In [1]:
#!pip install seaborn
In [2]:
import seaborn as sns
datasets = sns.get_dataset_names()
print(datasets)
[''''anagrams'''', ''''anscombe'''', ''''attention'''', ''''brain_networks'''', ''''car_crashes'''', ''''diamonds'''', ''''dots'''', ''''dowjones'''', ''''exercise'''', ''''flights'''', ''''fmri'''', ''''geyser'''', ''''glue'''', ''''healthexp'''', ''''iris'''', ''''mpg'''', ''''penguins'''', ''''planets'''', ''''seaice'''', ''''taxis'''', ''''tips'''', ''''titanic'''']
In [3]:
data = sns.load_dataset("anagrams")
print(data.head())
subidr attnr num1 num2 num3 0 1 divided 2 4.0 7 1 2 divided 3 4.0 5 2 3 divided 3 5.0 6 3 4 divided 5 7.0 5 4 5 divided 4 5.0 8
In [4]:
for datasetname in datasets:
data = sns.load_dataset(datasetname)
print("\n------------\n-- ", datasetname)
print(data.head())
------------
-- anagrams
subidr attnr num1 num2 num3
0 1 divided 2 4.0 7
1 2 divided 3 4.0 5
2 3 divided 3 5.0 6
3 4 divided 5 7.0 5
4 5 divided 4 5.0 8
------------
-- anscombe
dataset x y
0 I 10.0 8.04
1 I 8.0 6.95
2 I 13.0 7.58
3 I 9.0 8.81
4 I 11.0 8.33
------------
-- attention
Unnamed: 0 subject attention solutions score
0 0 1 divided 1 2.0
1 1 2 divided 1 3.0
2 2 3 divided 1 3.0
3 3 4 divided 1 5.0
4 4 5 divided 1 4.0
------------
-- brain_networks
network 1 1.1 2 0 node 1 1 1
1 hemi lh rh lh
2 NaN NaN NaN NaN
3 0 56.05574417114258 92.03103637695312 3.391575574874878
4 1 55.5472526550293 43.6900749206543 -65.49598693847656
2.1 3 3.1 0 1 1 1
1 rh lh rh
2 NaN NaN NaN
3 38.65968322753906 26.203819274902344 -49.71556854248047
4 -13.974522590637207 -28.27496337890625 -39.05012893676758
4 4.1 5 ... 0 1 1 1 ...
1 lh rh lh ...
2 NaN NaN NaN ...
3 47.4610366821289 26.746612548828125 -35.898860931396484 ...
4 -1.2106596231460571 -19.012897491455078 19.568010330200195 ...
16.5 16.6 16.7 0 3 4 4
1 rh lh rh
2 NaN NaN NaN
3 0.6079040169715881 -70.27054595947266 77.36577606201172
4 57.49507141113281 -76.39321899414062 127.26136016845705
17 17.1 17.2 0 1 1 2
1 lh rh lh
2 NaN NaN NaN
3 -21.73455047607422 1.0282527208328247 7.7917842864990225
4 -13.035799026489258 46.3818244934082 -15.752449989318848
17.3 17.4 17.5 0 2 3 3
1 rh lh rh
2 NaN NaN NaN
3 68.90372467041016 -10.520872116088867 120.49046325683594
4 31.00033187866211 -39.607521057128906 24.76401138305664
17.6
0 4
1 lh
2 NaN
3 -39.686431884765625
4 -36.7710075378418
[5 rows x 63 columns]
------------
-- car_crashes
total speeding alcohol not_distracted no_previous ins_premium 0 18.8 7.332 5.640 18.048 15.040 784.55
1 18.1 7.421 4.525 16.290 17.014 1053.48
2 18.6 6.510 5.208 15.624 17.856 899.47
3 22.4 4.032 5.824 21.056 21.280 827.34
4 12.0 4.200 3.360 10.920 10.680 878.41
ins_losses abbrev
0 145.08 AL
1 133.93 AK
2 110.35 AZ
3 142.39 AR
4 165.63 CA
------------
-- diamonds
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75
------------
-- dots
align choice time coherence firing_rate
0 dots T1 -80 0.0 33.189967
1 dots T1 -80 3.2 31.691726
2 dots T1 -80 6.4 34.279840
3 dots T1 -80 12.8 32.631874
4 dots T1 -80 25.6 35.060487
------------
-- dowjones
Date Price
0 1914-12-01 55.00
1 1915-01-01 56.55
2 1915-02-01 56.00
3 1915-03-01 58.30
4 1915-04-01 66.45
------------
-- exercise
Unnamed: 0 id diet pulse time kind
0 0 1 low fat 85 1 min rest
1 1 1 low fat 85 15 min rest
2 2 1 low fat 88 30 min rest
3 3 2 low fat 90 1 min rest
4 4 2 low fat 92 15 min rest
------------
-- flights
year month passengers
0 1949 Jan 112
1 1949 Feb 118
2 1949 Mar 132
3 1949 Apr 129
4 1949 May 121
------------
-- fmri
subject timepoint event region signal
0 s13 18 stim parietal -0.017552
