EDA TED Talks

import pandas as pd import seaborn as sns import matplotlib.pyplot as plt

df = pd.read_csv('data.csv')

df.head()

titleobject

authorobject

Climate action needs new frontline leadership

Ozawa Bineshi Albert

The dark history of the overthrow of Hawaii

Sydney Iaukea

How play can spark new ideas for your business

Martin Reeves

Why is China appointing judges to combat climate change?

James K. Thornton

Cement's carbon problem — and 2 ways to fix it

Mahendra Singhi

df.shape

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5440 entries, 0 to 5439
Data columns (total 6 columns):
 #   Column  Non-Null Count  Dtype 
---  ------  --------------  ----- 
 0   title   5440 non-null   object
 1   author  5439 non-null   object
 2   date    5440 non-null   object
 3   views   5440 non-null   int64 
 4   likes   5440 non-null   int64 
 5   link    5440 non-null   object
dtypes: int64(2), object(4)
memory usage: 255.1+ KB

df.isnull().sum()

df.nunique()

# Date df.sort_values('date', ascending=False)[['title', 'date']]

titleobject

"Back on My Feet"0%

The secrets of the world's most famous symphony0%

5438 others100%

dateobject

April 20182.3%

April 20192.3%

198 others95.4%

124

"Back on My Feet"

September 2021

213

The secrets of the world's most famous symphony

September 2021

Siri, Alexa, Google ... what comes next?

September 2021

What makes a job "good" — and the case for investing in people

September 2021

How biochar removes CO2 from the air — and helps farmers thrive

September 2021

120

A program to empower Black teachers in the US

September 2021

230

What is MSG, and is it actually bad for you?

September 2021

Got millet? How marketing could improve the lives of African farmers

September 2021

227

The rise and fall of the Lakota Empire

September 2021

How to fix broken supply chains

September 2021

df.sort_values('date', ascending=True)[['title', 'date']]

titleobject

A passionate, personal case for education0%

Hooked by an octopus0%

5438 others100%

dateobject

April 20182.3%

April 20192.3%

198 others95.4%

4986

A passionate, personal case for education

April 2009

4311

Hooked by an octopus

April 2010

4284

The ocean's shifting baseline

April 2010

4626

Making law on the high seas

April 2010

4628

What a bike ride can teach you

April 2010

4638

Saving the ocean one island at a time

April 2010

4642

Natural pest control ... using bugs!

April 2010

4643

Sustainable seafood? Let's get smart

April 2010

4648

Tough truths about plastic pollution

April 2010

4659

Tagging tuna in the deep ocean

April 2010

# Views df.sort_values('views', ascending=False)[['title', 'views']]

titleobject

Do schools kill creativity?0%

Your body language may shape who you are0%

5438 others100%

viewsint64

532 - 72000000

5436

Do schools kill creativity?

72000000

4084

Your body language may shape who you are

64000000

2958

Inside the mind of a master procrastinator

60000000

4765

How great leaders inspire action

57000000

4605

The power of vulnerability

56000000

3504

How to speak so that people want to listen

49000000

2168

My philosophy for a happy life

43000000

3251

The next outbreak? We're not ready

43000000

3017

What makes a good life? Lessons from the longest study on happiness

41000000

3994

Looks aren't everything. Believe me, I'm a model.

38000000

# Views df.sort_values('views', ascending=True)[['title', 'views']]

titleobject

Year In Ideas 20150%

Post-Pandemic Paradise in Rapa Nui0%

5438 others100%

viewsint64

532 - 72000000

3039

Year In Ideas 2015

532

613

Post-Pandemic Paradise in Rapa Nui

1200

552

Virtual Worlds

1300

1064

"Jamie Raeburn" / "Baloo Baleerie" / "Twa recruitin Sergeants"

1300

1692

"Part II. The Journey Through Time" / "Ruslan and Lyudmila"

1300

478

The case for public media

1500

"Dive In"

1600

541

A chef shares: Here's how we can feed the planet without hurting the climate

2100

2230

Facing the future together

2200

Cement's carbon problem — and 2 ways to fix it

2400

#Likes df.sort_values('likes', ascending=False)[['title', 'likes']]

titleobject

Do schools kill creativity?0%

Your body language may shape who you are0%

5438 others100%

likesint64

15 - 2100000

5436

Do schools kill creativity?

2100000

4084

Your body language may shape who you are

1900000

2958

Inside the mind of a master procrastinator

1800000

4605

The power of vulnerability

1700000

4765

How great leaders inspire action

1700000

3504

How to speak so that people want to listen

1400000

2168

My philosophy for a happy life

1300000

3251

The next outbreak? We're not ready

1300000

3017

What makes a good life? Lessons from the longest study on happiness

1200000

4990

10 things you didn't know about orgasm

1100000

#Likes df.sort_values('likes', ascending=True)[['title', 'likes']]

titleobject

Year In Ideas 20150%

Post-Pandemic Paradise in Rapa Nui0%

5438 others100%

likesint64

15 - 2100000

3039

Year In Ideas 2015

613

Post-Pandemic Paradise in Rapa Nui

552

Virtual Worlds

1692

"Part II. The Journey Through Time" / "Ruslan and Lyudmila"

1064

"Jamie Raeburn" / "Baloo Baleerie" / "Twa recruitin Sergeants"

478

The case for public media

"Dive In"

541

A chef shares: Here's how we can feed the planet without hurting the climate

2230

Facing the future together

2273

"Good Morning Young Artist" and "Ms. Metronome"

df.nunique()

df.sort_values('likes', ascending=False)[['author', 'likes']]

authorobject

Alex Gendler0.8%

4442 others99.2%

Missing0%

likesint64

15 - 2100000

5436

Sir Ken Robinson

2100000

4084

Amy Cuddy

1900000

2958

Tim Urban

1800000

4605

Brené Brown

1700000

4765

Simon Sinek

1700000

3504

Julian Treasure

1400000

2168

Sam Berns

1300000

3251

Bill Gates

1300000

3017

Robert Waldinger

1200000

4990

Mary Roach

1100000

df.groupby('author')['likes'].mean().sort_values(ascending=False)

df.groupby('author')['views'].sum().sort_values(ascending=False)

The authors below are the viewest in all TED Talks

df['author'].value_counts()

df.nunique()

df['date'].hist() plt.xticks(rotation=90) plt.show()

df.describe()

viewsfloat64

likesfloat64

count

5440

mean

2061575.958

62607.61673

std

3567097.765

107646.7695

min

532

25%

670750

20000

50%

1300000

40500

75%

2100000

65000

max

72000000

2100000

df.plot(kind='box', vert=False)

df.corr()

viewsfloat64

likesfloat64

views

0.9996610444

likes

0.9996610444

sns.pairplot(df)

.css-9i38tn{letter-spacing:inherit;-webkit-text-decoration:none;text-decoration:none;}EDA TED Talks

EDA TED Talks