# strings.py

letter = "b"
word = "good-bye"
subword = "good"

word_length = len(word)
word_first_char = word[0]
word_subword = word[5:8]

print(f"Length of word: {word_length}")
print(f"First letter: {word_first_char}")
print(f"Last three characters: {word_subword}")

print(f"{letter} is in {word}: {(word.index(letter))}")
print(f"{subword} is in {word}: {(subword in word)}")
print(f"remove the last character: {(word[:-1])}")

Length of word: 8
First character: g
Last three characters: bye
b is in good-bye: 5
good is in good-bye: True
chop off the last character: good-by

# Define two variables x and y
x = 100
y = 3.14

# Print out the variable types for each
print(type(x))
print(type(y))

<class 'int'>
<class 'float'>

# Demonstrates different math operations
using f-strings

n1 = 7    # First number
n2 = 3    # Second number
 
# Output results of different math operations
print(f"{n1} + {n2} = {(n1 + n2)}")           # Addition
print(f"{n1} - {n2} = {(n1 - n2)}")           # Subtraction 
print(f"{n1} * {n2} = {(n1 * n2)}")           # Multiplication 
print(f"{n1} / {n2} = {(n1 / n2)}")           # Division 
print(f"{n1} // {n2} = {(n1 // n2)}")         # Floor Division
print(f"{n1} ** {n2} = {(n1 ** n2)}")         # Power/Exponent
print(f"{n1} % {n2} = {(n1 % n2)}")           # Modulo/Remainder

7 + 3 = 10
7 - 3 = 4
7 * 3 = 21
7 / 3 = 2.3333333333333335
7 // 3 = 2
7 ^ 3 = 343
7 % 3 = 1

# compare.py
# Demonstrate comparison operators                                                                               

# Assign values to variables using parallel assignment                                                           
c1, c2, c3, c4 = 25, 50, 75, 50
print(f"  c1 = {c1}, c2 = {c2}, c3 = {c3}), c4 = {c4}")

# Output results of different comparison operations                                                             
 
# Testing equality                                                                                               
print(f"c1 = c3 is {(c1 == c3)}")

# Changing values using abbreviated assignment operators                                                        
c1 *= 3    	# Shorthand for c1 = c1 * 3                                                                       
c4 += 1    	# Shorthand for c4 = c4 + 1                                                                       

print(f"c1 = {c1}, c2 = {c2}, c3 = {c3}, c4 = {c4}")
 
# Testing less than and greater than
print(f"  c1 < c2 is {(c1 < c2)}")
print(f"  c4 <= c2 is {(c4 <= c2)}")
print(f"  c1 > c2 is {(c1 > c2)}")
print(f"  c3 >= c2 is {(c3 >= c2)}")

 c1 = 25, c2 = 50, c3 = 75), c4 = 50
c1 = c3 is False
c1 = 75, c2 = 50, c3 = 75, c4 = 51
  c1 < c2 is False
  c4 <= c2 is False
  c1 > c2 is True
  c3 >= c2 is True

# hello.py
# This is a single line comment 
'''
This is a block comment to show 
comments across multiple lines.
'''

print("Hello, World!")

Hello, World!

# hello2.py

greeting = "Hello, World!"

print(greeting) # print greeting
print(f"Greeting 1: {greeting}") # print greeting as part of a string phrase
print(f"Greeting 2: {greeting}\n") # print with newline (\n) character

Hello, World!
Greeting 1: Hello, World!
Greeting 2: Hello, World!

x = 7
x

7

# Assigns variable x to have value 7
x = 7

'''
Now we want to print out what x is. We can do this by simply typing x and 
hitting run. This comment spans multiple lines. These types of comments are 
useful when describing complex functions or algorithms.
'''

x

7

# Assign x, y, and z variables 
x = 7
y = 10
z = 4

z
print(x)
print(y)

7
10

# Assign x and y variables 

x = 7
    y = 10
    
print(x)
print(y)