1 s5 14 stim parietal -0.080883
2 s12 18 stim parietal -0.081033
3 s11 18 stim parietal -0.046134
4 s10 18 stim parietal -0.037970
------------
-- geyser
duration waiting kind
0 3.600 79 long
1 1.800 54 short
2 3.333 74 long
3 2.283 62 short
4 4.533 85 long
------------
-- glue
Model Year Encoder Task Score
0 ERNIE 2019 Transformer CoLA 75.5
1 T5 2019 Transformer CoLA 71.6
2 RoBERTa 2019 Transformer CoLA 67.8
3 BERT 2018 Transformer CoLA 60.5
4 BiLSTM+ELMo 2018 LSTM CoLA 32.1
------------
-- healthexp
Year Country Spending_USD Life_Expectancy
0 1970 Germany 252.311 70.6
1 1970 France 192.143 72.2
2 1970 Great Britain 123.993 71.9
3 1970 Japan 150.437 72.0
4 1970 USA 326.961 70.9
------------
-- iris
sepal_length sepal_width petal_length petal_width species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
------------
-- mpg
mpg cylinders displacement horsepower weight acceleration 0 18.0 8 307.0 130.0 3504 12.0
1 15.0 8 350.0 165.0 3693 11.5
2 18.0 8 318.0 150.0 3436 11.0
3 16.0 8 304.0 150.0 3433 12.0
4 17.0 8 302.0 140.0 3449 10.5
model_year origin name
0 70 usa chevrolet chevelle malibu
1 70 usa buick skylark 320
2 70 usa plymouth satellite
3 70 usa amc rebel sst
4 70 usa ford torino
------------
-- penguins
species island bill_length_mm bill_depth_mm flipper_length_mm 0 Adelie Torgersen 39.1 18.7 181.0
1 Adelie Torgersen 39.5 17.4 186.0
2 Adelie Torgersen 40.3 18.0 195.0
3 Adelie Torgersen NaN NaN NaN
4 Adelie Torgersen 36.7 19.3 193.0
body_mass_g sex
0 3750.0 Male
1 3800.0 Female
2 3250.0 Female
3 NaN NaN
4 3450.0 Female
------------
-- planets
method number orbital_period mass distance year
0 Radial Velocity 1 269.300 7.10 77.40 2006
1 Radial Velocity 1 874.774 2.21 56.95 2008
2 Radial Velocity 1 763.000 2.60 19.84 2011
3 Radial Velocity 1 326.030 19.40 110.62 2007
4 Radial Velocity 1 516.220 10.50 119.47 2009
------------
-- seaice
Date Extent
0 1980-01-01 14.200
1 1980-01-03 14.302
2 1980-01-05 14.414
3 1980-01-07 14.518
4 1980-01-09 14.594
------------
-- taxis
pickup dropoff passengers distance fare tip 0 2019-03-23 20:21:09 2019-03-23 20:27:24 1 1.60 7.0 2.15
1 2019-03-04 16:11:55 2019-03-04 16:19:00 1 0.79 5.0 0.00
2 2019-03-27 17:53:01 2019-03-27 18:00:25 1 1.37 7.5 2.36
3 2019-03-10 01:23:59 2019-03-10 01:49:51 1 7.70 27.0 6.15
4 2019-03-30 13:27:42 2019-03-30 13:37:14 3 2.16 9.0 1.10
tolls total color payment pickup_zone 0 0.0 12.95 yellow credit card Lenox Hill West
1 0.0 9.30 yellow cash Upper West Side South
2 0.0 14.16 yellow credit card Alphabet City
3 0.0 36.95 yellow credit card Hudson Sq
4 0.0 13.40 yellow credit card Midtown East
dropoff_zone pickup_borough dropoff_borough
0 UN/Turtle Bay South Manhattan Manhattan
1 Upper West Side South Manhattan Manhattan
2 West Village Manhattan Manhattan
3 Yorkville West Manhattan Manhattan
4 Yorkville West Manhattan Manhattan
------------
-- tips
total_bill tip sex smoker day time size
0 16.99 1.01 Female No Sun Dinner 2
1 10.34 1.66 Male No Sun Dinner 3
2 21.01 3.50 Male No Sun Dinner 3
3 23.68 3.31 Male No Sun Dinner 2
4 24.59 3.61 Female No Sun Dinner 4
------------
-- titanic
survived pclass sex age sibsp parch fare embarked class 0 0 3 male 22.0 1 0 7.2500 S Third
1 1 1 female 38.0 1 0 71.2833 C First
2 1 3 female 26.0 0 0 7.9250 S Third
3 1 1 female 35.0 1 0 53.1000 S First
4 0 3 male 35.0 0 0 8.0500 S Third
who adult_male deck embark_town alive alone
0 man True NaN Southampton no False
1 woman False C Cherbourg yes False
2 woman False NaN Southampton yes True
3 woman False C Southampton yes False
4 man True NaN Southampton no True