# Integer: whole numbers
x = 10; print(type(x))          # <class 'int'>
# Float: decimals
x = 1.04; print(type(x))        # <class 'float'>
# Boolean: True=1, False=0 (capital T/F)
print(True + True)               # 2
print(True == 1, False == 0)     # True True
# String: quoted text
x = 'praveen'; y = "praveen"; z = "bangalore's"
print(type(z))                  # <class 'str'>

<class 'int'>
<class 'float'>
2
True True
<class 'str'>

x = 'bangalore'
print(x[1:3])    # 'an'  (index 1 to 2, 3 exclusive)
print(x[::2])    # 'bn aoe' — positions 0,2,4,6,8
print(x[::-1])   # 'erolagnab' — step -1 = reverse
print(x[-3])     # 'o' — 3rd from end
print(x[:4])     # 'bang' — first 4 chars
print(x[2:])     # 'ngalore' — from index 2 to end
print(x[-4:-1])  # 'lor' — slice with negatives

# Concatenation — only string + string
x = 'praveen'; y = 'kumar'
print(x + ' ' + y)  # praveen kumar
print('1' + 'praveen')  # '1praveen' — not 1+praveen as number

an
bn aoe
erolagnab
o
bang
ngalore
praveen kumar
1praveen

# 1) Trim edges — user typed extra spaces
x = ' praveen '
print(repr(x.strip()))           # 'praveen' — front/back spaces removed
# why strip before isalpha? ' praveen '.isalpha() is False (space is not alpha)

# 2) Normalize case
print('hello'.replace('ll','k')) # 'heko' — replace substring
print('praveen'.upper())         # 'PRAVEEN' — for case-insensitive compare
print('PRAVEEN'.lower())         # 'praveen'
print('praveen'.capitalize())    # 'Praveen' — first letter up, rest low
print('praveen patel'.endswith('e'))  # False — check suffix

# 3) Check content type
print('praveen'.isalpha())       # True — only letters?
print('6363402404'.isdecimal())  # True — only digits 0-9?

# 4) Split & re-join — CSV ↔ list
print('my,name,is,praveen'.split(','))  # ['my','name','is','praveen'] — delimiter ','
print('|'.join(['my','name','is','praveen']))  # my|name|is|praveen — new delimiter '|'

# 5) Real validation chain — Indian mobile: 10 digits, all numeric, starts 6/7/8/9
x = '6363402404'
valid = len(x)==10 and x.isdecimal() and x[0] in '6789'
print(valid)  # True — valid Indian mobile
# try: x=' 6363402404 ' → strip first, then validate

# 6) Re-assemble sentence
words = ['hey','wassup','how','are','you?']
print(' '.join(words))  # hey wassup how are you?

'praveen'
heko
PRAVEEN
praveen
Praveen
False
True
True
['my', 'name', 'is', 'praveen']
my|name|is|praveen
True
hey wassup how are you?

x = 'my name is praveen, i m from bangalore, bangalore is beautiful'
i = x.find('bangalore')
i_len = len('bangalore')  # 9
xlen = 27 + i             # magic 27? breaks if text changes
print(x[27:xlen])         # works only for this exact sentence

x = 'my name is praveen, i m from bangalore, bangalore is beautiful'
word = 'bangalore'
i = x.find(word)          # 19 — computed, not guessed
print(i)                  # 19
print(x[i : i + len(word)])  # x[19:28] → 'bangalore' — works for any sentence
# also works with slice length directly
print(x[i : i+9])         # same, but len(word) is self-documenting

19
bangalore
bangalore

s = 'AbCdeFG123KL'
# Three buckets — each character tested once
upper = ''.join(c for c in s if c.isupper())   # 'ACFGKL' — capitals
lower = ''.join(c for c in s if c.islower())   # 'bde'    — small
digits = ''.join(c for c in s if c.isnumeric())# '123'    — numbers
print(upper, lower, digits)
print(upper + lower + digits)  # 'ACFGKLbde123' — re-assembled by type

# Why this order? In many validation rules you want capitals first,
# then lower, then digits — e.g. generating a normalized ID.

# PySpark equivalent (for a DataFrame column `code`):
# F.regexp_extract(col('code'), '[A-Z]+', 0)  → capitals
# F.regexp_extract(col('code'), '[a-z]+', 0)  → lower
# F.regexp_extract(col('code'), '[0-9]+', 0)  → digits

ACFGKL bde 123
ACFGKLbde123