HW4 by Scott

.vscode/launch.json

@@ -7,6 +7,13 @@
             "program": "simulation/SimulationRunner.py",
             "justMyCode": true,
             "args": "./HotdogSimulation.py"
+        },
+        {
+            "name": "Python: File",
+            "type": "python",
+            "request": "launch",
+            "program": "${file}",
+            "justMyCode": true
         }
     ]
 }

Leon_Submissions/Homework1.py

@@ -0,0 +1,28 @@
+# Question 1: 
+# The international standard for floating-point representation is 
+# called the "IEEE 754 Standard for Floating-Point Arithmetic."
+
+# Question 2: 
+# 32-bit and 64-bit formats are the most widely used ones in practice.
+
+# Question 3: 
+# My computer supports all these formats
+import numpy as np
+
+supported_formats = np.finfo(np.float32).bits, np.finfo(np.float64).bits
+print(f"Your computer supports the following floating-point formats: {supported_formats}")
+
+
+# Question 4:
+# Using the Pandas multiplication operator (df['Number1'] * df['Number2'])
+# , the result is automatically converted to a floating-point data type. 
+# On the other hand, when I multiply the numbers using the normal Python
+# multiplication operator (num1 * num2), the result remains an integer 
+# data type.
+
+# Question 5:
+# The size of a floating-point number in memory is primarily determined 
+# by the data type and not the actual value it represents. So the size 
+# of a Python floating-point number does not change as it gets larger.
+import sys
+print(sys.getsizeof(70))

Leon_Submissions/Homework2.py

@@ -0,0 +1,30 @@
+# Question 7:
+# 1. Strings in Python are sequences of Unicode characters, while bytes 
+# are sequences of raw binary data.
+# 2. Strings in Python are immutable, bytes objects are mutable 
+# 3. Strings in Python are encoded using a specific character encoding, 
+# bytes objects do not have an inherent encoding and represent raw binary 
+# data.
+import sys
+
+string_example = "Hello"
+bytes_example = b"Hello"
+
+string_size = sys.getsizeof(string_example)
+bytes_size = sys.getsizeof(bytes_example)
+
+print("Size of string:", string_size)
+print("Size of bytes:", bytes_size)
+
+# Emojis are represented using Unicode characters, which require more 
+# bytes to store compared to ASCII characters. Therefore, if you have 
+# a string that contains emojis, its size will be larger than a string 
+# without emojis. 
+
+def print_string_as_numbers(input_string):
+    for char in input_string:
+        print(ord(char), end=' ')
+
+# Example usage
+input_string = "Hello, World!"
+print_string_as_numbers(input_string)

Leon_Submissions/Homework3.py

@@ -0,0 +1,36 @@
+# Question 8: It assumes that the CSV file being read 
+# (tomato_sales_error.csv) has a column named "Tomato_Sales." 
+# If the column doesn't exist in the CSV file or if there is an issue 
+# with the file itself, an error will be raised.
+
+# Question 9: 
+import pandas as pd
+
+def read_tomato_sales(file_name):
+    data = pd.read_csv(file_name)
+
+    # Ensure required columns exist
+    required_columns = ["Store", "Region", "Tomato_Sales"]
+    missing_columns = set(required_columns) - set(data.columns)
+    if missing_columns:
+        raise ValueError(f"Invalid CSV format: Missing columns: {', '.join(missing_columns)}")
+
+    # Validate Tomato_Sales column
+    tomato_sales = data["Tomato_Sales"]
+    if not tomato_sales.dtype == int and not tomato_sales.dtype == float:
+        raise ValueError("Invalid CSV format: 'Tomato_Sales' column must contain numerical values.")
+
+    # Calculate total tomato sales
+    total_sales = tomato_sales.sum()
+    print(f"Total tomato sales: {total_sales}")
+
+# Question 10: Bytes represent raw binary data, while strings represent 
+# textual data. Using bytes allows us to handle various character 
+# encodings. By working with bytes, we can ensure that the data remains in 
+# its raw encoded form, allowing for accurate handling of different 
+# encodings.
+
+# In the interactive Python REPL (Read-Eval-Print Loop), the "_" variable 
+# is a special variable that is automatically assigned the result of the 
+# last expression evaluated. The type of the "_" variable reflects the 
+# type of the last expression evaluated in the REPL.

