
import pandas as pd


df1 = pd.read_csv('respondents.csv')
df2 = pd.read_csv('states.csv')

df1

df2


result = pd.merge(df1,df2, on=["State_Key", "State_Key"])


result


result = pd.merge(df1, df2, how='left', on=["State_Key", "State_Key"])
#can specify type of join with how option 'right', 'left', 'outer', 'inner'


result.head()


df3 = pd.read_csv('states2.csv')

df3


df4 = df2.append(df3, ignore_index=True)
df4


df5 = pd.read_csv('states3.csv')
df5


df6 = pd.concat([df2,df5])
df6


df6 = pd.concat([df2,df5],axis=1)
df6


df6 = pd.merge(df2,df5, on=["State_Key", "State_Key"])

df6


import datetime

x = datetime.datetime.now()
print(x)

2023-01-23 16:10:32.502755


print(x.year)
print(x.strftime("%A"))

2023
Monday


print(x.strftime("%b"))

Jan


x = datetime.datetime(2020, 5, 17)

print(x)

2020-05-17 00:00:00


from datetime import date, time, datetime
date(year=2020, month=1, day=31)

datetime.date(2020, 1, 31)


today = date.today()
today

datetime.date(2023, 1, 23)


date(year=2023, month=2, day=29)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-23-e9eb18261f30> in <module>
----> 1 date(year=2023, month=2, day=29)

ValueError: day is out of range for month


datetime(year=2020, month=1, day=31, hour=13, minute=14, second=31)

datetime.datetime(2020, 1, 31, 13, 14, 31)


x = datetime.now()


y=datetime.now()

y-x

datetime.timedelta(seconds=12, microseconds=236854)


date.fromisoformat("2020-01-31")

datetime.date(2020, 1, 31)


date_string = "01-31-2020 14:45:37"
format_string = "%m-%d-%Y %H:%M:%S"
datetime.strptime(date_string, format_string)

datetime.datetime(2020, 1, 31, 14, 45, 37)


import numpy as np
mu, sigma = 0, 1000 # mean and standard deviation
N=1000
s = np.random.normal(mu, sigma, N)


df7=pd.read_excel('employee_data.xlsx')


df7 = pd.DataFrame(s, columns = ['Error'])
result['Error']=round(df7['Error'],0)
result.head()


result['Salary_New']=result['Salary']+result['Error']
result.head()

	Person_Key	Age_Key	Gender_Key	State_Key	Children	Salary	Opinion_Key
0	1	2	2	9	2	63017	5
1	2	2	2	10	3	100302	1
2	3	2	2	2	0	144043	5
3	4	1	2	2	0	36025	4
4	5	2	1	9	0	97543	3
...	...	...	...	...	...	...	...
394	395	2	2	2	0	60715	3
395	396	2	1	10	2	91760	2
396	397	2	2	1	1	82558	1
397	398	2	1	7	1	84880	5
398	399	2	2	4	2	76933	5

	State_Key	State_Name
0	1	Arizona
1	2	California
2	3	Florida
3	4	Illinois
4	5	Michigan
5	6	Minnesota
6	7	New York
7	8	Ohio
8	9	Texas
9	10	Virginia

	Person_Key	Age_Key	Gender_Key	State_Key	Children	Salary	Opinion_Key	State_Name
0	1	2	2	9	2	63017	5	Texas
1	5	2	1	9	0	97543	3	Texas
2	8	2	2	9	1	101894	4	Texas
3	14	3	2	9	2	67748	3	Texas
4	15	1	2	9	2	47172	3	Texas
...	...	...	...	...	...	...	...	...
394	371	3	1	8	0	64879	3	Ohio
395	373	2	1	8	2	90675	4	Ohio
396	374	2	2	8	2	109417	4	Ohio
397	386	3	1	8	0	80256	3	Ohio
398	387	3	2	8	2	87059	3	Ohio

	Person_Key	Age_Key	Gender_Key	State_Key	Children	Salary	Opinion_Key	State_Name
0	1	2	2	9	2	63017	5	Texas
1	2	2	2	10	3	100302	1	Virginia
2	3	2	2	2	0	144043	5	California
3	4	1	2	2	0	36025	4	California
4	5	2	1	9	0	97543	3	Texas

	State_Key	State_Name
0	11	Alabama
1	12	Connecticut
2	13	Georgia
3	14	Indiana
4	15	Mississippi
5	16	Montana
6	17	New Jersey
7	18	Oklahoma
8	19	Tennessee
9	20	West Virginia

	State_Key	State_Capital
0	1	Phoenix
1	2	Sacremento
2	3	Tallahassee
3	4	Springfield
4	5	Lansing
5	6	Saint Paul
6	7	Albany
7	8	Columbus
8	9	Austin
9	10	Richmond

	Person_Key	Age_Key	Gender_Key	State_Key	Children	Salary	Opinion_Key	State_Name	Error
0	1	2	2	9	2	63017	5	Texas	-1169.0
1	2	2	2	10	3	100302	1	Virginia	484.0
2	3	2	2	2	0	144043	5	California	-719.0
3	4	1	2	2	0	36025	4	California	-308.0
4	5	2	1	9	0	97543	3	Texas	539.0