Python Data cleaning

The purpose of data cleaning is to improve data quality
Pandas Common data cleaning in Handling of null and missing values Processing of duplicate values Handling of outliers

Null and missing values

• A null value generally indicates that the data is unknown Not applicable or add data later
• Missing values are incomplete values for one or more attributes in the dataset

stay Pandas Provides functions for checking or handling null and missing values ,
among
isnull（ ) and notnull ( ) Function can determine whether there are null and missing values .
For missing data have access to dropna( ) and fillna( ) Method to delete and populate

from pandas import DataFrame ,Series
import pandas as pd
from numpy import NAN
series_obj = Series([1,None,NAN])
pd.isnull(series_obj) # Check Whether it is null or missing 

This code means , Created a Series object , Object contains 1 . None NAN Three values
And then call isnull（） Function check
The first is normal , The last two are missing

notnull( ) function

seeing the name of a thing one thinks of its function Empathy

dropna（） Method

dropna Delete rows and columns with null or missing values

About His grammar

He has four parameters
The first two parameters Is to see whether to delete rows and columns
The last two parameters See the filtering standard