IndentationError: unexpected indent

# regex.jl
number1 = "(555)123-4567"
number2 = "123-45-6789"

# check if matches
if occursin(r"\([0-9]{3}\)[0-9]{3}-[0-9]{4}", number1)
   println("match!")
end

if occursin(r"\([0-9]{3}\)[0-9]{3}-[0-9]{4}", number2)
  println("match!")
else
  println("no match!")
end

# capture matches
# use parentheses to "capture" different parts of a regular 
# expression for later use the first set of parentheses corresponds 
# to index 1, second to index 2, etc.

number_details = match(r"\(([0-9]{3})\)([0-9]{3}-[0-9]{4})", number1)

if number_details != nothing
   area_code = number_details[1]
   phone_number = number_details[2]

   println("area code: $area_code")
   println("phone number: $phone_number")
end

match!
no match!
area code: 555
phone number: 123-4567

x, y, z = 100, 200, 300
print(f"x = {x}, y = {y}, z = {z}")

# Test if x equals 100
if x == 100:
    print(f"{x} equals 100")
    
# Test if y does not equal z
if y != z:
    print(f"{y} does not equal {z}")
    
# Test multiple conditions
if x < y < z:
    print(f"{y} is less than {z} and greater than {x}")

# Test multiple conditions using "and"
if x < y and x < z:
    print(f"{x} is less than {y} and {z}")

# Test multiple conditions using "or"
if y < x or y < z:
    print(f"{y} is less than {x} or {z]")

# if-else statement 
if x < 100:
    print(f"{x} less than 100")
else:
    print(f"{x} is equal to or greater than 100")
    
# Same logic as above but using the ternary operator
print(f"{x} less than 100 again" if x < 100 else f"{x} equal to or greater than 100 again")

# if-elif-else statement
if y < 100:
    print(f"{y} is less than 100")
elif y < 200:
    print(f"{y} is less than 200")
elif y < 300:
    print(f"{y} is less than 300")
else:
    print(f"{y} is greater than or equal to 300")

x = 100, y = 200, z = 300
100 equals 100
200 does not equal 300
200 is less than 300 and greater than 100
100 is less than 200 and 300
200 is less than 100 or 300
100 is equal to or greater than 100
100 equal to or greater than 100 again
200 is less than 300

# Demonstrates use of loops

i = 1

# while loop for incrementing i by 1 from 1 to 3
while i <= 3:
    print(f"while: {i}")
    i +=1

# for loop 
for j in range(1,4):
    print(f"for: {j}")
    
for j in range(1,4):
    print(f"for again: {j}")
    
# nested for loop
for j in range(1,4):
    for k in range(1,4):
        print(f"nested for: {j} * {k} = {j*k}")

while: 1
while: 2
while: 3
for: 1
for: 2
for: 3
for again: 1
for again: 2
for again: 3
nested for: 1 * 1 = 1
nested for: 1 * 2 = 2
nested for: 1 * 3 = 3
nested for: 2 * 1 = 2
nested for: 2 * 2 = 4
nested for: 2 * 3 = 6
nested for: 3 * 1 = 3
nested for: 3 * 2 = 6
nested for: 3 * 3 = 9

# Demonstrate comparison operators

# Assign values to variables using parallel assignment
c1, c2, c3, c4 = 25, 50, 75, 50
print(f"c1 = {c1}, c2 = {c2}, c3 = {c3}, c4 = {c4}")

# Output results of different comparison operations

# Testing equality
print(f" c1 = c3 is {c1 == c3}")
print(f" c2 = c4 is {c2 == c4}")

# Changing values using abbreviated assignment operators 
c1 *= 3     # shorthand for c1 = c1 * 3
c4 += 1     # shorthand for c4 = c4 + 1

print(f"c1 = {c1}, c2 = {c2}, c3 = {c3}, c4 = {c4}")

