In [ ]:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

In [ ]:
print(sns.get_dataset_names())

['anagrams', 'anscombe', 'attention', 'brain_networks', 'car_crashes', 'diamonds', 'dots', 'exercise', 'flights', 'fmri', 'gammas', 'geyser', 'iri
s', 'mpg', 'penguins', 'planets', 'taxis', 'tips', 'titanic']

In [ ]:
sns.set(style="darkgrid") #whitegrid, darkgrid, white, dark, ticks.
color = ["red", "blue"]

In [ ]:
df = sns.load_dataset("tips")
df.tail()

Out[ ]: total_bill tip sex smoker day time size

239 29.03 5.92 Male No Sat Dinner 3

240 27.18 2.00 Female Yes Sat Dinner 2

241 22.67 2.00 Male Yes Sat Dinner 2

242 17.82 1.75 Male No Sat Dinner 2

243 18.78 3.00 Female No Thur Dinner 2

In [ ]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 244 entries, 0 to 243
Data columns (total 7 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 total_bill 244 non-null float64
1 tip 244 non-null float64
2 sex 244 non-null category
3 smoker 244 non-null category
4 day 244 non-null category
5 time 244 non-null category
6 size 244 non-null int64
dtypes: category(4), float64(2), int64(1)
memory usage: 7.4 KB

In [ ]:
df['day'].value_counts()

Sat 87
Out[ ]:
Sun 76
Thur 62
Fri 19
Name: day, dtype: int64

In [ ]:
df['smoker'].value_counts()

No 151
Out[ ]:
Yes 93
Name: smoker, dtype: int64

In [ ]:
df['time'].value_counts()

Dinner 176
Out[ ]:
Lunch 68
Name: time, dtype: int64

In [ ]:
sns.relplot(x="total_bill", y="tip",data=df)

<seaborn.axisgrid.FacetGrid at 0x23361d547f0>
Out[ ]:

In [ ]:
sns.relplot(x="total_bill", y="tip",hue="sex",data=df)

<seaborn.axisgrid.FacetGrid at 0x233624bfac0>
Out[ ]:

In [ ]:
sns.relplot(x="total_bill", y="tip",hue="smoker",data=df, palette =color)

<seaborn.axisgrid.FacetGrid at 0x233625b06a0>
Out[ ]:

In [ ]:
sns.relplot(x="total_bill", y="tip",hue="smoker",data=df, style = "time")

<seaborn.axisgrid.FacetGrid at 0x233625b0610>
Out[ ]:

In [ ]:
df['size'].value_counts()

2 156
Out[ ]:
3 38
4 37
5 5
1 4
6 4
Name: size, dtype: int64

In [ ]:
sns.relplot(x="total_bill", y="tip",hue="smoker",data=df, style = "time", size="size")
# shows the size of the plot as the number of observations in the data set.

<seaborn.axisgrid.FacetGrid at 0x23362698af0>
Out[ ]:

In [ ]:
sns.relplot(x="total_bill", y="tip",hue="smoker",data=df, style = "time", size="size", sizes=(15,200))

<seaborn.axisgrid.FacetGrid at 0x233627d1730>
Out[ ]:

In [ ]:
sns.relplot(x="total_bill", y="tip",data=df, size="size", kind='line')

<seaborn.axisgrid.FacetGrid at 0x23363a11a90>
Out[ ]:

In [ ]:
np.random.seed(0) # set seed for reproducibility i.e. same random numbers every time
df1 = pd.DataFrame(dict(time = np.arange(500),value=np.random.randn(500).cumsum()))

In [ ]:
df1.head()

Out[ ]: time value

0 0 1.764052

1 1 2.164210

2 2 3.142948

3 3 5.383841

4 4 7.251399

In [ ]:
sns.relplot(x="time", y="value",data=df1, kind='line')

<seaborn.axisgrid.FacetGrid at 0x23363c156a0>
Out[ ]:

In [ ]:
df2 = pd.DataFrame(np.random.randn(500,2).cumsum(axis = 0), columns=['time','value'])

In [ ]:
sns.lineplot(x="time", y="value",data=df2)

<AxesSubplot:xlabel='time', ylabel='value'>
Out[ ]:

In [ ]:
sns.lineplot(x="time", y="value",data=df2, sort=False)

