Dropping rows/columns from a Pandas dataframe
Pandas
import modules
import pandas as pd
import numpy as np
create dummy dataframe
raw_data = {'name': ['Willard Morris', 'Al Jennings', 'Omar Mullins', 'Spencer McDaniel'],
'age': [20, 19, 22, 21],
'favorite_color': ['blue', 'red', 'yellow', "green"],
'grade': [88, 92, 95, 70]}
df = pd.DataFrame(raw_data, index = ['Willard Morris', 'Al Jennings', 'Omar Mullins', 'Spencer McDaniel'])
df
age | favorite_color | grade | name | |
---|---|---|---|---|
Willard Morris | 20 | blue | 88 | Willard Morris |
Al Jennings | 19 | red | 92 | Al Jennings |
Omar Mullins | 22 | yellow | 95 | Omar Mullins |
Spencer McDaniel | 21 | green | 70 | Spencer McDaniel |
drop a row by name
df.drop(['Willard Morris', 'Spencer McDaniel'])
age | favorite_color | grade | name | |
---|---|---|---|---|
Al Jennings | 19 | red | 92 | Al Jennings |
Omar Mullins | 22 | yellow | 95 | Omar Mullins |
drop a row by number
df.drop(df.index[0], inplace=True)
df
age | favorite_color | grade | name | |
---|---|---|---|---|
Al Jennings | 19 | red | 92 | Al Jennings |
Omar Mullins | 22 | yellow | 95 | Omar Mullins |
Spencer McDaniel | 21 | green | 70 | Spencer McDaniel |
drop first 2 rows (put ':' to left of # to drop last X rows)
df.drop(df.index[:2], inplace=True)
df
age | favorite_color | grade | name | |
---|---|---|---|---|
Spencer McDaniel | 21 | green | 70 | Spencer McDaniel |
dropping column by name
df.drop(['age'], axis = 1, inplace = True)
df
favorite_color | grade | name | |
---|---|---|---|
Spencer McDaniel | green | 70 | Spencer McDaniel |