Leon_Submissions/leon.py

@@ -0,0 +1 @@
+print('Hi')

Scott_Submissions/A_BrainTeaser_byScott.py

@@ -0,0 +1,100 @@
+# A quick brain teaser
+print('What has a head and a tail but no body?')
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+#
+# A coin

Scott_Submissions/Floating_Point_Formats.py

@@ -0,0 +1,2 @@
+import sys
+print(sys.float_info)

Scott_Submissions/HW1_Scott.rtf

@@ -0,0 +1,37 @@
+{\rtf1\ansi\ansicpg1252\cocoartf2580
+\cocoatextscaling0\cocoaplatform0{\fonttbl\f0\fnil\fcharset0 HelveticaNeue;\f1\fnil\fcharset0 Menlo-Regular;}
+{\colortbl;\red255\green255\blue255;\red0\green0\blue0;\red0\green0\blue0;}
+{\*\expandedcolortbl;;\cssrgb\c0\c0\c0\c87059;\cssrgb\c0\c0\c0\c3922;}
+\margl1440\margr1440\vieww11520\viewh8400\viewkind0
+\deftab720
+\pard\pardeftab720\partightenfactor0
+
+\f0\fs32 \cf2 \expnd0\expndtw0\kerning0
+1. What is the name of the international standard for floating-point representation?\
+	\
+	The IEEE-754 standard describes floating-point formats, a way to represent real numbers in hardware.\
+\
+\
+2. How many bits are the floating point numbers defined by that standard allowed to be?\
+\
+	The floating-point numbers defined by the international standard can be allowed to be of different lengths depending on the specific interchange format. For binary interchange, the formats can be 16 bits, 32 bits, 64 bits, and any multiple of 32 bits \uc0\u8805  128. For decimal interchange, the formats can be any multiple of 32 bits.\
+\
+\
+3. Does your computer support all those formats? Can you think of an easy way to check with only one line of Python?\
+\
+import sys\
+print(sys.float_info)\
+\
+scott@MacBook-Pro-6 python-bootcamp % python3 Floating_Point_Formats.py \
+sys.float_info(max=1.7976931348623157e+308, max_exp=1024, max_10_exp=308, min=2.2250738585072014e-308, min_exp=-1021, min_10_exp=-307, dig=15, mant_dig=53, epsilon=2.220446049250313e-16, radix=2, rounds=1)\
+\
+\
+\pard\pardeftab720\sa320\partightenfactor0
+\cf2 4. Why doesn't this code give the same answers to the two multiplications?\
+	Because they are different operations. The normal Python multiplication operator will multiply two numbers together and return the product. The Pandas multiplication operator, on the other hand, performs element-wise multiplication on the corresponding columns in a DataFrame. In other words, it multiplies the first element in the first column with the first element in the second column, the second element in the first column with the second element in the second column, and so on. \
+	Floating-point arithmetic has a limited precision due to the finite number of bits used to represent floating-point numbers in binary format. This can lead to rounding errors and loss of precision in arithmetic operations, particularly with very large or very small numbers.\
+\
+5. You can use 
+\f1\fs27\fsmilli13600 \cf2 \cb3 sys.getsizeof
+\f0\fs32 \cf2 \cb1  to see how large a Python object is. Does the size of a Python floating-point number change as it gets larger? Why or why not?\
+	The size of a Python floating-point number does not change as it gets larger. This is because Python uses a fixed number of bytes to represent floating-point numbers, regardless of their value.}

Scott_Submissions/HW2.py

@@ -0,0 +1,54 @@
+# Name three practical differences between Python strings and bytes. 
+# Using sys.getsizeof, see how the sizes may be different. 
+# Do emoji change this answer?
+
+# Encoding
+# Strings are created using Unicode character points. 
+# While bytes are used to represent actual bytes in memory, which can be encoded using ASCII or UTF-8.
+
+# Usage
+# Strings are usually used to represent text.
+# While bytes are used to represent binary data.
+
+# Memory Size 
+# Strings take up more memory than bytes, because they are Unicode-based and can contain any character.
+# While bytes are limited to binary data.
+
+
+print("---------------------------------------------")
+print("This is the Memory Size test print out:")
+
+
+import sys
+
+my_string = "Hello, world!"
+my_bytes = b'\x48\x65\x6c\x6c'
+
+print(sys.getsizeof(my_string)) # Prints 62
+print(sys.getsizeof(my_bytes)) # Prints 37
+
+print()
+print('Test the emoji:')
+
+x = 'pizza' # Prints 54
+y = b'pizza' # Prints 38
+z = '🍕' #Prints 80
+
+print(sys.getsizeof(x))
+print(sys.getsizeof(y))
+print(sys.getsizeof(z))
+
+
+print("---------------------------------------------")
+
+print("This is the String to Sequence of Numbers print out:")
+
+def String_to_SequenceofNumbers():
+    my_string = input("Enter a string: ")
+    num_sequence = [ord(c) for c in my_string]
+    print(num_sequence)
+
+if __name__ == "__main__":
+    String_to_SequenceofNumbers()
+
+print("---------------------------------------------")

