38 lines
2.2 KiB
Python
38 lines
2.2 KiB
Python
# question 8: If the column or data type is invalid, and we take them into calculations without noticing this, wrong number will be produced.
|
||
# question 9：
|
||
def read_tomato_sales(file_name):
|
||
data = pd.read_csv(file_name)
|
||
if "Tomato_Sales" in data.columns and data["Tomato_Sales"].dtype == "int64":
|
||
total_sales = data["Tomato_Sales"].sum()
|
||
print(f"Total tomato sales: {total_sales}")
|
||
else:
|
||
raise ValueError("Invalid column or data type.")
|
||
# question 10: Reasons:
|
||
# 1. Different languages may have different character encodings, which define how characters are represented
|
||
# as binary data. By using bytes, you can handle various character encodings, such as UTF-8, UTF-16, or others.
|
||
# 2. Bytes are language-agnostic and treat text as raw binary data.
|
||
# 3. Bytes can handle any kind of binary data, including text data in different languages, as well as
|
||
# non-textual data such as images, audio, or video.
|
||
def process_multilingual_data(data):
|
||
# Convert string to bytes using UTF-8 encoding
|
||
byte_data = data.encode('utf-8')
|
||
|
||
# Convert bytes back to string for display or further processing
|
||
processed_data = byte_data.decode('utf-8')
|
||
|
||
return processed_data
|
||
|
||
# Example usage
|
||
text = "This is shunan zhao"
|
||
processed_text = process_multilingual_data(text)
|
||
print(processed_text)
|
||
# 1: ord("😀") gives you the Unicode code point of the character, while 0xf09f9880 represents the byte
|
||
# sequence in UTF-8 encoding used to represent that character.
|
||
# 2.5: A REPL is an interactive programming environment that allows you to enter commands or expressions,
|
||
# which are then evaluated and the results are printed or displayed.
|
||
# 3: the "_" variable is a special variable that holds the result of the last executed expression or
|
||
# statement. It is often referred to as the "underscore variable."
|
||
#The type can vary based on the context and the value assigned to in the current REPL session. For example:
|
||
# If the last executed expression was an integer, the type of "_" would be int.
|
||
# If the last executed expression was a string, the type of "_" would be str.
|
||
# If the last executed expression was a list, the type of "_" would be list. |