Dizeleri Bölme ve Değiştirme

import pandas as pd

df = pd.DataFrame({'tags': ['python,data,pandas', 'ml,ai', 'sql,db,query']})

# Split into a list of strings
df['tag_list'] = df['tags'].str.split(',')
print(df['tag_list'])
# 0    [python, data, pandas]
# 1                  [ml, ai]
# 2         [sql, db, query]

# Count tags per row
df['tag_count'] = df['tag_list'].str.len()
print(df['tag_count'].tolist())  # [3, 2, 3]

import pandas as pd

df = pd.DataFrame({'full_name': ['Alice Smith', 'Bob Jones', 'Carol White']})

# Split into two columns
name_parts = df['full_name'].str.split(' ', expand=True)
name_parts.columns = ['first_name', 'last_name']
df = pd.concat([df, name_parts], axis=1)
print(df)
#     full_name first_name last_name
# 0  Alice Smith      Alice     Smith
# 1    Bob Jones        Bob     Jones
# 2  Carol White      Carol     White

import pandas as pd

df = pd.DataFrame({'email': ['alice@example.com', 'bob@work.org', 'carol@test.net']})

# Split at '@', keep only the first split
parts = df['email'].str.split('@', n=1, expand=True)
df['username'] = parts[0]
df['domain'] = parts[1]
print(df[['username', 'domain']])
#   username       domain
# 0    alice  example.com
# 1      bob     work.org
# 2    carol     test.net

import pandas as pd

df = pd.DataFrame({'filepath': ['data/raw/sales.csv', 'data/clean/orders.xlsx', 'reports/q1.pdf']})

# Split on the last '/' to separate directory from filename
parts = df['filepath'].str.rsplit('/', n=1, expand=True)
df['directory'] = parts[0]
df['filename'] = parts[1]
print(df[['directory', 'filename']])
#     directory    filename
# 0    data/raw   sales.csv
# 1  data/clean  orders.xlsx
# 2     reports       q1.pdf

import pandas as pd

df = pd.DataFrame({'price': ['$1,200.50', '$800.00', '$3,450.75']})

# Remove dollar sign and commas
df['price_clean'] = (
    df['price']
    .str.replace('$', '', regex=False)  # literal $
    .str.replace(',', '', regex=False)  # literal comma
)
df['price_float'] = df['price_clean'].astype(float)
print(df)
#       price price_clean  price_float
# 0  $1,200.50    1200.50       1200.5
# 1    $800.00     800.00        800.0
# 2  $3,450.75    3450.75       3450.75

import pandas as pd

df = pd.DataFrame({'date': ['01-15-2024', '03-20-2024', '07-04-2024']})

# Reformat from MM-DD-YYYY to YYYY-MM-DD using groups
df['date_iso'] = df['date'].str.replace(
    r'(\d{2})-(\d{2})-(\d{4})',
    r'\3-\1-\2',
    regex=True
)
print(df)
#          date   date_iso
# 0  01-15-2024  2024-01-15
# 1  03-20-2024  2024-03-20
# 2  07-04-2024  2024-07-04

import pandas as pd

df = pd.DataFrame({'text': ['foo bar', 'hello foo', 'world', 'foo foo']})

original = df['text'].copy()
df['text'] = df['text'].str.replace('foo', 'baz', regex=False)

changed = (df['text'] != original).sum()
print(f'{changed} rows were modified')  # 3
print(df['text'].tolist())
# ['baz bar', 'hello baz', 'world', 'baz baz']

import pandas as pd

df = pd.DataFrame({'dept': ['Eng', 'Engg', 'HR', 'Human Resources', 'Mktg', 'Marketing']})

# Standardisation map
substitutions = {
    'Engg': 'Engineering',
    'Eng': 'Engineering',
    'Human Resources': 'HR',
    'Mktg': 'Marketing'
}

for old, new in substitutions.items():
    df['dept'] = df['dept'].str.replace(old, new, regex=False)

print(df['dept'].tolist())
# ['Engineering', 'Engineering', 'HR', 'HR', 'Marketing', 'Marketing']

import pandas as pd

df = pd.DataFrame({'parts': [['alpha', 'beta'], ['foo', 'bar', 'baz']]})

# Join list elements with a hyphen
df['joined'] = df['parts'].str.join('-')
print(df['joined'])
# 0     alpha-beta
# 1  foo-bar-baz

import pandas as pd

df = pd.DataFrame({'address': ['123  Main   St', '  456 Oak  Ave  ', '789 Pine St']})

df['address_clean'] = (
    df['address']
    .str.replace(r'\s+', ' ', regex=True)
    .str.strip()
)
print(df['address_clean'].tolist())
# ['123 Main St', '456 Oak Ave', '789 Pine St']

import pandas as pd

df = pd.DataFrame({'record': ['Alice:25:Engineer', 'Bob:34:Manager', 'Carol:28:Analyst']})

parts = df['record'].str.split(':', expand=True)
parts.columns = ['name', 'age', 'role']
parts['age'] = parts['age'].astype(int)

result = pd.concat([df, parts], axis=1)
print(result)
#              record   name  age      role
# 0  Alice:25:Engineer  Alice   25  Engineer
# 1    Bob:34:Manager    Bob   34   Manager
# 2  Carol:28:Analyst  Carol   28   Analyst