Scott_Submissions/HW3.py

@@ -0,0 +1,63 @@
+# 1. Why does ord("😀") give a different number than 0xf09f9880, which is what the hexdump of the same character yields?
+# 
+#   The ord() function returns the Unicode code point of a character as an integer, which is 128512 for the smiley face.
+#   However, the hexdump command, returns the UTF-8 encoding of character.
+#   The hexadecimal representation of 128512 is 0x1F600.
+#   The UTF-8 encoding of the "😀" character is represented by the sequence of bytes F0 9F 98 80 in hexadecimal.
+#   UTF-8 is one of the encoding schemes used to represent Unicode characters as binary data.
+#
+#
+# 8. Hypothetical Situation: If the dataframe is not formatted or cleaned, while the column storing the tomoto sales data isn't named exactly same as 'Tomato_Sales'
+#       It will raise a KeyError instead.
+#
+#
+# 9. The solution of the hypothetical situation from my question 8:
+
+def read_tomato_sales(file_name):
+    data = pd.read_csv(file_name)
+    if not pd.api.types.is_numeric_dtype(data["Tomato_Sales"]):
+        raise TypeError("Tomato_Sales column should contain only numeric values")
+    total_sales = data.iloc[:, -1].sum()  # This is the key
+    print(f"Total tomato sales: {total_sales}")
+# read_tomato_sales("tomato_sales_error.csv")
+
+
+# 10. Different human languages can use various character encodings such as UTF-8, UTF-16, or ASCII. 
+#   While using bytes, you can work with raw data without worrying about specific encodings. 
+#   This allows us to avoid encoding-related errors and ensures compatibility across different language texts.
+
+def encode_decode_data():
+    print('-' * 20)
+    data = input("Enter a sentence using any language: ")
+    print('-' * 20)
+    print("The sentence you entered is: {}".format(data))
+    print('-' * 20)
+    encoded_data = data.encode('utf-8')
+    print("This sentence after encoded is: {}".format(encoded_data))
+    print('-' * 20)
+    byte_length = len(encoded_data)
+    print("The byte length of this sentence is: {}".format(byte_length))
+    print('-' * 20)
+    decoded_data = encoded_data.decode()
+    print("This sentence after decoded is: {}".format(decoded_data))
+    print('-' * 20)
+
+if __name__ == "__main__":
+    run_function = 'function1'
+
+    if run_function == 'function1':
+        encode_decode_data()
+    elif run_function == 'function2':
+        read_tomato_sales(file_name)
+
+
+# 2.5. REPL stands for Read-Eval-Print Loop. 
+#   A REPL is an interactive programming environment that allows you to read input, evaluate expressions or statements, print output, and repeat the process. 
+#   It provides a quick way to experiment with code, test small snippets, and get immediate feedback. 
+#   The Python REPL allows you to interactively enter Python code and see the results immediately without needing to write a full script and execute it separately.
+
+
+# 3. The '_' is a convention that holds the value of the last printed expression or the result of the last evaluated expression. 
+#   The actual type of the "_" variable depends on the value assigned to it.
+
+

