Working with text
 > Formatting settings > Detecting Matches

data in Python # Generate an example DataFramed named df

df = pd.DataFrame({"x": [0.123, 4.567, 8.901]})

# Detect if a regex pattern is present in strings with .str.contains()

suits.str.contains("[ae]") # False True True True

# x
# Count the number of matches with .str.count()

# 0 0.123
suits.str.count("[ae]") # 0 1 2 2

# 1 4.567

Learn Python online at www.DataCamp.com # 2 8.901 # Locate the position of substrings with str.find()

suits.str.find("e") # -1 -1 1 4

# Visualize and format table output

df.style.format(precision = 1)

- x The output of style.format

> Extracting matches
Example data used throughout 0 0.1 is an HTML table
>
this cheat sheet 1 4.5 # Extract matches from strings with str.findall()

suits.str.findall(".[ae]") # [] ["ia"] ["he"[ ["pa", "de"]

2 8.9

Throughout this cheat sheet, we’ll be using two pandas series named suits and # Extract capture groups with .str.extractall()

rock_paper_scissors. suits.str.extractall("([ae])(.)")

# 0 1

import pandas as pd

Splitting strings
# match

suits = pd.Series(["clubs", "Diamonds", "hearts", "Spades"])

> # 1 0
# 2 0
a m

e a

rock_paper_scissors = pd.Series(["rock ", " paper", "scissors"]) # 3 0 a d

# Split strings into list of characters with .str.split(pat="")

# 1 e s

suits.str.split(pat="")


# Get subset of strings that match with x[x.str.contains()]

String lengths and substrings

# [, "c" "l" "u" "b" "s", ]
suits[suits.str.contains("d")] # "Diamonds" "Spades"

> # [, "D" "i" "a" "m" "o" "n" "d" "s", ]

# [, "h" "e" "a" "r" "t" "s", ]

# [, "S" "p" "a" "d" "e" "s", ]

# Get the number of characters with .str.len()

suits.str.len() # Returns 5 8 6 6

# Split strings by a separator with .str.split()

suits.str.split(pat = "a")


> Replacing matches

# Get substrings by position with .str[]

# Replace a regex match with another string with .str.replace()

suits.str[2:5] # Returns "ubs" "amo" "art" "ade"

# ["clubs"]

suits.str.replace("a", "4") # "clubs" "Di4monds" "he4rts" "Sp4des"

# ["Di", "monds"]

# Get substrings by negative position with .str[]

# ["he", "rts"]

# Remove a suffix with .str.removesuffix()

suits.str[:-3] # "cl" "Diamo" "hea" "Spa

# ["Sp", "des"]

suits.str.removesuffix # "club" "Diamond" "heart" "Spade"

# Remove whitespace from the start/end with .str.strip()

# Split strings and return DataFrame with .str.split(expand=True)
# Replace a substring with .str.slice_replace()

rock_paper_scissors.str.strip() # "rock" "paper" "scissors"

suits.str.split(pat = "a", expand=True)


rhymes = pd.Series(["vein", "gain", "deign"])

rhymes.str.slice_replace(0, 1, "r") # "rein" "rain" "reign"

# Pad strings to a given length with .str.pad()

# 0 1

suits.str.pad(8, fillchar="_") # "___clubs" "Diamonds" "__hearts" "__Spades" # 0 clubs None

# 1 Di monds

# 2 he rts

# 3 Sp des

> Changing case

# Convert to lowercase with .str.lower()
> Joining or concatenating strings Learn Python Online at
suits.str.lower() # "clubs" "diamonds" "hearts" "spades"

www.DataCamp.com
# Convert to uppercase with .str.upper()
# Combine two strings with +

suits.str.upper() # "CLUBS" "DIAMONDS" "HEARTS" "SPADES"

suits + "5" # "clubs5" "Diamonds5" "hearts5" "Spades5"

# Convert to title case with .str.title()

# Collapse character vector to string with .str.cat()

pd.Series("hello, world!").str.title() # "Hello, World!"

suits.str.cat(sep=", ") # "clubs, Diamonds, hearts, Spades"

# Convert to sentence case with .str.capitalize()

# Duplicate and concatenate strings with *

pd.Series("hello, world!").str.capitalize() # "Hello, world!" suits * 2 # "clubsclubs" "DiamondsDiamonds" "heartshearts" "SpadesSpades"