python pandas
pandas data structure
Series: one-dimension array, similar to python list, but only can storage same type of data.
Time-Series: index as time series.
DataFrame: two-dimension tablet data structure, similar to R data.frame.
Panel: three-dimension array, container of DataFrame.
install pandas
pip3 install pandas
cookbook of pandas
ipython
import pandas as pd
from pandas import Series
s = Series([1,4,'ww','tt'])
s.index
//check the index of series
s.values
//check the value of series
s2 = Series(['Wang','man',24], index=['name','sex','age'])
//define index of series
s2
sd = {'python':9000, 'c':9001, 'c#':9000}
s3 = Series(sd)
//another method to define series
s4 = Series(sd, index=['java','c++','c#'])
pd.isnull(s4)
//check the value whether null or not
s4.isnull()
//check the object whether null or not
from pandas import Series.DataFrame
data = {"name":['google','baidu','yahoo'], "marks":[100,200,300], "price":[1,2,3]}
f1 = DataFrame(data)
// define DataFrame based on dict
f1
f2 = DataFrame(data, columns=['name','price','marks'])
f2
f3 = DataFrame(data, columns=['name','price','marks'], index=['a','b','c'])
f3
newdata = {'lang':{'first':'python','second':'java'}, 'price':{'first':5000,'second':2000}}
f4 = DataFrame(newdata)
f4
//define index for columns and rows
f3['name']