Parch', 'Age', 'Fare', 'FamilySize', 'IsAlone'] #pretty name/values for charts
data1_x_calc = ['Sex_Code','Pclass', 'Embarked_Code', 'Title_Code','SibSp', 'Parch', 'Age', 'Fare'] #coded for algorithm calculation
data1_xy =  Target + data1_x
print('Original X Y: ', data1_xy, '\n')

#define x variables for original w/bin features to remove continuous variables
data1_x_bin = ['Sex_Code','Pclass', 'Embarked_Code', 'Title_Code', 'FamilySize', 'AgeBin_Code', 'FareBin_Code']
data1_xy_bin = Target + data1_x_bin
print('Bin X Y: ', data1_xy_bin, '\n')

#define x and y variables for dummy features original
data1_dummy = pd.get_dummies(data1[data1_x])
data1_x_dummy = data1_dummy.columns.tolist()
data1_xy_dummy = Target + data1_x_dummy
print('Dummy X Y: ', data1_xy_dummy, '\n')

data1_dummy.head()