数据缺失的处理

1. 直接删除：对于一个条目下数据大部分缺损可以直接删除。
2. 插值 ：使用估算值填充缺失的部分，前提缺失不能太多。
3. 插值扩展：插值后增加加一列条目说明填充位置。

数据读取

import pandas as pd
from sklearn.model_selection import train_test_split

# Load the data
data = pd.read_csv('../input/melbourne-housing-snapshot/melb_data.csv')

# Select target
y = data.Price

# To keep things simple, we'll use only numerical predictors
melb_predictors = data.drop(['Price'], axis=1)
X = melb_predictors.select_dtypes(exclude=['object'])

# Divide data into training and validation subsets
X_train, X_valid, y_train, y_valid = train_test_split(X, y, train_size=0.8, test_size=0.2,
                                                      random_state=0)

from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error

# Function for comparing different approaches
def score_dataset(X_train, X_valid, y_train, y_valid):
    model = RandomForestRegressor(n_estimators=10, random_state=0)
    model.fit(X_train, y_train)
    preds = model.predict(X_valid)
    return mean_absolute_error(y_valid, preds)

1. 直接删除

# Get names of columns with missing values
cols_with_missing = [col for col in X_train.columns
                     if X_train[col].isnull().any()]
# cols_with_missing  = ['Car', 'BuildingArea', 'YearBuilt']
# X_train[col].isnull().any() 表示列中有至少一个空值存在

# Drop columns in training and validation data
reduced_X_train = X_train.drop(cols_with_missing, axis=1)
reduced_X_valid = X_valid.drop(cols_with_missing, axis=1)

print("MAE from Approach 1 (Drop columns with missing values):")
print(score_dataset(reduced_X_train, reduced_X_valid, y_train, y_valid))

2. 插值

from sklearn.impute import SimpleImputer

# SimpleImputer模块默认平均插值
my_imputer = SimpleImputer()
imputed_X_train = pd.DataFrame(my_imputer.fit_transform(X_train))
imputed_X_valid = pd.DataFrame(my_imputer.transform(X_valid))

# imputed_X_train.columns为 0,1,2... ,需替换
imputed_X_train.columns = X_train.columns
imputed_X_valid.columns = X_valid.columns

print("MAE from Approach 2 (Imputation):")
print(score_dataset(imputed_X_train, imputed_X_valid, y_train, y_valid))

（其他）
通俗地讲清楚fit_transform()和transform()的区别
中位数插值
SimpleImputer(strategy=‘median’)

插值扩展

# Make copy to avoid changing original data (when imputing)
X_train_plus = X_train.copy()
X_valid_plus = X_valid.copy()

# Make new columns indicating what will be imputed
for col in cols_with_missing:
    X_train_plus[col + '_was_missing'] = X_train_plus[col].isnull()
    X_valid_plus[col + '_was_missing'] = X_valid_plus[col].isnull()

# Imputation
my_imputer = SimpleImputer()
imputed_X_train_plus = pd.DataFrame(my_imputer.fit_transform(X_train_plus))
imputed_X_valid_plus = pd.DataFrame(my_imputer.transform(X_valid_plus))

# Imputation removed column names; put them back
imputed_X_train_plus.columns = X_train_plus.columns
imputed_X_valid_plus.columns = X_valid_plus.columns

print("MAE from Approach 3 (An Extension to Imputation):")
print(score_dataset(imputed_X_train_plus, imputed_X_valid_plus, y_train, y_valid))

X_valid_plus

技巧

计算缺失数

X_train.isnull().sum()