import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
from matplotlib import style
plt.style.use(['dark_background'])

import urllib.request
import json

import seaborn as sns
sns.set(color_codes=True)

Plotting the composition of data

Static composition

Pie chart

p = sns.load_dataset('penguins')

p.head()

	species	island	culmen_length_mm	culmen_depth_mm	flipper_length_mm	body_mass_g	sex
0	Adelie	Torgersen	39.1	18.7	181.0	3750.0	MALE
1	Adelie	Torgersen	39.5	17.4	186.0	3800.0	FEMALE
2	Adelie	Torgersen	40.3	18.0	195.0	3250.0	FEMALE
3	Adelie	Torgersen	NaN	NaN	NaN	NaN	NaN
4	Adelie	Torgersen	36.7	19.3	193.0	3450.0	FEMALE

p.groupby('species')['species'].count()

species
Adelie       152
Chinstrap     68
Gentoo       124
Name: species, dtype: int64

c = p.groupby('species')['species'].count()

plt.pie(c);
plt.show()

plt.pie(c, labels=c.index);
plt.show()

plt.pie(c, labels=c.index, autopct="%.2f%%");
plt.show()

plt.pie(c, labels=c.index, autopct="%.2f%%",
        explode=[0, 1, 0]);
plt.show()

plt.pie(c, labels=c.index, autopct="%.2f%%",
        explode=[0, 1, 0], startangle=180);
plt.show()

plt.pie(c, labels=c.index, autopct="%.2f%%",
        explode=[0, 1, 0], startangle=180, shadow=True);
plt.show()

plt.pie(np.random.randint(0, 10, 10));
plt.show()

Donut chart

plt.pie(np.random.randint(0, 10, 10), wedgeprops=dict(width=0.3));
plt.show()

cmap = plt.get_cmap('Accent')
my_colours = cmap(np.arange(10))

plt.pie(np.random.randint(0, 10, 10), 
        wedgeprops=dict(width=0.3),
        colors=my_colours);
plt.show()

plt.pie(c, labels=c.index, autopct="%.2f%%", wedgeprops=dict(width=0.3));
plt.show()

c_i = p.groupby('island')['island'].count()

plt.pie(c_i, labels=c_i.index, autopct="%.2f%%", wedgeprops=dict(width=0.3));
plt.show()

c = pd.crosstab(p.species, p.island)

c = c.T

c

species	Adelie	Chinstrap	Gentoo
island
Biscoe	44	0	124
Dream	56	68	0
Torgersen	52	0	0

plt.pie(c.sum(axis=1), labels=c.index, 
        radius = 1, wedgeprops=dict(width=0.3));

plt.pie(c.sum(axis=1), labels=c.index, 
        radius = 1, wedgeprops=dict(width=0.3));
plt.pie(c.values.flatten(), radius=0.7, 
        wedgeprops=dict(width=0.3));

cmap = plt.get_cmap('tab20c')
outer_colors = cmap(np.array([0, 4, 8]))
inner_colors = cmap(np.array([1, 2, 3, 5, 6, 7, 9, 10, 11]))

plt.pie(c.sum(axis=1), labels=c.index, 
        radius = 1, wedgeprops=dict(width=0.3), 
        colors=outer_colors);
plt.pie(c.values.flatten(), radius=0.7, 
        wedgeprops=dict(width=0.3),
        colors=inner_colors);

plt.pie(c.sum(axis=1), labels=c.index, 
        radius = 1, wedgeprops=dict(width=0.3), 
        colors=outer_colors);
plt.pie(c.values.flatten(), radius=0.7, 
        labels = ['A', '', 'G', 'A', 'C', '', 'A', '', ''],
        wedgeprops=dict(width=0.3),
        colors=inner_colors);

plt.pie(c.sum(axis=1), labels=c.index, 
        radius = 1, wedgeprops=dict(width=0.3), 
        colors=outer_colors);
plt.pie(c.values.flatten(), radius=0.7, 
        labels = ['A', '', 'G', 'A', 'C', '', 'A', '', ''],
        wedgeprops=dict(width=0.3),
        colors=inner_colors,
        labeldistance=0.75);