<AxesSubplot:xlabel='time', ylabel='value'>
Out[ ]:

In [ ]:
sns.relplot(x = 'total_bill', y = 'tip', data = df,hue='sex', row='sex',col='smoker')

<seaborn.axisgrid.FacetGrid at 0x23363e38340>
Out[ ]:

In [ ]:
fmri = sns.load_dataset("fmri")
fmri.head()

Out[ ]: 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

In [ ]:
sns.relplot(data=fmri,x="timepoint",y='signal',kind='line',ci=None)
# ci stands for confidence interval

<seaborn.axisgrid.FacetGrid at 0x23363d73c10>
Out[ ]:

In [ ]:
sns.relplot(data=fmri,x="timepoint",y='signal',kind='line',ci='sd')

<seaborn.axisgrid.FacetGrid at 0x23364307dc0>
Out[ ]:

In [ ]:
sns.relplot(data=fmri,x="timepoint",y='signal',kind='line',hue='event')

<seaborn.axisgrid.FacetGrid at 0x2336438e5b0>
Out[ ]:

In [ ]:
fmri['signal'].describe()

count 1064.000000
Out[ ]:
mean 0.003540
std 0.093930
min -0.255486
25% -0.046070
50% -0.013653
75% 0.024293
max 0.564985
Name: signal, dtype: float64

In [ ]:
sns.relplot(data=fmri,x="timepoint",y='signal',kind='line',hue='region',style='event')

<seaborn.axisgrid.FacetGrid at 0x2336469c6d0>
Out[ ]:

In [ ]:
flight = sns.load_dataset("flights")
flight.head()

Out[ ]: year month passengers

0 1949 Jan 112

1 1949 Feb 118

2 1949 Mar 132

3 1949 Apr 129

4 1949 May 121

In [ ]:
sns.relplot(data=flight,x="year",y='passengers',kind='line',hue='month')

<seaborn.axisgrid.FacetGrid at 0x233647fd4c0>
Out[ ]:

In [ ]:
sns.relplot(data=flight,x="year",y='passengers',kind='line',hue='month',markers=True)
# markers=True shows the markers on the line plot

<seaborn.axisgrid.FacetGrid at 0x23366b8f3d0>
Out[ ]:

In [ ]:
sns.relplot(data=fmri,x="timepoint",y='signal',kind='line',hue='region',style='event',markers=True)

<seaborn.axisgrid.FacetGrid at 0x23366c72430>
Out[ ]:

In [ ]:
df['day'].value_counts()

Sat 87
Out[ ]:
Sun 76
Thur 62
Fri 19
Name: day, dtype: int64

In [ ]:
sns.catplot(x="day",y="tip",data=df)
#catplot is used for categorical data
#by default catplot shows stripplot

<seaborn.axisgrid.FacetGrid at 0x23366e2b880>
Out[ ]:

In [ ]:
sns.catplot(x="day",y="tip",data=df,jitter=False)

<seaborn.axisgrid.FacetGrid at 0x23366e91eb0>
Out[ ]:

In [ ]:
sns.catplot(x="day",y="tip",data=df,kind='swarm')

C:\ProgramData\Anaconda3\lib\site-packages\seaborn\categorical.py:1296: UserWarning: 8.1% of the points cannot be placed; you may want to decrease
the size of the markers or use stripplot.
warnings.warn(msg, UserWarning)
<seaborn.axisgrid.FacetGrid at 0x23366eedd00>
Out[ ]:

In [ ]:
sns.catplot(x="day",y="tip",data=df,kind='swarm',hue='size')

C:\ProgramData\Anaconda3\lib\site-packages\seaborn\categorical.py:1296: UserWarning: 8.1% of the points cannot be placed; you may want to decrease
the size of the markers or use stripplot.
warnings.warn(msg, UserWarning)
<seaborn.axisgrid.FacetGrid at 0x23368a260a0>
Out[ ]:

In [ ]:
sns.catplot(x="smoker",y="tip",data=df,order=['No','Yes'])

<seaborn.axisgrid.FacetGrid at 0x23368aae1c0>
Out[ ]:

In [ ]:
sns.catplot(x="day",y="tip",data=df,kind='box')

<seaborn.axisgrid.FacetGrid at 0x2336927f910>
Out[ ]:

