...
Code Block |
---|
import pandas as pd import numpy as np # Create a DataFrame d = { 'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine', 'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'], 'Age':[26,24,23,22,23,24,26,24,22,23,24,24], 'Score':[85,63,55,74,31,77,85,63,42,62,89,77] } df = pd.DataFrame(d,columns=['Name','Age','Score']) # get the maximum values of all the column in dataframe - it will be raghu, 26, 89, object df.max() # get the maximum value of the column 'Age' - it will be 26 df['Age'].max() # get the maximum value of the column 'Name' - it will be raghu df['Name'].max() |
Get the minimum value of column in Pandas DataFrame
Code Block |
---|
import pandas as pd import numpy as np # Create a DataFrame d = { 'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine', 'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'], 'Age':[26,24,23,22,23,24,26,24,22,23,24,24], 'Score':[85,63,55,74,31,77,85,63,42,62,89,77] } df = pd.DataFrame(d,columns=['Name','Age','Score']) # get the minimum values of all the column in dataframe - it will display Alex, 22, 31, object df.min() # get the minimum value of the column 'Age' - it will be 22 df['Age'].min() # get the minimum value of the column 'Name' - it will be Alex df['Name'].min() |
Select row with maximum and minimum value in Pandas DataFrame
Code Block |
---|
import pandas as pd import numpy as np #Create a DataFrame d = { 'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine', 'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'], 'Age':[26,24,23,22,23,24,26,24,22,23,24,24], 'Score':[85,63,55,74,31,77,85,63,42,62,89,77]} df = pd.DataFrame(d,columns=['Name','Age','Score']) # get the row of max value df.loc[df['Score'].idxmax()] # get the row of minimum value df.loc[df['Score'].idxmin()] |
Get the unique values (rows) of a Pandas Dataframe
Code Block |
---|
Create Dataframe: import pandas as pd import numpy as np #Create a DataFrame d = { 'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine', 'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'], 'Age':[26,24,23,22,23,24,26,24,22,23,24,24] } df = pd.DataFrame(d,columns=['Name','Age']) # get the unique values (rows) print df.drop_duplicates() # get the unique values (rows) by retaining last row print df.drop_duplicates(keep='last') |
Get the list of column headers or column name in a Pandas DataFrame
Code Block |
---|
import pandas as pd import numpy as np #Create a DataFrame d = { 'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine', 'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'], 'Age':[26,24,23,22,23,24,26,24,22,23,24,24], 'Score':[85,63,55,74,31,77,85,63,42,62,89,77]} df = pd.DataFrame(d,columns=['Name','Age','Score']) # method 1: get list of column name list(df.columns.values) # method 2: get list of column name list(df) |
Delete or Drop the duplicate row of a Pandas DataFrame
Code Block |
---|
import pandas as pd
import numpy as np
#Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24],
'Score':[85,63,55,74,31,77,85,63,42,62,89,77]}
df = pd.DataFrame(d,columns=['Name','Age','Score'])
# drop duplicate rows
df.drop_duplicates()
# drop duplicate rows by retaining last occurrence
df.drop_duplicates(keep='last')
# drop duplicate by a column name
df.drop_duplicates(['Name'], keep='last') |
Drop or delete the row in Pandas DataFrame with conditions
Code Block |
---|
import numpy as np
#Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24],
'Score':[85,63,55,74,31,77,85,63,42,62,89,77]}
df = pd.DataFrame(d,columns=['Name','Age','Score'])
# Drop an observation or row
df.drop([1,2])
# Drop a row by condition
df[df.Name != 'Alisa']
# Drop a row by index
df.drop(df.index[2])
# Drop bottom 3 rows
df[:-3] |
Generator
Random number generation
...