cmap = plt.get_cmap('tab20b')
outer_colors = cmap(np.array([0, 4, 8]))
inner_colors = cmap(np.array([1, 2, 3, 5, 6, 7, 9, 10, 11]))
plt.pie(c.sum(axis=1), labels=c.index, 
        radius = 1, wedgeprops=dict(width=0.3), 
        colors=outer_colors);
plt.pie(c.values.flatten(), radius=0.7, 
        labels = ['A', '', 'G', 'A', 'C', '', 'A', '', ''],
        wedgeprops=dict(width=0.3),
        colors=inner_colors,
        labeldistance=0.75, textprops=dict(color='w'));

Stacked bar plot

url = 'https://api.covid19india.org/states_daily.json'
urllib.request.urlretrieve(url, 'data.json')

with open('data.json') as f:
  data = json.load(f)
data = data['states_daily']
df = pd.json_normalize(data)

df.head()

	an	ap	ar	as	br	ch	ct	date	dd	dl	dn	ga	gj	hp	hr	jh	jk	ka	kl	la	ld	mh	ml	mn	mp	mz	nl	or	pb	py	rj	sk	status	tg	tn	tr	tt	un	up	ut	wb
0	0	1	0	0	0	0	0	14-Mar-20	0	7	0	0	0	0	14	0	2	6	19	0	0	14	0	0	0	0	0	0	1	0	3	0	Confirmed	1	1	0	81	0	12	0	0
1	0	0	0	0	0	0	0	14-Mar-20	0	1	0	0	0	0	0	0	0	0	3	0	0	0	0	0	0	0	0	0	0	0	1	0	Recovered	0	0	0	9	0	4	0	0
2	0	0	0	0	0	0	0	14-Mar-20	0	1	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	Deceased	0	0	0	2	0	0	0	0
3	0	0	0	0	0	0	0	15-Mar-20	0	0	0	0	0	0	0	0	0	0	5	0	0	18	0	0	0	0	0	0	0	0	1	0	Confirmed	2	0	0	27	0	1	0	0
4	0	0	0	0	0	0	0	15-Mar-20	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	2	0	Recovered	1	0	0	4	0	0	0	0

df_ = df.tail(3)
df_.drop('date', axis=1, inplace=True)
df_.set_index('status', inplace=True)
df_ = df_.T
df_ = df_.apply(pd.to_numeric)
df_.drop('tt', inplace=True)

/usr/local/lib/python3.6/dist-packages/pandas/core/frame.py:3997: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  errors=errors,

df_.head()

status	Confirmed	Recovered	Deceased
an	3	12	0
ap	765	376	12
ar	7	1	0
as	1202	416	0
br	349	277	4

plt.bar(df_.index, df_.Confirmed);

plt.bar(df_.index, df_.Confirmed);
plt.xticks(rotation=90);

plt.bar(df_.index, df_.Confirmed);
plt.bar(df_.index, df_.Recovered, bottom=df_.Confirmed);
plt.xticks(rotation=90);

plt.bar(df_.index, df_.Confirmed);
plt.bar(df_.index, df_.Recovered, bottom=df_.Confirmed);
plt.bar(df_.index, df_.Deceased, bottom=df_.Confirmed + df_.Recovered);
plt.xticks(rotation=90);

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.bar(df_.index, df_.Confirmed);
plt.bar(df_.index, df_.Recovered, bottom=df_.Confirmed);
plt.bar(df_.index, df_.Deceased, bottom=df_.Confirmed + df_.Recovered);
plt.xticks(rotation=90);

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.bar(df_.index, df_.Confirmed, color='Orange');
plt.bar(df_.index, df_.Recovered, bottom=df_.Confirmed, color='Green');
plt.bar(df_.index, df_.Deceased, bottom=df_.Confirmed + df_.Recovered, color='Red');
plt.xticks(rotation=90);

