
import numpy as np
import pandas as pd


pd.Series([1., 2., 3.], index=['a', 'b', 'c'])

a    1.0
b    2.0
c    3.0
dtype: float64


pd.Series([1,2,np.nan])

0    1.0
1    2.0
2    NaN
dtype: float64


## Numpy to pandas
import numpy as np
h = [[1,2],[3,4]] 
df_h = pd.DataFrame(h)
print('Data Frame:', df_h)

Data Frame:    0  1
0  1  2
1  3  4


## Pandas to numpy
df_h_n = np.array(df_h)
print('Numpy array:', df_h_n)

Numpy array: [[1 2]
 [3 4]]


dic = {'Name': ["John", "Smith"], 'Age': [30, 40]}
pd.DataFrame(data=dic)


## Create date
# Days
dates_d = pd.date_range('20300101', periods=6, freq='D')
print('Day:', dates_d)

Day: DatetimeIndex(['2030-01-01', '2030-01-02', '2030-01-03', '2030-01-04',
               '2030-01-05', '2030-01-06'],
              dtype='datetime64[ns]', freq='D')


# Months
dates_m = pd.date_range('20300101', periods=6, freq='M')
print('Month:', dates_m)

Month: DatetimeIndex(['2030-01-31', '2030-02-28', '2030-03-31', '2030-04-30',
               '2030-05-31', '2030-06-30'],
              dtype='datetime64[ns]', freq='M')


random = np.random.randn(6,4)
# Create data with date
df = pd.DataFrame(random,
                  index=dates_m,
                  columns=list('ABCD'))


df.head(3)


df.tail(3)


df.describe()


## Slice
### Using name
df['A']

2030-01-31    0.470902
2030-02-28    0.109920
2030-03-31    0.859818
2030-04-30   -0.710085
2030-05-31   -0.428340
2030-06-30   -1.718539
Freq: M, Name: A, dtype: float64


df[['A', 'B']]


### using a slice for row
df[0:3]


## Multi col
df.loc[:,['A','B']]


df.iloc[:, :2]


df.drop(columns=['A', 'C'])


df1 = pd.DataFrame({'name': ['John', 'Smith','Paul'],
                     'Age': ['25', '30', '50']},
                    index=[0, 1, 2])
df2 = pd.DataFrame({'name': ['Adam', 'Smith' ],
                     'Age': ['26', '11']},
                    index=[3, 4])  
df_concat = pd.concat([df1,df2]) 
df_concat


df_concat.drop_duplicates('name')


df_concat.sort_values('Age')


df_concat.rename(columns={"name": "Surname", "Age": "Age_ppl"})

	A	B	C	D
2030-01-31	0.470902	-0.697177	-1.576668	-0.091692
2030-02-28	0.109920	1.391333	-0.305348	-0.075809
2030-03-31	0.859818	0.857116	-2.080500	-0.731118

	A	B	C	D
2030-04-30	-0.710085	0.134623	-1.329340	0.480398
2030-05-31	-0.428340	0.131123	-0.097111	0.122400
2030-06-30	-1.718539	0.505573	-0.537040	0.531134

	A	B	C	D
count	6.000000	6.000000	6.000000	6.000000
mean	-0.236054	0.387098	-0.987668	0.039219
std	0.925187	0.713913	0.789894	0.462023
min	-1.718539	-0.697177	-2.080500	-0.731118
25%	-0.639649	0.131998	-1.514836	-0.087721
50%	-0.159210	0.320098	-0.933190	0.023295
75%	0.380656	0.769230	-0.363271	0.390898
max	0.859818	1.391333	-0.097111	0.531134

	A	B	C	D
2030-01-31	0.470902	-0.697177	-1.576668	-0.091692
2030-02-28	0.109920	1.391333	-0.305348	-0.075809
2030-03-31	0.859818	0.857116	-2.080500	-0.731118

	B	D
2030-01-31	-0.697177	-0.091692
2030-02-28	1.391333	-0.075809
2030-03-31	0.857116	-0.731118
2030-04-30	0.134623	0.480398
2030-05-31	0.131123	0.122400
2030-06-30	0.505573	0.531134

	Name	Age
0	John	30
1	Smith	40

	name	Age
0	John	25
1	Smith	30
2	Paul	50
3	Adam	26
4	Smith	11

	name	Age
0	John	25
1	Smith	30
2	Paul	50
3	Adam	26

	name	Age
4	Smith	11
0	John	25
3	Adam	26
1	Smith	30
2	Paul	50