# Testing less than and greater than 
print(f" c1 < c2 is {c1 < c2}")
print(f" c4 <= c2 is {c4 < c2}")
print(f" c1 > c2 is {c1 > c2}")
print(f" c3 >= c2 is {c3 >= c2}")

c1 = 25, c2 = 50, c3 = 75, c4 = 50
 c1 = c3 is False
 c2 = c4 is True
c1 = 75, c2 = 50, c3 = 75, c4 = 51
 c1 < c2 is False
 c4 <= c2 is False
 c1 > c2 is True
 c3 >= c2 is True

39, State-gov, 77516, Bachelors, 13, Never-married, Adm-clerical, Not-in-family, White, Male, 2174, 0, 40, United-States, <=50K
50, Self-emp-not-inc, 83311, Bachelors, 13, Married-civ-spouse, Exec-managerial, Husband, White, Male, 0, 0, 13, United-States, <=50K
38, Private, 215646, HS-grad, 9, Divorced, Handlers-cleaners, Not-in-family, White, Male, 0, 0, 40, United-States, <=50K
53, Private, 234721, 11th, 7, Married-civ-spouse, Handlers-cleaners, Husband, Black, Male, 0, 0, 40, United-States, <=50K
28, Private, 338409, Bachelors, 13, Married-civ-spouse, Prof-specialty, Wife, Black, Female, 0, 0, 40, Cuba, <=50K

# process_file.py
# Tabulate and report counts for sex in Adult Data Set
# https://archive.ics.uci.edu/ml/datasets/adult

# relative path of file
data_file = open("_data/adult/adult.data", "r")

# absolute path of file
# data_file = open("/Users/user/data/adult/adult.data", "r")

# initialize collection (dictionary for tabulating counts)
gender_dict = {}

# read each line, extract sex, and keep track of counts
for line in data_file:

    # skip empty lines
    if not line.strip():
        continue

    # split line into array, based on delimiter (comma and space)
    line_array = line.strip().split(", ")

    # tabulate the counts for gender
    gender = line_array[9]  # Adjusted index to 9 (Python is 0-indexed)
    if gender in gender_dict:
        gender_dict[gender] += 1
    else:
        gender_dict[gender] = 1

# close the input file
data_file.close()

# report total counts
print("Sort by key (alphabetical):")
for gender in sorted(gender_dict.keys()):
    print(f"  {gender} = {gender_dict[gender]}")

# report total counts by key, in reverse order
print("Sort by key (reverse alphabetical):")
for gender in sorted(gender_dict.keys(), reverse=True):
    print(f"  {gender} = {gender_dict[gender]}")

# report total counts by value, in reverse order (send output to file)
with open("process_file_output.txt", "w") as output_file:
    print("Sort by value (reverse numerical):")
    for gender, count in sorted(gender_dict.items(), key=lambda item: item[1], reverse=True):
        print(f"  {gender} = {count}")
        output_file.write(f"{gender} = {count}\n")

Sort by key (alphabetical):
  Female = 10771
  Male = 21790
Sort by key (reverse alphabetical):
  Male = 21790
  Female = 10771
Sort by value (reverse numerical):
  Male = 21790
  Female = 10771

$ python process_file.py
Sort by key (alphabetical):
  Female = 10771
  Male = 21790
Sort by key (reverse alphabetical):
  Male = 21790
  Female = 10771
Sort by value (reverse numerical):
  Male = 21790
  Female = 10771

$ ls -1
process_file.py
process_file_output.txt

$ cat process_file_output.txt
Male = 21790
Female = 10771

pip install numpy

import numpy as np

# Creating an array
array1 = np.array([1, 2, 3, 4, 5])

# Getting the mean of the values in our array
mean = np.mean(array1)  

from sklearn.model_selection import train_test_split

# Load the pandas package
import pandas as pd

# Import pandas
import pandas as pd

# Create data as key-value pairs
data = {'id': [1,2,3,4,5],
        'gender': ["F", "M", "F", "M", "F"],
        'age': [68, 54, 49, 28, 36]}
        
