import pandas as pd
import numpy as np
data = {"ID":[202001, 202002, 202003, 202004, 202005, 202006, 202007, 202008, 202009, 202010],
       "Chinese":[98, 67, 84, 88, 78, 90, 93, np.nan, 82, 87],
       "Math":[92, 80, 73, np.nan, 88, 78, 90, 82, 77, 69],
       "English":[88, 79, 90, 73, 79, 83, 81, np.nan, 71, np.nan]
       }
df = pd.DataFrame(data)
df

df.isnull().values.any()

df.isnull().sum().any()

df.isnull().sum()

all_data_na = (df.isnull().sum()/len(df))*100
all_data_na = all_data_na.drop(all_data_na[all_data_na == 0].index).sort_values(ascending=False)
missing_data = pd.DataFrame({'缺失率' : all_data_na})
missing_data

df.info()

df.shape[0] - df.isnull().sum()

df.notnull().sum()

# 用上下平均值填充English
df['English'] = df['English'].fillna(df['English'].interpolate())
df.head(10)

# 用中位數填充value列：
df['Math'] = df['Math'].fillna(df['Math'].median())
df.head(10)

# 用-1填充Chinese列：
df['Chinese'] = df['Chinese'].fillna(-1)
df.head(10)