Portfolio


%matplotlib inline

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

x = np.linspace(0, 10, 20)
y = x ** 2

plt.plot(x, y)
plt.show()


%matplotlib inline

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

x = np.linspace(0, 10, 20)
y = x ** 2

sns.set()

plt.plot(x, y)

plt.show()


tips = sns.load_dataset("tips") # sns.load_dataset : seaborn에서 제공하는 데이터 불러오기            
    sns.relplot(x="total_bill", y="tip", data=tips)
    
    plt.show()                 
sns.relplot(x="total_bill", y="tip", data=tips)

plt.show()


tips.head(10)


Out[-]
  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
5	     25.29	4.71	  Male	No	  Sun	 Dinner	 4
6	      8.77	2.00	   Male	No	  Sun	 Dinner	 2
7	     26.88	3.12	  Male	No	  Sun	 Dinner	 4
8	     15.04	1.96	  Male	No	  Sun	 Dinner	 2 
9	     14.78	3.23	  Male	No	  Sun	 Dinner	 2


type(tips)


Out[-]
pandas.core.frame.DataFrame


sns.relplot(x="total_bill", y="tip", hue="smoker", data=tips)


sns.relplot(x="total_bill", y="tip", hue="smoker", style='smoker', data=tips)


sns.relplot(x="total_bill", y="tip", hue="size", data=tips)


sns.relplot(x="total_bill", y="tip", hue="size", size='size', data=tips)


sns.relplot(x="total_bill", y="tip", size="size", sizes=(15, 200), data=tips)


fmri = sns.load_dataset("fmri")
sns.relplot(x="timepoint", y="signal", hue="event", style="event",
            col="subject", col_wrap=3,             
            height=10, aspect=.75, linewidth=2.5, 
            kind="line", data=fmri.query("region == 'frontal'"));


titanic = sns.load_dataset("titanic")
f, ax = plt.subplots(figsize=(7, 3))
sns.countplot(y="deck", data=titanic, color="c") # 가로 그래프 생성
																								 # y 대신 x를 사용하면 세로 그래프


titanic.head(10)


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
5	       0	     3	  male	 NaN	    0	    0	  8.4583	       Q	 Third	  man	     True	   NaN	 Queenstown	  no	 True
6	       0	     1	  male	54.0	    0	    0	 51.8625	       S	 First	  man	     True	     E	Southampton	  no	 True
7	       0	     3	  male	 2.0	    3	    1	 21.0750	       S	 Third	child	    False	   NaN	Southampton	  no	False
8	       1	     3	female	27.0	    0	    2	 11.1333	       S	 Third	woman	    False	   NaN	Southampton	 yes	False
9	       1	     2	female	14.0	    1	    0	 30.0708	       C	Second  child	    False	   NaN	  Cherbourg	 yes	False


sns.pairplot(titanic, hue='class')

plt.show()


import plotly.express as px

df = px.data.gapminder().query("country=='Canada'")

fig = px.line(df, 
							x="year", y="lifeExp", 
							title='Life expectancy in Canada')

fig.show()


fig = px.scatter(x=[0, 1, 2, 3, 4], y=[0, 1, 4, 9, 16])
fig.show()


data_canada = px.data.gapminder().query("country == 'Canada'")

fig = px.bar(data_canada,
						 x='year', y='pop')

fig.show()


data_canada


Out[-]
   country continent	year	lifeExp	     pop	  gdpPercap	iso_alpha	iso_num
240	Canada	Americas	1952	68.750	14785584	11367.16112	      CAN	    124
241	Canada	Americas	1957	69.960	17010154	12489.95006	      CAN	    124
242	Canada	Americas	1962	71.300	18985849	13462.48555	      CAN	    124
243	Canada	Americas	1967	72.130	20819767	16076.58803	      CAN	    124
244	Canada	Americas	1972	72.880	22284500	18970.57086	      CAN	    124
245	Canada	Americas	1977	74.210	23796400	22090.88306	      CAN	    124
246	Canada	Americas	1982	75.760	25201900	22898.79214	      CAN	    124
247	Canada	Americas	1987	76.860	26549700	26626.51503	      CAN	    124
248	Canada	Americas	1992	77.950	28523502	26342.88426	      CAN	    124
249	Canada	Americas	1997	78.610	30305843	28954.92589	      CAN	    124
250	Canada	Americas	2002	79.770	31902268	33328.96507	      CAN	    124
251	Canada	Americas	2007	80.653	33390141	36319.23501	      CAN	    124


