x = 17
y = 5
x % y # remainder of the division (2)
x // y # integer division (quotient) (3)
print(divmod(x, y)) # returns a tuple with the quotient and the remainder (3, 2)

# find the square root of 30
# using 'math' (the most precise method)
import math
math.sqrt(30) # 5.477225575051661

# using **
30**0.5 # 5.477225575051661

# using pow()
pow(30, 0.5) # 5.477225575051661

x = 'I don\'t know' # \ is an escape character
print(x) # I don't know
x = 'first line\nsecond line' # \n is a newline character
print(x) # first line
         # second line
# to print a backslash, use r (raw string) as a prefix
print(r'C:\Users\Owner\Desktop') # C:\Users\Owner\Desktop
# raw strings cannot end in a backslash. To include a backslash at the end, use double backslashes
print('C:\\Users\\Owner\\Desktop\\') # C:\Users\Owner\Desktop\

Name = 'Doe' # string
Age = 30 # integer
Height = 5.9 # float
is_adult = True # boolean
print (f'{Name} is {Age} years old, {Height} feet tall and is an adult: {is_adult}') # Doe is 30 years old, 5.9 feet tall and is an adult: True

# 'input() function calls for user input
name = input("Enter your name: ")
print("Hello, " + name + "!")

# User inputs are strings. We must convert it to a number using a type conversion function.
temperature = input("Enter the temperature in Fahrenheit: ")
celsius = ((float(temperature) - 32) * 5/9)
print("The temperature in Celsius is:", celsius)

# open and read the file as nouvelles in VSC
  with open("C:/Users/Owner/Desktop/Transcripts.csv", "r", encoding="utf-8") as file: # "utf-8" specifies encoding for special characters
      nouvelles = file.read()

# Alors que s'est ouverte samedi la Semaine de la francophonie, quelque 2,5 millions de personnes ne maîtrisent pas, en France, les compétences de base du français – parler, lire, écrire. À Paris, une association propose des activités de lecture et joue un rôle crucial dans l’évolution individuelle et professionnelle de ceux qui en bénéficient. Reportage.

# count most frequenct 3 words in nouvelles in descending order
words = nouvelles.split()
word_count = {}
for word in words:
    if word in word_count:
        word_count[word] += 1
    else:
        word_count[word] = 1
word_count = sorted(word_count.items(), key=lambda x: x[1], reverse=True)
print(word_count[:3]) # [('de', 5), ('la', 2), ('en', 2)]

from google.colab import files
uploaded = files.upload()

# click "Choose Files" and read the file
with open('transcript.csv', 'r') as file:
         transcript = file.read()

# ChatGPT's method to filter most common 100 words
from google.colab import files
uploaded = files.upload()

with open('Transcripts.csv', 'r') as file:
         df = file.read()

import pandas as pd
from collections import Counter
import re

# Tokenize words (removing punctuation and converting to lowercase)
words = re.findall(r'\b\w+\b', df.lower())

# Count word frequencies
word_counts = Counter(words)

# Get the 100 most common words
most_common_words = word_counts.most_common(100)

# Convert to DataFrame for display
common_words_df = pd.DataFrame(most_common_words, columns=['Word', 'Count'])

# dowload the file to the computer
common_words_df.to_csv('common_words.csv', index=False)
files.download('common_words.csv')

# find out non-integers
x = [1, 5, 'hello']

for i, item in enumerate(x):
  if not isinstance(item, int):
    print(f"{i}: {item}") # 2: hello