In [ ]:
df["day"].describe()

count 244
Out[ ]:
unique 4
top Sat
freq 87
Name: day, dtype: object

In [ ]:
thur = df[df["day"]=="Thur"]
thur.describe()

Out[ ]: total_bill tip size

count 62.000000 62.000000 62.000000

mean 17.682742 2.771452 2.451613

std 7.886170 1.240223 1.066285

min 7.510000 1.250000 1.000000

25% 12.442500 2.000000 2.000000

50% 16.200000 2.305000 2.000000

75% 20.155000 3.362500 2.000000

max 43.110000 6.700000 6.000000

In [ ]:
sns.catplot(x="day",y="tip",data=thur,kind='box',hue='sex')
# to plot boxplot for thursday

<seaborn.axisgrid.FacetGrid at 0x2336a695640>
Out[ ]:

In [ ]:
sns.catplot(x="day",y="tip",data=thur,kind='box',hue='sex',dodge = False, fliersize = 10)

<seaborn.axisgrid.FacetGrid at 0x2336a658880>
Out[ ]:

In [ ]:
sns.catplot(x="day",y="tip",data=df,kind='violin')

<seaborn.axisgrid.FacetGrid at 0x2336a571070>
Out[ ]:

In [ ]:
sns.catplot(x="day",y="tip",data=df,kind='violin',inner='quartile')

<seaborn.axisgrid.FacetGrid at 0x2336a5d8d00>
Out[ ]:

In [ ]:
dim = sns.load_dataset("diamonds")
dim.describe()

Out[ ]: carat depth table price x y z

count 53940.000000 53940.000000 53940.000000 53940.000000 53940.000000 53940.000000 53940.000000

mean 0.797940 61.749405 57.457184 3932.799722 5.731157 5.734526 3.538734

std 0.474011 1.432621 2.234491 3989.439738 1.121761 1.142135 0.705699

min 0.200000 43.000000 43.000000 326.000000 0.000000 0.000000 0.000000

25% 0.400000 61.000000 56.000000 950.000000 4.710000 4.720000 2.910000

50% 0.700000 61.800000 57.000000 2401.000000 5.700000 5.710000 3.530000

75% 1.040000 62.500000 59.000000 5324.250000 6.540000 6.540000 4.040000

max 5.010000 79.000000 95.000000 18823.000000 10.740000 58.900000 31.800000

In [ ]:
sns.catplot(x="cut",y="price",data=dim,kind='boxen')

<seaborn.axisgrid.FacetGrid at 0x2336a5fd250>
Out[ ]:

In [ ]:
sns.catplot(x="day",y="tip",data=df,kind='boxen')

<seaborn.axisgrid.FacetGrid at 0x2336cd4c0a0>
Out[ ]:

In [ ]:
sns.catplot(x="sex",y="tip",data=df,kind='bar')

<seaborn.axisgrid.FacetGrid at 0x2336ba22130>
Out[ ]:

In [ ]:
t = sns.load_dataset("titanic")

In [ ]:
t

Out[ ]: survived pclass sex age sibsp parch fare embarked class who adult_male deck embark_town alive alone

0 0 3 male 22.0 1 0 7.2500 S Third man True NaN Southampton no False

1 1 1 female 38.0 1 0 71.2833 C First woman False C Cherbourg yes False

2 1 3 female 26.0 0 0 7.9250 S Third woman False NaN Southampton yes True

3 1 1 female 35.0 1 0 53.1000 S First woman False C Southampton yes False

4 0 3 male 35.0 0 0 8.0500 S Third man True NaN Southampton no True

... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

886 0 2 male 27.0 0 0 13.0000 S Second man True NaN Southampton no True

887 1 1 female 19.0 0 0 30.0000 S First woman False B Southampton yes True

888 0 3 female NaN 1 2 23.4500 S Third woman False NaN Southampton no False

889 1 1 male 26.0 0 0 30.0000 C First man True C Cherbourg yes True

890 0 3 male 32.0 0 0 7.7500 Q Third man True NaN Queenstown no True

891 rows × 15 columns

In [ ]:
sns.catplot(x = 'sex',y='survived',kind='bar',data=t,hue="class")

<seaborn.axisgrid.FacetGrid at 0x2336ba2ee80>
Out[ ]:

In [ ]: