Exercises_code_and_solutions.ipynb

Kernel: Python [default]

Wine

Introduction:

This exercise is a adaptation from the UCI Wine dataset. The only pupose is to practice deleting data with pandas.

Step 1. Import the necessary libraries

import pandas as pd
import numpy as np

Step 2. Import the dataset from this address.

Step 3. Assign it to a variable called wine

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data'
wine = pd.read_csv(url)

wine.head()

Step 4. Delete the first, fourth, seventh, nineth, eleventh, thirteenth and fourteenth columns

wine = wine.drop(wine.columns[[0,3,6,8,11,12,13]], axis = 1)

wine.head()

Step 5. Assign the columns as below:

The attributes are (donated by Riccardo Leardi, riclea '@' anchem.unige.it):

1. alcohol

2. malic_acid

3. alcalinity_of_ash

4. magnesium

5. flavanoids

6. proanthocyanins

7. hue

wine.columns = ['alcohol', 'malic_acid', 'alcalinity_of_ash', 'magnesium', 'flavanoids', 'proanthocyanins', 'hue']
wine.head()

Step 6. Set the values of the first 3 rows from alcohol as NaN

wine.iloc[0:3, 0] = np.nan
wine.head()

Step 7. Now set the value of the rows 3 and 4 of magnesium as NaN

wine.iloc[2:4, 3] = np.nan
wine.head()

Step 8. Fill the value of NaN with the number 10 in alcohol and 100 in magnesium

wine.alcohol.fillna(10, inplace = True)

wine.magnesium.fillna(100, inplace = True)

wine.head()

Step 9. Count the number of missing values

wine.isnull().sum()

alcohol              0
malic_acid           0
alcalinity_of_ash    0
magnesium            0
flavanoids           0
proanthocyanins      0
hue                  0
dtype: int64

Step 10. Create an array of 10 random numbers up until 10

random = np.random.randint(10, size = 10)
random

array([2, 3, 0, 5, 0, 9, 4, 0, 7, 2])

Step 11. Use random numbers you generated as an index and assign NaN value to each of cell.

wine.alcohol[random] = np.nan
wine.head(10)

Step 12. How many missing values do we have?

wine.isnull().sum()

alcohol              7
malic_acid           0
alcalinity_of_ash    0
magnesium            0
flavanoids           0
proanthocyanins      0
hue                  0
dtype: int64

Step 13. Delete the rows that contain missing values

wine = wine.dropna(axis = 0, how = "any")
wine.head()

Step 14. Print only the non-null values in alcohol

mask = wine.alcohol.notnull()
mask

1      True
6      True
8      True
10     True
11     True
12     True
13     True
14     True
15     True
16     True
17     True
18     True
19     True
20     True
21     True
22     True
23     True
24     True
25     True
26     True
27     True
28     True
29     True
30     True
31     True
32     True
33     True
34     True
35     True
36     True
       ... 
147    True
148    True
149    True
150    True
151    True
152    True
153    True
154    True
155    True
156    True
157    True
158    True
159    True
160    True
161    True
162    True
163    True
164    True
165    True
166    True
167    True
168    True
169    True
170    True
171    True
172    True
173    True
174    True
175    True
176    True
Name: alcohol, dtype: bool

wine.alcohol[mask]

1      10.00
6      14.06
8      13.86
10     14.12
11     13.75
12     14.75
13     14.38
14     13.63
15     14.30
16     13.83
17     14.19
18     13.64
19     14.06
20     12.93
21     13.71
22     12.85
23     13.50
24     13.05
25     13.39
26     13.30
27     13.87
28     14.02
29     13.73
30     13.58
31     13.68
32     13.76
33     13.51
34     13.48
35     13.28
36     13.05
       ...  
147    13.32
148    13.08
149    13.50
150    12.79
151    13.11
152    13.23
153    12.58
154    13.17
155    13.84
156    12.45
157    14.34
158    13.48
159    12.36
160    13.69
161    12.85
162    12.96
163    13.78
164    13.73
165    13.45
166    12.82
167    13.58
168    13.40
169    12.20
170    12.77
171    14.16
172    13.71
173    13.40
174    13.27
175    13.17
176    14.13
Name: alcohol, dtype: float64

Step 15. Reset the index, so it starts with 0 again

wine = wine.reset_index(drop = True)
wine.head()

BONUS: Create your own question and answer it.