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.bar(df_.index, df_.Confirmed, color='Orange');
plt.bar(df_.index, df_.Recovered, bottom=df_.Confirmed, color='Green');
plt.bar(df_.index, df_.Deceased, bottom=df_.Confirmed + df_.Recovered, color='Red');
plt.xticks(rotation=90);

for i, val in enumerate(df_.index):
    y = df_.loc[val].sum() + 100
    x = i
    plt.text(x, y, str(y), ha="center");

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.bar(df_.index, df_.Confirmed, color='Orange');
plt.bar(df_.index, df_.Recovered, bottom=df_.Confirmed, color='Green');
plt.bar(df_.index, df_.Deceased, bottom=df_.Confirmed + df_.Recovered, color='Red');
plt.xticks(rotation=90);

for i, val in enumerate(df_.index):
    y = df_.loc[val].sum() + 100
    if y > 1000:
        x = i
        plt.text(x, y, str(y), ha="center");

Relative stacked bar plots

df_.head()

status	Confirmed	Recovered	Deceased
an	3	12	0
ap	765	376	12
ar	7	1	0
as	1202	416	0
br	349	277	4

df_['Total'] = 0

df_['Total'] = df_.sum(axis = 1)

df_.head()

status	Confirmed	Recovered	Deceased	Total
an	3	12	0	15
ap	765	376	12	1153
ar	7	1	0	8
as	1202	416	0	1618
br	349	277	4	630

df_['ConfirmedFraction'] = df_['Confirmed'] / df_['Total']
df_['RecoveredFraction'] = df_['Recovered'] / df_['Total']
df_['DeceasedFraction'] = df_['Deceased'] / df_['Total']

df_.head()

status	Confirmed	Recovered	Deceased	Total	ConfirmedFraction	RecoveredFraction	DeceasedFraction
an	3	12	0	15	0.200000	0.800000	0.000000
ap	765	376	12	1153	0.663487	0.326106	0.010408
ar	7	1	0	8	0.875000	0.125000	0.000000
as	1202	416	0	1618	0.742892	0.257108	0.000000
br	349	277	4	630	0.553968	0.439683	0.006349

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.bar(df_.index, df_.ConfirmedFraction, color='Orange');
plt.bar(df_.index, df_.RecoveredFraction, bottom=df_.ConfirmedFraction, color='Green');
plt.bar(df_.index, df_.DeceasedFraction, bottom=df_.ConfirmedFraction + df_.RecoveredFraction, color='Red');
plt.xticks(rotation=90);

df_ = df_.sort_values('ConfirmedFraction', ascending=False)

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.bar(df_.index, df_.ConfirmedFraction, color='Orange');
plt.bar(df_.index, df_.RecoveredFraction, bottom=df_.ConfirmedFraction, color='Green');
plt.bar(df_.index, df_.DeceasedFraction, bottom=df_.ConfirmedFraction + df_.RecoveredFraction, color='Red');
plt.xticks(rotation=90);

df_ = df_.sort_values('Total', ascending=False)

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.bar(df_.index, df_.Confirmed, color='Orange');
plt.bar(df_.index, df_.Recovered, bottom=df_.Confirmed, color='Green');
plt.bar(df_.index, df_.Deceased, bottom=df_.Confirmed + df_.Recovered, color='Red');
plt.xticks(rotation=90);

for i, val in enumerate(df_.index):
    y = df_.loc[val, 'Total'] + 100
    if y > 1000:
        x = i
        plt.text(x, y, str(y), ha="center");

df_ = df_.sort_values('Total', ascending=False)

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.barh(df_.index, df_.Confirmed, color='Orange');
plt.barh(df_.index, df_.Recovered, left=df_.Confirmed, color='Green');
plt.barh(df_.index, df_.Deceased, left=df_.Confirmed + df_.Recovered, color='Red');
plt.xticks(rotation=90);

