Concatenating and appending dataframes

https://youtu.be/ylIRlTFt_Fk



In [1]:

    
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],
                    'Int_rate':[2, 3, 2, 2],
                    'Low_tier_HPI':[50, 52, 50, 53]},
                   index = [2001, 2002, 2003, 2004])



In [12]:

    
print(pd.concat([df1, df2, df3])); #wow: NaNs
#concat[2001] will cause a error









    



      HPI  Int_rate  Low_tier_HPI  US_GDP_Thousands
2001   80         2           NaN              50.0
2002   85         3           NaN              55.0
2003   88         2           NaN              65.0
2004   85         2           NaN              55.0
2005   80         2           NaN              50.0
2006   85         3           NaN              55.0
2007   88         2           NaN              65.0
2008   85         2           NaN              55.0
2001   80         2          50.0               NaN
2002   85         3          52.0               NaN
2003   88         2          50.0               NaN
2004   85         2          53.0               NaN



In [13]:

    
print(pd.concat([df1, df2]));









    



      HPI  Int_rate  US_GDP_Thousands
2001   80         2                50
2002   85         3                55
2003   88         2                65
2004   85         2                55
2005   80         2                50
2006   85         3                55
2007   88         2                65
2008   85         2                55



In [16]:

    
df4 = df1.append(df2);
print(df4);









    



      HPI  Int_rate  US_GDP_Thousands
2001   80         2                50
2002   85         3                55
2003   88         2                65
2004   85         2                55
2005   80         2                50
2006   85         3                55
2007   88         2                65
2008   85         2                55



In [17]:

    
df5 = df4.append(df3);
print(df5); #similar to concatenation









    



      HPI  Int_rate  Low_tier_HPI  US_GDP_Thousands
2001   80         2           NaN              50.0
2002   85         3           NaN              55.0
2003   88         2           NaN              65.0
2004   85         2           NaN              55.0
2005   80         2           NaN              50.0
2006   85         3           NaN              55.0
2007   88         2           NaN              65.0
2008   85         2           NaN              55.0
2001   80         2          50.0               NaN
2002   85         3          52.0               NaN
2003   88         2          50.0               NaN
2004   85         2          53.0               NaN



In [20]:

    
s = pd.Series([80, 2, 50], index = ["HPI", "Int_rate", "US_GDP_Thousands"]);
df6 = df1.append(s, ignore_index = True);
print(df6);









    



   HPI  Int_rate  US_GDP_Thousands
0   80         2                50
1   85         3                55
2   88         2                65
3   85         2                55
4   80         2                50



In [ ]: