Curso DS - pandas

import numpy as np import pandas as pd from numpy.random import randn

np.random.seed(101)

df = pd.DataFrame(randn(5,4), ["a", "b", "c", "d", "e"], ["one", "two", "three", "four"]) df

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

-0.31931804459303326

-2.018168244037392

0.7401220570561068

0.18869530944922425

-0.758872056210466

0.19079432237171562

1.9787573241128278

randn(5,4)

# Call columns # df.one df[["one", "two"]]

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

-0.31931804459303326

-2.018168244037392

0.7401220570561068

0.18869530944922425

-0.758872056210466

0.19079432237171562

1.9787573241128278

# Create new coloum df["new_column"] = df["one"] + df["two"]

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

-0.31931804459303326

-2.018168244037392

0.7401220570561068

0.18869530944922425

-0.758872056210466

0.19079432237171562

1.9787573241128278

df.drop("new_column", axis=1)

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

-0.31931804459303326

-2.018168244037392

0.7401220570561068

0.18869530944922425

-0.758872056210466

0.19079432237171562

1.9787573241128278

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

-0.31931804459303326

-2.018168244037392

0.7401220570561068

0.18869530944922425

-0.758872056210466

0.19079432237171562

1.9787573241128278

#Para eliminarlo del df original. Inplace true df.drop("new_column", axis=1, inplace=True) df

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

-0.31931804459303326

-2.018168244037392

0.7401220570561068

0.18869530944922425

-0.758872056210466

0.19079432237171562

1.9787573241128278

df >= 0

onebool

twobool

true

false

true

false

true

df[df >= 0]

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

nan

0.7401220570561068

0.18869530944922425

nan

0.19079432237171562

1.9787573241128278

df["one"]>= 0

# Si quiero filtrar df[df["one"]>=0]

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

-0.31931804459303326

0.18869530944922425

-0.758872056210466

0.19079432237171562

1.9787573241128278

# Si negar una condición df[~(df["one"]>=0)]

onefloat64

twofloat64

-2.018168244037392

0.7401220570561068

df[(df["one"]>=0) & (df["four"]< 1)]

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

-0.31931804459303326

0.18869530944922425

-0.758872056210466

0.19079432237171562

1.9787573241128278

# Quitar los index df.reset_index()

indexobject

onefloat64

2.706849839399938

0.6511179479432686

-2.018168244037392

0.18869530944922425

0.19079432237171562

index = ["a1", "a2", "a3", "a4", "a5"] df["index"] = index df.set_index("index")

onefloat64

twofloat64

2.706849839399938

0.6281327087844596

0.6511179479432686

-0.31931804459303326

-2.018168244037392

0.7401220570561068

0.18869530944922425

-0.758872056210466

0.19079432237171562

1.9787573241128278

# Index Levels outside = ['G1','G1','G1','G2','G2','G2'] inside = [1,2,3,1,2,3] hier_index = list(zip(outside,inside)) hier_index = pd.MultiIndex.from_tuples(hier_index)

type(hier_index)

hier_index

df = pd.DataFrame(np.random.randn(6,2),index=hier_index,columns=['A','B']) df

Afloat64

Bfloat64

('G1', 1)

-0.993263499973366

0.19679950499134005

('G1', 2)

-1.1366445936091856

0.000366479605643592

('G1', 3)

1.025984152081572

-0.1565979042889875

('G2', 1)

-0.031579143908112575

0.6498258334908454

('G2', 2)

2.154846443259472

-0.6102588558227414

('G2', 3)

-0.755325340010558

-0.34641850351854453

df.loc["G1", 1]

df.index.names df.index.names = ["Grupos", "numeros"]

df.index

df.xs(1, level="numeros")

Afloat64

Bfloat64

-0.993263499973366

0.19679950499134005

-0.031579143908112575

0.6498258334908454

df = pd.DataFrame(np.random.rand(5,4)) df[df <= 0.5] = np.nan df

0float64

1float64

nan

0.6376586528178253

0.6517677034763694

nan

0.6599245188671674

0.5296233987530145

0.7845218499756547

0.6872420375766887

0.9753611270341379

nan

0float64

1float64

nan

0.6376586528178253

0.6517677034763694

nan

0.6599245188671674

0.5296233987530145

0.7845218499756547

0.6872420375766887

0.9753611270341379

nan

# Retorna los row que tenga almenos 3 not-nan df.dropna(thresh=3)

0float64

1float64

nan

0.6376586528178253

0.6599245188671674

0.5296233987530145

0.7845218499756547

0.6872420375766887

df.fillna(0)

