[Visualization] Plotly_Part1

 

 

 

 

plotly

https://plotly.com/python/

 

 

plotly/datasets

https://github.com/plotly/datasets

 

In [1]:

# interactive graphs
import plotly.express as px
import pandas as pd
import numpy as np

 

In [2]:

df = px.data.gapminder();df

 

Out[2]:

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4
...	...	...	...	...	...	...	...	...
1699	Zimbabwe	Africa	1987	62.351	9216418	706.157306	ZWE	716
1700	Zimbabwe	Africa	1992	60.377	10704340	693.420786	ZWE	716
1701	Zimbabwe	Africa	1997	46.809	11404948	792.449960	ZWE	716
1702	Zimbabwe	Africa	2002	39.989	11926563	672.038623	ZWE	716
1703	Zimbabwe	Africa	2007	43.487	12311143	469.709298	ZWE	716

1704 rows × 8 columns

 

In [3]:

df_italy = px.data.gapminder().query("country == 'Italy'")
g = px.bar(df_italy, x = 'year', y = 'pop')
g.show()

 

 

 

 

 

 

customizing

 

In [4]:

df.isnull().sum()

 

Out[4]:

country      0
continent    0
year         0
lifeExp      0
pop          0
gdpPercap    0
iso_alpha    0
iso_num      0
dtype: int64

 

In [5]:

g = px.bar(df_italy, x = 'year', y = 'pop', hover_data=['continent','gdpPercap'], color='lifeExp', labels={'Population/Life Exp of Italy'}, height = 600 )
g.show()
# hover_data : 사용하고자하는 값들의 목록

 

 

 

 

 

diabetes data

 

In [6]:

df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/diabetes.csv")
df

 

Out[6]:

	Pregnancies	Glucose	BloodPressure	SkinThickness	Insulin	BMI	DiabetesPedigreeFunction	Age	Outcome
0	6	148	72	35	0	33.6	0.627	50	1
1	1	85	66	29	0	26.6	0.351	31	0
2	8	183	64	0	0	23.3	0.672	32	1
3	1	89	66	23	94	28.1	0.167	21	0
4	0	137	40	35	168	43.1	2.288	33	1
...	...	...	...	...	...	...	...	...	...
763	10	101	76	48	180	32.9	0.171	63	0
764	2	122	70	27	0	36.8	0.340	27	0
765	5	121	72	23	112	26.2	0.245	30	0
766	1	126	60	0	0	30.1	0.349	47	1
767	1	93	70	31	0	30.4	0.315	23	0

768 rows × 9 columns

 

In [7]:

g = px.scatter( data_frame= df, x = 'Age', y='BMI', color='Outcome')
g.show()

 

 

 

 

 

plotly graph objects

https://plotly.com/python/graph-objects/

 

 

graph_object란

plotly express가 그래프 객체 위에 구하여 모두 그래프 객체의 그림을 출력으로 준다.

 

In [8]:

import plotly.graph_objects as go

 

 

Apple

 

In [9]:

df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/finance-charts-apple.csv")
df

 

Out[9]:

	Date	AAPL.Open	AAPL.High	AAPL.Low	AAPL.Close	AAPL.Volume	AAPL.Adjusted	dn	mavg	up	direction
0	2015-02-17	127.489998	128.880005	126.919998	127.830002	63152400	122.905254	106.741052	117.927667	129.114281	Increasing
1	2015-02-18	127.629997	128.779999	127.449997	128.720001	44891700	123.760965	107.842423	118.940333	130.038244	Increasing
2	2015-02-19	128.479996	129.029999	128.330002	128.449997	37362400	123.501363	108.894245	119.889167	130.884089	Decreasing
3	2015-02-20	128.619995	129.500000	128.050003	129.500000	48948400	124.510914	109.785449	120.763500	131.741551	Increasing
4	2015-02-23	130.020004	133.000000	129.660004	133.000000	70974100	127.876074	110.372516	121.720167	133.067817	Increasing
...	...	...	...	...	...	...	...	...	...	...	...
501	2017-02-10	132.460007	132.940002	132.050003	132.119995	20065500	132.119995	114.494004	124.498666	134.503328	Decreasing
502	2017-02-13	133.080002	133.820007	132.750000	133.289993	23035400	133.289993	114.820798	125.205166	135.589534	Increasing
503	2017-02-14	133.470001	135.089996	133.250000	135.020004	32815500	135.020004	115.175718	125.953499	136.731280	Increasing
504	2017-02-15	135.520004	136.270004	134.619995	135.509995	35501600	135.509995	115.545035	126.723499	137.901963	Decreasing
505	2017-02-16	135.669998	135.899994	134.839996	135.350006	22118000	135.350006	116.203299	127.504333	138.805366	Decreasing

506 rows × 11 columns

 

 

Tesla

 

In [10]:

df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/tesla-stock-price.csv")

 

In [11]:

df.sort_values('date',inplace=True)

 

In [12]:

fig = go.Figure([go.Scatter(name = 'Open',x = df['date'], y= df['open'], mode = 'markers', text = df['close'])]) 
fig.add_scatter(name = 'High',x = df['date'], y= df['high'], mode = 'lines')
fig.add_scatter(name = 'Low',x = df['date'], y= df['low'], mode = 'lines')
fig.update_layout(title='Tesla Stock Perfomance 2 year outdated')
fig.show()

 

 

 

 

 

plotly 3D

 

In [13]:

np.random.seed(1)
N = 70
fig = go.Figure(data=[go.Mesh3d(x=(55*np.random.randn(N)),
y=(65*np.random.randn(N)),
z=(35*np.random.randn(N)),
opacity = 0.5,
color='rgba(80,22,90,0.8)' )])

fig.update_layout(
    scene = dict(xaxis = dict(nticks=5, range=[-200,200],),
                 yaxis = dict(nticks=5, range=[-150,200],),
                 zaxis = dict(nticks=5, range=[-200,200],),),
                 width = 850,
                 margin=dict(r=25, l=15, b=15, t=15))

fig.show()
# opcity : 불투명