Time-varying composition of data

Stacked area plots

 df.head()

	an	ap	ar	as	br	ch	ct	date	dd	dl	dn	ga	gj	hp	hr	jh	jk	ka	kl	la	ld	mh	ml	mn	mp	mz	nl	or	pb	py	rj	sk	status	tg	tn	tr	tt	un	up	ut	wb
0	0	1	0	0	0	0	0	14-Mar-20	0	7	0	0	0	0	14	0	2	6	19	0	0	14	0	0	0	0	0	0	1	0	3	0	Confirmed	1	1	0	81	0	12	0	0
1	0	0	0	0	0	0	0	14-Mar-20	0	1	0	0	0	0	0	0	0	0	3	0	0	0	0	0	0	0	0	0	0	0	1	0	Recovered	0	0	0	9	0	4	0	0
2	0	0	0	0	0	0	0	14-Mar-20	0	1	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	Deceased	0	0	0	2	0	0	0	0
3	0	0	0	0	0	0	0	15-Mar-20	0	0	0	0	0	0	0	0	0	0	5	0	0	18	0	0	0	0	0	0	0	0	1	0	Confirmed	2	0	0	27	0	1	0	0
4	0	0	0	0	0	0	0	15-Mar-20	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	2	0	Recovered	1	0	0	4	0	0	0	0

df_ = df[['mh', 'date', 'status']]

df_.head()

	mh	date	status
0	14	14-Mar-20	Confirmed
1	0	14-Mar-20	Recovered
2	0	14-Mar-20	Deceased
3	18	15-Mar-20	Confirmed
4	0	15-Mar-20	Recovered

df_['mh'] = pd.to_numeric(df_['mh'])
df_['date'] = pd.to_datetime(df_['date'])

df_.head()

	mh	date	status
0	14	2020-03-14	Confirmed
1	0	2020-03-14	Recovered
2	0	2020-03-14	Deceased
3	18	2020-03-15	Confirmed
4	0	2020-03-15	Recovered

date | confirmed | recoverd | deceased |

2020-03-14 | 14 | 0 | 0

2020-03-14 | 18 | 0 | 0

pivot

df_ = df_.pivot_table(values="mh", columns="status", index="date")

df_.head()

status	Confirmed	Deceased	Recovered
date
2020-03-14	14	0	0
2020-03-15	18	0	0
2020-03-16	6	0	0
2020-03-17	3	1	0
2020-03-18	3	0	0

df_.plot.area();

plt.stackplot(df_.index, df_.Confirmed, df_.Recovered, df_.Deceased);

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.stackplot(df_.index, df_.Confirmed, df_.Recovered, df_.Deceased);

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.stackplot(df_.index, df_.Confirmed, df_.Recovered, df_.Deceased,
              colors=['orange', 'green', 'red']);

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.stackplot(df_.index, df_.Confirmed, df_.Recovered, df_.Deceased,
              labels=['Confirmed', 'Recovered', 'Deceased'],
              colors=['orange', 'green', 'red']);

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.stackplot(df_.index, df_.Confirmed, df_.Recovered, df_.Deceased,
              labels=['Confirmed', 'Recovered', 'Deceased'],
              colors=['orange', 'green', 'red']);
plt.legend();

Relative stacked area plot

fig = plt.gcf();
fig.set_size_inches(15, 6);
plt.stackplot(df_.index, df_.Confirmed/df_.sum(axis=1), 
              df_.Recovered/df_.sum(axis=1), 
              df_.Deceased/df_.sum(axis=1),
              labels=['Confirmed', 'Recovered', 'Deceased'],
              colors=['orange', 'green', 'red']);
plt.legend();

def plot_stacked_area_by_state(state):
    df_ = df[[state, 'date', 'status']]
    df_[state] = pd.to_numeric(df_[state])
    df_['date'] = pd.to_datetime(df_['date'])
    df_ = df_.pivot_table(values=state, columns="status", index="date")
    fig = plt.gcf();
    fig.set_size_inches(15, 6);
    plt.stackplot(df_.index, df_.Confirmed/df_.sum(axis=1), 
                df_.Recovered/df_.sum(axis=1), 
                df_.Deceased/df_.sum(axis=1),
                labels=['Confirmed', 'Recovered', 'Deceased'],
                colors=['orange', 'green', 'red']);
    plt.legend();

plot_stacked_area_by_state('tn')

