Exercise 6

import pandas as pd
import numpy as np

data = {
    'Animal':['cat','cat','snake','dog','dog','cat','snake','cat','dog','dog'],
    'Age':[2.5,3.0,0.5,np.nan,5.0,2.0,4.5,np.nan,7.0,3.0],
    'Priority':['yes','yes','no','yes','no','no','no','yes','no','no'],
    'Visits':[1,3,2,3,2,3,1,1,2,1]
}
data

{'Animal': ['cat',
  'cat',
  'snake',
  'dog',
  'dog',
  'cat',
  'snake',
  'cat',
  'dog',
  'dog'],
 'Age': [2.5, 3.0, 0.5, nan, 5.0, 2.0, 4.5, nan, 7.0, 3.0],
 'Priority': ['yes', 'yes', 'no', 'yes', 'no', 'no', 'no', 'yes', 'no', 'no'],
 'Visits': [1, 3, 2, 3, 2, 3, 1, 1, 2, 1]}

index = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j']

df = pd.DataFrame(data, index=index)
df

	Animal	Age	Priority	Visits
a	cat	2.5	yes	1
b	cat	3.0	yes	3
c	snake	0.5	no	2
d	dog	NaN	yes	3
e	dog	5.0	no	2
f	cat	2.0	no	3
g	snake	4.5	no	1
h	cat	NaN	yes	1
i	dog	7.0	no	2
j	dog	3.0	no	1

df.info()

<class 'pandas.core.frame.DataFrame'>
Index: 10 entries, a to j
Data columns (total 4 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   Animal    10 non-null     object 
 1   Age       8 non-null      float64
 2   Priority  10 non-null     object 
 3   Visits    10 non-null     int64  
dtypes: float64(1), int64(1), object(2)
memory usage: 400.0+ bytes

df.describe()

	Age	Visits
count	8.000000	10.000000
mean	3.437500	1.900000
std	2.007797	0.875595
min	0.500000	1.000000
25%	2.375000	1.000000
50%	3.000000	2.000000
75%	4.625000	2.750000
max	7.000000	3.000000

df.head(3)

	Animal	Age	Priority	Visits
a	cat	2.5	yes	1
b	cat	3.0	yes	3
c	snake	0.5	no	2

df.iloc[:3]

	Animal	Age	Priority	Visits
a	cat	2.5	yes	1
b	cat	3.0	yes	3
c	snake	0.5	no	2

df[['Animal', 'Age']]

	Animal	Age
a	cat	2.5
b	cat	3.0
c	snake	0.5
d	dog	NaN
e	dog	5.0
f	cat	2.0
g	snake	4.5
h	cat	NaN
i	dog	7.0
j	dog	3.0

df.loc[:, ['Animal', 'Age']]

	Animal	Age
a	cat	2.5
b	cat	3.0
c	snake	0.5
d	dog	NaN
e	dog	5.0
f	cat	2.0
g	snake	4.5
h	cat	NaN
i	dog	7.0
j	dog	3.0

df

	Animal	Age	Priority	Visits
a	cat	2.5	yes	1
b	cat	3.0	yes	3
c	snake	0.5	no	2
d	dog	NaN	yes	3
e	dog	5.0	no	2
f	cat	2.0	no	3
g	snake	4.5	no	1
h	cat	NaN	yes	1
i	dog	7.0	no	2
j	dog	3.0	no	1

df['Visits'].groupby([df['Animal'], df['Priority']]).count()

Animal  Priority
cat     no          1
        yes         3
dog     no          3
        yes         1
snake   no          2
Name: Visits, dtype: int64

df.groupby('Animal')['Age'].mean()

Animal
cat      2.5
dog      5.0
snake    2.5
Name: Age, dtype: float64

df['Age'].groupby(df['Animal']).mean()

Animal
cat      2.5
dog      5.0
snake    2.5
Name: Age, dtype: float64

df.groupby('Animal')['Age'].describe()

	count	mean	std	min	25%	50%	75%	max
Animal
cat	3.0	2.5	0.500000	2.0	2.25	2.5	2.75	3.0
dog	3.0	5.0	2.000000	3.0	4.00	5.0	6.00	7.0
snake	2.0	2.5	2.828427	0.5	1.50	2.5	3.50	4.5

df.describe()

	Age	Visits
count	8.000000	10.000000
mean	3.437500	1.900000
std	2.007797	0.875595
min	0.500000	1.000000
25%	2.375000	1.000000
50%	3.000000	2.000000
75%	4.625000	2.750000
max	7.000000	3.000000