0float64

1float64

0.6376586528178253

0.6517677034763694

0.6599245188671674

0.5296233987530145

0.7845218499756547

0.6872420375766887

0.9753611270341379

df.mean()

data = {'Company':['GOOG','GOOG','MSFT','MSFT','FB','FB'], 'Person':['Sam','Charlie','Amy','Vanessa','Carl','Sarah'], 'Sales':[200,120,340,124,243,350]} df = pd.DataFrame(data) df

Companyobject

Personobject

GOOG

Sam

GOOG

Charlie

MSFT

Amy

MSFT

Vanessa

Carl

Sarah

df_company = df.groupby("Company") df_company.mean()

Salesfloat64

296.5

GOOG

160

MSFT

232

df_company.sum()

Salesint64

593

GOOG

320

MSFT

464

df_company.sample()

Companyobject

Personobject

Sarah

GOOG

Sam

MSFT

Amy

df.groupby("Company").sum().loc["FB"]

df.groupby("Company").count()

Personint64

Salesint64

GOOG

MSFT

df.groupby("Company").describe().transpose()

FBfloat64

GOOGfloat64

('Sales', 'count')

('Sales', 'mean')

296.5

160

('Sales', 'std')

75.66042558696059

56.568542494923804

('Sales', 'min')

243

120

('Sales', '25%')

269.75

140

('Sales', '50%')

296.5

160

('Sales', '75%')

323.25

180

('Sales', 'max')

350

200

df_books = pd.read_csv("/work/bestsellers-with-categories_e591527f-ae45-4fa5-b0d1-d50142128fa6.csv") df_books

Nameobject

Publication Manual of the American Psychological Association, 6th Edition1.8%

StrengthsFinder 2.01.6%

349 others96.5%

Authorobject

Jeff Kinney2.2%

Suzanne Collins2%

246 others95.8%

10-Day Green Smoothie Cleanse

JJ Smith

11/22/63: A Novel

Stephen King

12 Rules for Life: An Antidote to Chaos

Jordan B. Peterson

1984 (Signet Classics)

George Orwell

5,000 Awesome Facts (About Everything!) (National Geographic Kids)

National Geographic Kids

A Dance with Dragons (A Song of Ice and Fire)

George R. R. Martin

A Game of Thrones / A Clash of Kings / A Storm of Swords / A Feast of Crows / A Dance with Dragons

George R. R. Martin

A Gentleman in Moscow: A Novel

Amor Towles

A Higher Loyalty: Truth, Lies, and Leadership

James Comey

A Man Called Ove: A Novel

Fredrik Backman

df_books.groupby("Author").sum()

User Ratingfloat64

4.0 - 57.599999999999994

Reviewsint64

257 - 278329

Abraham Verghese

9.2

9732

Adam Gasiewski

4.4

3113

Adam Mansbach

4.8

9568

Adir Levy

4.8

8170

Admiral William H. McRaven

4.7

10199

Adult Coloring Book Designs

4.5

2313

Alan Moore

4.8

3829

Alex Michaelides

4.5

27536

Alice Schertle

4.9

1884

Allie Brosh

4.7

4896

df_books.groupby("Author").agg(["min", "max"])

Name minobject

Cutting for Stone0.4%

Milk and Vine: Inspirational Quotes From Classic Vines0.4%

246 others99.2%

Name maxobject

Cutting for Stone0.4%

Milk and Vine: Inspirational Quotes From Classic Vines0.4%

246 others99.2%

Abraham Verghese

Cutting for Stone

Adam Gasiewski

Milk and Vine: Inspirational Quotes From Classic Vines

Adam Mansbach

Go the F**k to Sleep

Adir Levy

What Should Danny Do? (The Power to Choose Series)

Admiral William H. McRaven

Make Your Bed: Little Things That Can Change Your Life...And Maybe the World

Adult Coloring Book Designs

Adult Coloring Book Designs: Stress Relief Coloring Book: Garden Designs, Mandalas, Animals, and Paisley Patterns

Alan Moore

Watchmen

Alex Michaelides

The Silent Patient

Alice Schertle

Little Blue Truck

Allie Brosh

Hyperbole and a Half: Unfortunate Situations, Flawed Coping Mechanisms, Mayhem, and Other Things That Happened

df_books.groupby("Author").agg({"Year": "mean", "User Rating": "min"})

Yearfloat64

2009.0 - 2019.0

User Ratingfloat64

3.3 - 4.9

Abraham Verghese

2010.5

4.6

Adam Gasiewski

2017

4.4

Adam Mansbach

2011

4.8

Adir Levy

2019

4.8

Admiral William H. McRaven

2017

4.7

Adult Coloring Book Designs

2016

4.5

Alan Moore

2009

4.8

Alex Michaelides

2019

4.5

Alice Schertle

2014

4.9

Allie Brosh

2013

4.7

df_books.groupby('Author').agg({"Year": lambda x: x.mean() - 2000})