/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  This is separate from the ipykernel package so we can avoid doing imports until
/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  after removing the cwd from sys.path.

plot_stacked_area_by_state('wb')

/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  This is separate from the ipykernel package so we can avoid doing imports until
/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  after removing the cwd from sys.path.

plot_stacked_area_by_state('dl')

/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  This is separate from the ipykernel package so we can avoid doing imports until
/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  after removing the cwd from sys.path.

Plotting relationships between data

Scatter plot

t = sns.load_dataset('tips')

t.head()

	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

sns.scatterplot(x='total_bill', y='tip', data=t);

<matplotlib.axes._subplots.AxesSubplot at 0x7f0b9b9dc550>

t['tip_fraction'] = t['tip']/t['total_bill']

sns.scatterplot(x='total_bill', y='tip_fraction', data=t);

sns.scatterplot(x='total_bill', y='tip', data=t,
                hue='time');

sns.scatterplot(x='total_bill', y='tip', data=t,
                hue='sex');

sns.scatterplot(x='total_bill', y='tip', data=t,
                hue='smoker');

sns.scatterplot(x='total_bill', y='tip', data=t,
                hue='day');

sns.scatterplot(x='total_bill', y='tip', data=t,
                hue='size');

sns.scatterplot(x='total_bill', y='tip', data=t,
                hue='size', style='sex');

sns.scatterplot(x='total_bill', y='tip', data=t,
                hue='time', style='sex', size='size');

sns.scatterplot(x='total_bill', y='tip', data=t,
                hue='time', style='sex', size='size');
plt.legend(bbox_to_anchor=(1.05, 1));

sns.regplot(x='total_bill', y='tip', data=t);

sns.regplot(x='total_bill', y='tip_fraction', data=t);

sns.regplot(x='total_bill', y='tip_fraction', data=t, marker="+");

d = sns.load_dataset('diamonds')

d.head()

	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

sns.scatterplot('x', 'price', data=d.sample(1000));

sns.regplot('x', 'price', data=d.sample(1000));

sns.regplot('x', 'price', data=d.sample(1000), order=2, marker="+");

Bar plots

sns.barplot(x="day", y ="tip", data=t);

sns.barplot(x="day", y ="tip_fraction", data=t);

sns.barplot(x="day", y ="tip", data=t);

sns.barplot(x="day", y ="tip", data=t, estimator=np.median);

def my_estimate(v):
    return np.quantile(v, 0.25)

sns.barplot(x="day", y ="tip", data=t, estimator=my_estimate);

sns.barplot(x="day", y ="tip", hue="sex", data=t, estimator=np.median);

sns.barplot(x="day", y ="tip", hue="smoker", data=t, estimator=np.median);

sns.barplot(x="day", y ="tip", hue="time", data=t, estimator=np.median);

sns.barplot(x="day", y ="tip_fraction", hue="time", data=t, estimator=np.median);

d.head()

