FilesExpand file tree

main

/

test_examples.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

59 lines (43 loc) · 2.14 KB

main

/

test_examples.py

Copy path

Top

File metadata and controls

• Code
• Blame

59 lines (43 loc) · 2.14 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

import pandas as pd

reviews = pd.read_csv("winemag-data-130k-v2.csv", index_col=0) # Load the CSV file into a DataFrame,

#Look at an overview of your data by running the following line

print(reviews.info) # Print a concise summary of the DataFrame,

#including the number of non-null entries and data types of each column

#Select the description column from reviews and assign the result to the variable desc.

print(reviews.description)

print(reviews['description'])

desc = reviews['description']

print(type(desc))

#Select the first value from the description column of reviews, assigning it to variable first_description

first_description = reviews.description[0]

print(first_description)

"""first_description = reviews.description.iloc[0]

Note that while this is the preferred way to obtain the entry in the DataFrame,

many other options will return a valid result, such as reviews.description.loc[0], reviews.description[0]"""

Second_description = reviews.description.iloc[0]

print(Second_description)

Third_description = reviews.description.loc[0]

print(Third_description)

Fourth_description = reviews.description[0]

print(Fourth_description)

#Select the first row of data (the first record) from reviews, assigning it to the variable first_row

first_row = reviews.iloc[0]

print(first_row)

"""4.

Select the first 10 values from the description column in reviews, assigning the result to variable first_descriptions.

Hint: format your output as a pandas Series"""

first_descriptions = reviews.description.iloc[:10]

print(first_descriptions)

#Note that many other options will return a valid result, such as desc.head(10) and reviews.loc[:9, "description"].

ops_description = desc.head(10)

print(ops_description)

ops_2_description = reviews.loc[:9, "description"]

print(ops_2_description)

#Select the records with index labels 1, 2, 3, 5, and 8, assigning the result to the variable sample_reviews.

#In other words, generate the following DataFrame:

sample_reviews = reviews.iloc[[1,2,3,5,8]]

print(sample_reviews)

#option 2 of the generating the same DataFrame

cols = [1,2,3,5,8]

df = reviews.iloc[cols]

print(df)