# 用随机森林对缺失值预测填充函数
def set_missing(df):
# 把已有的数值型特征取出来
process_df = df.ix[:,[变量]]
# 分成已知该特征和未知该特征两部分
known = process_df[process_df.变量.notnull()].as_matrix()
unknown = process_df[process_df.变量.isnull()].as_matrix()
# X为特征属性值
X = known[:, 1:]
# y为结果标签值
y = known[:, 0]
# fit到RandomForestRegressor之中
rfr = RandomForestRegressor(random_state=0, n_estimators=200,max_depth=3,n_jobs=-1)
rfr.fit(X,y)
# 用得到的模型进行未知特征值预测
predicted = rfr.predict(unknown[:, 1:]).round(0)
print(predicted)
# 用得到的预测结果填补原缺失数据
df.loc[(df.变量.isnull()), '变量'] = predicted
return df