	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

sns.scatterplot('x', 'price', data=d.sample(1000));

sns.barplot('x', 'price', data=d.sample(1000));

d['x_q'] = pd.cut(d['x'], bins=15);

d.head()

	carat	cut	color	clarity	depth	table	price	x	y	z	x_q
0	0.23	Ideal	E	SI2	61.5	55.0	326	3.95	3.98	2.43	(3.58, 4.296]
1	0.21	Premium	E	SI1	59.8	61.0	326	3.89	3.84	2.31	(3.58, 4.296]
2	0.23	Good	E	VS1	56.9	65.0	327	4.05	4.07	2.31	(3.58, 4.296]
3	0.29	Premium	I	VS2	62.4	58.0	334	4.20	4.23	2.63	(3.58, 4.296]
4	0.31	Good	J	SI2	63.3	58.0	335	4.34	4.35	2.75	(4.296, 5.012]

sns.barplot('x_q', 'price', data=d.sample(1000));

d['x_q'] = pd.cut(d['x'], bins=15, labels=False);

d.head()

	carat	cut	color	clarity	depth	table	price	x	y	z	x_q
0	0.23	Ideal	E	SI2	61.5	55.0	326	3.95	3.98	2.43	5
1	0.21	Premium	E	SI1	59.8	61.0	326	3.89	3.84	2.31	5
2	0.23	Good	E	VS1	56.9	65.0	327	4.05	4.07	2.31	5
3	0.29	Premium	I	VS2	62.4	58.0	334	4.20	4.23	2.63	5
4	0.31	Good	J	SI2	63.3	58.0	335	4.34	4.35	2.75	6

sns.barplot('x_q', 'price', data=d.sample(1000));

Line plot

f = sns.load_dataset('fmri')

f.head()

	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

sns.lineplot('timepoint', 'signal', data=f);

sns.lineplot('timepoint', 'signal', data=f, hue="region");

sns.lineplot('timepoint', 'signal', data=f, hue="event");

sns.lineplot('timepoint', 'signal', data=f, hue="event", style="region");

sns.lineplot('timepoint', 'signal', data=f, marker=True);

sns.lineplot('timepoint', 'signal', data=f, marker=True, estimator=np.median);

sns.lineplot('timepoint', 'signal', data=f, units='subject', estimator=None);

f_ = f[(f.region == "parietal") & (f.event == "cue")]

f_.head()

	subject	timepoint	event	region	signal
532	s3	4	cue	parietal	0.058219
533	s6	5	cue	parietal	0.038145
534	s7	5	cue	parietal	-0.008158
535	s8	5	cue	parietal	0.047136
536	s9	5	cue	parietal	0.055847

sns.lineplot('timepoint', 'signal', data=f_, hue='subject', estimator=None);

x = np.array([-3, -2, -1, 0, 1, 2, 3])

y = x * x

sns.lineplot(x, y);

with open('data.json') as f:
  data = json.load(f)
data = data['states_daily']
df = pd.json_normalize(data)
df['date'] = pd.to_datetime(df['date']) 
df.drop('tt', axis=1, inplace=True)
df.set_index('date', inplace=True)
df = df[df['status'] == 'Confirmed']
df.drop('status', axis=1, inplace=True)
df = df.apply(pd.to_numeric)
df = df.rolling(7).mean()
df.reset_index(inplace=True)

df.head()

	date	an	ap	ar	as	br	ch	ct	dd	dl	dn	ga	gj	hp	hr	jh	jk	ka	kl	la	ld	mh	ml	mn	mp	mz	nl	or	pb	py	rj	sk	tg	tn	tr	un	up	ut	wb
0	2020-03-14	0	1	0	0	0	0	0	0	7	0	0	0	0	14	0	2	6	19	0	0	14	0	0	0	0	0	0	1	0	3	0	1	1	0	0	12	0	0
1	2020-03-15	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	5	0	0	18	0	0	0	0	0	0	0	0	1	0	2	0	0	0	1	0	0
2	2020-03-16	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	1	3	0	0	6	0	0	0	0	0	1	0	1	0	0	1	0	0	0	0	1	0
3	2020-03-17	0	0	0	0	0	0	0	0	1	0	0	0	0	1	0	0	2	0	0	0	3	0	0	0	0	0	0	0	0	0	0	1	0	0	0	2	0	1
4	2020-03-18	0	0	0	0	0	0	0	0	2	0	0	0	0	1	0	1	5	0	8	0	3	0	0	0	0	0	1	1	0	3	0	8	1	0	0	2	1	0