Scott_Submissions/HW4.py

@@ -0,0 +1,147 @@
+# 1. Annotate the following python expressions with the specific types of each literal, as well as the overall return value:
+# i = 3
+# f = 3.0
+# c = 3+3j
+# b = b'abcdefg'
+# s = 'abcdefg'
+# s = "abcdefg"
+
+i = 3
+f = 3.0
+c = 3+3j
+b = b'abcdefg'
+s1 = 'abcdefg'
+s2 = "abcdefg"
+
+def check_the_datatype():
+    print()
+    print('This is the answer for Q1:')
+    print()
+    variable_names = ['i', 'f', 'c', 'b', 's1', 's2']
+    data_list = [i, f, c, b, s1, s2]
+    for variable, data in zip(variable_names, data_list):
+        print("The type of this assigned value {} = {} is: {}".format(variable, data, type(data).__name__))
+
+
+
+# 2. For each of the types string, bytestring, integer, floating point, and imaginary literals, 
+#   construct a 5x5 table showing what happens when the character "0" or number 0 is compared to each other type
+
+from tabulate import tabulate
+from termcolor import colored
+
+from tabulate import tabulate
+from termcolor import colored
+
+def tablesQ2():
+    print()
+    print('-' * 20)
+    print()
+    print('This is the answer for Q2:')
+    print()
+    types = ["String", "Byte String", "Integer", "Floating Point", "Imaginary"]
+    literals = ['"0"', 'b"0"', '0', '0.0', '0j']
+
+    table_data = []
+
+    for type_ in types:
+        
+        row = [type_]
+
+        for literal in literals:
+            
+            if type_ == "String":
+                result = literal == '"0"'
+            elif type_ == "Byte String":
+                result = literal.encode() == b"0"
+            elif type_ == "Integer":
+                try:
+                    result = int(literal) == 0
+                except ValueError:
+                    result = False
+            elif type_ == "Floating Point":
+                try:
+                    result = float(literal) == 0.0
+                except ValueError:
+                    result = False
+            elif type_ == "Imaginary":
+                result = literal.replace('j', 'j0') == "0j"
+            color = 'green' if result else 'red'
+            colored_result = colored(result, color)
+            row.append(colored_result)
+
+        table_data.append(row)
+
+    table = tabulate(table_data, headers=["Type"] + literals, tablefmt="pipe")
+    print(table)
+
+
+
+# 3. Now do the same thing for the + and == operators for each pair of types in two other 5x5 tables.
+
+def tablesQ3():
+    print()
+    print('-' * 20)
+    print()
+    print('This is the answer for Q3:')
+    print()
+
+    operators = ["+", "=="]
+    types = ["str", "bytes", "int", "float", "complex"]
+    literals = ['"0"', 'b"0"', '0', '0.0', '0+0j']
+
+    for operator in operators:
+        print(f"Table for {operator} Operator:")
+        table_data = []
+
+        for type_ in types:
+            row = [type_]
+
+            for literal in literals:
+                try:
+                    result = eval(f"{literal} {operator} {type_}({literal})")
+                    color = 'green'
+                except TypeError:
+                    result = False
+                    color = 'red'
+
+                colored_result = colored(result, color)
+                row.append(colored_result)
+
+            table_data.append(row)
+
+        table = tabulate(table_data, headers=["Type"] + literals, tablefmt="pipe")
+        print(table)
+        print()
+
+
+
+# Write a small program that uses the AST module to open the lexer/parser example, and dumps the resulting AST. 
+# See if there are any arguments to the parse method which make the output easier to read.
+
+# By default, ast.dump() prints the AST in a compact format. 
+# However, there are two optional arguments that can enhance the readability:
+# indent: Specifies the number of spaces to use for indentation. Setting it to a positive integer (e.g., 4) indents each level of the AST by that amount.
+# annotate_fields: When set to True, adds field names as comments to the output, making it easier to identify each part of the AST.
+
+import ast
+
+def dump_ast(filename):
+    with open(filename, 'r') as file:
+        source_code = file.read()
+
+    try:
+        tree = ast.parse(source_code)
+        ast_dump = ast.dump(tree, indent=4, annotate_fields=True)
+        print(ast_dump)
+    except SyntaxError as e:
+        print(f"Syntax error in {filename}: {e}")
+
+
+
+
+if __name__ == "__main__":
+    check_the_datatype()
+    tablesQ2()
+    tablesQ3()
+    print()

Scott_Submissions/Q4.py

@@ -0,0 +1,18 @@
+import pandas as pd
+import numpy as np
+
+# Generate two random 64-bit integers
+num1 = np.random.randint(0, 10 - 1)
+num2 = np.random.randint(0, 10 - 1)
+
+# Multiply them together using the normal Python multiplication operator
+print(f"num1 * num2 = {num1 * num2}")
+
+# Create a Pandas DataFrame with the generated numbers
+data = {'Number1': [num1], 'Number2': [num2]}
+df = pd.DataFrame(data)
+
+# Multiply the numbers together using the Pandas multiplication operator
+df['Product'] = df['Number1'] * df['Number2']
+
+print(df)

Scott_Submissions/Q5.py

@@ -0,0 +1,4 @@
+import sys
+num = 99999999999
+size = sys.getsizeof(num)
+print(f"The size of the float is {size} bytes.")

