Tutorial by Examples

First try use pivot: import pandas as pd import numpy as np df = pd.DataFrame({'Name':['Mary', 'Josh','Jon','Lucy', 'Jane', 'Sue'], 'Age':[34, 37, 29, 40, 29, 31], 'City':['Boston','New York', 'Chicago', 'Los Angeles', 'Chicago', 'Boston'], ...

import pandas as pd import numpy as np df = pd.DataFrame({'Name':['Mary', 'Jon','Lucy', 'Jane', 'Sue', 'Mary', 'Lucy'], 'Age':[35, 37, 40, 29, 31, 26, 28], 'City':['Boston', 'Chicago', 'Los Angeles', 'Chicago', 'Boston', 'Boston', 'Chicago'], ...

import pandas as pd import numpy as np np.random.seed(0) tuples = list(zip(*[['bar', 'bar', 'foo', 'foo', 'qux', 'qux'], ['one', 'two', 'one', 'two','one', 'two']])) idx = pd.MultiIndex.from_tuples(tuples, names=['first', 'second']) df = pd.DataFrame(np.random.randn(6, ...

import pandas as pd df = pd.DataFrame({'Sex': ['M', 'M', 'F', 'M', 'F', 'F', 'M', 'M', 'F', 'F'], 'Age': [20, 19, 17, 35, 22, 22, 12, 15, 17, 22], 'Heart Disease': ['Y', 'N', 'Y', 'N', 'N', 'Y', 'N', 'Y', 'N', 'Y']}) df Age Heart Disease Sex 0 20 ...

>>> df ID Year Jan_salary Feb_salary Mar_salary 0 1 2016 4500 4200 4700 1 2 2016 3800 3600 4400 2 3 2016 5500 5200 5300 >>> melted_df = pd.melt(df,id_vars=['ID','Year'], v...

import pandas as pd df = pd.DataFrame([{'var1': 'a,b,c', 'var2': 1, 'var3': 'XX'}, {'var1': 'd,e,f,x,y', 'var2': 2, 'var3': 'ZZ'}]) print(df) reshaped = \ (df.set_index(df.columns.drop('var1',1).tolist()) .var1.str.split(',', expand=True) .stack() .reset_ind...