date | state | confirmed

2020-03-14 | an | 0

2020-03-14 | ap | 1

df_ = pd.melt(df, id_vars="date", 
              value_vars = list(df.columns).remove("date"),
              var_name = "state", value_name = "confirmed")

df_.head()

	date	state	confirmed
0	2020-03-14	an	0
1	2020-03-15	an	0
2	2020-03-16	an	0
3	2020-03-17	an	0
4	2020-03-18	an	0

sns.lineplot('date', 'confirmed', data=df_);

sns.lineplot('date', 'confirmed', hue="state", data=df_);

states = ['mh', 'tn', 'dl', 'wb', 'ka', 'gj']

df_ = df_[df_.state.isin(states)]

sns.lineplot('date', 'confirmed', hue="state", data=df_);

sns.lineplot('date', 'confirmed', hue="state", data=df_,
             palette='Reds');

fig = plt.gcf();
fig.set_size_inches(15, 6);
sns.lineplot('date', 'confirmed', hue="state", data=df_,
             palette='Reds');

fig = plt.gcf();
fig.set_size_inches(15, 6);
sns.lineplot('date', 'confirmed', hue="state", data=df_,
             palette='Reds', hue_order = ['wb', 'gj', 'ka', 'dl', 'tn', 'mh']);

Heatmap

X [10 x 10]

X(i, j) -> value

x = np.random.rand(10, 10)

x

array([[0.44147103, 0.86844671, 0.97218962, 0.6935189 , 0.8069725 ,
        0.5578699 , 0.09532397, 0.78801904, 0.32624519, 0.03927953],
       [0.07426231, 0.14167535, 0.4004343 , 0.89695182, 0.24108825,
        0.2987024 , 0.452844  , 0.79566103, 0.44566233, 0.93156571],
       [0.29919083, 0.14043667, 0.82908301, 0.18849677, 0.92083531,
        0.72199571, 0.23918676, 0.11534281, 0.71111679, 0.59196739],
       [0.35287507, 0.93144292, 0.09984819, 0.06610241, 0.08692311,
        0.97267655, 0.76874109, 0.24189725, 0.24577086, 0.88816116],
       [0.57603578, 0.17206053, 0.03900838, 0.235467  , 0.72562216,
        0.71056661, 0.77237925, 0.92932866, 0.29885186, 0.07685464],
       [0.15220609, 0.0629219 , 0.61211092, 0.24377965, 0.3031736 ,
        0.2807313 , 0.56958555, 0.41459585, 0.51102999, 0.78950917],
       [0.31998926, 0.72196797, 0.25143335, 0.05519168, 0.58413424,
        0.89281645, 0.96354152, 0.67733497, 0.41681635, 0.62967471],
       [0.80862028, 0.26639888, 0.09040902, 0.9266112 , 0.87010557,
        0.52039608, 0.66714736, 0.70316625, 0.7854821 , 0.16920598],
       [0.94350783, 0.36418735, 0.77478057, 0.6535443 , 0.16562476,
        0.50576092, 0.65717018, 0.5047263 , 0.68163753, 0.72439885],
       [0.23512086, 0.86044499, 0.51851838, 0.6618975 , 0.19513392,
        0.91105141, 0.79445037, 0.34064833, 0.97714602, 0.66702951]])

sns.heatmap(x)

<matplotlib.axes._subplots.AxesSubplot at 0x7f0b9b9edef0>

fl = sns.load_dataset('flights')

fl.head()

	year	month	passengers
0	1949	January	112
1	1949	February	118
2	1949	March	132
3	1949	April	129
4	1949	May	121

fl.sample(10)

	year	month	passengers
12	1950	January	115
64	1954	May	234
102	1957	July	465
22	1950	November	114
129	1959	October	407
32	1951	September	184
124	1959	May	420
77	1955	June	315
62	1954	March	235
95	1956	December	306

