-
Notifications
You must be signed in to change notification settings - Fork 0
/
pandas_6.py
60 lines (47 loc) · 1.86 KB
/
pandas_6.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
import pandas as pd
df1 = pd.DataFrame({'HPI':[80,85,88,85],
'Int_rate':[2, 3, 2, 2],
'US_GDP_Thousands':[50, 55, 65, 55]},
index = [2001, 2002, 2003, 2004])
df2 = pd.DataFrame({'HPI':[80,85,88,85],
'Int_rate':[2, 3, 2, 2],
'US_GDP_Thousands':[50, 55, 65, 55]},
index = [2005, 2006, 2007, 2008])
df3 = pd.DataFrame({'HPI':[80,85,88,85],
'Unemployment':[7, 8, 9, 6],
'Low_tier_HPI':[50, 52, 50, 53]},
index = [2001, 2002, 2003, 2004])
#print(pd.merge(df1,df2, on=['HPI','Int_rate']))
#df4 = pd.merge(df1,df3, on='HPI')
#df4.set_index('HPI', inplace=True)
#print(df4)
#df1.set_index('HPI', inplace=True)
#df3.set_index('HPI', inplace=True)
#joined = df1.join(df3)
#print(joined)
df1 = pd.DataFrame({
'Int_rate':[2, 3, 2, 2],
'US_GDP_Thousands':[50, 55, 65, 55],
'Year':[2001, 2002, 2003, 2004]
})
df3 = pd.DataFrame({
'Unemployment':[7, 8, 9, 6],
'Low_tier_HPI':[50, 52, 50, 53],
'Year':[2001, 2003, 2004, 2005]})
#merged = pd.merge(df1,df3, on='Year')
#merged.set_index('Year', inplace=True)
#print(merged)
#Left - equal to left outer join SQL - use keys from left frame only
#Right - right outer join from SQL- use keys from right frame only.
#Outer - full outer join - use union of keys
#Inner - use only intersection of keys. Default.
#merged = pd.merge(df1,df3, on='Year', how='left')
#merged.set_index('Year', inplace=True)
#print(merged)
#merged = pd.merge(df1,df3, on='Year', how='inner')
#merged.set_index('Year', inplace=True)
#print(merged)
df1.set_index('Year', inplace=True)
df3.set_index('Year', inplace=True)
joined = df1.join(df3, how='outer')
print(joined)