pandas-缺失值处理

import pandas as pd
import numpy as np

# header=0以第一行作为列名
tip = pd.read_csv("lianx.csv",sep=‘,‘,header=0)
tip.head()

a = list(tip.columns)
print(a)
b = []
c = 0
for i in a:
    c= c+1
    if c in [1,4,7,9,11,13,14]:
        b.append(i)
# print(b)
# 删除列
tip = tip.drop(b,axis=1)
tip.head()

c = [‘alcohol‘,‘malic_acid‘,‘alcalinity_of_ash‘,‘magnesium‘,‘flavanoids‘,‘proanthocyanins‘,‘hue‘]
b = list(tip.columns[:7])
b2 = list(tip.columns)
print(b)
print(b2)
d = dict(zip(b,c))
print(d)
tip.rename(columns=d,inplace=True)
tip.head()

#tip.iloc[:3,0]=np.nan
tip.iloc[:3,0]=np.nan
tip.head()

tip[‘alcohol‘] = tip[‘alcohol‘].fillna(10)
tip[‘magnesium‘] = tip[‘magnesium‘].fillna(100)
tip.head()

import random
seven = np.random.randint(0,10,10)
seven

tip.iloc[seven,0]=np.nan
tip.head()

tip.isnull().sum()

tip.dropna()

a = list(tip.index)
b = list(range(len(a)))
c = dict(zip(a,b))
tip.rename(index=c)# 映射操作