year    month   passengers

0 1949 January 112

1 1949 February 118

2 1949 March 132

year January February March

1949 112 118 132

1950

1951

fl_ = fl.pivot(index='year', columns='month', values='passengers');

fl_.head()

month	January	February	March	April	May	June	July	August	September	October	November	December
year
1949	112	118	132	129	121	135	148	148	136	119	104	118
1950	115	126	141	135	125	149	170	170	158	133	114	140
1951	145	150	178	163	172	178	199	199	184	162	146	166
1952	171	180	193	181	183	218	230	242	209	191	172	194
1953	196	196	236	235	229	243	264	272	237	211	180	201

sns.heatmap(fl_.T)

<matplotlib.axes._subplots.AxesSubplot at 0x7f0b9baf99e8>

fig = plt.gcf();
fig.set_size_inches(15, 10)
sns.heatmap(fl_.T, annot=True, fmt="d");

fig = plt.gcf();
fig.set_size_inches(15, 10)
sns.heatmap(fl_.T, annot=True, fmt="d", cmap="YlGnBu");

fig = plt.gcf();
fig.set_size_inches(15, 10)
sns.heatmap(fl_.T, annot=True, fmt="d", 
            cmap=sns.diverging_palette(50, 200, n=45));

fig = plt.gcf();
fig.set_size_inches(15, 10)
sns.heatmap(fl_.T, annot=True, fmt="d", 
            cmap=sns.diverging_palette(250, 10, n=45),
            center=fl_.loc[1954, 'January']);

Task on open-ended visualisation

http://ml-india.org/datasets/

df = pd.read_excel('ameo_2015.xlsx')

df.head()

	ID	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	10board	12graduation	12percentage	12board	CollegeID	CollegeTier	Degree	Specialization	collegeGPA	CollegeCityID	CollegeCityTier	CollegeState	GraduationYear	English	Logical	Quant	Domain	ComputerProgramming	ElectronicsAndSemicon	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
0	203097	420000	2012-06-01	present	senior quality engineer	Bangalore	f	1990-02-19	84.3	board ofsecondary education,ap	2007	95.8	board of intermediate education,ap	1141	2	B.Tech/B.E.	computer engineering	78.00	1141	0	Andhra Pradesh	2011	515	585	525	0.635979	445	-1	-1	-1	-1	-1	-1	0.9737	0.8128	0.5269	1.35490	-0.4455
1	579905	500000	2013-09-01	present	assistant manager	Indore	m	1989-10-04	85.4	cbse	2007	85.0	cbse	5807	2	B.Tech/B.E.	electronics and communication engineering	70.06	5807	0	Madhya Pradesh	2012	695	610	780	0.960603	-1	466	-1	-1	-1	-1	-1	-0.7335	0.3789	1.2396	-0.10760	0.8637
2	810601	325000	2014-06-01	present	systems engineer	Chennai	f	1992-08-03	85.0	cbse	2010	68.2	cbse	64	2	B.Tech/B.E.	information technology	70.00	64	0	Uttar Pradesh	2014	615	545	370	0.450877	395	-1	-1	-1	-1	-1	-1	0.2718	1.7109	0.1637	-0.86820	0.6721
3	267447	1100000	2011-07-01	present	senior software engineer	Gurgaon	m	1989-12-05	85.6	cbse	2007	83.6	cbse	6920	1	B.Tech/B.E.	computer engineering	74.64	6920	1	Delhi	2011	635	585	625	0.974396	615	-1	-1	-1	-1	-1	-1	0.0464	0.3448	-0.3440	-0.40780	-0.9194
4	343523	200000	2014-03-01	2015-03-01 00:00:00	get	Manesar	m	1991-02-27	78.0	cbse	2008	76.8	cbse	11368	2	B.Tech/B.E.	electronics and communication engineering	73.90	11368	0	Uttar Pradesh	2012	545	625	465	0.124502	-1	233	-1	-1	-1	-1	-1	-0.8810	-0.2793	-1.0697	0.09163	-0.1295