Pandas: Pandas methods like SQL Cheatsheet

DDL
dropna

fillna



df["new_column"] = df.dropna(subset=["old_column"])  -- this will create a new column with no Null.

drop("column_name", axis = "columns")

# using "column_name" as an index
pd.read_csv("csvfile.csv", indx_col = "column_name")

#Good reducing memory usage for column can be catergorize
.astype("category")



read_csv(  ..., parse_dates=["date column"])

DML
select
select distinct
select count(distinct)
sort
select count()
select rank/topN Analysis



Where clause 
isnull/isin between duplicates

where
wildcard like


SQL Update
pd["Column"].str.replace("new_values","old_values")



this works like group by or bobj Break feature

.set_index(keys = ["xxx","yyy"])  

.sort_index()


.drop_duplicates()