Page History

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()

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()

import pandas as pd
import numpy as np
# 
#CreateCreate 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()]

Create Dataframe:
import pandas as pd
import numpy as np
# 
#CreateCreate 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')

import pandas as pd
import numpy as np
# 
#CreateCreate 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)

import pandas as pd
import numpy as np
# 
#CreateCreate 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')

import numpypandas as nppd
 
#Create# 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]

import pandas as pd
import numpy as np
# 
#CreateCreate a DataFrame
d = {
    'countries':['A','B','C'],
    'population_in_million':[100,200,120],
    'gdp_percapita':[2000,7000,15000]
    }
 
df = pd.DataFrame(d,columns=['countries','population_in_million','gdp_percapita'])

# shape from wide to long with melt function in pandas
df2=pd.melt(df,id_vars=['countries'],var_name='metrics', value_name='values')

import pandas as pd
import numpy as np
# 
#CreateCreate a DataFrame
d = {
    'countries':['A','B','C','A','B','C'],
    'metrics':['population_in_million','population_in_million','population_in_million',
                             'gdp_percapita','gdp_percapita','gdp_percapita'],
    'values':[100,200,120,2000,7000,15000]
    }
 
df = pd.DataFrame(d,columns=['countries','metrics','values'])

# reshape from long to wide in pandas python
df2=df.pivot(index='countries', columns='metrics', values='values')

import pandas as pd
import numpy as np
 
 
header = pd.MultiIndex.from_product([['Semester1','Semester2'],['Maths','Science']])
d=([[12,45,67,56],[78,89,45,67],[45,67,89,90],[67,44,56,55]])
 
 
df = pd.DataFrame(d,
                  index=['Alisa','Bobby','Cathrine','Jack'],
                  columns=header)

# stack the dataframe
stacked_df=df.stack()

# unstack the dataframe
unstacked_df = stacked_df.unstack()

# stack the dataframe of column at level 0
stacked_df_lvl=df.stack(level=0)

# unstack the dataframe
unstacked_df1 = stacked_df_lvl.unstack()