# Put the data into a data frame
df = pd.DataFrame(data)

# display dataframe
print(df)

  id gender  age
0   1      F   68
1   2      M   54
2   3      F   49
3   4      M   28
4   5      F   36

print(df.head(2))

 id gender  age
0   1      F   68
1   2      M   54

println(df.tail(2))

  id gender  age
3   4      M   28
4   5      F   36

# dataframe size
print(df.shape)

(5, 3)

# dataframe column names
print(df.columns)

Index(['id', 'gender', 'age'], dtype='object')

# describe dataframe
print(df.describe())

 id        age
count  5.000000   5.000000
mean   3.000000  47.000000
std    1.581139  15.620499
min    1.000000  28.000000
25%    2.000000  36.000000
50%    3.000000  49.000000
75%    4.000000  54.000000
max    5.000000  68.000000

# call by column name
print(df['age'])

# get column by column number
println(df.iloc[:, 2])

0    68
1    54
2    49
3    28
4    36
Name: age, dtype: int64

0    68
1    54
2    49
3    28
4    36
Name: age, dtype: int64

# print row 2
print(df.iloc[1])

id         2
gender     M
age       54
Name: 1, dtype: object

# get element in row 2, column 3
print(df.iloc[1,2])

54

# print out rows 1, 3, & 5
print(df.iloc[[0, 2, 4], :])

   id gender  age
0   1      F   68
2   3      F   49
4   5      F   36

# print out all rows and only columns 1 (id) and 3 (age)
print("Using column names:\n")
print(df[['id', 'age']])
print("")

print("Using column numbers:\n")
print(df.iloc[:, [0, 2]])

Using column names:

   id  age
0   1   68
1   2   54
2   3   49
3   4   28
4   5   36


Using column numbers:


   id  age
0   1   68
1   2   54
2   3   49
3   4   28
4   5   36

# print out all rows where age is greater than 50
print(df[df['age'] > 50])

   id gender  age
0   1      F   68
1   2      M   54

# print out all rows where gender is female ("F")
print(df[df['gender'] == 'F'])

   id gender  age
0   1      F   68
2   3      F   49
4   5      F   36

# print out all rows where gender is female ("F") and age is between 25-50
print(df[(df['gender'] == 'F') & (df['age'] > 25) & (df['age'] < 50)])

   id gender  age
2   3      F   49
4   5      F   36

# add a column for weight
df['weight'] = [100, 120, 150, 175, 300]

# add a column for height
df['height'] = [62, 60, 61, 63, 64]

print(df)
print("")

print("Describe dataframe to see column names and summary:\n")
print(df.describe())

   id gender  age  weight  height
0   1      F   68     100      62
1   2      M   54     120      60
2   3      F   49     150      61
3   4      M   28     175      63
4   5      F   36     300      64

Describe dataframe to see column names and summary:

             id        age      weight     height
count  5.000000   5.000000    5.000000   5.000000
mean   3.000000  47.000000  169.000000  62.000000
std    1.581139  15.620499   78.612976   1.581139
min    1.000000  28.000000  100.000000  60.000000
25%    2.000000  36.000000  120.000000  61.000000
50%    3.000000  49.000000  150.000000  62.000000
75%    4.000000  54.000000  175.000000  63.000000
max    5.000000  68.000000  300.000000  64.000000

# Add a column with calculated BMI
df['bmi'] = (df['weight'] / df['height']**2) * 703

# Print the DataFrame
print(df)
print()

# Print summary statistics of the DataFrame
print("Describe dataframe to see new bmi column and summary:\n")
print(df.describe())

   id gender  age  weight  height        bmi
0   1      F   68     100      62  18.288241
1   2      M   54     120      60  23.433333
2   3      F   49     150      61  28.339156
3   4      M   28     175      63  30.996473
4   5      F   36     300      64  51.489258