Scott_Submissions/cr-example.py

@@ -0,0 +1,7 @@
+import time
+
+i=0
+while True:
+    print(f"\015{i=}", end='')
+    i += 1
+    time.sleep(0.2)

Scott_Submissions/test.py

@@ -0,0 +1,5 @@
+char1 = "u"
+result1 = ord(char1)
+print("ASCII value of the character {} is {}.".format(char1, result1))
+
+

http-performance/Webpage.ipynb

@@ -0,0 +1,78 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0593e529",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from urllib.parse import urlparse\n",
+    "\n",
+    "class JPEGRequestHandler:\n",
+    "    def __init__(self, app):\n",
+    "        self.app = app\n",
+    "\n",
+    "    def __call__(self, environ, start_response):\n",
+    "        url = urlparse(environ['REQUEST_URI'])\n",
+    "        path = url.path\n",
+    "\n",
+    "        if path.endswith('.jpg'):\n",
+    "            file_path = path[1:]\n",
+    "\n",
+    "            if os.path.isfile(file_path):\n",
+    "                with open(file_path, 'rb') as file:\n",
+    "                    response_body = file.read()\n",
+    "                    status = '200 OK'\n",
+    "                    headers = [('Content-type', 'image/jpeg'),\n",
+    "                               ('Content-Length', str(len(response_body)))]\n",
+    "\n",
+    "                    start_response(status, headers)\n",
+    "                    return [response_body]\n",
+    "            else:\n",
+    "                status = '404 Not Found'\n",
+    "                headers = [('Content-type', 'text/plain'),\n",
+    "                           ('Content-Length', '0')]\n",
+    "\n",
+    "                start_response(status, headers)\n",
+    "                return []\n",
+    "        else:\n",
+    "            status = '403 Forbidden'\n",
+    "            headers = [('Content-type', 'text/plain'),\n",
+    "                       ('Content-Length', '0')]\n",
+    "\n",
+    "            start_response(status, headers)\n",
+    "            return []\n",
+    "\n",
+    "if __name__ == '__main__':\n",
+    "    from werkzeug.serving import run_simple\n",
+    "    from werkzeug.middleware.dispatcher import DispatcherMiddleware\n",
+    "\n",
+    "    app = DispatcherMiddleware(JPEGRequestHandler(app), {'/': app})\n",
+    "    run_simple('0.0.0.0', 8000, app, use_reloader=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

http-performance/app.py

@@ -0,0 +1,44 @@
+import os
+from urllib.parse import urlparse
+
+class JPEGRequestHandler:
+    def __init__(self, app):
+        self.app = app
+
+    def __call__(self, environ, start_response):
+        url = urlparse(environ['REQUEST_URI'])
+        path = url.path
+
+        if path.endswith('.jpg'):
+            file_path = path[1:]
+
+            if os.path.isfile(file_path):
+                with open(file_path, 'rb') as file:
+                    response_body = file.read()
+                    status = '200 OK'
+                    headers = [('Content-type', 'image/jpeg'),
+                               ('Content-Length', str(len(response_body)))]
+
+                    start_response(status, headers)
+                    return [response_body]
+            else:
+                status = '404 Not Found'
+                headers = [('Content-type', 'text/plain'),
+                           ('Content-Length', '0')]
+
+                start_response(status, headers)
+                return []
+        else:
+            status = '403 Forbidden'
+            headers = [('Content-type', 'text/plain'),
+                       ('Content-Length', '0')]
+
+            start_response(status, headers)
+            return []
+
+if __name__ == '__main__':
+    from werkzeug.serving import run_simple
+    from werkzeug.middleware.dispatcher import DispatcherMiddleware
+
+    app = DispatcherMiddleware(JPEGRequestHandler(app), {'/': app})
+    run_simple('0.0.0.0', 8000, app, use_reloader=True)

