from pandas import Series, DataFrame
import pandas as pd

obj = Series([1,2,3,4])
obj.values
obj2 = Series([1,2,3,4], index=['d','c','b','a'])
obj2['a']
obj2[['c','a','b']]

#keep the mapping relationship
obj2[obj2>0]
obj2*2
np.exp(obj2)

sdata = {'a':1, 'b': 11, 'c':111}
obj3 = Series(sdata)
obj4 = Series(sdata, index=['a','b']) #restrict
obj4 = Series(sdata, index=['a','b', 'd']) #NaN

pd.isnull(obj4)
obj4.isnull()
pd.notnull(obj4)

obj3 + obj4

obj3.name = "population" #name

data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],
        'year': [2000, 2001, 2002, 2001, 2002],
                'pop': [1.5, 1.7, 3.6, 2.4, 2.9]}
frame = DataFrame(data)
frame = DataFrame(data, columns=['year','pop','state'])

frame.shape

frame['state']
frame2 = DataFrame(data, columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
frame.ix['three']
frame['year']
frame['debt'] = 11

val = Series([-1.2, -1.5, -1.7], index=['two','four','five'])
frame2['debt'] = val #blank will be set NaN

frame2['eastern'] = frame2.state == 'Ohio'

#如果使用nested dict,则可以不用添加index了..
pop = {'Nevada': {2001: 2.4, 2002: 2.9},
'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}
#!!!!!!!!!mongo的数据正好可以进来!!!!!!

#transerval?
frame2.T

frame['price'].dtype # -> object, can't be describe..
frame['price'].astype('int32').describe()  # it works

df = pd.DataFrame(np.random.randn(10,4))
pieces = [df[:3], df[3:7], df[7:]]
pd.concat(pieces)

pd.merge(left, right, on="Key")

df.append(s, ignore_index=True) #will not change self

sw = frame.groupby('weight')
sw.size() #count of each weight
sw.sum() #sum of each group each column

#multi criteria
frame.loc[(frame.nlp == 0) & (frame.total > 0)]

ts = pd.Series(np.random.randn(1000), 
    index=pd.date_range('1/1/2000', periods = 1000))
ts = ts.cumsum()
ts.plot()

frame.hist(alpha=0.5, bins=100) #or auto