Describe dataframe to see new bmi column and summary:

             id        age      weight     height        bmi
count  5.000000   5.000000    5.000000   5.000000   5.000000
mean   3.000000  47.000000  169.000000  62.000000  30.509292
std    1.581139  15.620499   78.612976   1.581139  12.693789
min    1.000000  28.000000  100.000000  60.000000  18.288241
25%    2.000000  36.000000  120.000000  61.000000  23.433333
50%    3.000000  49.000000  150.000000  62.000000  28.339156
75%    4.000000  54.000000  175.000000  63.000000  30.996473
max    5.000000  68.000000  300.000000  64.000000  51.489258

# Get counts of males and females in the DataFrame
gender_counts = df['gender'].value_counts().reset_index()
gender_counts.columns = ['gender', 'N']

# Print the result
print(gender_counts)
```

  gender  N
0      F  3
1      M  2

# Sort the DataFrame by gender and then by age in reverse order for age (oldest to youngest)
sorted_df = df.sort_values(by=['gender', 'age'], ascending=[True, False])

# Print the sorted DataFrame
print(sorted_df)

   id gender  age
0   1      F   68
2   3      F   49
4   5      F   36
1   2      M   54
3   4      M   28

# Reshape from wide to long format (disclude 'id' column)
long_df = pd.melt(df, id_vars=['id'], var_name='variable', value_name='value')

# Print the reshaped DataFrame
print(long_df)

       id variable      value
0    1   gender          F
1    2   gender          M
2    3   gender          F
3    4   gender          M
4    5   gender          F
5    1      age         68
6    2      age         54
7    3      age         49
8    4      age         28
9    5      age         36
10   1   weight        100
11   2   weight        120
12   3   weight        150
13   4   weight        175
14   5   weight        300
15   1   height         62
16   2   height         60
17   3   height         61
18   4   height         63
19   5   height         64
20   1      bmi  18.288241
21   2      bmi  23.433333
22   3      bmi  28.339156
23   4      bmi  30.996473
24   5      bmi  51.489258

# Unstack the DataFrame to get back to wide format based on "id"
wide_df = long_df.pivot(index='id', columns='variable', values='value')

# Print the reshaped DataFrame
print(wide_df)

variable age        bmi gender height weight
id                                          
1         68  18.288241      F     62    100
2         54  23.433333      M     60    120
3         49  28.339156      F     61    150
4         28  30.996473      M     63    175
5         36  51.489258      F     64    300

# Get number of rows and columns
nrows, ncols = df.shape
print(f"(nrows, ncols) = ({nrows}, {ncols})")

# Use nested for loop to get information from the DataFrame by row and column
for row in range(nrows):
    for col in range(ncols):
        print(f"value for row {row+1} and col {col+1} is {df.iloc[row, col]}")

(nrows, ncols) = (5, 6)
value for row 1 and col 1 is 1
value for row 1 and col 2 is F
value for row 1 and col 3 is 68
value for row 1 and col 4 is 100
value for row 1 and col 5 is 62
value for row 1 and col 6 is 18.28824141519251
value for row 2 and col 1 is 2
value for row 2 and col 2 is M
value for row 2 and col 3 is 54
value for row 2 and col 4 is 120
value for row 2 and col 5 is 60
value for row 2 and col 6 is 23.433333333333334
value for row 3 and col 1 is 3
value for row 3 and col 2 is F
value for row 3 and col 3 is 49
value for row 3 and col 4 is 150
value for row 3 and col 5 is 61
value for row 3 and col 6 is 28.339156140822357
value for row 4 and col 1 is 4
value for row 4 and col 2 is M
value for row 4 and col 3 is 28
value for row 4 and col 4 is 175
value for row 4 and col 5 is 63
value for row 4 and col 6 is 30.99647266313933
value for row 5 and col 1 is 5
value for row 5 and col 2 is F
value for row 5 and col 3 is 36
value for row 5 and col 4 is 300