lexer_parser.py

@@ -0,0 +1,76 @@
+from enum import Enum
+
+class Tokens(Enum):
+    QUOTE = 1,
+    CHAR = 2,
+    NEWLINE = 3,
+    SPACE = 4
+
+class Lexer:
+    tokens = list()
+    def __init__(self):
+        pass
+    def lex(self, str):
+        for c in str:
+            if c == "'" or c == '"':
+                self.tokens.append(Tokens.QUOTE)
+                print("Token: QUOTE")
+            elif c == "\n":
+                self.tokens.append(Tokens.NEWLINE)
+                print("Token: NEWLINE")
+            elif c == " ":
+                self.tokens.append(Tokens.SPACE)
+                print("Token: SPACE")
+            else:
+                self.tokens.append(Tokens.CHAR)
+                print("Token: CHAR")
+    def __str__(self):
+        return ",".join(Tokens(token).name for token in self.tokens)
+
+class States(Enum):
+    INITIAL = 0,
+    BEGINQUOTE = 1
+    
+class Parser:
+    def __init__(self):
+        self.state = States.INITIAL
+        self.line = 1
+
+    def transition(self, state):
+        print(f"{States(self.state).name} -> {States(state).name}")
+        self.state = state
+
+    def parse(self, tokens):
+        for token in tokens:
+            if self.state == States.INITIAL:
+                if token == Tokens.QUOTE:
+                    self.transition(States.BEGINQUOTE)
+                elif token == Tokens.NEWLINE:
+                    self.line += 1
+                continue
+            if self.state == States.BEGINQUOTE:
+                if token == Tokens.QUOTE:
+                    self.transition(States.INITIAL)
+                elif token == Tokens.CHAR or token == Tokens.SPACE:
+                    pass                    
+                elif token == Tokens.NEWLINE:
+                    raise ValueError(f"Unterminated string on line {self.line}")
+                continue
+
+if __name__ == "__main__":
+    test1 = """abcdefg
+    "abcde
+    'a'
+    bareword
+"""
+
+    lexer = Lexer()
+    lexer.lex(test1)
+    # print(lexer)
+    parser = Parser()
+    try:
+        parser.parse(lexer.tokens)
+    except ValueError as error:
+        print(error)
+
+

max submission/5_26_HW.py

@@ -0,0 +1,20 @@
+# Question7:
+# Difference: 
+# 1. Byte objects are sequence of Bytes, whereas Strings are sequence of characters. 
+# 2. Byte objects are in machine readable form internally; Strings are only in human readable form. 
+# 3. strings (str) support various character encodings, such as UTF-8, ASCII, and more. Bytes (bytes), on the other hand, represent raw binary data and can hold any byte values. 
+## Emojis can affect the size difference.
+import sys
+string_size = sys.getsizeof("Hello")
+bytes_size = sys.getsizeof(b"Hello")
+emoji_size = sys.getsizeof("😀")
+print(f"String size: {string_size} bytes")
+print(f"Bytes size: {bytes_size} bytes")
+print(f"emoji size: {emoji_size} bytes")
+
+# python routine:
+def print_string_as_numbers(string):
+    for char in string:
+        print(ord(char))
+input_string = "Hello, world!"
+print_string_as_numbers(input_string)

max submission/5_31.HW.py

@@ -0,0 +1,38 @@
+# 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.

max submission/hw1 1-5.py

@@ -0,0 +1,21 @@
+# question 1: The international standard for floating-point representation is called IEEE 754.
+
+# question 2: The IEEE 754 standard allows floating-point numbers to be represented with different bit sizes. The most commonly used formats specified by the standard are single precision (32 bits) and double precision (64 bits).
+
+# question 3: 	
+import sys
+print(sys.float_info)
+sys.float_info(max=1.7976931348623157e+308, max_exp=1024, max_10_exp=308, min=2.2250738585072014e-308, min_exp=-1021, min_10_exp=-307, dig=15, mant_dig=53, epsilon=2.220446049250313e-16, radix=2, rounds=1)
+
+# question 4: 	In the first multiplication (num1 * num2), you are using the normal Python multiplication 
+# operator, which operates on native Python integers. Python integers have arbitrary precision, meaning they can
+#  represent very large numbers accurately. However, when the result exceeds the limit of a 64-bit signed integer 
+# (2^63 - 1), an overflow may occur, and the result may not be accurate.
+# In the second multiplication (df['Number1'] * df['Number2']), you are using the Pandas multiplication operator 
+# on the columns of a DataFrame. By default, Pandas uses NumPy for numerical computations, and NumPy uses 
+# fixed-size data types. In this case, the integers in the DataFrame are most likely represented as 64-bit 
+# signed integers (int64), which have a maximum value of 2^63 - 1. If the result of the multiplication exceeds 
+# this limit, it will overflow and wrap around, leading to incorrect results.
+
+# Question5: 5.	The size of a Python floating-point number is determined by the implementation and is not influenced by the magnitude of the value it represents. So it does not change as the value of the number gets larger.
+