Sample Data¶

In [472]:

n = 200
comp = ['C' + i for i in np.random.randint( 1,4, size  = n).astype(str)] # 3x Company
dept = ['D' + i for i in np.random.randint( 1,6, size  = n).astype(str)] # 5x Department
grp =  ['G' + i for i in np.random.randint( 1,3, size  = n).astype(str)] # 2x Groups
value1 = np.random.normal( loc=50 , scale=5 , size = n)
value2 = np.random.normal( loc=20 , scale=3 , size = n)
#value3 = np.random.normal( loc=5 , scale=30 , size = n)

mydf = pd.DataFrame({
    'comp':comp, 
    'dept':dept, 
    'grp': grp,
    'value1':value1, 
    'value2':value2
    #'value3':value3 
})
mydf.head()

Out[472]:

  comp dept grp     value1     value2
0   C2   D4  G1  50.265891  24.075876
1   C2   D3  G2  44.306847  19.393717
2   C2   D1  G2  56.247403  17.939938
3   C3   D1  G2  41.746750  18.240598
4   C1   D4  G2  50.915616  20.373281