Yearfloat64

9.0 - 19.0

Abraham Verghese

10.5

Adam Gasiewski

Adam Mansbach

Adir Levy

Admiral William H. McRaven

Adult Coloring Book Designs

Alan Moore

Alex Michaelides

Alice Schertle

Allie Brosh

url = "https://static.platzi.com/media/public/uploads/hpcharactersdataraw_3d934e85-dfa4-42ec-8520-fadfbecae574.json" pd.read_json(url)

Nameobject

Cornelius Agrippa0.2%

Aunt Marge Dursley0.2%

1348 others99.7%

Linkobject

https://www.hp-lexicon.org/character/cornelius-agrippa/0.2%

https://www.hp-lexicon.org/character/dursley-family/marjorie-dursley/0.2%

1348 others99.7%

Mrs. Abbott

https://www.hp-lexicon.org/character/abbott-family/mrs-abbott/

Hannah Abbott

https://www.hp-lexicon.org/character/abbott-family/hannah-abbott/

Abel Treetops

https://www.hp-lexicon.org/character/abel-treetops/

Euan Abercrombie

https://www.hp-lexicon.org/character/abercrombie-euan/

Aberforth Dumbledore

https://www.hp-lexicon.org/character/dumbledore-family/aberforth-dumbledore/

Abernathy

https://www.hp-lexicon.org/character/abernathy/

Abraham Peasegood

https://www.hp-lexicon.org/character/abraham-peasegood/

Abraham Potter

https://www.hp-lexicon.org/character/potter-family/abraham-potter/

Abraxas Malfoy

https://www.hp-lexicon.org/character/malfoy-family/abraxas-malfoy/

Achilles Tolliver

https://www.hp-lexicon.org/character/achilles-tolliver/

left = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'], 'A': ['A0', 'A1', 'A2', 'A3'], 'B': ['B0', 'B1', 'B2', 'B3']}) right = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'], 'C': ['C0', 'C1', 'C2', 'C3'], 'D': ['D0', 'D1', 'D2', 'D3']}) print(left, "\n\n", right)

  key   A   B
0  K0  A0  B0
1  K1  A1  B1
2  K2  A2  B2
3  K3  A3  B3 

   key   C   D
0  K0  C0  D0
1  K1  C1  D1
2  K2  C2  D2
3  K3  C3  D3

pd.merge(left, right, how="inner", on="key")

keyobject

Aobject

left = pd.DataFrame({ 'A': ['A0', 'A1', 'A2', 'A3'], 'B': ['B0', 'B1', 'B2', 'B3']}, index = ['K0', 'K1', 'K2', 'K3']) right = pd.DataFrame({ 'C': ['C0', 'C1', 'C2', 'C3'], 'D': ['D0', 'D1', 'D2', 'D3']}, index = ['K0', 'K1', 'K2', 'K3']) print(left, "\n\n", right)

     A   B
K0  A0  B0
K1  A1  B1
K2  A2  B2
K3  A3  B3 

      C   D
K0  C0  D0
K1  C1  D1
K2  C2  D2
K3  C3  D3

left.join(right)

Aobject

Bobject

df = pd.DataFrame({'col1':[1,2,3,4],'col2':[444,555,666,444],'col3':['abc','def','ghi','xyz']}) df.head()

col1int64

col2int64

444

555

666

444

df["col2"].unique()

# Si quiero la cuenta de los unicos df["col2"].nunique()

# Retorna el numero de ocurencias de cada label df["col2"].value_counts()

col1int64

col2int64

444

555

666

444

df["col2"].apply(lambda x: x*2)

df.drop("col1", axis=1)

col2int64

col3object

444

abc

555

def

666

ghi

444

xyz

#sort by columns df.sort_values('col2')

col1int64

col2int64

444

555

666

data = {'A':['foo','foo','foo','bar','bar','bar'], 'B':['one','one','two','two','one','one'], 'C':['x','y','x','y','x','y'], 'D':[1,3,2,5,4,1]} df = pd.DataFrame(data) df

Aobject

Bobject

foo

one

foo

one

foo

two

bar

two

bar

one

bar

one

df.pivot_table(values="D", columns="A").T

Dfloat64

bar

3.3333333333333335

foo

df.pivot_table(values="D", index=["A", "B"], columns="C").T

bar onefloat64

bar twofloat64

nan