数据缺失值处理
In [1]:
import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestRegressor,RandomForestClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.impute import SimpleImputer
In [2]:
df = pd.DataFrame()
df['x0'] = [1,2,3,4,5,np.nan]
df['x1'] = [np.nan,7,8,1,2,5]
df
Out[2]:
x0 x1
0 1.0 NaN
1 2.0 7.0
2 3.0 8.0
3 4.0 1.0
4 5.0 2.0
5 NaN 5.0
删除
In [3]:
df_new = df.dropna()
df_new
Out[3]:
x0 x1
1 2.0 7.0
2 3.0 8.0
3 4.0 1.0
4 5.0 2.0
填补
统计法
利用其它行或列的数据的均值，中位数或总和来补全缺失值In [4]:
df_new = df.copy()
df_new['x0'] = df_new['x0'].fillna(df_new['x0'].mean())
df_new['x1'] = df_new['x1'].fillna(df_new['x1'].median())
#df_new['x1'] = df_new['x1'].fillna(df_new['x1'].sum())
df_new
Out[4]:
x0 x1
0 1.0 5.0
1 2.0 7.0
2 3.0 8.0
3 4.0 1.0
4 5.0 2.0
5 3.0 5.0
取均值不算上空值的个数In [5]:
df_new = np.array(df)
mean_imputer = SimpleImputer(strategy='mean')
mean_imputer = mean_imputer.fit(df_new)
imputed_df = mean_imputer.transform(df_new)
print(imputed_df)
[[1. 4.6][2. 7. ][3. 8. ][4. 1. ][5. 2. ][3. 5. ]]
聚类法
利用无监督机器学习的聚类方法。通过K均值的聚类方法将所有样本进行聚类划分，然后再通过划分的种类的均值对各自类中的缺失值进行填补。归其本质还是通过找相似来填补缺失值。In [6]:
# TODO
模型法
使用其它变量训练模型来预测缺失值： 随机森林In [7]:
age_df = pd.DataFrame()
age_df['age'] = [np.nan,7,8,9,np.nan,6,6,7,9]
age_df['height'] = [1,2,3,4,3,1,1,2,4]
age_df
Out[7]:
age height
0 NaN 1
1 7.0 2
2 8.0 3
3 9.0 4
4 NaN 3
5 6.0 1
6 6.0 1
7 7.0 2
8 9.0 4
In [8]:
known_age = age_df[age_df.age.notnull()].values
unknown_age = age_df[age_df.age.isnull()].values
unknown_age
Out[8]:
array([[nan, 1.],[nan, 3.]])
In [9]:
X = known_age[:, 1:]
y = known_age[:, 0]
In [10]:
rfr = RandomForestClassifier(random_state=0, n_estimators=2000, n_jobs=-1)
#rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1)
rfr.fit(X, y)
Out[10]:
RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',max_depth=None, max_features='auto', max_leaf_nodes=None,min_impurity_decrease=0.0, min_impurity_split=None,min_samples_leaf=1, min_samples_split=2,min_weight_fraction_leaf=0.0, n_estimators=2000,n_jobs=-1, oob_score=False, random_state=0, verbose=0,warm_start=False)
In [11]:
predictedAges = rfr.predict(unknown_age[:, 1:])
age_df["new_age"] = age_df["age"]
age_df.loc[(age_df.age.isnull()), 'new_age' ] = predictedAges
age_df
Out[11]:
age height new_age
0 NaN 1 6.0
1 7.0 2 7.0
2 8.0 3 8.0
3 9.0 4 9.0
4 NaN 3 8.0
5 6.0 1 6.0
6 6.0 1 6.0
7 7.0 2 7.0
8 9.0 4 9.0
)
