import pandas as pd
data = {'name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'],
'year': [2012, 2012, 2013, 2014, 2014],
'reports': [4, 24, 31, 2, 3]}
df = pd.DataFrame(data, index = ['Cochice', 'Pima', 'Santa Cruz', 'Maricopa', 'Yuma'])
df
name | reports | year | |
---|---|---|---|
Cochice | Jason | 4 | 2012 |
Pima | Molly | 24 | 2012 |
Santa Cruz | Tina | 31 | 2013 |
Maricopa | Jake | 2 | 2014 |
Yuma | Amy | 3 | 2014 |
5 rows × 3 columns
df.drop(['Cochice', 'Pima'])
name | reports | year | |
---|---|---|---|
Santa Cruz | Tina | 31 | 2013 |
Maricopa | Jake | 2 | 2014 |
Yuma | Amy | 3 | 2014 |
3 rows × 3 columns
Note: axis=1 denotes that we are referring to a column, not a row
df.drop('reports', axis=1)
name | year | |
---|---|---|
Cochice | Jason | 2012 |
Pima | Molly | 2012 |
Santa Cruz | Tina | 2013 |
Maricopa | Jake | 2014 |
Yuma | Amy | 2014 |
5 rows × 2 columns
Specifically: Create a new dataframe called df that includes all rows where the value of a cell in the name column does not equal "Tina"
df = df[df.name != 'Tina']
df
name | reports | year | |
---|---|---|---|
Cochice | Jason | 4 | 2012 |
Pima | Molly | 24 | 2012 |
Maricopa | Jake | 2 | 2014 |
Yuma | Amy | 3 | 2014 |
4 rows × 3 columns