import plotly
print(plotly.__version__) #버전확인


Out[-]
4.5.4


# 버전이 낮으면 파이차트 불가능
# !pip3 install plotly


import plotly.express as px
fig = px.pie(values=[1, 2, 3])
fig.show()


import plotly.graph_objects as go

labels = ['Oxygen','Hydrogen','Carbon_Dioxide','Nitrogen']
values = [4500, 2500, 1053, 500]

fig = go.Figure(data=[go.Pie(labels=labels, values=values, pull=[0, 0, 0.2, 0])])

fig.show()


import plotly.graph_objects as go

fig =go.Figure(go.Sunburst(
    labels=["Eve", "Cain", "Seth", "Enos", "Noam", "Abel", "Awan", "Enoch", "Azura"],
    parents=["", "Eve", "Eve", "Seth", "Seth", "Eve", "Eve", "Awan", "Eve" ],
    values=[10, 14, 12, 10, 2, 6, 6, 4, 4],
))

fig.update_layout(margin = dict(t=0, l=0, r=0, b=0))

fig.show()


import plotly.figure_factory as ff

df = [
    dict(Task='Morning Sleep', Start='2016-01-01', 
				 Finish='2016-01-01 6:00:00', Resource='Sleep'),
    dict(Task='Breakfast', Start='2016-01-01 7:00:00', 
				 Finish='2016-01-01 7:30:00', Resource='Food'),
    dict(Task='Work', Start='2016-01-01 9:00:00',
				 Finish='2016-01-01 11:25:00', Resource='Brain'),
    dict(Task='Break', Start='2016-01-01 11:30:00',
				 Finish='2016-01-01 12:00:00', Resource='Rest'),
    dict(Task='Lunch', Start='2016-01-01 12:00:00',
				 Finish='2016-01-01 13:00:00', Resource='Food'),
    dict(Task='Work', Start='2016-01-01 13:00:00',
				 Finish='2016-01-01 17:00:00', Resource='Brain'),
    dict(Task='Exercise', Start='2016-01-01 17:30:00',
				 Finish='2016-01-01 18:30:00', Resource='Cardio'),
    dict(Task='Post Workout Rest', Start='2016-01-01 18:30:00',
				 Finish='2016-01-01 19:00:00', Resource='Rest'),
    dict(Task='Dinner', Start='2016-01-01 19:00:00',
				 Finish='2016-01-01 20:00:00', Resource='Food'),
    dict(Task='Evening Sleep', Start='2016-01-01 21:00:00',
				 Finish='2016-01-01 23:59:00', Resource='Sleep')
]

colors = dict(Cardio = 'rgb(46, 137, 205)',
              Food = 'rgb(114, 44, 121)',
              Sleep = 'rgb(198, 47, 105)',
              Brain = 'rgb(58, 149, 136)',
              Rest = 'rgb(107, 127, 135)')

fig = ff.create_gantt(df, colors=colors, index_col='Resource', 
											title='Daily Schedule', show_colorbar=True,
										  bar_width=0.8, showgrid_x=True, showgrid_y=True)
fig.show()


import plotly.express as px

fig =px.scatter(x=range(10), y=range(10))
fig.show()
# fig.write_html("path/to/file.html")


import plotly.express as px

fig =px.scatter(x=range(10), y=range(10))

fig.show()
# html로 저장
fig.write_html("file.html")

5일차 데이터 시각화2

목차

Seaborn

relplot

countplot()

pairplot()

Plotly Python Open Source Graphing Library

Plotly

Line

Scatter

Bar

Pie

Sunburst

gantt