value for row 5 and col 5 is 64
value for row 5 and col 6 is 51.4892578125

# Initialize the list and day variable
day_array = ["Monday", "Tuesday", "Wednesday", "Thursday", "Friday"]
day = "Thursday"

# Get the array length and specific days
array_length = len(day_array)
array_first_day = day_array[0]  # Indexing in Python starts at 0
array_last_day = day_array[-1]  # Python's negative indexing for last element

# Print information about the array
print(f"Length of array: {array_length}")
print(f"First day of week: {array_first_day}")
print(f"Third day of week: {day_array[2]}")
print(f"Last day of week: {array_last_day}")

# Check if the day is in the array
print(f"{day} is in {day_array}: {day in day_array}")

# Add "Sunday" to the beginning and "Saturday" to the end
day_array.insert(0, "Sunday")
day_array.append("Saturday")

# Print each element in the array
print("Day of week:")
for day in day_array:
    print(f"  {day}")

# Join array elements with ";" and print
print(f"Day of the week: {';'.join(day_array)}")

# Sort the array and print again
day_array.sort()
print(f"Day of the week (sorted): {';'.join(day_array)}")

Length of array: 5
First day of week: Monday
Third day of week: Wednesday
Last day of week: Friday
Thursday is in ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday']: True
Day of week: 
  Sunday
  Monday
  Tuesday
  Wednesday
  Thursday
  Friday
  Saturday
Day of the week: Sunday;Monday;Tuesday;Wednesday;Thursday;Friday;Saturday
Day of the week (sorted): Friday;Monday;Saturday;Sunday;Thursday;Tuesday;Wednesday

color_set = {"red", "yellow", "blue"}
color_set2 = {"red", "orange", "yellow"}

print("Length of set:", len(color_set))

print("Color Set 1")
for color in color_set:
    print("  ", color)

print("Color Set 2:", "---".join(color_set2))

print("Intersection:", color_set.intersection(color_set2))
print("Union:", color_set.union(color_set2))
print("Difference:", color_set.difference(color_set2))
print("Difference:", color_set2.difference(color_set))

Length of set: 3
Color Set 1
  yellow
  blue
  red
Color Set 2: yellow---orange---red
Intersection: {'yellow', 'red'}
Union: {'yellow', 'orange', 'blue', 'red'}
Difference: {'blue'}
Difference: {'orange'}

day_dict = {}
day_length_dict = {}

day_dict["Mon"] = "Monday"
day_dict["Tue"] = "Tuesday"
day_dict["Wed"] = "Wednesday"
day_dict["Thu"] = "Thursday"
day_dict["Fri"] = "Friday"

if "Wed" in day_dict:
    print(day_dict["Wed"])

if "Sat" not in day_dict:
    print('no key "Sat"')

print("print key-value pairs")
for day in day_dict.keys():
    print(f"  {day} = {day_dict[day]}")

print("print values (sorted)")
for day_value in sorted(day_dict.values()):
    print(f"  {day_value}")

# get length of each value and keep track of lengths
for day_value in day_dict.values():
    day_length = len(day_value)
    day_length_dict[day_value] = day_length

print("print lengths")
for day in day_length_dict.keys():
    print(f"  {day} = {day_length_dict[day]}")

print("print lengths in descending order")
for length, day in sorted(zip(day_length_dict.values(), day_length_dict.keys()), reverse=True):
    print(f"  {day} = {length}")

print("print lengths in ascending order")
for length, day in sorted(zip(day_length_dict.values(), day_length_dict.keys()), reverse=False):
    print(f"  {day} = {length}")

Wednesday
no key "Sat"
print key-value pairs
  Mon = Monday
  Tue = Tuesday
  Wed = Wednesday
  Thu = Thursday
  Fri = Friday
print values (sorted)
  Friday
  Monday
  Thursday
  Tuesday
  Wednesday
print lengths
  Monday = 6
  Tuesday = 7
  Wednesday = 9
  Thursday = 8
  Friday = 6
print lengths in descending order
  Wednesday = 9
  Thursday = 8
  Tuesday = 7
  Monday = 6
  Friday = 6
print lengths in ascending order
  Friday = 6
  Monday = 6
  Tuesday = 7
  Thursday = 8
  Wednesday = 9